jyapayne/langflow
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions

Merge branch 'feature/store' into bug/undo-copy and fixed edit node modal

Browse source
This commit is contained in:
Lucas Oliveira 2023-11-23 14:39:53 -03:00
commit 807ea46464
295 changed files with 17396 additions and 7418 deletions
Download patch file Download diff file Expand all files Collapse all files

8
.devcontainer/devcontainer.json
View file

@ -15,7 +15,7 @@
// "forwardPorts": [],
// Use 'postCreateCommand' to run commands after the container is created.
"postCreateCommand": "make install_frontend && make install_backend",
"postCreateCommand": "make setup_devcontainer",
"containerEnv": {
"POETRY_VIRTUALENVS_IN_PROJECT": "true"
@ -31,11 +31,13 @@
"sourcery.sourcery",
"eamodio.gitlens",
"ms-vscode.makefile-tools",
"GitHub.vscode-pull-request-github"
"GitHub.vscode-pull-request-github",
"Codium.codium",
"ms-azuretools.vscode-docker"
]
}
}
// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
// "remoteUser": "root"
}
}

20
.env.example
View file

@ -56,6 +56,14 @@ LANGFLOW_REMOVE_API_KEYS=
# LANGFLOW_REDIS_CACHE_EXPIRE (default: 3600)
LANGFLOW_CACHE_TYPE=
# Auto login
# If set to true then a superuser will be logged in automatically
# and the login page will be skipped, keeping the
# default experience of Langflow
# Values: true, false
# Example: LANGFLOW_AUTO_LOGIN=true
LANGFLOW_AUTO_LOGIN=
# Superuser username
# Example: LANGFLOW_SUPERUSER=admin
LANGFLOW_SUPERUSER=
@ -63,3 +71,15 @@ LANGFLOW_SUPERUSER=
# Superuser password
# Example: LANGFLOW_SUPERUSER_PASSWORD=123456
LANGFLOW_SUPERUSER_PASSWORD=
# STORE_URL
# Example: LANGFLOW_STORE_URL=https://api.langflow.store
LANGFLOW_STORE_URL=
# DOWNLOAD_WEBHOOK_URL
#
LANGFLOW_DOWNLOAD_WEBHOOK_URL=
# LIKE_WEBHOOK_URL
#
LANGFLOW_LIKE_WEBHOOK_URL=

2
.github/workflows/lint.yml vendored
View file

@ -15,7 +15,7 @@ on:
- "pyproject.toml"
env:
POETRY_VERSION: "1.4.0"
POETRY_VERSION: "1.7.0"
jobs:
lint:

4
.gitignore vendored
View file

@ -254,4 +254,6 @@ langflow.db
/tmp/*
src/backend/langflow/frontend/
.docker
.docker
.idea

3
.vscode/launch.json vendored
View file

@ -16,7 +16,8 @@
"debug"
],
"jinja": true,
"justMyCode": true
"justMyCode": true,
"envFile": "${workspaceFolder}/.env"
},
{
"name": "Python: Remote Attach",

2
Dockerfile
View file

@ -11,5 +11,5 @@ WORKDIR $HOME/app
COPY --chown=user . $HOME/app
RUN pip install langflow>==0.0.86 -U --user
RUN pip install langflow>==0.5.0 -U --user
CMD ["python", "-m", "langflow", "run", "--host", "0.0.0.0", "--port", "7860"]

22
Makefile
View file

@ -23,16 +23,19 @@ tests:
poetry run pytest tests
tests_frontend:
cd src/frontend && ./run-tests.sh
ifeq ($(UI), true)
cd src/frontend && ./run-tests.sh --ui
else
cd src/frontend && ./run-tests.sh
endif
format:
poetry run black .
poetry run ruff . --fix
poetry run ruff format .
cd src/frontend && npm run format
lint:
poetry run mypy src/backend/langflow
poetry run black . --check
poetry run ruff . --fix
install_frontend:
@ -42,18 +45,20 @@ install_frontendc:
cd src/frontend && rm -rf node_modules package-lock.json && npm install
run_frontend:
@-kill -9 `lsof -t -i:3000`
cd src/frontend && npm start
run_cli:
poetry run langflow run --path src/frontend/build
poetry run langflow --path src/frontend/build
run_cli_debug:
poetry run langflow run --path src/frontend/build --log-level debug
poetry run langflow --path src/frontend/build --log-level debug
setup_devcontainer:
make init
make build_frontend
poetry run langflow --path src/frontend/build
@echo 'Run Cli'
make run_cli
frontend:
@-make install_frontend || (echo "An error occurred while installing frontend dependencies. Attempting to fix." && make install_frontendc)
@ -68,12 +73,13 @@ install_backend:
backend:
make install_backend
@-kill -9 `lsof -t -i:7860`
ifeq ($(login),1)
@echo "Running backend without autologin";
poetry run langflow run --backend-only --port 7860 --host 0.0.0.0 --no-open-browser
poetry run langflow run --backend-only --port 7860 --host 0.0.0.0 --no-open-browser --env-file .env
else
@echo "Running backend with autologin";
LANGFLOW_AUTO_LOGIN=True poetry run langflow run --backend-only --port 7860 --host 0.0.0.0 --no-open-browser
LANGFLOW_AUTO_LOGIN=True poetry run langflow run --backend-only --port 7860 --host 0.0.0.0 --no-open-browser --env-file .env
endif
build_and_run:

2
base.Dockerfile
View file

@ -23,7 +23,7 @@ ENV PYTHONUNBUFFERED=1 \
\
# poetry
# https://python-poetry.org/docs/configuration/#using-environment-variables
POETRY_VERSION=1.5.1 \
POETRY_VERSION=1.7 \
# make poetry install to this location
POETRY_HOME="/opt/poetry" \
# make poetry create the virtual environment in the project's root

9
docker_example/Dockerfile
View file

@ -1,14 +1,15 @@
FROM python:3.10-slim
RUN apt-get update && apt-get install gcc g++ git make -y
RUN apt-get update && apt-get install gcc g++ git make -y && apt-get clean \
&& rm -rf /var/lib/apt/lists/*
RUN useradd -m -u 1000 user
USER user
ENV HOME=/home/user \
PATH=/home/user/.local/bin:$PATH
PATH=/home/user/.local/bin:$PATH
WORKDIR $HOME/app
COPY --chown=user . $HOME/app
RUN pip install langflow>==0.0.71 -U --user
CMD ["langflow", "--host", "0.0.0.0", "--port", "7860"]
RUN pip install langflow>==0.5.0 -U --user
CMD ["python", "-m", "langflow", "run", "--host", "0.0.0.0", "--port", "7860"]

2
docker_example/docker-compose.yml
View file

@ -7,4 +7,4 @@ services:
dockerfile: Dockerfile
ports:
- "7860:7860"
command: langflow --host 0.0.0.0
command: langflow run --host 0.0.0.0

16
docs/docs/components/embeddings.mdx
View file

@ -12,6 +12,22 @@ Embeddings are vector representations of text that capture the semantic meaning
---
### BedrockEmbeddings
Used to load [Amazon Bedrocks’s](https://aws.amazon.com/bedrock/) embedding models.
**Params**
- **credentials_profile_name:** The name of the profile in the ~/.aws/credentials or ~/.aws/config files, which has either access keys or role information specified. If not specified, the default credential profile or, if on an EC2 instance, credentials from IMDS will be used. See [the AWS documentation](https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html) for more details.
- **model_id:** Id of the model to call, e.g., amazon.titan-embed-text-v1, this is equivalent to the modelId property in the list-foundation-models api.
- **endpoint_url:** Needed if you don’t want to default to us-east-1 endpoint.
- **region_name:** The aws region e.g., us-west-2. Fallsback to AWS_DEFAULT_REGION env variable or region specified in ~/.aws/config in case it is not provided here.
---
### CohereEmbeddings
Used to load [Cohere’s](https://cohere.com/) embedding models.

38
docs/docs/components/llms.mdx
View file

@ -217,4 +217,40 @@ Vertex AI is a cloud computing platform offered by Google Cloud Platform (GCP).
- **top_k:** How the model selects tokens for output, the next token is selected from – defaults to `40`.
- **top_p:** Tokens are selected from most probable to least until the sum of their – defaults to `0.95`.
- **tuned_model_name:** The name of a tuned model. If provided, model_name is ignored.
- **verbose:** This parameter is used to control the level of detail in the output of the chain. When set to True, it will print out some internal states of the chain while it is being run, which can help debug and understand the chain's behavior. If set to False, it will suppress the verbose output – defaults to `False`.
- **verbose:** This parameter is used to control the level of detail in the output of the chain. When set to True, it will print out some internal states of the chain while it is being run, which can help debug and understand the chain's behavior. If set to False, it will suppress the verbose output – defaults to `False`.
---
### QianfanLLMEndpoint
Wrapper around [Baidu Qianfan](https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html) large language models.
:::info
The Qianfan Big Model Platform is a one-stop platform for enterprise developers to develop and operate large models and services. It provides data management based on ERNIE Bot's underlying model (Ernie Bot), automatic model customization and fine-tuning, and one-stop large-scale model customization services for cloud deployment of prediction services, and provides ERNIE Bot's enterprise level service API that can be quickly called, helping to implement the demand for generative AI applications in various industries.
:::
- **Model Name:** Model name. you could get from https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu preset models are mapping to an endpoint. `Model Name` will be ignored if `Endpoint` is set.
- **Qianfan Ak:** which you could get from https://cloud.baidu.com/product/wenxinworkshop.
- **Qianfan Sk:** which you could get from https://cloud.baidu.com/product/wenxinworkshop.
- **Top p:** Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo. The diversity of the output text is affected, and the larger the value, the stronger the diversity of the generated text - defaults to `0.8`.
- **Temperature:** Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo. Higher values make the output more random, while lower values make it more concentrated and deterministic - defaults to `0.95`.
- **Penalty Score:** Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo. By increasing the penalty for generated tokens, the phenomenon of duplicate generation is reduced. A higher value indicates a higher penalty - defaults to `1.0`.
- **Endpoint:** Endpoint of the Qianfan LLM, required if custom model used.
---
### QianfanChatEndpoint
Wrapper around [Baidu Qianfan](https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html) chat large language models. This component supports some of the LLMs (Large Language Models) available by Baidu qianfan and is used for tasks such as chatbots, Generative Question-Answering (GQA), and summarization.
:::info
The Qianfan Big Model Platform is a one-stop platform for enterprise developers to develop and operate large models and services. It provides data management based on ERNIE Bot's underlying model (Ernie Bot), automatic model customization and fine-tuning, and one-stop large-scale model customization services for cloud deployment of prediction services, and provides ERNIE Bot's enterprise level service API that can be quickly called, helping to implement the demand for generative AI applications in various industries.
:::
- **Model Name:** Model name. you could get from https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu preset models are mapping to an endpoint. `Model Name` will be ignored if `Endpoint` is set.
- **Qianfan Ak:** which you could get from https://cloud.baidu.com/product/wenxinworkshop.
- **Qianfan Sk:** which you could get from https://cloud.baidu.com/product/wenxinworkshop.
- **Top p:** Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo. The diversity of the output text is affected, and the larger the value, the stronger the diversity of the generated text - defaults to `0.8`.
- **Temperature:** Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo. Higher values make the output more random, while lower values make it more concentrated and deterministic - defaults to `0.95`.
- **Penalty Score:** Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo. By increasing the penalty for generated tokens, the phenomenon of duplicate generation is reduced. A higher value indicates a higher penalty - defaults to `1.0`.
- **Endpoint:** Endpoint of the Qianfan LLM, required if custom model used.

2
docs/docs/guidelines/components.mdx
View file

@ -5,7 +5,7 @@ import ReactPlayer from "react-player";
# Component
Components are the building blocks of the flows. They are made of inputs, outputs, and parameters that define their functionality, providing a convenient and straightforward way to compose LLM-based applications. Learn more about components and how they work in the LangChain [documentation](https://docs.langchain.com/docs/category/components) section.
Components are the building blocks of the flows. They are made of inputs, outputs, and parameters that define their functionality, providing a convenient and straightforward way to compose LLM-based applications. Learn more about components and how they work in the LangChain [documentation](https://python.langchain.com/docs/integrations/components) section.
### Component's Features

8
docs/docusaurus.config.js
View file

@ -31,7 +31,7 @@ module.exports = {
[
remarkCodeHike,
{
theme: "github-light",
theme: "github-dark",
showCopyButton: true,
lineNumbers: true,
},
@ -112,8 +112,10 @@ module.exports = {
},
colorMode: {
defaultMode: "light",
disableSwitch: true,
respectPrefersColorScheme: false,
/* Allow users to chose light or dark mode. */
disableSwitch: false,
/* Respect user preferences, such as low light mode in the evening */
respectPrefersColorScheme: true,
},
announcementBar: {
content:

932
package-lock.json generated Normal file
View file

@ -0,0 +1,932 @@
{
"name": "langflow",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"dependencies": {
"@radix-ui/react-popover": "^1.0.7",
"cmdk": "^0.2.0"
}
},
"node_modules/@babel/runtime": {
"version": "7.23.2",
"resolved": "https://registry.npmjs.org/@babel/runtime/-/runtime-7.23.2.tgz",
"integrity": "sha512-mM8eg4yl5D6i3lu2QKPuPH4FArvJ8KhTofbE7jwMUv9KX5mBvwPAqnV3MlyBNqdp9RyRKP6Yck8TrfYrPvX3bg==",
"dependencies": {
"regenerator-runtime": "^0.14.0"
},
"engines": {
"node": ">=6.9.0"
}
},
"node_modules/@floating-ui/core": {
"version": "1.5.0",
"resolved": "https://registry.npmjs.org/@floating-ui/core/-/core-1.5.0.tgz",
"integrity": "sha512-kK1h4m36DQ0UHGj5Ah4db7R0rHemTqqO0QLvUqi1/mUUp3LuAWbWxdxSIf/XsnH9VS6rRVPLJCncjRzUvyCLXg==",
"dependencies": {
"@floating-ui/utils": "^0.1.3"
}
},
"node_modules/@floating-ui/dom": {
"version": "1.5.3",
"resolved": "https://registry.npmjs.org/@floating-ui/dom/-/dom-1.5.3.tgz",
"integrity": "sha512-ClAbQnEqJAKCJOEbbLo5IUlZHkNszqhuxS4fHAVxRPXPya6Ysf2G8KypnYcOTpx6I8xcgF9bbHb6g/2KpbV8qA==",
"dependencies": {
"@floating-ui/core": "^1.4.2",
"@floating-ui/utils": "^0.1.3"
}
},
"node_modules/@floating-ui/react-dom": {
"version": "2.0.4",
"resolved": "https://registry.npmjs.org/@floating-ui/react-dom/-/react-dom-2.0.4.tgz",
"integrity": "sha512-CF8k2rgKeh/49UrnIBs4BdxPUV6vize/Db1d/YbCLyp9GiVZ0BEwf5AiDSxJRCr6yOkGqTFHtmrULxkEfYZ7dQ==",
"dependencies": {
"@floating-ui/dom": "^1.5.1"
},
"peerDependencies": {
"react": ">=16.8.0",
"react-dom": ">=16.8.0"
}
},
"node_modules/@floating-ui/utils": {
"version": "0.1.6",
"resolved": "https://registry.npmjs.org/@floating-ui/utils/-/utils-0.1.6.tgz",
"integrity": "sha512-OfX7E2oUDYxtBvsuS4e/jSn4Q9Qb6DzgeYtsAdkPZ47znpoNsMgZw0+tVijiv3uGNR6dgNlty6r9rzIzHjtd/A=="
},
"node_modules/@radix-ui/primitive": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/@radix-ui/primitive/-/primitive-1.0.1.tgz",
"integrity": "sha512-yQ8oGX2GVsEYMWGxcovu1uGWPCxV5BFfeeYxqPmuAzUyLT9qmaMXSAhXpb0WrspIeqYzdJpkh2vHModJPgRIaw==",
"dependencies": {
"@babel/runtime": "^7.13.10"
}
},
"node_modules/@radix-ui/react-arrow": {
"version": "1.0.3",
"resolved": "https://registry.npmjs.org/@radix-ui/react-arrow/-/react-arrow-1.0.3.tgz",
"integrity": "sha512-wSP+pHsB/jQRaL6voubsQ/ZlrGBHHrOjmBnr19hxYgtS0WvAFwZhK2WP/YY5yF9uKECCEEDGxuLxq1NBK51wFA==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-primitive": "1.0.3"
},
"peerDependencies": {
"@types/react": "*",
"@types/react-dom": "*",
"react": "^16.8 || ^17.0 || ^18.0",
"react-dom": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
},
"@types/react-dom": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-compose-refs": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/@radix-ui/react-compose-refs/-/react-compose-refs-1.0.1.tgz",
"integrity": "sha512-fDSBgd44FKHa1FRMU59qBMPFcl2PZE+2nmqunj+BWFyYYjnhIDWL2ItDs3rrbJDQOtzt5nIebLCQc4QRfz6LJw==",
"dependencies": {
"@babel/runtime": "^7.13.10"
},
"peerDependencies": {
"@types/react": "*",
"react": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-context": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/@radix-ui/react-context/-/react-context-1.0.1.tgz",
"integrity": "sha512-ebbrdFoYTcuZ0v4wG5tedGnp9tzcV8awzsxYph7gXUyvnNLuTIcCk1q17JEbnVhXAKG9oX3KtchwiMIAYp9NLg==",
"dependencies": {
"@babel/runtime": "^7.13.10"
},
"peerDependencies": {
"@types/react": "*",
"react": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-dialog": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/react-dialog/-/react-dialog-1.0.0.tgz",
"integrity": "sha512-Yn9YU+QlHYLWwV1XfKiqnGVpWYWk6MeBVM6x/bcoyPvxgjQGoeT35482viLPctTMWoMw0PoHgqfSox7Ig+957Q==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/primitive": "1.0.0",
"@radix-ui/react-compose-refs": "1.0.0",
"@radix-ui/react-context": "1.0.0",
"@radix-ui/react-dismissable-layer": "1.0.0",
"@radix-ui/react-focus-guards": "1.0.0",
"@radix-ui/react-focus-scope": "1.0.0",
"@radix-ui/react-id": "1.0.0",
"@radix-ui/react-portal": "1.0.0",
"@radix-ui/react-presence": "1.0.0",
"@radix-ui/react-primitive": "1.0.0",
"@radix-ui/react-slot": "1.0.0",
"@radix-ui/react-use-controllable-state": "1.0.0",
"aria-hidden": "^1.1.1",
"react-remove-scroll": "2.5.4"
},
"peerDependencies": {
"react": "^16.8 || ^17.0 || ^18.0",
"react-dom": "^16.8 || ^17.0 || ^18.0"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/primitive": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/primitive/-/primitive-1.0.0.tgz",
"integrity": "sha512-3e7rn8FDMin4CgeL7Z/49smCA3rFYY3Ha2rUQ7HRWFadS5iCRw08ZgVT1LaNTCNqgvrUiyczLflrVrF0SRQtNA==",
"dependencies": {
"@babel/runtime": "^7.13.10"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-compose-refs": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/react-compose-refs/-/react-compose-refs-1.0.0.tgz",
"integrity": "sha512-0KaSv6sx787/hK3eF53iOkiSLwAGlFMx5lotrqD2pTjB18KbybKoEIgkNZTKC60YECDQTKGTRcDBILwZVqVKvA==",
"dependencies": {
"@babel/runtime": "^7.13.10"
},
"peerDependencies": {
"react": "^16.8 || ^17.0 || ^18.0"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-context": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/react-context/-/react-context-1.0.0.tgz",
"integrity": "sha512-1pVM9RfOQ+n/N5PJK33kRSKsr1glNxomxONs5c49MliinBY6Yw2Q995qfBUUo0/Mbg05B/sGA0gkgPI7kmSHBg==",
"dependencies": {
"@babel/runtime": "^7.13.10"
},
"peerDependencies": {
"react": "^16.8 || ^17.0 || ^18.0"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-dismissable-layer": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/react-dismissable-layer/-/react-dismissable-layer-1.0.0.tgz",
"integrity": "sha512-n7kDRfx+LB1zLueRDvZ1Pd0bxdJWDUZNQ/GWoxDn2prnuJKRdxsjulejX/ePkOsLi2tTm6P24mDqlMSgQpsT6g==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/primitive": "1.0.0",
"@radix-ui/react-compose-refs": "1.0.0",
"@radix-ui/react-primitive": "1.0.0",
"@radix-ui/react-use-callback-ref": "1.0.0",
"@radix-ui/react-use-escape-keydown": "1.0.0"
},
"peerDependencies": {
"react": "^16.8 || ^17.0 || ^18.0",
"react-dom": "^16.8 || ^17.0 || ^18.0"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-focus-guards": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/react-focus-guards/-/react-focus-guards-1.0.0.tgz",
"integrity": "sha512-UagjDk4ijOAnGu4WMUPj9ahi7/zJJqNZ9ZAiGPp7waUWJO0O1aWXi/udPphI0IUjvrhBsZJGSN66dR2dsueLWQ==",
"dependencies": {
"@babel/runtime": "^7.13.10"
},
"peerDependencies": {
"react": "^16.8 || ^17.0 || ^18.0"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-focus-scope": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/react-focus-scope/-/react-focus-scope-1.0.0.tgz",
"integrity": "sha512-C4SWtsULLGf/2L4oGeIHlvWQx7Rf+7cX/vKOAD2dXW0A1b5QXwi3wWeaEgW+wn+SEVrraMUk05vLU9fZZz5HbQ==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-compose-refs": "1.0.0",
"@radix-ui/react-primitive": "1.0.0",
"@radix-ui/react-use-callback-ref": "1.0.0"
},
"peerDependencies": {
"react": "^16.8 || ^17.0 || ^18.0",
"react-dom": "^16.8 || ^17.0 || ^18.0"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-id": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/react-id/-/react-id-1.0.0.tgz",
"integrity": "sha512-Q6iAB/U7Tq3NTolBBQbHTgclPmGWE3OlktGGqrClPozSw4vkQ1DfQAOtzgRPecKsMdJINE05iaoDUG8tRzCBjw==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-use-layout-effect": "1.0.0"
},
"peerDependencies": {
"react": "^16.8 || ^17.0 || ^18.0"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-portal": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/react-portal/-/react-portal-1.0.0.tgz",
"integrity": "sha512-a8qyFO/Xb99d8wQdu4o7qnigNjTPG123uADNecz0eX4usnQEj7o+cG4ZX4zkqq98NYekT7UoEQIjxBNWIFuqTA==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-primitive": "1.0.0"
},
"peerDependencies": {
"react": "^16.8 || ^17.0 || ^18.0",
"react-dom": "^16.8 || ^17.0 || ^18.0"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-presence": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/react-presence/-/react-presence-1.0.0.tgz",
"integrity": "sha512-A+6XEvN01NfVWiKu38ybawfHsBjWum42MRPnEuqPsBZ4eV7e/7K321B5VgYMPv3Xx5An6o1/l9ZuDBgmcmWK3w==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-compose-refs": "1.0.0",
"@radix-ui/react-use-layout-effect": "1.0.0"
},
"peerDependencies": {
"react": "^16.8 || ^17.0 || ^18.0",
"react-dom": "^16.8 || ^17.0 || ^18.0"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-primitive": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-1.0.0.tgz",
"integrity": "sha512-EyXe6mnRlHZ8b6f4ilTDrXmkLShICIuOTTj0GX4w1rp+wSxf3+TD05u1UOITC8VsJ2a9nwHvdXtOXEOl0Cw/zQ==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-slot": "1.0.0"
},
"peerDependencies": {
"react": "^16.8 || ^17.0 || ^18.0",
"react-dom": "^16.8 || ^17.0 || ^18.0"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-slot": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/react-slot/-/react-slot-1.0.0.tgz",
"integrity": "sha512-3mrKauI/tWXo1Ll+gN5dHcxDPdm/Df1ufcDLCecn+pnCIVcdWE7CujXo8QaXOWRJyZyQWWbpB8eFwHzWXlv5mQ==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-compose-refs": "1.0.0"
},
"peerDependencies": {
"react": "^16.8 || ^17.0 || ^18.0"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-use-callback-ref": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/react-use-callback-ref/-/react-use-callback-ref-1.0.0.tgz",
"integrity": "sha512-GZtyzoHz95Rhs6S63D2t/eqvdFCm7I+yHMLVQheKM7nBD8mbZIt+ct1jz4536MDnaOGKIxynJ8eHTkVGVVkoTg==",
"dependencies": {
"@babel/runtime": "^7.13.10"
},
"peerDependencies": {
"react": "^16.8 || ^17.0 || ^18.0"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-use-controllable-state": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/react-use-controllable-state/-/react-use-controllable-state-1.0.0.tgz",
"integrity": "sha512-FohDoZvk3mEXh9AWAVyRTYR4Sq7/gavuofglmiXB2g1aKyboUD4YtgWxKj8O5n+Uak52gXQ4wKz5IFST4vtJHg==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-use-callback-ref": "1.0.0"
},
"peerDependencies": {
"react": "^16.8 || ^17.0 || ^18.0"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-use-escape-keydown": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/react-use-escape-keydown/-/react-use-escape-keydown-1.0.0.tgz",
"integrity": "sha512-JwfBCUIfhXRxKExgIqGa4CQsiMemo1Xt0W/B4ei3fpzpvPENKpMKQ8mZSB6Acj3ebrAEgi2xiQvcI1PAAodvyg==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-use-callback-ref": "1.0.0"
},
"peerDependencies": {
"react": "^16.8 || ^17.0 || ^18.0"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/@radix-ui/react-use-layout-effect": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/@radix-ui/react-use-layout-effect/-/react-use-layout-effect-1.0.0.tgz",
"integrity": "sha512-6Tpkq+R6LOlmQb1R5NNETLG0B4YP0wc+klfXafpUCj6JGyaUc8il7/kUZ7m59rGbXGczE9Bs+iz2qloqsZBduQ==",
"dependencies": {
"@babel/runtime": "^7.13.10"
},
"peerDependencies": {
"react": "^16.8 || ^17.0 || ^18.0"
}
},
"node_modules/@radix-ui/react-dialog/node_modules/react-remove-scroll": {
"version": "2.5.4",
"resolved": "https://registry.npmjs.org/react-remove-scroll/-/react-remove-scroll-2.5.4.tgz",
"integrity": "sha512-xGVKJJr0SJGQVirVFAUZ2k1QLyO6m+2fy0l8Qawbp5Jgrv3DeLalrfMNBFSlmz5kriGGzsVBtGVnf4pTKIhhWA==",
"dependencies": {
"react-remove-scroll-bar": "^2.3.3",
"react-style-singleton": "^2.2.1",
"tslib": "^2.1.0",
"use-callback-ref": "^1.3.0",
"use-sidecar": "^1.1.2"
},
"engines": {
"node": ">=10"
},
"peerDependencies": {
"@types/react": "^16.8.0 || ^17.0.0 || ^18.0.0",
"react": "^16.8.0 || ^17.0.0 || ^18.0.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-dismissable-layer": {
"version": "1.0.5",
"resolved": "https://registry.npmjs.org/@radix-ui/react-dismissable-layer/-/react-dismissable-layer-1.0.5.tgz",
"integrity": "sha512-aJeDjQhywg9LBu2t/At58hCvr7pEm0o2Ke1x33B+MhjNmmZ17sy4KImo0KPLgsnc/zN7GPdce8Cnn0SWvwZO7g==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/primitive": "1.0.1",
"@radix-ui/react-compose-refs": "1.0.1",
"@radix-ui/react-primitive": "1.0.3",
"@radix-ui/react-use-callback-ref": "1.0.1",
"@radix-ui/react-use-escape-keydown": "1.0.3"
},
"peerDependencies": {
"@types/react": "*",
"@types/react-dom": "*",
"react": "^16.8 || ^17.0 || ^18.0",
"react-dom": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
},
"@types/react-dom": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-focus-guards": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/@radix-ui/react-focus-guards/-/react-focus-guards-1.0.1.tgz",
"integrity": "sha512-Rect2dWbQ8waGzhMavsIbmSVCgYxkXLxxR3ZvCX79JOglzdEy4JXMb98lq4hPxUbLr77nP0UOGf4rcMU+s1pUA==",
"dependencies": {
"@babel/runtime": "^7.13.10"
},
"peerDependencies": {
"@types/react": "*",
"react": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-focus-scope": {
"version": "1.0.4",
"resolved": "https://registry.npmjs.org/@radix-ui/react-focus-scope/-/react-focus-scope-1.0.4.tgz",
"integrity": "sha512-sL04Mgvf+FmyvZeYfNu1EPAaaxD+aw7cYeIB9L9Fvq8+urhltTRaEo5ysKOpHuKPclsZcSUMKlN05x4u+CINpA==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-compose-refs": "1.0.1",
"@radix-ui/react-primitive": "1.0.3",
"@radix-ui/react-use-callback-ref": "1.0.1"
},
"peerDependencies": {
"@types/react": "*",
"@types/react-dom": "*",
"react": "^16.8 || ^17.0 || ^18.0",
"react-dom": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
},
"@types/react-dom": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-id": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/@radix-ui/react-id/-/react-id-1.0.1.tgz",
"integrity": "sha512-tI7sT/kqYp8p96yGWY1OAnLHrqDgzHefRBKQ2YAkBS5ja7QLcZ9Z/uY7bEjPUatf8RomoXM8/1sMj1IJaE5UzQ==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-use-layout-effect": "1.0.1"
},
"peerDependencies": {
"@types/react": "*",
"react": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-popover": {
"version": "1.0.7",
"resolved": "https://registry.npmjs.org/@radix-ui/react-popover/-/react-popover-1.0.7.tgz",
"integrity": "sha512-shtvVnlsxT6faMnK/a7n0wptwBD23xc1Z5mdrtKLwVEfsEMXodS0r5s0/g5P0hX//EKYZS2sxUjqfzlg52ZSnQ==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/primitive": "1.0.1",
"@radix-ui/react-compose-refs": "1.0.1",
"@radix-ui/react-context": "1.0.1",
"@radix-ui/react-dismissable-layer": "1.0.5",
"@radix-ui/react-focus-guards": "1.0.1",
"@radix-ui/react-focus-scope": "1.0.4",
"@radix-ui/react-id": "1.0.1",
"@radix-ui/react-popper": "1.1.3",
"@radix-ui/react-portal": "1.0.4",
"@radix-ui/react-presence": "1.0.1",
"@radix-ui/react-primitive": "1.0.3",
"@radix-ui/react-slot": "1.0.2",
"@radix-ui/react-use-controllable-state": "1.0.1",
"aria-hidden": "^1.1.1",
"react-remove-scroll": "2.5.5"
},
"peerDependencies": {
"@types/react": "*",
"@types/react-dom": "*",
"react": "^16.8 || ^17.0 || ^18.0",
"react-dom": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
},
"@types/react-dom": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-popper": {
"version": "1.1.3",
"resolved": "https://registry.npmjs.org/@radix-ui/react-popper/-/react-popper-1.1.3.tgz",
"integrity": "sha512-cKpopj/5RHZWjrbF2846jBNacjQVwkP068DfmgrNJXpvVWrOvlAmE9xSiy5OqeE+Gi8D9fP+oDhUnPqNMY8/5w==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@floating-ui/react-dom": "^2.0.0",
"@radix-ui/react-arrow": "1.0.3",
"@radix-ui/react-compose-refs": "1.0.1",
"@radix-ui/react-context": "1.0.1",
"@radix-ui/react-primitive": "1.0.3",
"@radix-ui/react-use-callback-ref": "1.0.1",
"@radix-ui/react-use-layout-effect": "1.0.1",
"@radix-ui/react-use-rect": "1.0.1",
"@radix-ui/react-use-size": "1.0.1",
"@radix-ui/rect": "1.0.1"
},
"peerDependencies": {
"@types/react": "*",
"@types/react-dom": "*",
"react": "^16.8 || ^17.0 || ^18.0",
"react-dom": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
},
"@types/react-dom": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-portal": {
"version": "1.0.4",
"resolved": "https://registry.npmjs.org/@radix-ui/react-portal/-/react-portal-1.0.4.tgz",
"integrity": "sha512-Qki+C/EuGUVCQTOTD5vzJzJuMUlewbzuKyUy+/iHM2uwGiru9gZeBJtHAPKAEkB5KWGi9mP/CHKcY0wt1aW45Q==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-primitive": "1.0.3"
},
"peerDependencies": {
"@types/react": "*",
"@types/react-dom": "*",
"react": "^16.8 || ^17.0 || ^18.0",
"react-dom": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
},
"@types/react-dom": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-presence": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/@radix-ui/react-presence/-/react-presence-1.0.1.tgz",
"integrity": "sha512-UXLW4UAbIY5ZjcvzjfRFo5gxva8QirC9hF7wRE4U5gz+TP0DbRk+//qyuAQ1McDxBt1xNMBTaciFGvEmJvAZCg==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-compose-refs": "1.0.1",
"@radix-ui/react-use-layout-effect": "1.0.1"
},
"peerDependencies": {
"@types/react": "*",
"@types/react-dom": "*",
"react": "^16.8 || ^17.0 || ^18.0",
"react-dom": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
},
"@types/react-dom": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-primitive": {
"version": "1.0.3",
"resolved": "https://registry.npmjs.org/@radix-ui/react-primitive/-/react-primitive-1.0.3.tgz",
"integrity": "sha512-yi58uVyoAcK/Nq1inRY56ZSjKypBNKTa/1mcL8qdl6oJeEaDbOldlzrGn7P6Q3Id5d+SYNGc5AJgc4vGhjs5+g==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-slot": "1.0.2"
},
"peerDependencies": {
"@types/react": "*",
"@types/react-dom": "*",
"react": "^16.8 || ^17.0 || ^18.0",
"react-dom": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
},
"@types/react-dom": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-slot": {
"version": "1.0.2",
"resolved": "https://registry.npmjs.org/@radix-ui/react-slot/-/react-slot-1.0.2.tgz",
"integrity": "sha512-YeTpuq4deV+6DusvVUW4ivBgnkHwECUu0BiN43L5UCDFgdhsRUWAghhTF5MbvNTPzmiFOx90asDSUjWuCNapwg==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-compose-refs": "1.0.1"
},
"peerDependencies": {
"@types/react": "*",
"react": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-use-callback-ref": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/@radix-ui/react-use-callback-ref/-/react-use-callback-ref-1.0.1.tgz",
"integrity": "sha512-D94LjX4Sp0xJFVaoQOd3OO9k7tpBYNOXdVhkltUbGv2Qb9OXdrg/CpsjlZv7ia14Sylv398LswWBVVu5nqKzAQ==",
"dependencies": {
"@babel/runtime": "^7.13.10"
},
"peerDependencies": {
"@types/react": "*",
"react": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-use-controllable-state": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/@radix-ui/react-use-controllable-state/-/react-use-controllable-state-1.0.1.tgz",
"integrity": "sha512-Svl5GY5FQeN758fWKrjM6Qb7asvXeiZltlT4U2gVfl8Gx5UAv2sMR0LWo8yhsIZh2oQ0eFdZ59aoOOMV7b47VA==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-use-callback-ref": "1.0.1"
},
"peerDependencies": {
"@types/react": "*",
"react": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-use-escape-keydown": {
"version": "1.0.3",
"resolved": "https://registry.npmjs.org/@radix-ui/react-use-escape-keydown/-/react-use-escape-keydown-1.0.3.tgz",
"integrity": "sha512-vyL82j40hcFicA+M4Ex7hVkB9vHgSse1ZWomAqV2Je3RleKGO5iM8KMOEtfoSB0PnIelMd2lATjTGMYqN5ylTg==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-use-callback-ref": "1.0.1"
},
"peerDependencies": {
"@types/react": "*",
"react": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-use-layout-effect": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/@radix-ui/react-use-layout-effect/-/react-use-layout-effect-1.0.1.tgz",
"integrity": "sha512-v/5RegiJWYdoCvMnITBkNNx6bCj20fiaJnWtRkU18yITptraXjffz5Qbn05uOiQnOvi+dbkznkoaMltz1GnszQ==",
"dependencies": {
"@babel/runtime": "^7.13.10"
},
"peerDependencies": {
"@types/react": "*",
"react": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-use-rect": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/@radix-ui/react-use-rect/-/react-use-rect-1.0.1.tgz",
"integrity": "sha512-Cq5DLuSiuYVKNU8orzJMbl15TXilTnJKUCltMVQg53BQOF1/C5toAaGrowkgksdBQ9H+SRL23g0HDmg9tvmxXw==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/rect": "1.0.1"
},
"peerDependencies": {
"@types/react": "*",
"react": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/@radix-ui/react-use-size": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/@radix-ui/react-use-size/-/react-use-size-1.0.1.tgz",
"integrity": "sha512-ibay+VqrgcaI6veAojjofPATwledXiSmX+C0KrBk/xgpX9rBzPV3OsfwlhQdUOFbh+LKQorLYT+xTXW9V8yd0g==",
"dependencies": {
"@babel/runtime": "^7.13.10",
"@radix-ui/react-use-layout-effect": "1.0.1"
},
"peerDependencies": {
"@types/react": "*",
"react": "^16.8 || ^17.0 || ^18.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/@radix-ui/rect": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/@radix-ui/rect/-/rect-1.0.1.tgz",
"integrity": "sha512-fyrgCaedtvMg9NK3en0pnOYJdtfwxUcNolezkNPUsoX57X8oQk+NkqcvzHXD2uKNij6GXmWU9NDru2IWjrO4BQ==",
"dependencies": {
"@babel/runtime": "^7.13.10"
}
},
"node_modules/aria-hidden": {
"version": "1.2.3",
"resolved": "https://registry.npmjs.org/aria-hidden/-/aria-hidden-1.2.3.tgz",
"integrity": "sha512-xcLxITLe2HYa1cnYnwCjkOO1PqUHQpozB8x9AR0OgWN2woOBi5kSDVxKfd0b7sb1hw5qFeJhXm9H1nu3xSfLeQ==",
"dependencies": {
"tslib": "^2.0.0"
},
"engines": {
"node": ">=10"
}
},
"node_modules/cmdk": {
"version": "0.2.0",
"resolved": "https://registry.npmjs.org/cmdk/-/cmdk-0.2.0.tgz",
"integrity": "sha512-JQpKvEOb86SnvMZbYaFKYhvzFntWBeSZdyii0rZPhKJj9uwJBxu4DaVYDrRN7r3mPop56oPhRw+JYWTKs66TYw==",
"dependencies": {
"@radix-ui/react-dialog": "1.0.0",
"command-score": "0.1.2"
},
"peerDependencies": {
"react": "^18.0.0",
"react-dom": "^18.0.0"
}
},
"node_modules/command-score": {
"version": "0.1.2",
"resolved": "https://registry.npmjs.org/command-score/-/command-score-0.1.2.tgz",
"integrity": "sha512-VtDvQpIJBvBatnONUsPzXYFVKQQAhuf3XTNOAsdBxCNO/QCtUUd8LSgjn0GVarBkCad6aJCZfXgrjYbl/KRr7w=="
},
"node_modules/detect-node-es": {
"version": "1.1.0",
"resolved": "https://registry.npmjs.org/detect-node-es/-/detect-node-es-1.1.0.tgz",
"integrity": "sha512-ypdmJU/TbBby2Dxibuv7ZLW3Bs1QEmM7nHjEANfohJLvE0XVujisn1qPJcZxg+qDucsr+bP6fLD1rPS3AhJ7EQ=="
},
"node_modules/get-nonce": {
"version": "1.0.1",
"resolved": "https://registry.npmjs.org/get-nonce/-/get-nonce-1.0.1.tgz",
"integrity": "sha512-FJhYRoDaiatfEkUK8HKlicmu/3SGFD51q3itKDGoSTysQJBnfOcxU5GxnhE1E6soB76MbT0MBtnKJuXyAx+96Q==",
"engines": {
"node": ">=6"
}
},
"node_modules/invariant": {
"version": "2.2.4",
"resolved": "https://registry.npmjs.org/invariant/-/invariant-2.2.4.tgz",
"integrity": "sha512-phJfQVBuaJM5raOpJjSfkiD6BpbCE4Ns//LaXl6wGYtUBY83nWS6Rf9tXm2e8VaK60JEjYldbPif/A2B1C2gNA==",
"dependencies": {
"loose-envify": "^1.0.0"
}
},
"node_modules/js-tokens": {
"version": "4.0.0",
"resolved": "https://registry.npmjs.org/js-tokens/-/js-tokens-4.0.0.tgz",
"integrity": "sha512-RdJUflcE3cUzKiMqQgsCu06FPu9UdIJO0beYbPhHN4k6apgJtifcoCtT9bcxOpYBtpD2kCM6Sbzg4CausW/PKQ=="
},
"node_modules/loose-envify": {
"version": "1.4.0",
"resolved": "https://registry.npmjs.org/loose-envify/-/loose-envify-1.4.0.tgz",
"integrity": "sha512-lyuxPGr/Wfhrlem2CL/UcnUc1zcqKAImBDzukY7Y5F/yQiNdko6+fRLevlw1HgMySw7f611UIY408EtxRSoK3Q==",
"dependencies": {
"js-tokens": "^3.0.0 || ^4.0.0"
},
"bin": {
"loose-envify": "cli.js"
}
},
"node_modules/react": {
"version": "18.2.0",
"resolved": "https://registry.npmjs.org/react/-/react-18.2.0.tgz",
"integrity": "sha512-/3IjMdb2L9QbBdWiW5e3P2/npwMBaU9mHCSCUzNln0ZCYbcfTsGbTJrU/kGemdH2IWmB2ioZ+zkxtmq6g09fGQ==",
"peer": true,
"dependencies": {
"loose-envify": "^1.1.0"
},
"engines": {
"node": ">=0.10.0"
}
},
"node_modules/react-dom": {
"version": "18.2.0",
"resolved": "https://registry.npmjs.org/react-dom/-/react-dom-18.2.0.tgz",
"integrity": "sha512-6IMTriUmvsjHUjNtEDudZfuDQUoWXVxKHhlEGSk81n4YFS+r/Kl99wXiwlVXtPBtJenozv2P+hxDsw9eA7Xo6g==",
"peer": true,
"dependencies": {
"loose-envify": "^1.1.0",
"scheduler": "^0.23.0"
},
"peerDependencies": {
"react": "^18.2.0"
}
},
"node_modules/react-remove-scroll": {
"version": "2.5.5",
"resolved": "https://registry.npmjs.org/react-remove-scroll/-/react-remove-scroll-2.5.5.tgz",
"integrity": "sha512-ImKhrzJJsyXJfBZ4bzu8Bwpka14c/fQt0k+cyFp/PBhTfyDnU5hjOtM4AG/0AMyy8oKzOTR0lDgJIM7pYXI0kw==",
"dependencies": {
"react-remove-scroll-bar": "^2.3.3",
"react-style-singleton": "^2.2.1",
"tslib": "^2.1.0",
"use-callback-ref": "^1.3.0",
"use-sidecar": "^1.1.2"
},
"engines": {
"node": ">=10"
},
"peerDependencies": {
"@types/react": "^16.8.0 || ^17.0.0 || ^18.0.0",
"react": "^16.8.0 || ^17.0.0 || ^18.0.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/react-remove-scroll-bar": {
"version": "2.3.4",
"resolved": "https://registry.npmjs.org/react-remove-scroll-bar/-/react-remove-scroll-bar-2.3.4.tgz",
"integrity": "sha512-63C4YQBUt0m6ALadE9XV56hV8BgJWDmmTPY758iIJjfQKt2nYwoUrPk0LXRXcB/yIj82T1/Ixfdpdk68LwIB0A==",
"dependencies": {
"react-style-singleton": "^2.2.1",
"tslib": "^2.0.0"
},
"engines": {
"node": ">=10"
},
"peerDependencies": {
"@types/react": "^16.8.0 || ^17.0.0 || ^18.0.0",
"react": "^16.8.0 || ^17.0.0 || ^18.0.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/react-style-singleton": {
"version": "2.2.1",
"resolved": "https://registry.npmjs.org/react-style-singleton/-/react-style-singleton-2.2.1.tgz",
"integrity": "sha512-ZWj0fHEMyWkHzKYUr2Bs/4zU6XLmq9HsgBURm7g5pAVfyn49DgUiNgY2d4lXRlYSiCif9YBGpQleewkcqddc7g==",
"dependencies": {
"get-nonce": "^1.0.0",
"invariant": "^2.2.4",
"tslib": "^2.0.0"
},
"engines": {
"node": ">=10"
},
"peerDependencies": {
"@types/react": "^16.8.0 || ^17.0.0 || ^18.0.0",
"react": "^16.8.0 || ^17.0.0 || ^18.0.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/regenerator-runtime": {
"version": "0.14.0",
"resolved": "https://registry.npmjs.org/regenerator-runtime/-/regenerator-runtime-0.14.0.tgz",
"integrity": "sha512-srw17NI0TUWHuGa5CFGGmhfNIeja30WMBfbslPNhf6JrqQlLN5gcrvig1oqPxiVaXb0oW0XRKtH6Nngs5lKCIA=="
},
"node_modules/scheduler": {
"version": "0.23.0",
"resolved": "https://registry.npmjs.org/scheduler/-/scheduler-0.23.0.tgz",
"integrity": "sha512-CtuThmgHNg7zIZWAXi3AsyIzA3n4xx7aNyjwC2VJldO2LMVDhFK+63xGqq6CsJH4rTAt6/M+N4GhZiDYPx9eUw==",
"peer": true,
"dependencies": {
"loose-envify": "^1.1.0"
}
},
"node_modules/tslib": {
"version": "2.6.2",
"resolved": "https://registry.npmjs.org/tslib/-/tslib-2.6.2.tgz",
"integrity": "sha512-AEYxH93jGFPn/a2iVAwW87VuUIkR1FVUKB77NwMF7nBTDkDrrT/Hpt/IrCJ0QXhW27jTBDcf5ZY7w6RiqTMw2Q=="
},
"node_modules/use-callback-ref": {
"version": "1.3.0",
"resolved": "https://registry.npmjs.org/use-callback-ref/-/use-callback-ref-1.3.0.tgz",
"integrity": "sha512-3FT9PRuRdbB9HfXhEq35u4oZkvpJ5kuYbpqhCfmiZyReuRgpnhDlbr2ZEnnuS0RrJAPn6l23xjFg9kpDM+Ms7w==",
"dependencies": {
"tslib": "^2.0.0"
},
"engines": {
"node": ">=10"
},
"peerDependencies": {
"@types/react": "^16.8.0 || ^17.0.0 || ^18.0.0",
"react": "^16.8.0 || ^17.0.0 || ^18.0.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
},
"node_modules/use-sidecar": {
"version": "1.1.2",
"resolved": "https://registry.npmjs.org/use-sidecar/-/use-sidecar-1.1.2.tgz",
"integrity": "sha512-epTbsLuzZ7lPClpz2TyryBfztm7m+28DlEv2ZCQ3MDr5ssiwyOwGH/e5F9CkfWjJ1t4clvI58yF822/GUkjjhw==",
"dependencies": {
"detect-node-es": "^1.1.0",
"tslib": "^2.0.0"
},
"engines": {
"node": ">=10"
},
"peerDependencies": {
"@types/react": "^16.9.0 || ^17.0.0 || ^18.0.0",
"react": "^16.8.0 || ^17.0.0 || ^18.0.0"
},
"peerDependenciesMeta": {
"@types/react": {
"optional": true
}
}
}
}
}

6
package.json Normal file
View file

@ -0,0 +1,6 @@
{
"dependencies": {
"@radix-ui/react-popover": "^1.0.7",
"cmdk": "^0.2.0"
}
}

5311
poetry.lock generated
View file

File diff suppressed because it is too large Load diff

69
pyproject.toml
View file

@ -1,6 +1,6 @@
[tool.poetry]
name = "langflow"
version = "0.5.1"
version = "0.6.0a0"
description = "A Python package with a built-in web application"
authors = ["Logspace <contact@logspace.ai>"]
maintainers = [
@ -25,30 +25,32 @@ documentation = "https://docs.langflow.org"
langflow = "langflow.__main__:main"
[tool.poetry.dependencies]
python = ">=3.9,<3.11"
fastapi = "^0.103.0"
fastapi = "^0.104.0"
uvicorn = "^0.23.0"
beautifulsoup4 = "^4.12.2"
google-search-results = "^2.4.1"
google-api-python-client = "^2.79.0"
typer = "^0.9.0"
gunicorn = "^21.2.0"
langchain = "^0.0.308"
openai = "^0.27.8"
langchain = "~0.0.338"
openai = "^1.3.4"
pandas = "2.0.3"
chromadb = "^0.3.21"
huggingface-hub = { version = "^0.16.0", extras = ["inference"] }
rich = "^13.5.0"
llama-cpp-python = { version = "~0.1.0", optional = true }
chromadb = "^0.4.0"
huggingface-hub = { version = "^0.19.0", extras = ["inference"] }
rich = "^13.7.0"
llama-cpp-python = { version = "~0.2.0", optional = true }
networkx = "^3.1"
unstructured = "^0.10.0"
pypdf = "^3.15.0"
pypdf = "^3.17.0"
lxml = "^4.9.2"
pysrt = "^1.1.2"
fake-useragent = "^1.2.1"
fake-useragent = "^1.3.0"
docstring-parser = "^0.15"
psycopg2-binary = "^2.9.6"
pyarrow = "^12.0.0"
pyarrow = "^14.0.0"
tiktoken = "~0.5.0"
wikipedia = "^1.4.0"
qdrant-client = "^1.4.0"
@ -57,25 +59,26 @@ weaviate-client = "^3.23.0"
jina = "3.15.2"
sentence-transformers = { version = "^2.2.2", optional = true }
ctransformers = { version = "^0.2.10", optional = true }
cohere = "^4.27.0"
cohere = "^4.32.0"
python-multipart = "^0.0.6"
sqlmodel = "^0.0.8"
# install sqlmodel using https://github.com/honglei/sqlmodel.git
sqlmodel = { git = "https://github.com/honglei/sqlmodel.git", branch = "main" }
faiss-cpu = "^1.7.4"
anthropic = "^0.3.0"
anthropic = "^0.5.0"
orjson = "3.9.3"
multiprocess = "^0.70.14"
cachetools = "^5.3.1"
types-cachetools = "^5.3.0.5"
appdirs = "^1.4.4"
platformdirs = "^3.11.0"
pinecone-client = "^2.2.2"
supabase = "^1.0.3"
pymongo = "^4.4.0"
pymongo = "^4.5.0"
supabase = "^2.0.3"
certifi = "^2023.5.7"
google-cloud-aiplatform = "^1.26.1"
google-cloud-aiplatform = "^1.36.0"
psycopg = "^3.1.9"
psycopg-binary = "^3.1.9"
fastavro = "^1.8.0"
langchain-experimental = "^0.0.8"
langchain-experimental = "*"
celery = { extras = ["redis"], version = "^5.3.1", optional = true }
redis = { version = "^4.6.0", optional = true }
flower = { version = "^2.0.0", optional = true }
@ -84,28 +87,35 @@ passlib = "^1.7.4"
bcrypt = "^4.0.1"
python-jose = "^3.3.0"
metaphor-python = "^0.1.11"
pydantic = "^2.0.0"
pydantic-settings = "^2.0.3"
zep-python = { version = "^1.3.0", allow-prereleases = true }
pywin32 = { version = "^306", markers = "sys_platform == 'win32'" }
loguru = "^0.7.1"
langfuse = "^1.0.13"
langfuse = "^1.1.11"
pillow = "^10.0.0"
metal-sdk = "^2.2.0"
metal-sdk = "^2.4.0"
markupsafe = "^2.1.3"
extract-msg = "^0.45.0"
jq = "^1.6.0"
boto3 = "^1.28.63"
numexpr = "^2.8.6"
qianfan = "0.0.5"
pgvector = "^0.2.3"
[tool.poetry.group.dev.dependencies]
pytest-asyncio = "^0.21.1"
types-redis = "^4.6.0.5"
black = "^23.1.0"
ipykernel = "^6.21.2"
mypy = "^1.1.1"
ruff = "^0.0.254"
ruff = "^0.1.5"
httpx = "*"
pytest = "^7.2.2"
types-requests = "^2.28.11"
requests = "^2.28.0"
pytest-cov = "^4.0.0"
pytest = "^7.4.2"
types-requests = "^2.31.0"
requests = "^2.31.0"
pytest-cov = "^4.1.0"
pandas-stubs = "^2.0.0.230412"
types-pillow = "^9.5.0.2"
types-appdirs = "^1.4.3.5"
types-pyyaml = "^6.0.12.8"
types-python-jose = "^3.3.4.8"
types-passlib = "^1.7.7.13"
@ -134,6 +144,7 @@ markers = ["async_test"]
[tool.ruff]
exclude = ["src/backend/langflow/alembic/*"]
line-length = 120
[build-system]

61
src/backend/langflow/__main__.py
View file

@ -11,7 +11,7 @@ import typer
from dotenv import load_dotenv
from langflow.main import setup_app
from langflow.services.database.utils import session_getter
from langflow.services.getters import get_db_service, get_settings_service
from langflow.services.deps import get_db_service, get_settings_service
from langflow.services.utils import initialize_services, initialize_settings_service
from langflow.utils.logger import configure, logger
from multiprocess import Process, cpu_count # type: ignore
@ -61,6 +61,8 @@ def set_var_for_macos_issue():
import os
os.environ["OBJC_DISABLE_INITIALIZE_FORK_SAFETY"] = "YES"
# https://stackoverflow.com/questions/75747888/uwsgi-segmentation-fault-with-flask-python-app-behind-nginx-after-running-for-2 # noqa
os.environ["no_proxy"] = "*" # to avoid error with gunicorn
logger.debug("Set OBJC_DISABLE_INITIALIZE_FORK_SAFETY to YES to avoid error")
@ -70,6 +72,7 @@ def update_settings(
dev: bool = False,
remove_api_keys: bool = False,
components_path: Optional[Path] = None,
store: bool = True,
):
"""Update the settings from a config file."""
@ -88,16 +91,15 @@ def update_settings(
if components_path:
logger.debug(f"Adding component path {components_path}")
settings_service.settings.update_settings(COMPONENTS_PATH=components_path)
if not store:
logger.debug("Setting store to False")
settings_service.settings.update_settings(STORE=False)
@app.command()
def run(
host: str = typer.Option(
"127.0.0.1", help="Host to bind the server to.", envvar="LANGFLOW_HOST"
),
workers: int = typer.Option(
1, help="Number of worker processes.", envvar="LANGFLOW_WORKERS"
),
host: str = typer.Option("127.0.0.1", help="Host to bind the server to.", envvar="LANGFLOW_HOST"),
workers: int = typer.Option(1, help="Number of worker processes.", envvar="LANGFLOW_WORKERS"),
timeout: int = typer.Option(300, help="Worker timeout in seconds."),
port: int = typer.Option(7860, help="Port to listen on.", envvar="LANGFLOW_PORT"),
components_path: Optional[Path] = typer.Option(
@ -105,32 +107,17 @@ def run(
help="Path to the directory containing custom components.",
envvar="LANGFLOW_COMPONENTS_PATH",
),
config: str = typer.Option(
Path(__file__).parent / "config.yaml", help="Path to the configuration file."
),
config: str = typer.Option(Path(__file__).parent / "config.yaml", help="Path to the configuration file."),
# .env file param
env_file: Path = typer.Option(
None, help="Path to the .env file containing environment variables."
),
log_level: str = typer.Option(
"critical", help="Logging level.", envvar="LANGFLOW_LOG_LEVEL"
),
log_file: Path = typer.Option(
"logs/langflow.log", help="Path to the log file.", envvar="LANGFLOW_LOG_FILE"
),
env_file: Path = typer.Option(None, help="Path to the .env file containing environment variables."),
log_level: str = typer.Option("critical", help="Logging level.", envvar="LANGFLOW_LOG_LEVEL"),
log_file: Path = typer.Option("logs/langflow.log", help="Path to the log file.", envvar="LANGFLOW_LOG_FILE"),
cache: Optional[str] = typer.Option(
envvar="LANGFLOW_LANGCHAIN_CACHE",
help="Type of cache to use. (InMemoryCache, SQLiteCache)",
default=None,
),
dev: bool = typer.Option(False, help="Run in development mode (may contain bugs)"),
# This variable does not work but is set by the .env file
# and works with Pydantic
# database_url: str = typer.Option(
# None,
# help="Database URL to connect to. If not provided, a local SQLite database will be used.",
# envvar="LANGFLOW_DATABASE_URL",
# ),
path: str = typer.Option(
None,
help="Path to the frontend directory containing build files. This is for development purposes only.",
@ -151,6 +138,11 @@ def run(
help="Run only the backend server without the frontend.",
envvar="LANGFLOW_BACKEND_ONLY",
),
store: bool = typer.Option(
True,
help="Enables the store features.",
envvar="LANGFLOW_STORE",
),
):
"""
Run the Langflow.
@ -169,6 +161,7 @@ def run(
remove_api_keys=remove_api_keys,
cache=cache,
components_path=components_path,
store=store,
)
# create path object if path is provided
static_files_dir: Optional[Path] = Path(path) if path else None
@ -198,9 +191,7 @@ def run(
def run_on_mac_or_linux(host, port, log_level, options, app, open_browser=True):
webapp_process = Process(
target=run_langflow, args=(host, port, log_level, options, app)
)
webapp_process = Process(target=run_langflow, args=(host, port, log_level, options, app))
webapp_process.start()
status_code = 0
while status_code != 200:
@ -276,9 +267,7 @@ def print_banner(host, port):
)
# Create a panel with the title and the info text, and a border around it
panel = Panel(
f"{title}\n{info_text}", box=box.ROUNDED, border_style="blue", expand=False
)
panel = Panel(f"{title}\n{info_text}", box=box.ROUNDED, border_style="blue", expand=False)
# Print the banner with a separator line before and after
rprint(panel)
@ -310,12 +299,8 @@ def run_langflow(host, port, log_level, options, app):
@app.command()
def superuser(
username: str = typer.Option(..., prompt=True, help="Username for the superuser."),
password: str = typer.Option(
..., prompt=True, hide_input=True, help="Password for the superuser."
),
log_level: str = typer.Option(
"critical", help="Logging level.", envvar="LANGFLOW_LOG_LEVEL"
),
password: str = typer.Option(..., prompt=True, hide_input=True, help="Password for the superuser."),
log_level: str = typer.Option("critical", help="Logging level.", envvar="LANGFLOW_LOG_LEVEL"),
):
"""
Create a superuser.

2
src/backend/langflow/alembic/env.py
View file

@ -5,7 +5,7 @@ from sqlalchemy import pool
from alembic import context
from langflow.services.database.manager import SQLModel
from langflow.services.database.service import SQLModel
# this is the Alembic Config object, which provides
# access to the values within the .ini file in use.

48
src/backend/langflow/alembic/versions/7843803a87b5_store_updates.py Normal file
View file

@ -0,0 +1,48 @@
"""Store updates
Revision ID: 7843803a87b5
Revises: eb5866d51fd2
Create Date: 2023-10-18 23:08:57.744906
"""
from typing import Sequence, Union
from alembic import op
import sqlalchemy as sa
import sqlmodel
# revision identifiers, used by Alembic.
revision: str = "7843803a87b5"
down_revision: Union[str, None] = "eb5866d51fd2"
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
# ### commands auto generated by Alembic - please adjust! ###
try:
with op.batch_alter_table("flow", schema=None) as batch_op:
batch_op.add_column(sa.Column("is_component", sa.Boolean(), nullable=True))
with op.batch_alter_table("user", schema=None) as batch_op:
batch_op.add_column(
sa.Column(
"store_api_key", sqlmodel.sql.sqltypes.AutoString(), nullable=True
)
)
except Exception:
pass
# ### end Alembic commands ###
def downgrade() -> None:
# ### commands auto generated by Alembic - please adjust! ###
with op.batch_alter_table("user", schema=None) as batch_op:
batch_op.drop_column("store_api_key")
with op.batch_alter_table("flow", schema=None) as batch_op:
batch_op.drop_column("is_component")
# ### end Alembic commands ###

90
src/backend/langflow/alembic/versions/7d2162acc8b2_adds_updated_at_and_folder_cols.py Normal file
View file

@ -0,0 +1,90 @@
"""Adds updated_at and folder cols
Revision ID: 7d2162acc8b2
Revises: f5ee9749d1a6
Create Date: 2023-11-21 20:56:53.998781
"""
from typing import Sequence, Union
import sqlalchemy as sa
import sqlmodel
from alembic import op
# revision identifiers, used by Alembic.
revision: str = '7d2162acc8b2'
down_revision: Union[str, None] = 'f5ee9749d1a6'
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
# ### commands auto generated by Alembic - please adjust! ###
with op.batch_alter_table('component', schema=None) as batch_op:
batch_op.drop_index('ix_component_frontend_node_id')
batch_op.drop_index('ix_component_name')
op.drop_table('component')
op.drop_table('flowstyle')
with op.batch_alter_table('apikey', schema=None) as batch_op:
batch_op.alter_column('name',
existing_type=sa.VARCHAR(),
nullable=False)
with op.batch_alter_table('flow', schema=None) as batch_op:
batch_op.add_column(sa.Column('updated_at', sa.DateTime(), nullable=True))
batch_op.add_column(sa.Column('folder', sqlmodel.sql.sqltypes.AutoString(), nullable=True))
# ### end Alembic commands ###
def downgrade() -> None:
# ### commands auto generated by Alembic - please adjust! ###
try:
with op.batch_alter_table('flow', schema=None) as batch_op:
batch_op.drop_column('folder')
batch_op.drop_column('updated_at')
except Exception as e:
print(e)
pass
try:
with op.batch_alter_table('apikey', schema=None) as batch_op:
batch_op.alter_column('name',
existing_type=sa.VARCHAR(),
nullable=True)
except Exception as e:
print(e)
pass
try:
op.create_table('flowstyle',
sa.Column('color', sa.VARCHAR(), nullable=False),
sa.Column('emoji', sa.VARCHAR(), nullable=False),
sa.Column('flow_id', sa.CHAR(length=32), nullable=True),
sa.Column('id', sa.CHAR(length=32), nullable=False),
sa.ForeignKeyConstraint(['flow_id'], ['flow.id'], ),
sa.PrimaryKeyConstraint('id'),
sa.UniqueConstraint('id')
)
op.create_table('component',
sa.Column('id', sa.CHAR(length=32), nullable=False),
sa.Column('frontend_node_id', sa.CHAR(length=32), nullable=False),
sa.Column('name', sa.VARCHAR(), nullable=False),
sa.Column('description', sa.VARCHAR(), nullable=True),
sa.Column('python_code', sa.VARCHAR(), nullable=True),
sa.Column('return_type', sa.VARCHAR(), nullable=True),
sa.Column('is_disabled', sa.BOOLEAN(), nullable=False),
sa.Column('is_read_only', sa.BOOLEAN(), nullable=False),
sa.Column('create_at', sa.DATETIME(), nullable=False),
sa.Column('update_at', sa.DATETIME(), nullable=False),
sa.PrimaryKeyConstraint('id')
)
with op.batch_alter_table('component', schema=None) as batch_op:
batch_op.create_index('ix_component_name', ['name'], unique=False)
batch_op.create_index('ix_component_frontend_node_id', ['frontend_node_id'], unique=False)
except Exception as e:
print(e)
pass
# ### end Alembic commands ###

6
src/backend/langflow/alembic/versions/eb5866d51fd2_change_columns_to_be_nullable.py
View file

@ -9,6 +9,7 @@ from typing import Sequence, Union
from alembic import op
import sqlalchemy as sa
from sqlalchemy import exc
import sqlmodel # noqa: F401
# revision identifiers, used by Alembic.
@ -20,16 +21,21 @@ depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
# ### commands auto generated by Alembic - please adjust! ###
connection = op.get_bind()
try:
op.drop_table("flowstyle")
with op.batch_alter_table("component", schema=None) as batch_op:
batch_op.drop_index("ix_component_frontend_node_id")
batch_op.drop_index("ix_component_name")
except exc.SQLAlchemyError:
connection.execute("ROLLBACK")
except Exception:
pass
try:
op.drop_table("component")
except exc.SQLAlchemyError:
connection.execute("ROLLBACK")
except Exception:
pass
# ### end Alembic commands ###

45
src/backend/langflow/alembic/versions/f5ee9749d1a6_user_id_can_be_null_in_flow.py Normal file
View file

@ -0,0 +1,45 @@
"""User id can be null in Flow
Revision ID: f5ee9749d1a6
Revises: 7843803a87b5
Create Date: 2023-10-18 23:12:27.297016
"""
from typing import Sequence, Union
from alembic import op
import sqlalchemy as sa
import sqlmodel
# revision identifiers, used by Alembic.
revision: str = "f5ee9749d1a6"
down_revision: Union[str, None] = "7843803a87b5"
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
# ### commands auto generated by Alembic - please adjust! ###
try:
with op.batch_alter_table("flow", schema=None) as batch_op:
batch_op.alter_column(
"user_id", existing_type=sa.CHAR(length=32), nullable=True
)
except Exception:
pass
# ### end Alembic commands ###
def downgrade() -> None:
# ### commands auto generated by Alembic - please adjust! ###
try:
with op.batch_alter_table("flow", schema=None) as batch_op:
batch_op.alter_column(
"user_id", existing_type=sa.CHAR(length=32), nullable=False
)
except Exception:
pass
# ### end Alembic commands ###

4
src/backend/langflow/api/router.py
View file

@ -5,7 +5,7 @@ from langflow.api.v1 import (
endpoints_router,
validate_router,
flows_router,
component_router,
store_router,
users_router,
api_key_router,
login_router,
@ -17,7 +17,7 @@ router = APIRouter(
router.include_router(chat_router)
router.include_router(endpoints_router)
router.include_router(validate_router)
router.include_router(component_router)
router.include_router(store_router)
router.include_router(flows_router)
router.include_router(users_router)
router.include_router(api_key_router)

18
src/backend/langflow/api/utils.py
View file

@ -2,9 +2,7 @@ API_WORDS = ["api", "key", "token"]
def has_api_terms(word: str):
return "api" in word and (
"key" in word or ("token" in word and "tokens" not in word)
)
return "api" in word and ("key" in word or ("token" in word and "tokens" not in word))
def remove_api_keys(flow: dict):
@ -14,11 +12,7 @@ def remove_api_keys(flow: dict):
node_data = node.get("data").get("node")
template = node_data.get("template")
for value in template.values():
if (
isinstance(value, dict)
and has_api_terms(value["name"])
and value.get("password")
):
if isinstance(value, dict) and has_api_terms(value["name"]) and value.get("password"):
value["value"] = None
return flow
@ -39,9 +33,7 @@ def build_input_keys_response(langchain_object, artifacts):
input_keys_response["input_keys"][key] = value
# If the object has memory, that memory will have a memory_variables attribute
# memory variables should be removed from the input keys
if hasattr(langchain_object, "memory") and hasattr(
langchain_object.memory, "memory_variables"
):
if hasattr(langchain_object, "memory") and hasattr(langchain_object.memory, "memory_variables"):
# Remove memory variables from input keys
input_keys_response["input_keys"] = {
key: value
@ -51,9 +43,7 @@ def build_input_keys_response(langchain_object, artifacts):
# Add memory variables to memory_keys
input_keys_response["memory_keys"] = langchain_object.memory.memory_variables
if hasattr(langchain_object, "prompt") and hasattr(
langchain_object.prompt, "template"
):
if hasattr(langchain_object, "prompt") and hasattr(langchain_object.prompt, "template"):
input_keys_response["template"] = langchain_object.prompt.template
return input_keys_response

4
src/backend/langflow/api/v1/__init__.py
View file

@ -2,7 +2,7 @@ from langflow.api.v1.endpoints import router as endpoints_router
from langflow.api.v1.validate import router as validate_router
from langflow.api.v1.chat import router as chat_router
from langflow.api.v1.flows import router as flows_router
from langflow.api.v1.components import router as component_router
from langflow.api.v1.store import router as store_router
from langflow.api.v1.users import router as users_router
from langflow.api.v1.api_key import router as api_key_router
from langflow.api.v1.login import router as login_router
@ -10,7 +10,7 @@ from langflow.api.v1.login import router as login_router
__all__ = [
"chat_router",
"endpoints_router",
"component_router",
"store_router",
"validate_router",
"flows_router",
"users_router",

38
src/backend/langflow/api/v1/api_key.py
View file

@ -1,7 +1,7 @@
from uuid import UUID
from fastapi import APIRouter, HTTPException, Depends
from langflow.api.v1.schemas import ApiKeysResponse
from langflow.services.auth.utils import get_current_active_user
from langflow.api.v1.schemas import ApiKeysResponse, ApiKeyCreateRequest
from langflow.services.auth import utils as auth_utils
from langflow.services.database.models.api_key.api_key import (
ApiKeyCreate,
UnmaskedApiKeyRead,
@ -14,9 +14,17 @@ from langflow.services.database.models.api_key.crud import (
delete_api_key,
)
from langflow.services.database.models.user.user import User
from langflow.services.getters import get_session
from langflow.services.deps import (
get_session,
get_settings_service,
)
from typing import TYPE_CHECKING
from sqlmodel import Session
if TYPE_CHECKING:
pass
router = APIRouter(tags=["APIKey"], prefix="/api_key")
@ -24,7 +32,7 @@ router = APIRouter(tags=["APIKey"], prefix="/api_key")
@router.get("/", response_model=ApiKeysResponse)
def get_api_keys_route(
db: Session = Depends(get_session),
current_user: User = Depends(get_current_active_user),
current_user: User = Depends(auth_utils.get_current_active_user),
):
try:
user_id = current_user.id
@ -38,7 +46,7 @@ def get_api_keys_route(
@router.post("/", response_model=UnmaskedApiKeyRead)
def create_api_key_route(
req: ApiKeyCreate,
current_user: User = Depends(get_current_active_user),
current_user: User = Depends(auth_utils.get_current_active_user),
db: Session = Depends(get_session),
):
try:
@ -51,7 +59,7 @@ def create_api_key_route(
@router.delete("/{api_key_id}")
def delete_api_key_route(
api_key_id: UUID,
current_user=Depends(get_current_active_user),
current_user=Depends(auth_utils.get_current_active_user),
db: Session = Depends(get_session),
):
try:
@ -59,3 +67,21 @@ def delete_api_key_route(
return {"detail": "API Key deleted"}
except Exception as e:
raise HTTPException(status_code=400, detail=str(e)) from e
@router.post("/store")
def save_store_api_key(
api_key_request: ApiKeyCreateRequest,
current_user: User = Depends(auth_utils.get_current_active_user),
db: Session = Depends(get_session),
settings_service=Depends(get_settings_service),
):
try:
api_key = api_key_request.api_key
# Encrypt the API key
encrypted = auth_utils.encrypt_api_key(api_key, settings_service=settings_service)
current_user.store_api_key = encrypted
db.commit()
return {"detail": "API Key saved"}
except Exception as e:
raise HTTPException(status_code=400, detail=str(e)) from e

16
src/backend/langflow/api/v1/base.py
View file

@ -1,6 +1,6 @@
from typing import Optional
from langflow.template.frontend_node.base import FrontendNode
from pydantic import BaseModel, validator
from pydantic import field_validator, BaseModel
from langflow.interface.utils import extract_input_variables_from_prompt
from langchain.prompts import PromptTemplate
@ -30,11 +30,13 @@ class CodeValidationResponse(BaseModel):
imports: dict
function: dict
@validator("imports")
@field_validator("imports")
@classmethod
def validate_imports(cls, v):
return v or {"errors": []}
@validator("function")
@field_validator("function")
@classmethod
def validate_function(cls, v):
return v or {"errors": []}
@ -79,9 +81,7 @@ def validate_prompt(template: str):
# Check if there are invalid characters in the input_variables
input_variables = check_input_variables(input_variables)
if any(var in INVALID_NAMES for var in input_variables):
raise ValueError(
f"Invalid input variables. None of the variables can be named {', '.join(input_variables)}. "
)
raise ValueError(f"Invalid input variables. None of the variables can be named {', '.join(input_variables)}. ")
try:
PromptTemplate(template=template, input_variables=input_variables)
@ -132,9 +132,7 @@ def check_input_variables(input_variables: list):
return input_variables
def build_error_message(
input_variables, invalid_chars, wrong_variables, fixed_variables, empty_variables
):
def build_error_message(input_variables, invalid_chars, wrong_variables, fixed_variables, empty_variables):
input_variables_str = ", ".join([f"'{var}'" for var in input_variables])
error_string = f"Invalid input variables: {input_variables_str}. "

34
src/backend/langflow/api/v1/callback.py
View file

@ -1,19 +1,15 @@
import asyncio
from typing import Any, Dict, List, Optional
from uuid import UUID
from langchain.callbacks.base import AsyncCallbackHandler, BaseCallbackHandler
from langflow.api.v1.schemas import ChatResponse, PromptResponse
from typing import Any, Dict, List, Optional
from langflow.services.getters import get_chat_service
from langflow.utils.util import remove_ansi_escape_codes
from langchain.schema import AgentAction, AgentFinish
from loguru import logger
from langflow.api.v1.schemas import ChatResponse, PromptResponse
from langflow.services.deps import get_chat_service
from langflow.utils.util import remove_ansi_escape_codes
# https://github.com/hwchase17/chat-langchain/blob/master/callback.py
class AsyncStreamingLLMCallbackHandler(AsyncCallbackHandler):
@ -26,18 +22,16 @@ class AsyncStreamingLLMCallbackHandler(AsyncCallbackHandler):
async def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
resp = ChatResponse(message=token, type="stream", intermediate_steps="")
await self.websocket.send_json(resp.dict())
await self.websocket.send_json(resp.model_dump())
async def on_tool_start(
self, serialized: Dict[str, Any], input_str: str, **kwargs: Any
) -> Any:
async def on_tool_start(self, serialized: Dict[str, Any], input_str: str, **kwargs: Any) -> Any:
"""Run when tool starts running."""
resp = ChatResponse(
message="",
type="stream",
intermediate_steps=f"Tool input: {input_str}",
)
await self.websocket.send_json(resp.dict())
await self.websocket.send_json(resp.model_dump())
async def on_tool_end(self, output: str, **kwargs: Any) -> Any:
"""Run when tool ends running."""
@ -68,7 +62,7 @@ class AsyncStreamingLLMCallbackHandler(AsyncCallbackHandler):
try:
# This is to emulate the stream of tokens
for resp in resps:
await self.websocket.send_json(resp.dict())
await self.websocket.send_json(resp.model_dump())
except Exception as exc:
logger.error(f"Error sending response: {exc}")
@ -94,7 +88,7 @@ class AsyncStreamingLLMCallbackHandler(AsyncCallbackHandler):
resp = PromptResponse(
prompt=text,
)
await self.websocket.send_json(resp.dict())
await self.websocket.send_json(resp.model_dump())
self.chat_service.chat_history.add_message(self.client_id, resp)
async def on_agent_action(self, action: AgentAction, **kwargs: Any):
@ -105,10 +99,10 @@ class AsyncStreamingLLMCallbackHandler(AsyncCallbackHandler):
logs = log.split("\n")
for log in logs:
resp = ChatResponse(message="", type="stream", intermediate_steps=log)
await self.websocket.send_json(resp.dict())
await self.websocket.send_json(resp.model_dump())
else:
resp = ChatResponse(message="", type="stream", intermediate_steps=log)
await self.websocket.send_json(resp.dict())
await self.websocket.send_json(resp.model_dump())
async def on_agent_finish(self, finish: AgentFinish, **kwargs: Any) -> Any:
"""Run on agent end."""
@ -117,7 +111,7 @@ class AsyncStreamingLLMCallbackHandler(AsyncCallbackHandler):
type="stream",
intermediate_steps=finish.log,
)
await self.websocket.send_json(resp.dict())
await self.websocket.send_json(resp.model_dump())
class StreamingLLMCallbackHandler(BaseCallbackHandler):
@ -132,5 +126,5 @@ class StreamingLLMCallbackHandler(BaseCallbackHandler):
resp = ChatResponse(message=token, type="stream", intermediate_steps="")
loop = asyncio.get_event_loop()
coroutine = self.websocket.send_json(resp.dict())
coroutine = self.websocket.send_json(resp.model_dump())
asyncio.run_coroutine_threadsafe(coroutine, loop)

68
src/backend/langflow/api/v1/chat.py
View file

@ -8,18 +8,20 @@ from fastapi import (
status,
)
from fastapi.responses import StreamingResponse
from loguru import logger
from sqlmodel import Session
from langflow.api.utils import build_input_keys_response
from langflow.api.v1.schemas import BuildStatus, BuiltResponse, InitResponse, StreamData
from langflow.graph.graph.base import Graph
from langflow.services.auth.utils import get_current_active_user, get_current_user
from langflow.services.auth.utils import (
get_current_active_user,
get_current_user_by_jwt,
)
from langflow.services.cache.service import BaseCacheService
from langflow.services.cache.utils import update_build_status
from loguru import logger
from langflow.services.getters import get_chat_service, get_session, get_cache_service
from sqlmodel import Session
from langflow.services.chat.manager import ChatService
from langflow.services.cache.manager import BaseCacheService
from langflow.services.chat.service import ChatService
from langflow.services.deps import get_cache_service, get_chat_service, get_session
router = APIRouter(tags=["Chat"])
@ -34,16 +36,12 @@ async def chat(
):
"""Websocket endpoint for chat."""
try:
user = await get_current_user_by_jwt(token, db)
await websocket.accept()
user = await get_current_user(token, db)
if not user:
await websocket.close(
code=status.WS_1008_POLICY_VIOLATION, reason="Unauthorized"
)
await websocket.close(code=status.WS_1008_POLICY_VIOLATION, reason="Unauthorized")
if not user.is_active:
await websocket.close(
code=status.WS_1008_POLICY_VIOLATION, reason="Unauthorized"
)
await websocket.close(code=status.WS_1008_POLICY_VIOLATION, reason="Unauthorized")
if client_id in chat_service.cache_service:
await chat_service.handle_websocket(client_id, websocket)
@ -59,9 +57,7 @@ async def chat(
logger.error(f"Error in chat websocket: {exc}")
messsage = exc.detail if isinstance(exc, HTTPException) else str(exc)
if "Could not validate credentials" in str(exc):
await websocket.close(
code=status.WS_1008_POLICY_VIOLATION, reason="Unauthorized"
)
await websocket.close(code=status.WS_1008_POLICY_VIOLATION, reason="Unauthorized")
else:
await websocket.close(code=status.WS_1011_INTERNAL_ERROR, reason=messsage)
@ -103,15 +99,10 @@ async def init_build(
@router.get("/build/{flow_id}/status", response_model=BuiltResponse)
async def build_status(
flow_id: str, cache_service: "BaseCacheService" = Depends(get_cache_service)
):
async def build_status(flow_id: str, cache_service: "BaseCacheService" = Depends(get_cache_service)):
"""Check the flow_id is in the cache_service."""
try:
built = (
flow_id in cache_service
and cache_service[flow_id]["status"] == BuildStatus.SUCCESS
)
built = flow_id in cache_service and cache_service[flow_id]["status"] == BuildStatus.SUCCESS
return BuiltResponse(
built=built,
@ -160,6 +151,11 @@ async def stream_build(
number_of_nodes = len(graph.nodes)
update_build_status(cache_service, flow_id, BuildStatus.IN_PROGRESS)
try:
user_id = cache_service[flow_id]["user_id"]
except KeyError:
logger.debug("No user_id found in cache_service")
user_id = None
for i, vertex in enumerate(graph.generator_build(), 1):
try:
log_dict = {
@ -167,15 +163,13 @@ async def stream_build(
}
yield str(StreamData(event="log", data=log_dict))
if vertex.is_task:
vertex = try_running_celery_task(vertex)
vertex = await try_running_celery_task(vertex, user_id)
else:
vertex.build()
await vertex.build(user_id=user_id)
params = vertex._built_object_repr()
valid = True
logger.debug(f"Building node {str(vertex.vertex_type)}")
logger.debug(
f"Output: {params[:100]}{'...' if len(params) > 100 else ''}"
)
logger.debug(f"Output: {params[:100]}{'...' if len(params) > 100 else ''}")
if vertex.artifacts:
# The artifacts will be prompt variables
# passed to build_input_keys_response
@ -187,9 +181,7 @@ async def stream_build(
valid = False
update_build_status(cache_service, flow_id, BuildStatus.FAILURE)
vertex_id = (
vertex.parent_node_id if vertex.parent_is_top_level else vertex.id
)
vertex_id = vertex.parent_node_id if vertex.parent_is_top_level else vertex.id
if vertex_id in graph.top_level_nodes:
response = {
"valid": valid,
@ -200,12 +192,10 @@ async def stream_build(
yield str(StreamData(event="message", data=response))
langchain_object = graph.build()
langchain_object = await graph.build()
# Now we need to check the input_keys to send them to the client
if hasattr(langchain_object, "input_keys"):
input_keys_response = build_input_keys_response(
langchain_object, artifacts
)
input_keys_response = build_input_keys_response(langchain_object, artifacts)
else:
input_keys_response = {
"input_keys": None,
@ -233,7 +223,7 @@ async def stream_build(
raise HTTPException(status_code=500, detail=str(exc))
def try_running_celery_task(vertex):
async def try_running_celery_task(vertex, user_id):
# Try running the task in celery
# and set the task_id to the local vertex
# if it fails, run the task locally
@ -245,5 +235,5 @@ def try_running_celery_task(vertex):
except Exception as exc:
logger.debug(f"Error running task in celery: {exc}")
vertex.task_id = None
vertex.build()
await vertex.build(user_id=user_id)
return vertex

77
src/backend/langflow/api/v1/components.py
View file

@ -1,77 +0,0 @@
from datetime import timezone
from typing import List
from uuid import UUID
from langflow.services.database.models.component import Component, ComponentModel
from langflow.services.getters import get_session
from sqlmodel import Session, select
from fastapi import APIRouter, Depends, HTTPException
from sqlalchemy.exc import IntegrityError
from datetime import datetime
COMPONENT_NOT_FOUND = "Component not found"
COMPONENT_ALREADY_EXISTS = "A component with the same id already exists."
COMPONENT_DELETED = "Component deleted"
router = APIRouter(prefix="/components", tags=["Components"])
@router.post("/", response_model=Component)
def create_component(component: ComponentModel, db: Session = Depends(get_session)):
db_component = Component(**component.dict())
try:
db.add(db_component)
db.commit()
db.refresh(db_component)
except IntegrityError as e:
db.rollback()
raise HTTPException(
status_code=400,
detail=COMPONENT_ALREADY_EXISTS,
) from e
return db_component
@router.get("/{component_id}", response_model=Component)
def read_component(component_id: UUID, db: Session = Depends(get_session)):
if component := db.get(Component, component_id):
return component
else:
raise HTTPException(status_code=404, detail=COMPONENT_NOT_FOUND)
@router.get("/", response_model=List[Component])
def read_components(skip: int = 0, limit: int = 50, db: Session = Depends(get_session)):
query = select(Component)
query = query.offset(skip).limit(limit)
return db.execute(query).fetchall()
@router.patch("/{component_id}", response_model=Component)
def update_component(
component_id: UUID, component: ComponentModel, db: Session = Depends(get_session)
):
db_component = db.get(Component, component_id)
if not db_component:
raise HTTPException(status_code=404, detail=COMPONENT_NOT_FOUND)
component_data = component.dict(exclude_unset=True)
for key, value in component_data.items():
setattr(db_component, key, value)
db_component.update_at = datetime.now(timezone.utc)
db.commit()
db.refresh(db_component)
return db_component
@router.delete("/{component_id}")
def delete_component(component_id: UUID, db: Session = Depends(get_session)):
component = db.get(Component, component_id)
if not component:
raise HTTPException(status_code=404, detail=COMPONENT_NOT_FOUND)
db.delete(component)
db.commit()
return {"detail": COMPONENT_DELETED}

93
src/backend/langflow/api/v1/endpoints.py
View file

@ -1,33 +1,30 @@
from http import HTTPStatus
from typing import Annotated, Optional, Union
from langflow.services.auth.utils import api_key_security, get_current_active_user
from langflow.services.cache.utils import save_uploaded_file
from langflow.services.database.models.flow import Flow
from langflow.processing.process import process_graph_cached, process_tweaks
from langflow.services.database.models.user.user import User
from langflow.services.getters import (
get_session_service,
get_settings_service,
get_task_service,
)
from loguru import logger
from fastapi import APIRouter, Depends, HTTPException, UploadFile, Body, status
import sqlalchemy as sa
from langflow.interface.custom.custom_component import CustomComponent
from fastapi import APIRouter, Body, Depends, HTTPException, UploadFile, status
from loguru import logger
from langflow.api.v1.schemas import (
CustomComponentCode,
ProcessResponse,
TaskResponse,
TaskStatusResponse,
UploadFileResponse,
CustomComponentCode,
)
from langflow.services.getters import get_session
from langflow.interface.custom.custom_component import CustomComponent
from langflow.interface.custom.directory_reader import DirectoryReader
from langflow.processing.process import process_graph_cached, process_tweaks
from langflow.services.auth.utils import api_key_security, get_current_active_user
from langflow.services.cache.utils import save_uploaded_file
from langflow.services.database.models.flow import Flow
from langflow.services.database.models.user.user import User
from langflow.services.deps import (
get_session,
get_session_service,
get_settings_service,
get_task_service,
)
try:
from langflow.worker import process_graph_cached_task
@ -39,8 +36,7 @@ except ImportError:
from sqlmodel import Session
from langflow.services.task.manager import TaskService
from langflow.services.task.service import TaskService
# build router
router = APIRouter(tags=["Base"])
@ -92,12 +88,7 @@ async def process(
)
# Get the flow that matches the flow_id and belongs to the user
flow = (
session.query(Flow)
.filter(Flow.id == flow_id)
.filter(Flow.user_id == api_key_user.id)
.first()
)
flow = session.query(Flow).filter(Flow.id == flow_id).filter(Flow.user_id == api_key_user.id).first()
if flow is None:
raise ValueError(f"Flow {flow_id} not found")
@ -111,9 +102,7 @@ async def process(
logger.error(f"Error processing tweaks: {exc}")
if sync:
task_id, result = await task_service.launch_and_await_task(
process_graph_cached_task
if task_service.use_celery
else process_graph_cached,
process_graph_cached_task if task_service.use_celery else process_graph_cached,
graph_data,
inputs,
clear_cache,
@ -133,13 +122,9 @@ async def process(
)
if session_id is None:
# Generate a session ID
session_id = get_session_service().generate_key(
session_id=session_id, data_graph=graph_data
)
session_id = get_session_service().generate_key(session_id=session_id, data_graph=graph_data)
task_id, task = await task_service.launch_task(
process_graph_cached_task
if task_service.use_celery
else process_graph_cached,
process_graph_cached_task if task_service.use_celery else process_graph_cached,
graph_data,
inputs,
clear_cache,
@ -162,18 +147,12 @@ async def process(
# StatementError('(builtins.ValueError) badly formed hexadecimal UUID string')
if "badly formed hexadecimal UUID string" in str(exc):
# This means the Flow ID is not a valid UUID which means it can't find the flow
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND, detail=str(exc)
) from exc
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=str(exc)) from exc
except ValueError as exc:
if f"Flow {flow_id} not found" in str(exc):
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND, detail=str(exc)
) from exc
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=str(exc)) from exc
else:
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail=str(exc)
) from exc
raise HTTPException(status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail=str(exc)) from exc
except Exception as e:
# Log stack trace
logger.exception(e)
@ -227,12 +206,32 @@ def get_version():
@router.post("/custom_component", status_code=HTTPStatus.OK)
async def custom_component(
raw_code: CustomComponentCode,
user: User = Depends(get_current_active_user),
):
from langflow.interface.types import (
build_langchain_template_custom_component,
)
extractor = CustomComponent(code=raw_code.code)
extractor.is_check_valid()
extractor.validate()
return build_langchain_template_custom_component(extractor)
return build_langchain_template_custom_component(extractor, user_id=user.id)
@router.post("/custom_component/reload", status_code=HTTPStatus.OK)
async def reload_custom_component(path: str):
from langflow.interface.types import (
build_langchain_template_custom_component,
)
try:
reader = DirectoryReader("")
valid, content = reader.process_file(path)
if not valid:
raise ValueError(content)
extractor = CustomComponent(code=content)
extractor.validate()
return build_langchain_template_custom_component(extractor, user_id=user.id)
except Exception as exc:
raise HTTPException(status_code=400, detail=str(exc))

36
src/backend/langflow/api/v1/flows.py
View file

@ -1,24 +1,18 @@
from datetime import datetime
from typing import List
from uuid import UUID
import orjson
from fastapi import APIRouter, Depends, File, HTTPException, UploadFile
from fastapi.encoders import jsonable_encoder
from sqlmodel import Session
from langflow.api.utils import remove_api_keys
from langflow.api.v1.schemas import FlowListCreate, FlowListRead
from langflow.services.auth.utils import get_current_active_user
from langflow.services.database.models.flow import (
Flow,
FlowCreate,
FlowRead,
FlowUpdate,
)
from langflow.services.database.models.flow import Flow, FlowCreate, FlowRead, FlowUpdate
from langflow.services.database.models.user.user import User
from langflow.services.getters import get_session
from langflow.services.getters import get_settings_service
import orjson
from sqlmodel import Session
from fastapi import APIRouter, Depends, HTTPException
from fastapi import File, UploadFile
from langflow.services.deps import get_session, get_settings_service
# build router
router = APIRouter(prefix="/flows", tags=["Flows"])
@ -35,7 +29,8 @@ def create_flow(
if flow.user_id is None:
flow.user_id = current_user.id
db_flow = Flow.from_orm(flow)
db_flow = Flow.model_validate(flow, from_attributes=True)
db_flow.updated_at = datetime.utcnow()
session.add(db_flow)
session.commit()
@ -46,7 +41,6 @@ def create_flow(
@router.get("/", response_model=list[FlowRead], status_code=200)
def read_flows(
*,
session: Session = Depends(get_session),
current_user: User = Depends(get_current_active_user),
):
"""Read all flows."""
@ -65,12 +59,7 @@ def read_flow(
current_user: User = Depends(get_current_active_user),
):
"""Read a flow."""
if user_flow := (
session.query(Flow)
.filter(Flow.id == flow_id)
.filter(Flow.user_id == current_user.id)
.first()
):
if user_flow := (session.query(Flow).filter(Flow.id == flow_id).filter(Flow.user_id == current_user.id).first()):
return user_flow
else:
raise HTTPException(status_code=404, detail="Flow not found")
@ -90,12 +79,13 @@ def update_flow(
db_flow = read_flow(session=session, flow_id=flow_id, current_user=current_user)
if not db_flow:
raise HTTPException(status_code=404, detail="Flow not found")
flow_data = flow.dict(exclude_unset=True)
flow_data = flow.model_dump(exclude_unset=True)
if settings_service.settings.REMOVE_API_KEYS:
flow_data = remove_api_keys(flow_data)
for key, value in flow_data.items():
if value is not None:
setattr(db_flow, key, value)
db_flow.updated_at = datetime.utcnow()
session.add(db_flow)
session.commit()
session.refresh(db_flow)
@ -169,5 +159,5 @@ async def download_file(
current_user: User = Depends(get_current_active_user),
):
"""Download all flows as a file."""
flows = read_flows(session=session, current_user=current_user)
flows = read_flows(current_user=current_user)
return FlowListRead(flows=flows)

17
src/backend/langflow/api/v1/login.py
View file

@ -1,18 +1,15 @@
from sqlmodel import Session
from fastapi import APIRouter, Depends, HTTPException, status
from fastapi.security import OAuth2PasswordRequestForm
from sqlmodel import Session
from langflow.services.getters import get_session
from langflow.api.v1.schemas import Token
from langflow.services.auth.utils import (
authenticate_user,
create_user_tokens,
create_refresh_token,
create_user_longterm_token,
get_current_active_user,
create_user_tokens,
)
from langflow.services.getters import get_settings_service
from langflow.services.deps import get_session, get_settings_service
router = APIRouter(tags=["Login"])
@ -44,9 +41,7 @@ async def login_to_get_access_token(
@router.get("/auto_login")
async def auto_login(
db: Session = Depends(get_session), settings_service=Depends(get_settings_service)
):
async def auto_login(db: Session = Depends(get_session), settings_service=Depends(get_settings_service)):
if settings_service.auth_settings.AUTO_LOGIN:
return create_user_longterm_token(db)
@ -60,9 +55,7 @@ async def auto_login(
@router.post("/refresh")
async def refresh_token(
token: str, current_user: Session = Depends(get_current_active_user)
):
async def refresh_token(token: str):
if token:
return create_refresh_token(token)
else:

18
src/backend/langflow/api/v1/schemas.py
View file

@ -7,7 +7,7 @@ from langflow.services.database.models.flow import FlowCreate, FlowRead
from langflow.services.database.models.user import UserRead
from langflow.services.database.models.base import orjson_dumps
from pydantic import BaseModel, Field, validator
from pydantic import BaseModel, Field, field_validator
class BuildStatus(Enum):
@ -91,7 +91,8 @@ class ChatResponse(ChatMessage):
is_bot: bool = True
files: list = []
@validator("type")
@field_validator("type")
@classmethod
def validate_message_type(cls, v):
if v not in ["start", "stream", "end", "error", "info", "file"]:
raise ValueError("type must be start, stream, end, error, info, or file")
@ -109,12 +110,13 @@ class PromptResponse(ChatMessage):
class FileResponse(ChatMessage):
"""File response schema."""
data: Any
data: Any = None
data_type: str
type: str = "file"
is_bot: bool = True
@validator("data_type")
@field_validator("data_type")
@classmethod
def validate_data_type(cls, v):
if v not in ["image", "csv"]:
raise ValueError("data_type must be image or csv")
@ -149,9 +151,7 @@ class StreamData(BaseModel):
data: dict
def __str__(self) -> str:
return (
f"event: {self.event}\ndata: {orjson_dumps(self.data, indent_2=False)}\n\n"
)
return f"event: {self.event}\ndata: {orjson_dumps(self.data, indent_2=False)}\n\n"
class CustomComponentCode(BaseModel):
@ -198,3 +198,7 @@ class Token(BaseModel):
access_token: str
refresh_token: str
token_type: str
class ApiKeyCreateRequest(BaseModel):
api_key: str

198
src/backend/langflow/api/v1/store.py Normal file
View file

@ -0,0 +1,198 @@
import warnings
from typing import Annotated, List, Optional, Union
from uuid import UUID
from fastapi import APIRouter, Depends, HTTPException, Query
from langflow.services.auth import utils as auth_utils
from langflow.services.database.models.user.user import User
from langflow.services.deps import get_settings_service, get_store_service
from langflow.services.store.exceptions import CustomException
from langflow.services.store.schema import (
CreateComponentResponse,
DownloadComponentResponse,
ListComponentResponseModel,
StoreComponentCreate,
TagResponse,
UsersLikesResponse,
)
from langflow.services.store.service import StoreService
from langflow.services.store.utils import get_lf_version_from_pypi
router = APIRouter(prefix="/store", tags=["Components Store"])
def get_user_store_api_key(
user: User = Depends(auth_utils.get_current_active_user),
settings_service=Depends(get_settings_service),
):
if not user.store_api_key:
raise HTTPException(status_code=400, detail="You must have a store API key set.")
decrypted = auth_utils.decrypt_api_key(user.store_api_key, settings_service)
return decrypted
def get_optional_user_store_api_key(
user: User = Depends(auth_utils.get_current_active_user),
settings_service=Depends(get_settings_service),
):
if not user.store_api_key:
return None
decrypted = auth_utils.decrypt_api_key(user.store_api_key, settings_service)
return decrypted
@router.get("/check/")
def check_if_store_is_enabled(
settings_service=Depends(get_settings_service),
):
return {
"enabled": settings_service.settings.STORE,
}
@router.get("/check/api_key")
async def check_if_store_has_api_key(
api_key: Optional[str] = Depends(get_optional_user_store_api_key),
store_service: StoreService = Depends(get_store_service),
):
if api_key is None:
return {"has_api_key": False, "is_valid": False}
try:
is_valid = await store_service.check_api_key(api_key)
except Exception as e:
raise HTTPException(status_code=400, detail=str(e))
return {"has_api_key": api_key is not None, "is_valid": is_valid}
@router.post("/components/", response_model=CreateComponentResponse, status_code=201)
async def share_component(
component: StoreComponentCreate,
store_service: StoreService = Depends(get_store_service),
store_api_Key: str = Depends(get_user_store_api_key),
):
try:
# Verify if this is the latest version of Langflow
# If not, raise an error
if not component.last_tested_version:
# Get the local version of Langflow
from langflow import __version__ as current_version
component.last_tested_version = current_version
langflow_version = get_lf_version_from_pypi()
if langflow_version is None:
raise HTTPException(
status_code=500,
detail="Unable to verify the latest version of Langflow",
)
elif langflow_version != component.last_tested_version:
# If the user is using an older version of Langflow, we need to raise an error
# raise ValueError(
warnings.warn(
f"Your version of Langflow ({component.last_tested_version}) is outdated."
f" Please update to the latest version ({langflow_version}) and try again."
)
result = await store_service.upload(store_api_Key, component)
return result
except Exception as exc:
raise HTTPException(status_code=400, detail=str(exc))
@router.get("/components/", response_model=ListComponentResponseModel)
async def get_components(
component_id: Annotated[Optional[str], Query()] = None,
search: Annotated[Optional[str], Query()] = None,
private: Annotated[Optional[bool], Query()] = None,
is_component: Annotated[Optional[bool], Query()] = None,
tags: Annotated[Optional[list[str]], Query()] = None,
sort: Annotated[Union[list[str], None], Query()] = None,
liked: Annotated[bool, Query()] = False,
filter_by_user: Annotated[bool, Query()] = False,
fields: Annotated[Optional[list[str]], Query()] = None,
page: int = 1,
limit: int = 10,
store_service: StoreService = Depends(get_store_service),
store_api_Key: Optional[str] = Depends(get_optional_user_store_api_key),
):
try:
return await store_service.get_list_component_response_model(
component_id=component_id,
search=search,
private=private,
is_component=is_component,
fields=fields,
tags=tags,
sort=sort,
liked=liked,
filter_by_user=filter_by_user,
page=page,
limit=limit,
store_api_key=store_api_Key,
)
except CustomException as exc:
raise HTTPException(status_code=exc.status_code, detail=str(exc)) from exc
except Exception as exc:
raise HTTPException(status_code=500, detail=str(exc)) from exc
@router.get("/components/{component_id}", response_model=DownloadComponentResponse)
async def download_component(
component_id: UUID,
store_service: StoreService = Depends(get_store_service),
store_api_Key: str = Depends(get_user_store_api_key),
):
try:
component = await store_service.download(store_api_Key, component_id)
except CustomException as exc:
raise HTTPException(status_code=400, detail=str(exc)) from exc
except Exception as exc:
raise HTTPException(status_code=500, detail=str(exc)) from exc
if component is None:
raise HTTPException(status_code=400, detail="Component not found")
return component
@router.get("/tags", response_model=List[TagResponse])
async def get_tags(
store_service: StoreService = Depends(get_store_service),
):
try:
return await store_service.get_tags()
except CustomException as exc:
raise HTTPException(status_code=400, detail=str(exc)) from exc
except Exception as exc:
raise HTTPException(status_code=500, detail=str(exc))
@router.get("/users/likes", response_model=List[UsersLikesResponse])
async def get_list_of_components_liked_by_user(
store_service: StoreService = Depends(get_store_service),
store_api_Key: str = Depends(get_user_store_api_key),
):
try:
return await store_service.get_user_likes(store_api_Key)
except CustomException as exc:
raise HTTPException(status_code=400, detail=str(exc)) from exc
except Exception as exc:
raise HTTPException(status_code=500, detail=str(exc))
@router.post("/users/likes/{component_id}", response_model=UsersLikesResponse)
async def like_component(
component_id: UUID,
store_service: StoreService = Depends(get_store_service),
store_api_Key: str = Depends(get_user_store_api_key),
):
try:
result = await store_service.like_component(store_api_Key, str(component_id))
likes_count = await store_service.get_component_likes_count(str(component_id), store_api_Key)
return UsersLikesResponse(likes_count=likes_count, liked_by_user=result)
except CustomException as exc:
raise HTTPException(status_code=exc.status_code, detail=str(exc)) from exc
except Exception as exc:
raise HTTPException(status_code=500, detail=str(exc))

30
src/backend/langflow/api/v1/users.py
View file

@ -13,7 +13,7 @@ from sqlalchemy.exc import IntegrityError
from sqlmodel import Session, select
from fastapi import APIRouter, Depends, HTTPException
from langflow.services.getters import get_session, get_settings_service
from langflow.services.deps import get_session, get_settings_service
from langflow.services.auth.utils import (
get_current_active_superuser,
get_current_active_user,
@ -46,9 +46,7 @@ def add_user(
session.refresh(new_user)
except IntegrityError as e:
session.rollback()
raise HTTPException(
status_code=400, detail="This username is unavailable."
) from e
raise HTTPException(status_code=400, detail="This username is unavailable.") from e
return new_user
@ -96,14 +94,10 @@ def patch_user(
Update an existing user's data.
"""
if not user.is_superuser and user.id != user_id:
raise HTTPException(
status_code=403, detail="You don't have the permission to update this user"
)
raise HTTPException(status_code=403, detail="You don't have the permission to update this user")
if user_update.password:
if not user.is_superuser:
raise HTTPException(
status_code=400, detail="You can't change your password here"
)
raise HTTPException(status_code=400, detail="You can't change your password here")
user_update.password = get_password_hash(user_update.password)
if user_db := get_user_by_id(session, user_id):
@ -123,16 +117,12 @@ def reset_password(
Reset a user's password.
"""
if user_id != user.id:
raise HTTPException(
status_code=400, detail="You can't change another user's password"
)
raise HTTPException(status_code=400, detail="You can't change another user's password")
if not user:
raise HTTPException(status_code=404, detail="User not found")
if verify_password(user_update.password, user.password):
raise HTTPException(
status_code=400, detail="You can't use your current password"
)
raise HTTPException(status_code=400, detail="You can't use your current password")
new_password = get_password_hash(user_update.password)
user.password = new_password
session.commit()
@ -151,13 +141,9 @@ def delete_user(
Delete a user from the database.
"""
if current_user.id == user_id:
raise HTTPException(
status_code=400, detail="You can't delete your own user account"
)
raise HTTPException(status_code=400, detail="You can't delete your own user account")
elif not current_user.is_superuser:
raise HTTPException(
status_code=403, detail="You don't have the permission to delete this user"
)
raise HTTPException(status_code=403, detail="You don't have the permission to delete this user")
user_db = session.query(User).filter(User.id == user_id).first()
if not user_db:

47
src/backend/langflow/api/v1/validate.py
View file

@ -41,9 +41,7 @@ def post_validate_prompt(prompt_request: ValidatePromptRequest):
add_new_variables_to_template(input_variables, prompt_request)
remove_old_variables_from_template(
old_custom_fields, input_variables, prompt_request
)
remove_old_variables_from_template(old_custom_fields, input_variables, prompt_request)
update_input_variables_field(input_variables, prompt_request)
@ -58,19 +56,12 @@ def post_validate_prompt(prompt_request: ValidatePromptRequest):
def get_old_custom_fields(prompt_request):
try:
if (
len(prompt_request.frontend_node.custom_fields) == 1
and prompt_request.name == ""
):
if len(prompt_request.frontend_node.custom_fields) == 1 and prompt_request.name == "":
# If there is only one custom field and the name is empty string
# then we are dealing with the first prompt request after the node was created
prompt_request.name = list(
prompt_request.frontend_node.custom_fields.keys()
)[0]
prompt_request.name = list(prompt_request.frontend_node.custom_fields.keys())[0]
old_custom_fields = prompt_request.frontend_node.custom_fields[
prompt_request.name
].copy()
old_custom_fields = prompt_request.frontend_node.custom_fields[prompt_request.name].copy()
except KeyError:
old_custom_fields = []
prompt_request.frontend_node.custom_fields[prompt_request.name] = []
@ -92,40 +83,26 @@ def add_new_variables_to_template(input_variables, prompt_request):
)
if variable in prompt_request.frontend_node.template:
# Set the new field with the old value
template_field.value = prompt_request.frontend_node.template[variable][
"value"
]
template_field.value = prompt_request.frontend_node.template[variable]["value"]
prompt_request.frontend_node.template[variable] = template_field.to_dict()
# Check if variable is not already in the list before appending
if (
variable
not in prompt_request.frontend_node.custom_fields[prompt_request.name]
):
prompt_request.frontend_node.custom_fields[prompt_request.name].append(
variable
)
if variable not in prompt_request.frontend_node.custom_fields[prompt_request.name]:
prompt_request.frontend_node.custom_fields[prompt_request.name].append(variable)
except Exception as exc:
logger.exception(exc)
raise HTTPException(status_code=500, detail=str(exc)) from exc
def remove_old_variables_from_template(
old_custom_fields, input_variables, prompt_request
):
def remove_old_variables_from_template(old_custom_fields, input_variables, prompt_request):
for variable in old_custom_fields:
if variable not in input_variables:
try:
# Remove the variable from custom_fields associated with the given name
if (
variable
in prompt_request.frontend_node.custom_fields[prompt_request.name]
):
prompt_request.frontend_node.custom_fields[
prompt_request.name
].remove(variable)
if variable in prompt_request.frontend_node.custom_fields[prompt_request.name]:
prompt_request.frontend_node.custom_fields[prompt_request.name].remove(variable)
# Remove the variable from the template
prompt_request.frontend_node.template.pop(variable, None)
@ -137,6 +114,4 @@ def remove_old_variables_from_template(
def update_input_variables_field(input_variables, prompt_request):
if "input_variables" in prompt_request.frontend_node.template:
prompt_request.frontend_node.template["input_variables"][
"value"
] = input_variables
prompt_request.frontend_node.template["input_variables"]["value"] = input_variables

38
src/backend/langflow/components/agents/OpenAIConversationalAgent.py
View file

@ -1,17 +1,15 @@
from langflow import CustomComponent
from typing import Optional
from langchain.prompts import SystemMessagePromptTemplate
from langchain.tools import Tool
from langchain.schema.memory import BaseMemory
from langchain.chat_models import ChatOpenAI
from typing import List, Optional
from langchain.agents.agent import AgentExecutor
from langchain.agents.agent_toolkits.conversational_retrieval.openai_functions import _get_default_system_message
from langchain.agents.openai_functions_agent.base import OpenAIFunctionsAgent
from langchain.chat_models import ChatOpenAI
from langchain.memory.token_buffer import ConversationTokenBufferMemory
from langchain.prompts import SystemMessagePromptTemplate
from langchain.prompts.chat import MessagesPlaceholder
from langchain.agents.agent_toolkits.conversational_retrieval.openai_functions import (
_get_default_system_message,
)
from langchain.schema.memory import BaseMemory
from langchain.tools import Tool
from langflow import CustomComponent
class ConversationalAgent(CustomComponent):
@ -20,13 +18,14 @@ class ConversationalAgent(CustomComponent):
def build_config(self):
openai_function_models = [
"gpt-3.5-turbo-0613",
"gpt-3.5-turbo-16k-0613",
"gpt-4-0613",
"gpt-4-32k-0613",
"gpt-4-1106-preview",
"gpt-3.5-turbo",
"gpt-3.5-turbo-16k",
"gpt-4",
"gpt-4-32k",
]
return {
"tools": {"is_list": True, "display_name": "Tools"},
"tools": {"display_name": "Tools"},
"memory": {"display_name": "Memory"},
"system_message": {"display_name": "System Message"},
"max_token_limit": {"display_name": "Max Token Limit"},
@ -42,7 +41,7 @@ class ConversationalAgent(CustomComponent):
self,
model_name: str,
openai_api_key: str,
tools: Tool,
tools: List[Tool],
openai_api_base: Optional[str] = None,
memory: Optional[BaseMemory] = None,
system_message: Optional[SystemMessagePromptTemplate] = None,
@ -50,8 +49,8 @@ class ConversationalAgent(CustomComponent):
) -> AgentExecutor:
llm = ChatOpenAI(
model=model_name,
openai_api_key=openai_api_key,
openai_api_base=openai_api_base,
api_key=openai_api_key,
base_url=openai_api_base,
)
if not memory:
memory_key = "chat_history"
@ -71,7 +70,9 @@ class ConversationalAgent(CustomComponent):
extra_prompt_messages=[MessagesPlaceholder(variable_name=memory_key)],
)
agent = OpenAIFunctionsAgent(
llm=llm, tools=tools, prompt=prompt # type: ignore
llm=llm,
tools=tools,
prompt=prompt, # type: ignore
)
return AgentExecutor(
agent=agent,
@ -79,4 +80,5 @@ class ConversationalAgent(CustomComponent):
memory=memory,
verbose=True,
return_intermediate_steps=True,
handle_parsing_errors=True,
)

29
src/backend/langflow/components/chains/ConversationChain.py Normal file
View file

@ -0,0 +1,29 @@
from langflow import CustomComponent
from langchain.chains import ConversationChain
from typing import Optional, Union, Callable
from langflow.field_typing import BaseLanguageModel, BaseMemory, Chain
class ConversationChainComponent(CustomComponent):
display_name = "ConversationChain"
description = "Chain to have a conversation and load context from memory."
def build_config(self):
return {
"prompt": {"display_name": "Prompt"},
"llm": {"display_name": "LLM"},
"memory": {
"display_name": "Memory",
"info": "Memory to load context from. If none is provided, a ConversationBufferMemory will be used.",
},
"code": {"show": False},
}
def build(
self,
llm: BaseLanguageModel,
memory: Optional[BaseMemory] = None,
) -> Union[Chain, Callable]:
if memory is None:
return ConversationChain(llm=llm)
return ConversationChain(llm=llm, memory=memory)

30
src/backend/langflow/components/chains/LLMChain.py Normal file
View file

@ -0,0 +1,30 @@
from langflow import CustomComponent
from langchain.chains import LLMChain
from typing import Optional, Union, Callable
from langflow.field_typing import (
BasePromptTemplate,
BaseLanguageModel,
BaseMemory,
Chain,
)
class LLMChainComponent(CustomComponent):
display_name = "LLMChain"
description = "Chain to run queries against LLMs"
def build_config(self):
return {
"prompt": {"display_name": "Prompt"},
"llm": {"display_name": "LLM"},
"memory": {"display_name": "Memory"},
"code": {"show": False},
}
def build(
self,
prompt: BasePromptTemplate,
llm: BaseLanguageModel,
memory: Optional[BaseMemory] = None,
) -> Union[Chain, Callable]:
return LLMChain(prompt=prompt, llm=llm, memory=memory)

6
src/backend/langflow/components/chains/PromptRunner.py
View file

@ -8,7 +8,7 @@ from langchain.schema import Document
class PromptRunner(CustomComponent):
display_name: str = "Prompt Runner"
description: str = "Run a Chain with the given PromptTemplate"
beta = True
beta: bool = True
field_config = {
"llm": {"display_name": "LLM"},
"prompt": {
@ -18,9 +18,7 @@ class PromptRunner(CustomComponent):
"code": {"show": False},
}
def build(
self, llm: BaseLLM, prompt: PromptTemplate, inputs: dict = {}
) -> Document:
def build(self, llm: BaseLLM, prompt: PromptTemplate, inputs: dict = {}) -> Document:
chain = prompt | llm
# The input is an empty dict because the prompt is already filled
result = chain.invoke(input=inputs)

114
src/backend/langflow/components/documentloaders/FileLoader.py Normal file
View file

@ -0,0 +1,114 @@
from langchain.schema import Document
from langflow import CustomComponent
from langflow.utils.constants import LOADERS_INFO
class FileLoaderComponent(CustomComponent):
display_name: str = "File Loader"
description: str = "Generic File Loader"
beta = True
def build_config(self):
loader_options = ["Automatic"] + [loader_info["name"] for loader_info in LOADERS_INFO]
file_types = []
suffixes = []
for loader_info in LOADERS_INFO:
if "allowedTypes" in loader_info:
file_types.extend(loader_info["allowedTypes"])
suffixes.extend([f".{ext}" for ext in loader_info["allowedTypes"]])
return {
"file_path": {
"display_name": "File Path",
"required": True,
"field_type": "file",
"file_types": [
"json",
"txt",
"csv",
"jsonl",
"html",
"htm",
"conllu",
"enex",
"msg",
"pdf",
"srt",
"eml",
"md",
"pptx",
"docx",
],
"suffixes": [
".json",
".txt",
".csv",
".jsonl",
".html",
".htm",
".conllu",
".enex",
".msg",
".pdf",
".srt",
".eml",
".md",
".pptx",
".docx",
],
# "file_types" : file_types,
# "suffixes": suffixes,
},
"loader": {
"display_name": "Loader",
"is_list": True,
"required": True,
"options": loader_options,
"value": "Automatic",
},
"code": {"show": False},
}
def build(self, file_path: str, loader: str) -> Document:
file_type = file_path.split(".")[-1]
# Mapeie o nome do loader selecionado para suas informações
selected_loader_info = None
for loader_info in LOADERS_INFO:
if loader_info["name"] == loader:
selected_loader_info = loader_info
break
if selected_loader_info is None and loader != "Automatic":
raise ValueError(f"Loader {loader} not found in the loader info list")
if loader == "Automatic":
# Determine o loader automaticamente com base na extensão do arquivo
default_loader_info = None
for info in LOADERS_INFO:
if "defaultFor" in info and file_type in info["defaultFor"]:
default_loader_info = info
break
if default_loader_info is None:
raise ValueError(f"No default loader found for file type: {file_type}")
selected_loader_info = default_loader_info
if isinstance(selected_loader_info, dict):
loader_import: str = selected_loader_info["import"]
else:
raise ValueError(f"Loader info for {loader} is not a dict\nLoader info:\n{selected_loader_info}")
module_name, class_name = loader_import.rsplit(".", 1)
try:
# Importe o loader dinamicamente
loader_module = __import__(module_name, fromlist=[class_name])
loader_instance = getattr(loader_module, class_name)
except ImportError as e:
raise ValueError(f"Loader {loader} could not be imported\nLoader info:\n{selected_loader_info}") from e
result = loader_instance(file_path=file_path)
return result.load()

62
src/backend/langflow/components/documentloaders/UrlLoader.py Normal file
View file

@ -0,0 +1,62 @@
from typing import List
from langflow import CustomComponent
from langchain.document_loaders import AZLyricsLoader
from langchain.document_loaders import CollegeConfidentialLoader
from langchain.document_loaders import GitbookLoader
from langchain.document_loaders import HNLoader
from langchain.document_loaders import IFixitLoader
from langchain.document_loaders import IMSDbLoader
from langchain.document_loaders import WebBaseLoader
from langchain.schema import Document
class UrlLoaderComponent(CustomComponent):
display_name: str = "Url Loader"
description: str = "Generic Url Loader Component"
def build_config(self):
return {
"web_path": {
"display_name": "Url",
"required": True,
},
"loader": {
"display_name": "Loader",
"is_list": True,
"required": True,
"options": [
"AZLyricsLoader",
"CollegeConfidentialLoader",
"GitbookLoader",
"HNLoader",
"IFixitLoader",
"IMSDbLoader",
"WebBaseLoader",
],
"value": "WebBaseLoader",
},
"code": {"show": False},
}
def build(self, web_path: str, loader: str) -> List[Document]:
if loader == "AZLyricsLoader":
loader_instance = AZLyricsLoader(web_path=web_path) # type: ignore
elif loader == "CollegeConfidentialLoader":
loader_instance = CollegeConfidentialLoader(web_path=web_path) # type: ignore
elif loader == "GitbookLoader":
loader_instance = GitbookLoader(web_page=web_path) # type: ignore
elif loader == "HNLoader":
loader_instance = HNLoader(web_path=web_path) # type: ignore
elif loader == "IFixitLoader":
loader_instance = IFixitLoader(web_path=web_path) # type: ignore
elif loader == "IMSDbLoader":
loader_instance = IMSDbLoader(web_path=web_path) # type: ignore
elif loader == "WebBaseLoader":
loader_instance = WebBaseLoader(web_path=web_path) # type: ignore
if loader_instance is None:
raise ValueError(f"No loader found for: {web_path}")
return loader_instance.load()

0
src/backend/langflow/components/documentloaders/__init__.py Normal file
View file

46
src/backend/langflow/components/embeddings/AmazonBedrockEmbeddings.py Normal file
View file

@ -0,0 +1,46 @@
from typing import Optional
from langflow import CustomComponent
from langchain.embeddings import BedrockEmbeddings
from langchain.embeddings.base import Embeddings
class AmazonBedrockEmeddingsComponent(CustomComponent):
"""
A custom component for implementing an Embeddings Model using Amazon Bedrock.
"""
display_name: str = "Amazon Bedrock Embeddings"
description: str = "Embeddings model from Amazon Bedrock."
documentation = "https://python.langchain.com/docs/modules/data_connection/text_embedding/integrations/bedrock"
beta = True
def build_config(self):
return {
"model_id": {
"display_name": "Model Id",
"options": ["amazon.titan-embed-text-v1"],
},
"credentials_profile_name": {"display_name": "Credentials Profile Name"},
"endpoint_url": {"display_name": "Bedrock Endpoint URL"},
"region_name": {"display_name": "AWS Region"},
"code": {"show": False},
}
def build(
self,
model_id: str = "amazon.titan-embed-text-v1",
credentials_profile_name: Optional[str] = None,
endpoint_url: Optional[str] = None,
region_name: Optional[str] = None,
) -> Embeddings:
try:
output = BedrockEmbeddings(
credentials_profile_name=credentials_profile_name,
model_id=model_id,
endpoint_url=endpoint_url,
region_name=region_name,
) # type: ignore
except Exception as e:
raise ValueError("Could not connect to AmazonBedrock API.") from e
return output

0
src/backend/langflow/components/embeddings/__init__.py Normal file
View file

45
src/backend/langflow/components/llms/AmazonBedrock.py Normal file
View file

@ -0,0 +1,45 @@
from typing import Optional
from langflow import CustomComponent
from langchain.llms.bedrock import Bedrock
from langchain.llms.base import BaseLLM
class AmazonBedrockComponent(CustomComponent):
display_name: str = "Amazon Bedrock"
description: str = "LLM model from Amazon Bedrock."
def build_config(self):
return {
"model_id": {
"display_name": "Model Id",
"options": [
"ai21.j2-grande-instruct",
"ai21.j2-jumbo-instruct",
"ai21.j2-mid",
"ai21.j2-mid-v1",
"ai21.j2-ultra",
"ai21.j2-ultra-v1",
"anthropic.claude-instant-v1",
"anthropic.claude-v1",
"anthropic.claude-v2",
"cohere.command-text-v14",
],
},
"credentials_profile_name": {"display_name": "Credentials Profile Name"},
"streaming": {"display_name": "Streaming", "field_type": "bool"},
"code": {"show": False},
}
def build(
self,
model_id: str = "anthropic.claude-instant-v1",
credentials_profile_name: Optional[str] = None,
) -> BaseLLM:
try:
output = Bedrock(
credentials_profile_name=credentials_profile_name,
model_id=model_id,
) # type: ignore
except Exception as e:
raise ValueError("Could not connect to AmazonBedrock API.") from e
return output

92
src/backend/langflow/components/llms/BaiduQianfanChatEndpoints.py Normal file
View file

@ -0,0 +1,92 @@
from typing import Optional
from langflow import CustomComponent
from langchain.chat_models.baidu_qianfan_endpoint import QianfanChatEndpoint
from langchain.llms.base import BaseLLM
class QianfanChatEndpointComponent(CustomComponent):
display_name: str = "QianfanChatEndpoint"
description: str = (
"Baidu Qianfan chat models. Get more detail from "
"https://python.langchain.com/docs/integrations/chat/baidu_qianfan_endpoint."
)
def build_config(self):
return {
"model": {
"display_name": "Model Name",
"options": [
"ERNIE-Bot",
"ERNIE-Bot-turbo",
"BLOOMZ-7B",
"Llama-2-7b-chat",
"Llama-2-13b-chat",
"Llama-2-70b-chat",
"Qianfan-BLOOMZ-7B-compressed",
"Qianfan-Chinese-Llama-2-7B",
"ChatGLM2-6B-32K",
"AquilaChat-7B",
],
"info": "https://python.langchain.com/docs/integrations/chat/baidu_qianfan_endpoint",
"required": True,
},
"qianfan_ak": {
"display_name": "Qianfan Ak",
"required": True,
"password": True,
"info": "which you could get from https://cloud.baidu.com/product/wenxinworkshop",
},
"qianfan_sk": {
"display_name": "Qianfan Sk",
"required": True,
"password": True,
"info": "which you could get from https://cloud.baidu.com/product/wenxinworkshop",
},
"top_p": {
"display_name": "Top p",
"field_type": "float",
"info": "Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo",
"value": 0.8,
},
"temperature": {
"display_name": "Temperature",
"field_type": "float",
"info": "Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo",
"value": 0.95,
},
"penalty_score": {
"display_name": "Penalty Score",
"field_type": "float",
"info": "Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo",
"value": 1.0,
},
"endpoint": {
"display_name": "Endpoint",
"info": "Endpoint of the Qianfan LLM, required if custom model used.",
},
"code": {"show": False},
}
def build(
self,
model: str = "ERNIE-Bot-turbo",
qianfan_ak: Optional[str] = None,
qianfan_sk: Optional[str] = None,
top_p: Optional[float] = None,
temperature: Optional[float] = None,
penalty_score: Optional[float] = None,
endpoint: Optional[str] = None,
) -> BaseLLM:
try:
output = QianfanChatEndpoint( # type: ignore
model=model,
qianfan_ak=qianfan_ak,
qianfan_sk=qianfan_sk,
top_p=top_p,
temperature=temperature,
penalty_score=penalty_score,
endpoint=endpoint,
)
except Exception as e:
raise ValueError("Could not connect to Baidu Qianfan API.") from e
return output # type: ignore

92
src/backend/langflow/components/llms/BaiduQianfanLLMEndpoints.py Normal file
View file

@ -0,0 +1,92 @@
from typing import Optional
from langflow import CustomComponent
from langchain.llms.baidu_qianfan_endpoint import QianfanLLMEndpoint
from langchain.llms.base import BaseLLM
class QianfanLLMEndpointComponent(CustomComponent):
display_name: str = "QianfanLLMEndpoint"
description: str = (
"Baidu Qianfan hosted open source or customized models. "
"Get more detail from https://python.langchain.com/docs/integrations/chat/baidu_qianfan_endpoint"
)
def build_config(self):
return {
"model": {
"display_name": "Model Name",
"options": [
"ERNIE-Bot",
"ERNIE-Bot-turbo",
"BLOOMZ-7B",
"Llama-2-7b-chat",
"Llama-2-13b-chat",
"Llama-2-70b-chat",
"Qianfan-BLOOMZ-7B-compressed",
"Qianfan-Chinese-Llama-2-7B",
"ChatGLM2-6B-32K",
"AquilaChat-7B",
],
"info": "https://python.langchain.com/docs/integrations/chat/baidu_qianfan_endpoint",
"required": True,
},
"qianfan_ak": {
"display_name": "Qianfan Ak",
"required": True,
"password": True,
"info": "which you could get from https://cloud.baidu.com/product/wenxinworkshop",
},
"qianfan_sk": {
"display_name": "Qianfan Sk",
"required": True,
"password": True,
"info": "which you could get from https://cloud.baidu.com/product/wenxinworkshop",
},
"top_p": {
"display_name": "Top p",
"field_type": "float",
"info": "Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo",
"value": 0.8,
},
"temperature": {
"display_name": "Temperature",
"field_type": "float",
"info": "Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo",
"value": 0.95,
},
"penalty_score": {
"display_name": "Penalty Score",
"field_type": "float",
"info": "Model params, only supported in ERNIE-Bot and ERNIE-Bot-turbo",
"value": 1.0,
},
"endpoint": {
"display_name": "Endpoint",
"info": "Endpoint of the Qianfan LLM, required if custom model used.",
},
"code": {"show": False},
}
def build(
self,
model: str = "ERNIE-Bot-turbo",
qianfan_ak: Optional[str] = None,
qianfan_sk: Optional[str] = None,
top_p: Optional[float] = None,
temperature: Optional[float] = None,
penalty_score: Optional[float] = None,
endpoint: Optional[str] = None,
) -> BaseLLM:
try:
output = QianfanLLMEndpoint( # type: ignore
model=model,
qianfan_ak=qianfan_ak,
qianfan_sk=qianfan_sk,
top_p=top_p,
temperature=temperature,
penalty_score=penalty_score,
endpoint=endpoint,
)
except Exception as e:
raise ValueError("Could not connect to Baidu Qianfan API.") from e
return output # type: ignore

48
src/backend/langflow/components/retrievers/AmazonKendra.py Normal file
View file

@ -0,0 +1,48 @@
from typing import Optional
from langflow import CustomComponent
from langchain.retrievers import AmazonKendraRetriever
from langchain.schema import BaseRetriever
class AmazonKendraRetrieverComponent(CustomComponent):
display_name: str = "Amazon Kendra Retriever"
description: str = "Retriever that uses the Amazon Kendra API."
def build_config(self):
return {
"index_id": {"display_name": "Index ID"},
"region_name": {"display_name": "Region Name"},
"credentials_profile_name": {"display_name": "Credentials Profile Name"},
"attribute_filter": {
"display_name": "Attribute Filter",
"field_type": "code",
},
"top_k": {"display_name": "Top K", "field_type": "int"},
"user_context": {
"display_name": "User Context",
"field_type": "code",
},
"code": {"show": False},
}
def build(
self,
index_id: str,
top_k: int = 3,
region_name: Optional[str] = None,
credentials_profile_name: Optional[str] = None,
attribute_filter: Optional[dict] = None,
user_context: Optional[dict] = None,
) -> BaseRetriever:
try:
output = AmazonKendraRetriever(
index_id=index_id,
top_k=top_k,
region_name=region_name,
credentials_profile_name=credentials_profile_name,
attribute_filter=attribute_filter,
user_context=user_context,
) # type: ignore
except Exception as e:
raise ValueError("Could not connect to AmazonKendra API.") from e
return output

4
src/backend/langflow/components/retrievers/MetalRetriever.py
View file

@ -18,9 +18,7 @@ class MetalRetrieverComponent(CustomComponent):
"code": {"show": False},
}
def build(
self, api_key: str, client_id: str, index_id: str, params: Optional[dict] = None
) -> BaseRetriever:
def build(self, api_key: str, client_id: str, index_id: str, params: Optional[dict] = None) -> BaseRetriever:
try:
metal = Metal(api_key=api_key, client_id=client_id, index_id=index_id)
except Exception as e:

17
src/backend/langflow/components/toolkits/Metaphor.py
View file

@ -1,19 +1,18 @@
from typing import List, Union
from langflow import CustomComponent
from metaphor_python import Metaphor # type: ignore
from langchain.tools import Tool
from langchain.agents import tool
from langchain.agents.agent_toolkits.base import BaseToolkit
from langchain.tools import Tool
from metaphor_python import Metaphor # type: ignore
from langflow import CustomComponent
class MetaphorToolkit(CustomComponent):
display_name: str = "Metaphor"
description: str = "Metaphor Toolkit"
documentation = (
"https://python.langchain.com/docs/integrations/tools/metaphor_search"
)
beta = True
documentation = "https://python.langchain.com/docs/integrations/tools/metaphor_search"
beta: bool = True
# api key should be password = True
field_config = {
"metaphor_api_key": {"display_name": "Metaphor API Key", "password": True},
@ -33,9 +32,7 @@ class MetaphorToolkit(CustomComponent):
@tool
def search(query: str):
"""Call search engine with a query."""
return client.search(
query, use_autoprompt=use_autoprompt, num_results=search_num_results
)
return client.search(query, use_autoprompt=use_autoprompt, num_results=search_num_results)
@tool
def get_contents(ids: List[str]):

6
src/backend/langflow/components/utilities/GetRequest.py
View file

@ -10,7 +10,7 @@ class GetRequest(CustomComponent):
description: str = "Make a GET request to the given URL."
output_types: list[str] = ["Document"]
documentation: str = "https://docs.langflow.org/components/utilities#get-request"
beta = True
beta: bool = True
field_config = {
"url": {
"display_name": "URL",
@ -30,9 +30,7 @@ class GetRequest(CustomComponent):
},
}
def get_document(
self, session: requests.Session, url: str, headers: Optional[dict], timeout: int
) -> Document:
def get_document(self, session: requests.Session, url: str, headers: Optional[dict], timeout: int) -> Document:
try:
response = session.get(url, headers=headers, timeout=int(timeout))
try:

19
src/backend/langflow/components/utilities/JSONDocumentBuilder.py
View file

@ -11,8 +11,8 @@
# - **Document:** The Document containing the JSON object.
from langflow import CustomComponent
from langchain.schema import Document
from langflow import CustomComponent
from langflow.services.database.models.base import orjson_dumps
@ -21,9 +21,7 @@ class JSONDocumentBuilder(CustomComponent):
description: str = "Build a Document containing a JSON object using a key and another Document page content."
output_types: list[str] = ["Document"]
beta = True
documentation: str = (
"https://docs.langflow.org/components/utilities#json-document-builder"
)
documentation: str = "https://docs.langflow.org/components/utilities#json-document-builder"
field_config = {
"key": {"display_name": "Key"},
@ -38,18 +36,11 @@ class JSONDocumentBuilder(CustomComponent):
documents = None
if isinstance(document, list):
documents = [
Document(
page_content=orjson_dumps({key: doc.page_content}, indent_2=False)
)
for doc in document
Document(page_content=orjson_dumps({key: doc.page_content}, indent_2=False)) for doc in document
]
elif isinstance(document, Document):
documents = Document(
page_content=orjson_dumps({key: document.page_content}, indent_2=False)
)
documents = Document(page_content=orjson_dumps({key: document.page_content}, indent_2=False))
else:
raise TypeError(
f"Expected Document or list of Documents, got {type(document)}"
)
raise TypeError(f"Expected Document or list of Documents, got {type(document)}")
self.repr_value = documents
return documents

10
src/backend/langflow/components/utilities/PostRequest.py
View file

@ -10,7 +10,7 @@ class PostRequest(CustomComponent):
description: str = "Make a POST request to the given URL."
output_types: list[str] = ["Document"]
documentation: str = "https://docs.langflow.org/components/utilities#post-request"
beta = True
beta: bool = True
field_config = {
"url": {"display_name": "URL", "info": "The URL to make the request to."},
"headers": {
@ -65,16 +65,12 @@ class PostRequest(CustomComponent):
if not isinstance(document, list) and isinstance(document, Document):
documents: list[Document] = [document]
elif isinstance(document, list) and all(
isinstance(doc, Document) for doc in document
):
elif isinstance(document, list) and all(isinstance(doc, Document) for doc in document):
documents = document
else:
raise ValueError("document must be a Document or a list of Documents")
with requests.Session() as session:
documents = [
self.post_document(session, doc, url, headers) for doc in documents
]
documents = [self.post_document(session, doc, url, headers) for doc in documents]
self.repr_value = documents
return documents

15
src/backend/langflow/components/utilities/UpdateRequest.py
View file

@ -10,7 +10,7 @@ class UpdateRequest(CustomComponent):
description: str = "Make a PATCH request to the given URL."
output_types: list[str] = ["Document"]
documentation: str = "https://docs.langflow.org/components/utilities#update-request"
beta = True
beta: bool = True
field_config = {
"url": {"display_name": "URL", "info": "The URL to make the request to."},
"headers": {
@ -39,9 +39,7 @@ class UpdateRequest(CustomComponent):
) -> Document:
try:
if method == "PATCH":
response = session.patch(
url, headers=headers, data=document.page_content
)
response = session.patch(url, headers=headers, data=document.page_content)
elif method == "PUT":
response = session.put(url, headers=headers, data=document.page_content)
else:
@ -78,17 +76,12 @@ class UpdateRequest(CustomComponent):
if not isinstance(document, list) and isinstance(document, Document):
documents: list[Document] = [document]
elif isinstance(document, list) and all(
isinstance(doc, Document) for doc in document
):
elif isinstance(document, list) and all(isinstance(doc, Document) for doc in document):
documents = document
else:
raise ValueError("document must be a Document or a list of Documents")
with requests.Session() as session:
documents = [
self.update_document(session, doc, url, headers, method)
for doc in documents
]
documents = [self.update_document(session, doc, url, headers, method) for doc in documents]
self.repr_value = documents
return documents

11
src/backend/langflow/components/vectorstores/Chroma.py
View file

@ -14,10 +14,10 @@ class ChromaComponent(CustomComponent):
A custom component for implementing a Vector Store using Chroma.
"""
display_name: str = "Chroma (Custom Component)"
display_name: str = "Chroma"
description: str = "Implementation of Vector Store using Chroma"
documentation = "https://python.langchain.com/docs/integrations/vectorstores/chroma"
beta = True
beta: bool = True
def build_config(self):
"""
@ -86,8 +86,7 @@ class ChromaComponent(CustomComponent):
if chroma_server_host is not None:
chroma_settings = chromadb.config.Settings(
chroma_server_cors_allow_origins=chroma_server_cors_allow_origins
or None,
chroma_server_cors_allow_origins=chroma_server_cors_allow_origins or None,
chroma_server_host=chroma_server_host,
chroma_server_port=chroma_server_port or None,
chroma_server_grpc_port=chroma_server_grpc_port or None,
@ -104,6 +103,4 @@ class ChromaComponent(CustomComponent):
client_settings=chroma_settings,
)
return Chroma(
persist_directory=persist_directory, client_settings=chroma_settings
)
return Chroma(persist_directory=persist_directory, client_settings=chroma_settings)

64
src/backend/langflow/components/vectorstores/Redis.py Normal file
View file

@ -0,0 +1,64 @@
from typing import Optional
from langflow import CustomComponent
from langchain.vectorstores.redis import Redis
from langchain.schema import Document
from langchain.vectorstores.base import VectorStore
from langchain.embeddings.base import Embeddings
class RedisComponent(CustomComponent):
"""
A custom component for implementing a Vector Store using Redis.
"""
display_name: str = "Redis"
description: str = "Implementation of Vector Store using Redis"
documentation = "https://python.langchain.com/docs/integrations/vectorstores/redis"
beta = True
def build_config(self):
"""
Builds the configuration for the component.
Returns:
- dict: A dictionary containing the configuration options for the component.
"""
return {
"index_name": {"display_name": "Index Name", "value": "your_index"},
"code": {"show": False, "display_name": "Code"},
"documents": {"display_name": "Documents", "is_list": True},
"embedding": {"display_name": "Embedding"},
"redis_server_url": {
"display_name": "Redis Server Connection String",
"advanced": False,
},
"redis_index_name": {"display_name": "Redis Index", "advanced": False},
}
def build(
self,
embedding: Embeddings,
redis_server_url: str,
redis_index_name: str,
documents: Optional[Document] = None,
) -> VectorStore:
"""
Builds the Vector Store or BaseRetriever object.
Args:
- embedding (Embeddings): The embeddings to use for the Vector Store.
- documents (Optional[Document]): The documents to use for the Vector Store.
- redis_index_name (str): The name of the Redis index.
- redis_server_url (str): The URL for the Redis server.
Returns:
- VectorStore: The Vector Store object.
"""
return Redis.from_documents(
documents=documents, # type: ignore
embedding=embedding,
redis_url=redis_server_url,
index_name=redis_index_name,
)

18
src/backend/langflow/components/vectorstores/Vectara.py
View file

@ -1,19 +1,16 @@
from typing import Optional, Union
from langflow import CustomComponent
from langchain.schema import BaseRetriever, Document
from langchain.vectorstores import Vectara
from langchain.schema import Document
from langchain.vectorstores.base import VectorStore
from langchain.schema import BaseRetriever
from langchain.embeddings.base import Embeddings
from langflow import CustomComponent
class VectaraComponent(CustomComponent):
display_name: str = "Vectara"
description: str = "Implementation of Vector Store using Vectara"
documentation = (
"https://python.langchain.com/docs/integrations/vectorstores/vectara"
)
documentation = "https://python.langchain.com/docs/integrations/vectorstores/vectara"
beta = True
# api key should be password = True
field_config = {
@ -22,7 +19,6 @@ class VectaraComponent(CustomComponent):
"vectara_api_key": {"display_name": "Vectara API Key", "password": True},
"code": {"show": False},
"documents": {"display_name": "Documents"},
"embedding": {"display_name": "Embedding"},
}
def build(
@ -30,21 +26,21 @@ class VectaraComponent(CustomComponent):
vectara_customer_id: str,
vectara_corpus_id: str,
vectara_api_key: str,
embedding: Optional[Embeddings] = None,
documents: Optional[Document] = None,
) -> Union[VectorStore, BaseRetriever]:
# If documents, then we need to create a Vectara instance using .from_documents
if documents is not None and embedding is not None:
if documents is not None:
return Vectara.from_documents(
documents=documents, # type: ignore
vectara_customer_id=vectara_customer_id,
vectara_corpus_id=vectara_corpus_id,
vectara_api_key=vectara_api_key,
embedding=embedding,
source="langflow",
)
return Vectara(
vectara_customer_id=vectara_customer_id,
vectara_corpus_id=vectara_corpus_id,
vectara_api_key=vectara_api_key,
source="langflow",
)

74
src/backend/langflow/components/vectorstores/pgvector.py Normal file
View file

@ -0,0 +1,74 @@
from typing import Optional, List
from langflow import CustomComponent
from langchain.vectorstores.pgvector import PGVector
from langchain.schema import Document
from langchain.vectorstores.base import VectorStore
from langchain.embeddings.base import Embeddings
class PostgresqlVectorComponent(CustomComponent):
"""
A custom component for implementing a Vector Store using PostgreSQL.
"""
display_name: str = "PGVector"
description: str = "Implementation of Vector Store using PostgreSQL"
documentation = "https://python.langchain.com/docs/integrations/vectorstores/pgvector"
beta = True
def build_config(self):
"""
Builds the configuration for the component.
Returns:
- dict: A dictionary containing the configuration options for the component.
"""
return {
"index_name": {"display_name": "Index Name", "value": "your_index"},
"code": {"show": True, "display_name": "Code"},
"documents": {"display_name": "Documents", "is_list": True},
"embedding": {"display_name": "Embedding"},
"pg_server_url": {
"display_name": "PostgreSQL Server Connection String",
"advanced": False,
},
"collection_name": {"display_name": "Table", "advanced": False},
}
def build(
self,
embedding: Embeddings,
pg_server_url: str,
collection_name: str,
documents: Optional[List[Document]] = None,
) -> VectorStore:
"""
Builds the Vector Store or BaseRetriever object.
Args:
- embedding (Embeddings): The embeddings to use for the Vector Store.
- documents (Optional[Document]): The documents to use for the Vector Store.
- collection_name (str): The name of the PG table.
- pg_server_url (str): The URL for the PG server.
Returns:
- VectorStore: The Vector Store object.
"""
try:
if documents is None:
return PGVector.from_existing_index(
embedding=embedding,
collection_name=collection_name,
connection_string=pg_server_url,
)
return PGVector.from_documents(
embedding=embedding,
documents=documents,
collection_name=collection_name,
connection_string=pg_server_url,
)
except Exception as e:
raise RuntimeError(f"Failed to build PGVector: {e}")

15
src/backend/langflow/config.yaml
View file

@ -14,14 +14,14 @@ agents:
SQLAgent:
documentation: ""
chains:
LLMChain:
documentation: "https://python.langchain.com/docs/modules/chains/foundational/llm_chain"
# LLMChain:
# documentation: "https://python.langchain.com/docs/modules/chains/foundational/llm_chain"
LLMMathChain:
documentation: "https://python.langchain.com/docs/modules/chains/additional/llm_math"
LLMCheckerChain:
documentation: "https://python.langchain.com/docs/modules/chains/additional/llm_checker"
ConversationChain:
documentation: ""
# ConversationChain:
# documentation: ""
SeriesCharacterChain:
documentation: ""
MidJourneyPromptChain:
@ -106,6 +106,9 @@ embeddings:
documentation: "https://python.langchain.com/docs/modules/data_connection/text_embedding/integrations/cohere"
VertexAIEmbeddings:
documentation: "https://python.langchain.com/docs/modules/data_connection/text_embedding/integrations/google_vertex_ai_palm"
AmazonBedrockEmbeddings:
documentation: "https://python.langchain.com/docs/modules/data_connection/text_embedding/integrations/bedrock"
llms:
OpenAI:
documentation: "https://python.langchain.com/docs/modules/model_io/models/llms/integrations/openai"
@ -265,8 +268,8 @@ retrievers:
# ZepRetriever:
# documentation: "https://python.langchain.com/docs/modules/data_connection/retrievers/integrations/zep_memorystore"
vectorstores:
Chroma:
documentation: "https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/chroma"
# Chroma:
# documentation: "https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/chroma"
Qdrant:
documentation: "https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/qdrant"
Weaviate:

45
src/backend/langflow/field_typing/__init__.py
View file

@ -1,38 +1,28 @@
# LANGCHAIN_BASE_TYPES = {
# "Chain": Chain,
# "AgentExecutor": AgentExecutor,
# "Tool": Tool,
# "BaseLLM": BaseLLM,
# "PromptTemplate": PromptTemplate,
# "BaseLoader": BaseLoader,
# "Document": Document,
# "TextSplitter": TextSplitter,
# "VectorStore": VectorStore,
# "Embeddings": Embeddings,
# "BaseRetriever": BaseRetriever,
# "BaseOutputParser": BaseOutputParser,
# "BaseMemory": BaseMemory,
# "BaseChatMemory": BaseChatMemory,
# }
from .constants import (
Tool,
PromptTemplate,
Chain,
AgentExecutor,
BaseChatMemory,
BaseLanguageModel,
BaseLLM,
BaseLoader,
BaseMemory,
BaseOutputParser,
BasePromptTemplate,
BaseRetriever,
VectorStore,
Embeddings,
TextSplitter,
Document,
AgentExecutor,
NestedDict,
Callable,
Chain,
ChatPromptTemplate,
Data,
Document,
Embeddings,
NestedDict,
Object,
PromptTemplate,
TextSplitter,
Tool,
VectorStore,
)
__all__ = [
"NestedDict",
"Data",
@ -41,6 +31,7 @@ __all__ = [
"Chain",
"BaseChatMemory",
"BaseLLM",
"BaseLanguageModel",
"BaseLoader",
"BaseMemory",
"BaseOutputParser",
@ -50,4 +41,8 @@ __all__ = [
"TextSplitter",
"Document",
"AgentExecutor",
"Object",
"Callable",
"BasePromptTemplate",
"ChatPromptTemplate",
]

16
src/backend/langflow/field_typing/constants.py
View file

@ -1,21 +1,26 @@
from typing import Callable, Dict, Union
from langchain.agents.agent import AgentExecutor
from langchain.chains.base import Chain
from langchain.document_loaders.base import BaseLoader
from langchain.llms.base import BaseLLM
from langchain.llms.base import BaseLanguageModel, BaseLLM
from langchain.memory.chat_memory import BaseChatMemory
from langchain.prompts import PromptTemplate
from langchain.prompts import BasePromptTemplate, ChatPromptTemplate, PromptTemplate
from langchain.schema import BaseOutputParser, BaseRetriever, Document
from langchain.schema.embeddings import Embeddings
from langchain.schema.memory import BaseMemory
from langchain.text_splitter import TextSplitter
from langchain.tools import Tool
from langchain.vectorstores.base import VectorStore
from typing import Union, Dict
# Type alias for more complex dicts
NestedDict = Dict[str, Union[str, Dict]]
class Object:
pass
class Data:
pass
@ -25,7 +30,10 @@ LANGCHAIN_BASE_TYPES = {
"AgentExecutor": AgentExecutor,
"Tool": Tool,
"BaseLLM": BaseLLM,
"BaseLanguageModel": BaseLanguageModel,
"PromptTemplate": PromptTemplate,
"ChatPromptTemplate": ChatPromptTemplate,
"BasePromptTemplate": BasePromptTemplate,
"BaseLoader": BaseLoader,
"Document": Document,
"TextSplitter": TextSplitter,
@ -47,4 +55,6 @@ CUSTOM_COMPONENT_SUPPORTED_TYPES = {
"dict": dict,
"NestedDict": NestedDict,
"Data": Data,
"Object": Object,
"Callable": Callable,
}

35
src/backend/langflow/graph/edge/base.py
View file

@ -8,9 +8,7 @@ if TYPE_CHECKING:
class SourceHandle(BaseModel):
baseClasses: List[str] = Field(
..., description="List of base classes for the source handle."
)
baseClasses: List[str] = Field(..., description="List of base classes for the source handle.")
dataType: str = Field(..., description="Data type for the source handle.")
id: str = Field(..., description="Unique identifier for the source handle.")
@ -18,9 +16,7 @@ class SourceHandle(BaseModel):
class TargetHandle(BaseModel):
fieldName: str = Field(..., description="Field name for the target handle.")
id: str = Field(..., description="Unique identifier for the target handle.")
inputTypes: Optional[List[str]] = Field(
None, description="List of input types for the target handle."
)
inputTypes: Optional[List[str]] = Field(None, description="List of input types for the target handle.")
type: str = Field(..., description="Type of the target handle.")
@ -49,23 +45,17 @@ class Edge:
def validate_handles(self) -> None:
if self.target_handle.inputTypes is None:
self.valid_handles = (
self.target_handle.type in self.source_handle.baseClasses
)
self.valid_handles = self.target_handle.type in self.source_handle.baseClasses
else:
self.valid_handles = (
any(
baseClass in self.target_handle.inputTypes
for baseClass in self.source_handle.baseClasses
)
any(baseClass in self.target_handle.inputTypes for baseClass in self.source_handle.baseClasses)
or self.target_handle.type in self.source_handle.baseClasses
)
if not self.valid_handles:
logger.debug(self.source_handle)
logger.debug(self.target_handle)
raise ValueError(
f"Edge between {self.source.vertex_type} and {self.target.vertex_type} "
f"has invalid handles"
f"Edge between {self.source.vertex_type} and {self.target.vertex_type} " f"has invalid handles"
)
def __setstate__(self, state):
@ -87,11 +77,7 @@ class Edge:
# Both lists contain strings and sometimes a string contains the value we are
# looking for e.g. comgin_out=["Chain"] and target_reqs=["LLMChain"]
# so we need to check if any of the strings in source_types is in target_reqs
self.valid = any(
output in target_req
for output in self.source_types
for target_req in self.target_reqs
)
self.valid = any(output in target_req for output in self.source_types for target_req in self.target_reqs)
# Get what type of input the target node is expecting
self.matched_type = next(
@ -103,8 +89,7 @@ class Edge:
logger.debug(self.source_types)
logger.debug(self.target_reqs)
raise ValueError(
f"Edge between {self.source.vertex_type} and {self.target.vertex_type} "
f"has no matched type"
f"Edge between {self.source.vertex_type} and {self.target.vertex_type} " f"has no matched type"
)
def __repr__(self) -> str:
@ -117,8 +102,4 @@ class Edge:
return hash(self.__repr__())
def __eq__(self, __value: object) -> bool:
return (
self.__repr__() == __value.__repr__()
if isinstance(__value, Edge)
else False
)
return self.__repr__() == __value.__repr__() if isinstance(__value, Edge) else False

33
src/backend/langflow/graph/graph/base.py
View file

@ -1,18 +1,15 @@
from typing import Dict, Generator, List, Type, Union
from langchain.chains.base import Chain
from loguru import logger
from langflow.graph.edge.base import Edge
from langflow.graph.graph.constants import lazy_load_vertex_dict
from langflow.graph.graph.utils import process_flow
from langflow.graph.vertex.base import Vertex
from langflow.graph.vertex.types import (
FileToolVertex,
LLMVertex,
ToolkitVertex,
)
from langflow.graph.vertex.types import FileToolVertex, LLMVertex, ToolkitVertex
from langflow.interface.tools.constants import FILE_TOOLS
from langflow.utils import payload
from loguru import logger
from langchain.chains.base import Chain
class Graph:
@ -31,8 +28,8 @@ class Graph:
for node in self._nodes:
if node_id := node.get("id"):
self.top_level_nodes.append(node_id)
self._graph_data = process_flow(self.raw_graph_data)
self._nodes = self._graph_data["nodes"]
self._edges = self._graph_data["edges"]
self._build_graph()
@ -104,9 +101,7 @@ class Graph:
return
for node in self.nodes:
if not self._validate_node(node):
raise ValueError(
f"{node.vertex_type} is not connected to any other components"
)
raise ValueError(f"{node.vertex_type} is not connected to any other components")
def _validate_node(self, node: Vertex) -> bool:
"""Validates a node."""
@ -119,18 +114,16 @@ class Graph:
def get_nodes_with_target(self, node: Vertex) -> List[Vertex]:
"""Returns the nodes connected to a node."""
connected_nodes: List[Vertex] = [
edge.source for edge in self.edges if edge.target == node
]
connected_nodes: List[Vertex] = [edge.source for edge in self.edges if edge.target == node]
return connected_nodes
def build(self) -> Chain:
async def build(self) -> Chain:
"""Builds the graph."""
# Get root node
root_node = payload.get_root_node(self)
if root_node is None:
raise ValueError("No root node found")
return root_node.build()
return await root_node.build()
def topological_sort(self) -> List[Vertex]:
"""
@ -149,9 +142,7 @@ class Graph:
def dfs(node):
if state[node] == 1:
# We have a cycle
raise ValueError(
"Graph contains a cycle, cannot perform topological sort"
)
raise ValueError("Graph contains a cycle, cannot perform topological sort")
if state[node] == 0:
state[node] = 1
for edge in node.edges:
@ -245,7 +236,5 @@ class Graph:
def __repr__(self):
node_ids = [node.id for node in self.nodes]
edges_repr = "\n".join(
[f"{edge.source.id} --> {edge.target.id}" for edge in self.edges]
)
edges_repr = "\n".join([f"{edge.source.id} --> {edge.target.id}" for edge in self.edges])
return f"Graph:\nNodes: {node_ids}\nConnections:\n{edges_repr}"

5
src/backend/langflow/graph/graph/constants.py
View file

@ -47,10 +47,7 @@ class VertexTypesDict(LazyLoadDictBase):
**{t: types.DocumentLoaderVertex for t in documentloader_creator.to_list()},
**{t: types.TextSplitterVertex for t in textsplitter_creator.to_list()},
**{t: types.OutputParserVertex for t in output_parser_creator.to_list()},
**{
t: types.CustomComponentVertex
for t in custom_component_creator.to_list()
},
**{t: types.CustomComponentVertex for t in custom_component_creator.to_list()},
**{t: types.RetrieverVertex for t in retriever_creator.to_list()},
}

87
src/backend/langflow/graph/graph/utils.py
View file

@ -1,5 +1,6 @@
from collections import deque
import copy
from collections import deque
from typing import Dict, List
def find_last_node(nodes, edges):
@ -28,23 +29,14 @@ def ungroup_node(group_node_data, base_flow):
g_edges = flow["data"]["edges"]
# Redirect edges to the correct proxy node
updated_edges = get_updated_edges(
base_flow, g_nodes, g_edges, group_node_data["id"]
)
updated_edges = get_updated_edges(base_flow, g_nodes, g_edges, group_node_data["id"])
# Update template values
update_template(template, g_nodes)
nodes = [
n for n in base_flow["nodes"] if n["id"] != group_node_data["id"]
] + g_nodes
nodes = [n for n in base_flow["nodes"] if n["id"] != group_node_data["id"]] + g_nodes
edges = (
[
e
for e in base_flow["edges"]
if e["target"] != group_node_data["id"]
and e["source"] != group_node_data["id"]
]
[e for e in base_flow["edges"] if e["target"] != group_node_data["id"] and e["source"] != group_node_data["id"]]
+ g_edges
+ updated_edges
)
@ -55,6 +47,38 @@ def ungroup_node(group_node_data, base_flow):
return nodes
def raw_topological_sort(nodes, edges) -> List[Dict]:
# Redefine the above function but using the nodes and self._edges
# which are dicts instead of Vertex and Edge objects
# nodes have an id, edges have a source and target keys
# return a list of node ids in topological order
# States: 0 = unvisited, 1 = visiting, 2 = visited
state = {node["id"]: 0 for node in nodes}
nodes_dict = {node["id"]: node for node in nodes}
sorted_vertices = []
def dfs(node):
if state[node] == 1:
# We have a cycle
raise ValueError("Graph contains a cycle, cannot perform topological sort")
if state[node] == 0:
state[node] = 1
for edge in edges:
if edge["source"] == node:
dfs(edge["target"])
state[node] = 2
sorted_vertices.append(node)
# Visit each node
for node in nodes:
if state[node["id"]] == 0:
dfs(node["id"])
reverse_sorted = list(reversed(sorted_vertices))
return [nodes_dict[node_id] for node_id in reverse_sorted]
def process_flow(flow_object):
cloned_flow = copy.deepcopy(flow_object)
processed_nodes = set() # To keep track of processed nodes
@ -66,11 +90,7 @@ def process_flow(flow_object):
if node_id in processed_nodes:
return
if (
node.get("data")
and node["data"].get("node")
and node["data"]["node"].get("flow")
):
if node.get("data") and node["data"].get("node") and node["data"]["node"].get("flow"):
process_flow(node["data"]["node"]["flow"]["data"])
new_nodes = ungroup_node(node["data"], cloned_flow)
# Add new nodes to the queue for future processing
@ -79,7 +99,8 @@ def process_flow(flow_object):
# Mark node as processed
processed_nodes.add(node_id)
nodes_to_process = deque(cloned_flow["nodes"])
sorted_nodes_list = raw_topological_sort(cloned_flow["nodes"], cloned_flow["edges"])
nodes_to_process = deque(sorted_nodes_list)
while nodes_to_process:
node = nodes_to_process.popleft()
@ -108,29 +129,23 @@ def update_template(template, g_nodes):
if node_index != -1:
display_name = None
show = g_nodes[node_index]["data"]["node"]["template"][field]["show"]
advanced = g_nodes[node_index]["data"]["node"]["template"][field][
"advanced"
]
advanced = g_nodes[node_index]["data"]["node"]["template"][field]["advanced"]
if "display_name" in g_nodes[node_index]["data"]["node"]["template"][field]:
display_name = g_nodes[node_index]["data"]["node"]["template"][field][
"display_name"
]
display_name = g_nodes[node_index]["data"]["node"]["template"][field]["display_name"]
else:
display_name = g_nodes[node_index]["data"]["node"]["template"][field][
"name"
]
display_name = g_nodes[node_index]["data"]["node"]["template"][field]["name"]
g_nodes[node_index]["data"]["node"]["template"][field] = value
g_nodes[node_index]["data"]["node"]["template"][field]["show"] = show
g_nodes[node_index]["data"]["node"]["template"][field][
"advanced"
] = advanced
g_nodes[node_index]["data"]["node"]["template"][field][
"display_name"
] = display_name
g_nodes[node_index]["data"]["node"]["template"][field]["advanced"] = advanced
g_nodes[node_index]["data"]["node"]["template"][field]["display_name"] = display_name
def update_target_handle(new_edge, g_nodes, group_node_id):
def update_target_handle(
new_edge,
g_nodes,
group_node_id,
):
"""
Updates the target handle of a given edge if it is a proxy node.
@ -147,6 +162,8 @@ def update_target_handle(new_edge, g_nodes, group_node_id):
proxy_id = target_handle["proxy"]["id"]
if node := next((n for n in g_nodes if n["id"] == proxy_id), None):
set_new_target_handle(proxy_id, new_edge, target_handle, node)
else:
raise ValueError(f"Group node {group_node_id} has an invalid target proxy node {proxy_id}")
return new_edge

94
src/backend/langflow/graph/vertex/base.py
View file

@ -1,20 +1,18 @@
import ast
import inspect
import pickle
import types
from typing import TYPE_CHECKING, Any, Dict, List, Optional
from loguru import logger
from langflow.graph.utils import UnbuiltObject
from langflow.graph.vertex.utils import is_basic_type
from langflow.interface.initialize import loading
from langflow.interface.listing import lazy_load_dict
from langflow.utils.constants import DIRECT_TYPES
from loguru import logger
from langflow.utils.util import sync_to_async
import inspect
import types
from typing import Any, Dict, List, Optional
from typing import TYPE_CHECKING
if TYPE_CHECKING:
from langflow.graph.edge.base import Edge
@ -51,9 +49,7 @@ class Vertex:
self.params.pop(target_param, None)
continue
if target_param in self.params and not is_basic_type(
self.params[target_param]
):
if target_param in self.params and not is_basic_type(self.params[target_param]):
# edge.source.params = {}
edge.source._build_params()
edge.source._built_object = UnbuiltObject()
@ -99,29 +95,17 @@ class Vertex:
def _parse_data(self) -> None:
self.data = self._data["data"]
self.output = self.data["node"]["base_classes"]
template_dicts = {
key: value
for key, value in self.data["node"]["template"].items()
if isinstance(value, dict)
}
template_dicts = {key: value for key, value in self.data["node"]["template"].items() if isinstance(value, dict)}
self.required_inputs = [
template_dicts[key]["type"]
for key, value in template_dicts.items()
if value["required"]
template_dicts[key]["type"] for key, value in template_dicts.items() if value["required"]
]
self.optional_inputs = [
template_dicts[key]["type"]
for key, value in template_dicts.items()
if not value["required"]
template_dicts[key]["type"] for key, value in template_dicts.items() if not value["required"]
]
# Add the template_dicts[key]["input_types"] to the optional_inputs
self.optional_inputs.extend(
[
input_type
for value in template_dicts.values()
for input_type in value.get("input_types", [])
]
[input_type for value in template_dicts.values() for input_type in value.get("input_types", [])]
)
template_dict = self.data["node"]["template"]
@ -160,11 +144,7 @@ class Vertex:
# and use that as the value for the param
# If the type is "str", then we need to get the value of the "value" key
# and use that as the value for the param
template_dict = {
key: value
for key, value in self.data["node"]["template"].items()
if isinstance(value, dict)
}
template_dict = {key: value for key, value in self.data["node"]["template"].items() if isinstance(value, dict)}
params = self.params.copy() if self.params else {}
for edge in self.edges:
@ -209,11 +189,7 @@ class Vertex:
# before passing it to the build method
_value = value.get("value")
if isinstance(_value, list):
params[key] = {
k: v
for item in value.get("value", [])
for k, v in item.items()
}
params[key] = {k: v for item in value.get("value", []) for k, v in item.items()}
elif isinstance(_value, dict):
params[key] = _value
elif value.get("type") == "int" and value.get("value") is not None:
@ -238,18 +214,18 @@ class Vertex:
self._raw_params = params
self.params = params
def _build(self, user_id=None):
async def _build(self, user_id=None):
"""
Initiate the build process.
"""
logger.debug(f"Building {self.vertex_type}")
self._build_each_node_in_params_dict(user_id)
self._get_and_instantiate_class(user_id)
await self._build_each_node_in_params_dict(user_id)
await self._get_and_instantiate_class(user_id)
self._validate_built_object()
self._built = True
def _build_each_node_in_params_dict(self, user_id=None):
async def _build_each_node_in_params_dict(self, user_id=None):
"""
Iterates over each node in the params dictionary and builds it.
"""
@ -258,9 +234,9 @@ class Vertex:
if value == self:
del self.params[key]
continue
self._build_node_and_update_params(key, value, user_id)
await self._build_node_and_update_params(key, value, user_id)
elif isinstance(value, list) and self._is_list_of_nodes(value):
self._build_list_of_nodes_and_update_params(key, value, user_id)
await self._build_list_of_nodes_and_update_params(key, value, user_id)
def _is_node(self, value):
"""
@ -274,7 +250,7 @@ class Vertex:
"""
return all(self._is_node(node) for node in value)
def get_result(self, user_id=None, timeout=None) -> Any:
async def get_result(self, user_id=None, timeout=None) -> Any:
# Check if the Vertex was built already
if self._built:
return self._built_object
@ -290,29 +266,27 @@ class Vertex:
pass
# If there's no task_id, build the vertex locally
self.build(user_id)
await self.build(user_id)
return self._built_object
def _build_node_and_update_params(self, key, node, user_id=None):
async def _build_node_and_update_params(self, key, node, user_id=None):
"""
Builds a given node and updates the params dictionary accordingly.
"""
result = node.get_result(user_id)
result = await node.get_result(user_id)
self._handle_func(key, result)
if isinstance(result, list):
self._extend_params_list_with_result(key, result)
self.params[key] = result
def _build_list_of_nodes_and_update_params(
self, key, nodes: List["Vertex"], user_id=None
):
async def _build_list_of_nodes_and_update_params(self, key, nodes: List["Vertex"], user_id=None):
"""
Iterates over a list of nodes, builds each and updates the params dictionary.
"""
self.params[key] = []
for node in nodes:
built = node.get_result(user_id)
built = await node.get_result(user_id)
if isinstance(built, list):
if key not in self.params:
self.params[key] = []
@ -342,14 +316,14 @@ class Vertex:
if isinstance(self.params[key], list):
self.params[key].extend(result)
def _get_and_instantiate_class(self, user_id=None):
async def _get_and_instantiate_class(self, user_id=None):
"""
Gets the class from a dictionary and instantiates it with the params.
"""
if self.base_type is None:
raise ValueError(f"Base type for node {self.vertex_type} not found")
try:
result = loading.instantiate_class(
result = await loading.instantiate_class(
node_type=self.vertex_type,
base_type=self.base_type,
params=self.params,
@ -358,9 +332,7 @@ class Vertex:
self._update_built_object_and_artifacts(result)
except Exception as exc:
logger.exception(exc)
raise ValueError(
f"Error building node {self.vertex_type}: {str(exc)}"
) from exc
raise ValueError(f"Error building node {self.vertex_type}(ID:{self.id}): {str(exc)}") from exc
def _update_built_object_and_artifacts(self, result):
"""
@ -384,9 +356,9 @@ class Vertex:
raise ValueError(message)
def build(self, force: bool = False, user_id=None, *args, **kwargs) -> Any:
async def build(self, force: bool = False, user_id=None, *args, **kwargs) -> Any:
if not self._built or force:
self._build(user_id, *args, **kwargs)
await self._build(user_id, *args, **kwargs)
return self._built_object
@ -408,8 +380,4 @@ class Vertex:
def _built_object_repr(self):
# Add a message with an emoji, stars for sucess,
return (
"Built sucessfully ✨"
if self._built_object is not None
else "Failed to build 😵‍💫"
)
return "Built sucessfully ✨" if self._built_object is not None else "Failed to build 😵‍💫"

81
src/backend/langflow/graph/vertex/types.py
View file

@ -1,8 +1,8 @@
import ast
from typing import Any, Dict, List, Optional, Union
from langflow.graph.vertex.base import Vertex
from langflow.graph.utils import flatten_list
from langflow.graph.vertex.base import Vertex
from langflow.interface.utils import extract_input_variables_from_prompt
@ -34,18 +34,18 @@ class AgentVertex(Vertex):
elif isinstance(source_node, ChainVertex):
self.chains.append(source_node)
def build(self, force: bool = False, user_id=None, *args, **kwargs) -> Any:
async def build(self, force: bool = False, user_id=None, *args, **kwargs) -> Any:
if not self._built or force:
self._set_tools_and_chains()
# First, build the tools
for tool_node in self.tools:
tool_node.build(user_id=user_id)
await tool_node.build(user_id=user_id)
# Next, build the chains and the rest
for chain_node in self.chains:
chain_node.build(tools=self.tools, user_id=user_id)
await chain_node.build(tools=self.tools, user_id=user_id)
self._build(user_id=user_id)
await self._build(user_id=user_id)
return self._built_object
@ -62,13 +62,13 @@ class LLMVertex(Vertex):
def __init__(self, data: Dict, params: Optional[Dict] = None):
super().__init__(data, base_type="llms", params=params)
def build(self, force: bool = False, user_id=None, *args, **kwargs) -> Any:
async def build(self, force: bool = False, user_id=None, *args, **kwargs) -> Any:
# LLM is different because some models might take up too much memory
# or time to load. So we only load them when we need them.ß
if self.vertex_type == self.built_node_type:
return self.class_built_object
if not self._built or force:
self._build(user_id=user_id)
await self._build(user_id=user_id)
self.built_node_type = self.vertex_type
self.class_built_object = self._built_object
# Avoid deepcopying the LLM
@ -90,11 +90,11 @@ class WrapperVertex(Vertex):
def __init__(self, data: Dict):
super().__init__(data, base_type="wrappers")
def build(self, force: bool = False, user_id=None, *args, **kwargs) -> Any:
async def build(self, force: bool = False, user_id=None, *args, **kwargs) -> Any:
if not self._built or force:
if "headers" in self.params:
self.params["headers"] = ast.literal_eval(self.params["headers"])
self._build(user_id=user_id)
await self._build(user_id=user_id)
return self._built_object
@ -107,11 +107,9 @@ class DocumentLoaderVertex(Vertex):
# show how many documents are in the list?
if self._built_object:
avg_length = sum(
len(doc.page_content)
for doc in self._built_object
if hasattr(doc, "page_content")
) / len(self._built_object)
avg_length = sum(len(doc.page_content) for doc in self._built_object if hasattr(doc, "page_content")) / len(
self._built_object
)
return f"""{self.vertex_type}({len(self._built_object)} documents)
\nAvg. Document Length (characters): {int(avg_length)}
Documents: {self._built_object[:3]}..."""
@ -184,9 +182,7 @@ class TextSplitterVertex(Vertex):
# show how many documents are in the list?
if self._built_object:
avg_length = sum(len(doc.page_content) for doc in self._built_object) / len(
self._built_object
)
avg_length = sum(len(doc.page_content) for doc in self._built_object) / len(self._built_object)
return f"""{self.vertex_type}({len(self._built_object)} documents)
\nAvg. Document Length (characters): {int(avg_length)}
\nDocuments: {self._built_object[:3]}..."""
@ -197,7 +193,7 @@ class ChainVertex(Vertex):
def __init__(self, data: Dict):
super().__init__(data, base_type="chains")
def build(
async def build(
self,
force: bool = False,
user_id=None,
@ -205,14 +201,20 @@ class ChainVertex(Vertex):
**kwargs,
) -> Any:
if not self._built or force:
# Temporarily remove the code from the params
self.params.pop("code", None)
# Check if the chain requires a PromptVertex
# Temporarily remove "code" from the params
self.params.pop("code", None)
for key, value in self.params.items():
if isinstance(value, PromptVertex):
# Build the PromptVertex, passing the tools if available
tools = kwargs.get("tools", None)
self.params[key] = value.build(tools=tools, force=force)
self.params[key] = await value.build(tools=tools, force=force)
self._build(user_id=user_id)
await self._build(user_id=user_id)
return self._built_object
@ -221,7 +223,7 @@ class PromptVertex(Vertex):
def __init__(self, data: Dict):
super().__init__(data, base_type="prompts")
def build(
async def build(
self,
force: bool = False,
user_id=None,
@ -230,27 +232,18 @@ class PromptVertex(Vertex):
**kwargs,
) -> Any:
if not self._built or force:
if (
"input_variables" not in self.params
or self.params["input_variables"] is None
):
if "input_variables" not in self.params or self.params["input_variables"] is None:
self.params["input_variables"] = []
# Check if it is a ZeroShotPrompt and needs a tool
if "ShotPrompt" in self.vertex_type:
tools = (
[tool_node.build(user_id=user_id) for tool_node in tools]
if tools is not None
else []
)
tools = [await tool_node.build(user_id=user_id) for tool_node in tools] if tools is not None else []
# flatten the list of tools if it is a list of lists
# first check if it is a list
if tools and isinstance(tools, list) and isinstance(tools[0], list):
tools = flatten_list(tools)
self.params["tools"] = tools
prompt_params = [
key
for key, value in self.params.items()
if isinstance(value, str) and key != "format_instructions"
key for key, value in self.params.items() if isinstance(value, str) and key != "format_instructions"
]
else:
prompt_params = ["template"]
@ -260,21 +253,15 @@ class PromptVertex(Vertex):
prompt_text = self.params[param]
variables = extract_input_variables_from_prompt(prompt_text)
self.params["input_variables"].extend(variables)
self.params["input_variables"] = list(
set(self.params["input_variables"])
)
self.params["input_variables"] = list(set(self.params["input_variables"]))
elif isinstance(self.params, dict):
self.params.pop("input_variables", None)
self._build(user_id=user_id)
await self._build(user_id=user_id)
return self._built_object
def _built_object_repr(self):
if (
not self.artifacts
or self._built_object is None
or not hasattr(self._built_object, "format")
):
if not self.artifacts or self._built_object is None or not hasattr(self._built_object, "format"):
return super()._built_object_repr()
# We'll build the prompt with the artifacts
# to show the user what the prompt looks like
@ -284,9 +271,7 @@ class PromptVertex(Vertex):
# so the prompt format doesn't break
artifacts.pop("handle_keys", None)
try:
if not hasattr(self._built_object, "template") and hasattr(
self._built_object, "prompt"
):
if not hasattr(self._built_object, "template") and hasattr(self._built_object, "prompt"):
template = self._built_object.prompt.template
else:
template = self._built_object.template
@ -294,11 +279,7 @@ class PromptVertex(Vertex):
if value:
replace_key = "{" + key + "}"
template = template.replace(replace_key, value)
return (
template
if isinstance(template, str)
else f"{self.vertex_type}({template})"
)
return template if isinstance(template, str) else f"{self.vertex_type}({template})"
except KeyError:
return str(self._built_object)

21
src/backend/langflow/interface/agents/base.py
View file

@ -1,11 +1,11 @@
from typing import Dict, List, Optional
from typing import ClassVar, Dict, List, Optional
from langchain.agents import types
from langflow.custom.customs import get_custom_nodes
from langflow.interface.agents.custom import CUSTOM_AGENTS
from langflow.interface.base import LangChainTypeCreator
from langflow.services.getters import get_settings_service
from langflow.services.deps import get_settings_service
from langflow.template.frontend_node.agents import AgentFrontendNode
from loguru import logger
@ -15,7 +15,7 @@ from langflow.utils.util import build_template_from_class, build_template_from_m
class AgentCreator(LangChainTypeCreator):
type_name: str = "agents"
from_method_nodes = {"ZeroShotAgent": "from_llm_and_tools"}
from_method_nodes: ClassVar[Dict] = {"ZeroShotAgent": "from_llm_and_tools"}
@property
def frontend_node_class(self) -> type[AgentFrontendNode]:
@ -42,9 +42,7 @@ class AgentCreator(LangChainTypeCreator):
add_function=True,
method_name=self.from_method_nodes[name],
)
return build_template_from_class(
name, self.type_to_loader_dict, add_function=True
)
return build_template_from_class(name, self.type_to_loader_dict, add_function=True)
except ValueError as exc:
raise ValueError("Agent not found") from exc
except AttributeError as exc:
@ -56,15 +54,8 @@ class AgentCreator(LangChainTypeCreator):
names = []
settings_service = get_settings_service()
for _, agent in self.type_to_loader_dict.items():
agent_name = (
agent.function_name()
if hasattr(agent, "function_name")
else agent.__name__
)
if (
agent_name in settings_service.settings.AGENTS
or settings_service.settings.DEV
):
agent_name = agent.function_name() if hasattr(agent, "function_name") else agent.__name__
if agent_name in settings_service.settings.AGENTS or settings_service.settings.DEV:
names.append(agent_name)
return names

90
src/backend/langflow/interface/agents/custom.py
View file

@ -1,13 +1,6 @@
from typing import Any, List, Optional
from langchain.chains.llm import LLMChain
from langchain.agents import (
AgentExecutor,
Tool,
ZeroShotAgent,
initialize_agent,
AgentType,
)
from langchain.agents import AgentExecutor, AgentType, Tool, ZeroShotAgent, initialize_agent
from langchain.agents.agent_toolkits import (
SQLDatabaseToolkit,
VectorStoreInfo,
@ -16,23 +9,18 @@ from langchain.agents.agent_toolkits import (
)
from langchain.agents.agent_toolkits.json.prompt import JSON_PREFIX, JSON_SUFFIX
from langchain.agents.agent_toolkits.json.toolkit import JsonToolkit
from langchain.agents.agent_toolkits.pandas.prompt import PREFIX as PANDAS_PREFIX
from langchain.agents.agent_toolkits.pandas.prompt import (
SUFFIX_WITH_DF as PANDAS_SUFFIX,
)
from langchain.agents.agent_toolkits.sql.prompt import SQL_PREFIX, SQL_SUFFIX
from langchain.agents.agent_toolkits.vectorstore.prompt import (
PREFIX as VECTORSTORE_PREFIX,
)
from langchain.agents.agent_toolkits.vectorstore.prompt import (
ROUTER_PREFIX as VECTORSTORE_ROUTER_PREFIX,
)
from langchain.agents.agent_toolkits.vectorstore.prompt import PREFIX as VECTORSTORE_PREFIX
from langchain.agents.agent_toolkits.vectorstore.prompt import ROUTER_PREFIX as VECTORSTORE_ROUTER_PREFIX
from langchain.agents.mrkl.prompt import FORMAT_INSTRUCTIONS
from langchain.base_language import BaseLanguageModel
from langchain.chains.llm import LLMChain
from langchain.memory.chat_memory import BaseChatMemory
from langchain.sql_database import SQLDatabase
from langchain.tools.python.tool import PythonAstREPLTool
from langchain.tools.sql_database.prompt import QUERY_CHECKER
from langchain_experimental.agents.agent_toolkits.pandas.prompt import PREFIX as PANDAS_PREFIX
from langchain_experimental.agents.agent_toolkits.pandas.prompt import SUFFIX_WITH_DF as PANDAS_SUFFIX
from langchain_experimental.tools.python.tool import PythonAstREPLTool
from langflow.interface.base import CustomAgentExecutor
@ -53,7 +41,7 @@ class JsonAgent(CustomAgentExecutor):
@classmethod
def from_toolkit_and_llm(cls, toolkit: JsonToolkit, llm: BaseLanguageModel):
tools = toolkit if isinstance(toolkit, list) else toolkit.get_tools()
tool_names = {tool.name for tool in tools}
tool_names = list({tool.name for tool in tools})
prompt = ZeroShotAgent.create_prompt(
tools,
prefix=JSON_PREFIX,
@ -66,7 +54,8 @@ class JsonAgent(CustomAgentExecutor):
prompt=prompt,
)
agent = ZeroShotAgent(
llm_chain=llm_chain, allowed_tools=tool_names # type: ignore
llm_chain=llm_chain,
allowed_tools=tool_names, # type: ignore
)
return cls.from_agent_and_tools(agent=agent, tools=tools, verbose=True)
@ -90,11 +79,7 @@ class CSVAgent(CustomAgentExecutor):
@classmethod
def from_toolkit_and_llm(
cls,
path: str,
llm: BaseLanguageModel,
pandas_kwargs: Optional[dict] = None,
**kwargs: Any
cls, path: str, llm: BaseLanguageModel, pandas_kwargs: Optional[dict] = None, **kwargs: Any
):
import pandas as pd # type: ignore
@ -106,16 +91,18 @@ class CSVAgent(CustomAgentExecutor):
tools,
prefix=PANDAS_PREFIX,
suffix=PANDAS_SUFFIX,
input_variables=["df", "input", "agent_scratchpad"],
input_variables=["df_head", "input", "agent_scratchpad"],
)
partial_prompt = prompt.partial(df=str(df.head()))
partial_prompt = prompt.partial(df_head=str(df.head()))
llm_chain = LLMChain(
llm=llm,
prompt=partial_prompt,
)
tool_names = {tool.name for tool in tools}
tool_names = list({tool.name for tool in tools})
agent = ZeroShotAgent(
llm_chain=llm_chain, allowed_tools=tool_names, **kwargs # type: ignore
llm_chain=llm_chain,
allowed_tools=tool_names,
**kwargs, # type: ignore
)
return cls.from_agent_and_tools(agent=agent, tools=tools, verbose=True)
@ -139,9 +126,7 @@ class VectorStoreAgent(CustomAgentExecutor):
super().__init__(*args, **kwargs)
@classmethod
def from_toolkit_and_llm(
cls, llm: BaseLanguageModel, vectorstoreinfo: VectorStoreInfo, **kwargs: Any
):
def from_toolkit_and_llm(cls, llm: BaseLanguageModel, vectorstoreinfo: VectorStoreInfo, **kwargs: Any):
"""Construct a vectorstore agent from an LLM and tools."""
toolkit = VectorStoreToolkit(vectorstore_info=vectorstoreinfo, llm=llm)
@ -152,13 +137,13 @@ class VectorStoreAgent(CustomAgentExecutor):
llm=llm,
prompt=prompt,
)
tool_names = {tool.name for tool in tools}
tool_names = list({tool.name for tool in tools})
agent = ZeroShotAgent(
llm_chain=llm_chain, allowed_tools=tool_names, **kwargs # type: ignore
)
return AgentExecutor.from_agent_and_tools(
agent=agent, tools=tools, verbose=True, handle_parsing_errors=True
llm_chain=llm_chain,
allowed_tools=tool_names,
**kwargs, # type: ignore
)
return AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True, handle_parsing_errors=True)
def run(self, *args, **kwargs):
return super().run(*args, **kwargs)
@ -179,9 +164,7 @@ class SQLAgent(CustomAgentExecutor):
super().__init__(*args, **kwargs)
@classmethod
def from_toolkit_and_llm(
cls, llm: BaseLanguageModel, database_uri: str, **kwargs: Any
):
def from_toolkit_and_llm(cls, llm: BaseLanguageModel, database_uri: str, **kwargs: Any):
"""Construct an SQL agent from an LLM and tools."""
db = SQLDatabase.from_uri(database_uri)
toolkit = SQLDatabaseToolkit(db=db, llm=llm)
@ -199,9 +182,7 @@ class SQLAgent(CustomAgentExecutor):
llmchain = LLMChain(
llm=llm,
prompt=PromptTemplate(
template=QUERY_CHECKER, input_variables=["query", "dialect"]
),
prompt=PromptTemplate(template=QUERY_CHECKER, input_variables=["query", "dialect"]),
)
tools = [
@ -222,9 +203,11 @@ class SQLAgent(CustomAgentExecutor):
llm=llm,
prompt=prompt,
)
tool_names = {tool.name for tool in tools} # type: ignore
tool_names = list({tool.name for tool in tools}) # type: ignore
agent = ZeroShotAgent(
llm_chain=llm_chain, allowed_tools=tool_names, **kwargs # type: ignore
llm_chain=llm_chain,
allowed_tools=tool_names,
**kwargs, # type: ignore
)
return AgentExecutor.from_agent_and_tools(
agent=agent,
@ -255,10 +238,7 @@ class VectorStoreRouterAgent(CustomAgentExecutor):
@classmethod
def from_toolkit_and_llm(
cls,
llm: BaseLanguageModel,
vectorstoreroutertoolkit: VectorStoreRouterToolkit,
**kwargs: Any
cls, llm: BaseLanguageModel, vectorstoreroutertoolkit: VectorStoreRouterToolkit, **kwargs: Any
):
"""Construct a vector store router agent from an LLM and tools."""
@ -272,13 +252,13 @@ class VectorStoreRouterAgent(CustomAgentExecutor):
llm=llm,
prompt=prompt,
)
tool_names = {tool.name for tool in tools}
tool_names = list({tool.name for tool in tools})
agent = ZeroShotAgent(
llm_chain=llm_chain, allowed_tools=tool_names, **kwargs # type: ignore
)
return AgentExecutor.from_agent_and_tools(
agent=agent, tools=tools, verbose=True, handle_parsing_errors=True
llm_chain=llm_chain,
allowed_tools=tool_names,
**kwargs, # type: ignore
)
return AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True, handle_parsing_errors=True)
def run(self, *args, **kwargs):
return super().run(*args, **kwargs)

11
src/backend/langflow/interface/base.py
View file

@ -2,7 +2,7 @@ from abc import ABC, abstractmethod
from typing import Any, Dict, List, Optional, Type, Union
from langchain.chains.base import Chain
from langchain.agents import AgentExecutor
from langflow.services.getters import get_settings_service
from langflow.services.deps import get_settings_service
from pydantic import BaseModel
from langflow.template.field.base import TemplateField
@ -30,13 +30,8 @@ class LangChainTypeCreator(BaseModel, ABC):
settings_service = get_settings_service()
if self.name_docs_dict is None:
try:
type_settings = getattr(
settings_service.settings, self.type_name.upper()
)
self.name_docs_dict = {
name: value_dict["documentation"]
for name, value_dict in type_settings.items()
}
type_settings = getattr(settings_service.settings, self.type_name.upper())
self.name_docs_dict = {name: value_dict["documentation"] for name, value_dict in type_settings.items()}
except AttributeError as exc:
logger.error(f"Error getting settings for {self.type_name}: {exc}")

24
src/backend/langflow/interface/chains/base.py
View file

@ -1,15 +1,15 @@
from typing import Any, Dict, List, Optional, Type
from typing import Any, ClassVar, Dict, List, Optional, Type
from langflow.custom.customs import get_custom_nodes
from langflow.interface.base import LangChainTypeCreator
from langflow.interface.importing.utils import import_class
from langflow.services.getters import get_settings_service
from langflow.services.deps import get_settings_service
from langflow.template.frontend_node.chains import ChainFrontendNode
from loguru import logger
from langflow.utils.util import build_template_from_class, build_template_from_method
from langchain import chains
from langchain_experimental.sql import SQLDatabaseChain # type: ignore
from langchain_experimental.sql import SQLDatabaseChain
# Assuming necessary imports for Field, Template, and FrontendNode classes
@ -22,7 +22,7 @@ class ChainCreator(LangChainTypeCreator):
return ChainFrontendNode
#! We need to find a better solution for this
from_method_nodes = {
from_method_nodes: ClassVar[Dict] = {
"ConversationalRetrievalChain": "from_llm",
"LLMCheckerChain": "from_llm",
"SQLDatabaseChain": "from_llm",
@ -33,8 +33,7 @@ class ChainCreator(LangChainTypeCreator):
if self.type_dict is None:
settings_service = get_settings_service()
self.type_dict: dict[str, Any] = {
chain_name: import_class(f"langchain.chains.{chain_name}")
for chain_name in chains.__all__
chain_name: import_class(f"langchain.chains.{chain_name}") for chain_name in chains.__all__
}
from langflow.interface.chains.custom import CUSTOM_CHAINS
@ -45,8 +44,7 @@ class ChainCreator(LangChainTypeCreator):
self.type_dict = {
name: chain
for name, chain in self.type_dict.items()
if name in settings_service.settings.CHAINS
or settings_service.settings.DEV
if name in settings_service.settings.CHAINS or settings_service.settings.DEV
}
return self.type_dict
@ -61,9 +59,7 @@ class ChainCreator(LangChainTypeCreator):
method_name=self.from_method_nodes[name],
add_function=True,
)
return build_template_from_class(
name, self.type_to_loader_dict, add_function=True
)
return build_template_from_class(name, self.type_to_loader_dict, add_function=True)
except ValueError as exc:
raise ValueError(f"Chain {name} not found: {exc}") from exc
except AttributeError as exc:
@ -73,11 +69,7 @@ class ChainCreator(LangChainTypeCreator):
def to_list(self) -> List[str]:
names = []
for _, chain in self.type_to_loader_dict.items():
chain_name = (
chain.function_name()
if hasattr(chain, "function_name")
else chain.__name__
)
chain_name = chain.function_name() if hasattr(chain, "function_name") else chain.__name__
names.append(chain_name)
return names

18
src/backend/langflow/interface/chains/custom.py
View file

@ -4,7 +4,7 @@ from langchain.chains import ConversationChain
from langchain.memory.buffer import ConversationBufferMemory
from langchain.schema import BaseMemory
from langflow.interface.base import CustomChain
from pydantic import Field, root_validator
from pydantic.v1 import Field, root_validator
from langchain.chains.question_answering import load_qa_chain
from langflow.interface.utils import extract_input_variables_from_prompt
from langchain.base_language import BaseLanguageModel
@ -41,9 +41,7 @@ class BaseCustomConversationChain(ConversationChain):
values["template"] = values["template"].format(**format_dict)
values["template"] = values["template"]
values["input_variables"] = extract_input_variables_from_prompt(
values["template"]
)
values["input_variables"] = extract_input_variables_from_prompt(values["template"])
values["prompt"].template = values["template"]
values["prompt"].input_variables = values["input_variables"]
return values
@ -54,9 +52,7 @@ class SeriesCharacterChain(BaseCustomConversationChain):
character: str
series: str
template: Optional[
str
] = """I want you to act like {character} from {series}.
template: Optional[str] = """I want you to act like {character} from {series}.
I want you to respond and answer like {character}. do not write any explanations. only answer like {character}.
You must know all of the knowledge of {character}.
Current conversation:
@ -71,9 +67,7 @@ Human: {input}
class MidJourneyPromptChain(BaseCustomConversationChain):
"""MidJourneyPromptChain is a chain you can use to generate new MidJourney prompts."""
template: Optional[
str
] = """I want you to act as a prompt generator for Midjourney's artificial intelligence program.
template: Optional[str] = """I want you to act as a prompt generator for Midjourney's artificial intelligence program.
Your job is to provide detailed and creative descriptions that will inspire unique and interesting images from the AI.
Keep in mind that the AI is capable of understanding a wide range of language and can interpret abstract concepts, so feel free to be as imaginative and descriptive as possible.
For example, you could describe a scene from a futuristic city, or a surreal landscape filled with strange creatures.
@ -87,9 +81,7 @@ class MidJourneyPromptChain(BaseCustomConversationChain):
class TimeTravelGuideChain(BaseCustomConversationChain):
template: Optional[
str
] = """I want you to act as my time travel guide. You are helpful and creative. I will provide you with the historical period or future time I want to visit and you will suggest the best events, sights, or people to experience. Provide the suggestions and any necessary information.
template: Optional[str] = """I want you to act as my time travel guide. You are helpful and creative. I will provide you with the historical period or future time I want to visit and you will suggest the best events, sights, or people to experience. Provide the suggestions and any necessary information.
Current conversation:
{history}
Human: {input}

107
src/backend/langflow/interface/custom/code_parser.py
View file

@ -1,9 +1,12 @@
import ast
import inspect
import operator
import traceback
from typing import Any, Dict, List, Type, Union
from typing import Dict, Any, List, Type, Union
from cachetools import TTLCache, cachedmethod, keys
from fastapi import HTTPException
from langflow.interface.custom.schema import CallableCodeDetails, ClassCodeDetails
@ -11,6 +14,19 @@ class CodeSyntaxError(HTTPException):
pass
def get_data_type():
from langflow.field_typing import Data
return Data
def imports_key(*args, **kwargs):
imports = kwargs.pop("imports")
key = keys.methodkey(*args, **kwargs)
key += tuple(imports)
return key
class CodeParser:
"""
A parser for Python source code, extracting code details.
@ -20,6 +36,7 @@ class CodeParser:
"""
Initializes the parser with the provided code.
"""
self.cache = TTLCache(maxsize=1024, ttl=60)
if isinstance(code, type):
if not inspect.isclass(code):
raise ValueError("The provided code must be a class.")
@ -65,14 +82,20 @@ class CodeParser:
def parse_imports(self, node: Union[ast.Import, ast.ImportFrom]) -> None:
"""
Extracts "imports" from the code.
Extracts "imports" from the code, including aliases.
"""
if isinstance(node, ast.Import):
for alias in node.names:
self.data["imports"].append(alias.name)
if alias.asname:
self.data["imports"].append(f"{alias.name} as {alias.asname}")
else:
self.data["imports"].append(alias.name)
elif isinstance(node, ast.ImportFrom):
for alias in node.names:
self.data["imports"].append((node.module, alias.name))
if alias.asname:
self.data["imports"].append((node.module, f"{alias.name} as {alias.asname}"))
else:
self.data["imports"].append((node.module, alias.name))
def parse_functions(self, node: ast.FunctionDef) -> None:
"""
@ -89,22 +112,52 @@ class CodeParser:
arg_dict["type"] = ast.unparse(arg.annotation)
return arg_dict
@cachedmethod(operator.attrgetter("cache"))
def construct_eval_env(self, return_type_str: str, imports) -> dict:
"""
Constructs an evaluation environment with the necessary imports for the return type,
taking into account module aliases.
"""
eval_env: dict = {}
for import_entry in imports:
if isinstance(import_entry, tuple): # from module import name
module, name = import_entry
if name in return_type_str:
exec(f"import {module}", eval_env)
exec(f"from {module} import {name}", eval_env)
else: # import module
module = import_entry
alias = None
if " as " in module:
module, alias = module.split(" as ")
if module in return_type_str or (alias and alias in return_type_str):
exec(f"import {module} as {alias if alias else module}", eval_env)
return eval_env
@cachedmethod(cache=operator.attrgetter("cache"))
def parse_callable_details(self, node: ast.FunctionDef) -> Dict[str, Any]:
"""
Extracts details from a single function or method node.
"""
return_type = None
if node.returns:
return_type_str = ast.unparse(node.returns)
eval_env = self.construct_eval_env(return_type_str, tuple(self.data["imports"]))
try:
return_type = eval(return_type_str, eval_env)
except NameError:
# Handle cases where the type is not found in the constructed environment
pass
func = CallableCodeDetails(
name=node.name,
doc=ast.get_docstring(node),
args=[],
body=[],
return_type=ast.unparse(node.returns) if node.returns else None,
name=node.name, doc=ast.get_docstring(node), args=[], body=[], return_type=return_type or get_data_type()
)
func.args = self.parse_function_args(node)
func.body = self.parse_function_body(node)
return func.dict()
return func.model_dump()
def parse_function_args(self, node: ast.FunctionDef) -> List[Dict[str, Any]]:
"""
@ -127,22 +180,14 @@ class CodeParser:
num_defaults = len(node.args.defaults)
num_missing_defaults = num_args - num_defaults
missing_defaults = [None] * num_missing_defaults
default_values = [
ast.unparse(default).strip("'") if default else None
for default in node.args.defaults
]
default_values = [ast.unparse(default).strip("'") if default else None for default in node.args.defaults]
# Now check all default values to see if there
# are any "None" values in the middle
default_values = [
None if value == "None" else value for value in default_values
]
default_values = [None if value == "None" else value for value in default_values]
defaults = missing_defaults + default_values
args = [
self.parse_arg(arg, default)
for arg, default in zip(node.args.args, defaults)
]
args = [self.parse_arg(arg, default) for arg, default in zip(node.args.args, defaults)]
return args
def parse_varargs(self, node: ast.FunctionDef) -> List[Dict[str, Any]]:
@ -160,17 +205,11 @@ class CodeParser:
"""
Parses the keyword-only arguments of a function or method node.
"""
kw_defaults = [None] * (
len(node.args.kwonlyargs) - len(node.args.kw_defaults)
) + [
ast.unparse(default) if default else None
for default in node.args.kw_defaults
kw_defaults = [None] * (len(node.args.kwonlyargs) - len(node.args.kw_defaults)) + [
ast.unparse(default) if default else None for default in node.args.kw_defaults
]
args = [
self.parse_arg(arg, default)
for arg, default in zip(node.args.kwonlyargs, kw_defaults)
]
args = [self.parse_arg(arg, default) for arg, default in zip(node.args.kwonlyargs, kw_defaults)]
return args
def parse_kwargs(self, node: ast.FunctionDef) -> List[Dict[str, Any]]:
@ -240,23 +279,21 @@ class CodeParser:
elif isinstance(stmt, ast.AnnAssign):
if attr := self.parse_ann_assign(stmt):
class_details.attributes.append(attr)
elif isinstance(stmt, ast.FunctionDef):
elif isinstance(stmt, (ast.FunctionDef, ast.AsyncFunctionDef)):
method, is_init = self.parse_function_def(stmt)
if is_init:
class_details.init = method
else:
class_details.methods.append(method)
self.data["classes"].append(class_details.dict())
self.data["classes"].append(class_details.model_dump())
def parse_global_vars(self, node: ast.Assign) -> None:
"""
Extracts global variables from the code.
"""
global_var = {
"targets": [
t.id if hasattr(t, "id") else ast.dump(t) for t in node.targets
],
"targets": [t.id if hasattr(t, "id") else ast.dump(t) for t in node.targets],
"value": ast.unparse(node.value),
}
self.data["global_vars"].append(global_var)

30
src/backend/langflow/interface/custom/component.py
View file

@ -1,10 +1,11 @@
import ast
from typing import Any, Optional
from pydantic import BaseModel
from fastapi import HTTPException
import operator
from typing import Any, ClassVar, Optional
from langflow.utils import validate
from cachetools import TTLCache, cachedmethod
from fastapi import HTTPException
from langflow.interface.custom.code_parser import CodeParser
from langflow.utils import validate
class ComponentCodeNullError(HTTPException):
@ -15,19 +16,20 @@ class ComponentFunctionEntrypointNameNullError(HTTPException):
pass
class Component(BaseModel):
ERROR_CODE_NULL = "Python code must be provided."
ERROR_FUNCTION_ENTRYPOINT_NAME_NULL = (
"The name of the entrypoint function must be provided."
)
class Component:
ERROR_CODE_NULL: ClassVar[str] = "Python code must be provided."
ERROR_FUNCTION_ENTRYPOINT_NAME_NULL: ClassVar[str] = "The name of the entrypoint function must be provided."
code: Optional[str]
function_entrypoint_name = "build"
code: Optional[str] = None
_function_entrypoint_name: str = "build"
field_config: dict = {}
def __init__(self, **data):
super().__init__(**data)
self.cache = TTLCache(maxsize=1024, ttl=60)
for key, value in data.items():
setattr(self, key, value)
@cachedmethod(cache=operator.attrgetter("cache"))
def get_code_tree(self, code: str):
parser = CodeParser(code)
return parser.parse_code()
@ -39,7 +41,7 @@ class Component(BaseModel):
detail={"error": self.ERROR_CODE_NULL, "traceback": ""},
)
if not self.function_entrypoint_name:
if not self._function_entrypoint_name:
raise ComponentFunctionEntrypointNameNullError(
status_code=400,
detail={
@ -48,7 +50,7 @@ class Component(BaseModel):
},
)
return validate.create_function(self.code, self.function_entrypoint_name)
return validate.create_function(self.code, self._function_entrypoint_name)
def build_template_config(self, attributes) -> dict:
template_config = {}

25
src/backend/langflow/interface/custom/constants.py
View file

@ -1,22 +1,27 @@
DEFAULT_CUSTOM_COMPONENT_CODE = """from langflow import CustomComponent
from typing import Optional, List, Dict, Union
from langflow.field_typing import (
Tool,
PromptTemplate,
Chain,
AgentExecutor,
BaseChatMemory,
BaseLanguageModel,
BaseLLM,
BaseLoader,
BaseMemory,
BaseOutputParser,
BasePromptTemplate,
BaseRetriever,
VectorStore,
Embeddings,
TextSplitter,
Document,
AgentExecutor,
NestedDict,
Callable,
Chain,
ChatPromptTemplate,
Data,
Document,
Embeddings,
NestedDict,
Object,
PromptTemplate,
TextSplitter,
Tool,
VectorStore,
)

148
src/backend/langflow/interface/custom/custom_component.py
View file

@ -1,34 +1,47 @@
from typing import Any, Callable, List, Optional, Union
import operator
from typing import Any, Callable, ClassVar, List, Optional, Union
from uuid import UUID
import yaml
from cachetools import TTLCache, cachedmethod
from fastapi import HTTPException
from langflow.field_typing.constants import CUSTOM_COMPONENT_SUPPORTED_TYPES
from langflow.interface.custom.component import Component
from langflow.interface.custom.directory_reader import DirectoryReader
from langflow.services.getters import get_db_service
from langflow.interface.custom.utils import extract_inner_type
from langflow.interface.custom.utils import (
extract_inner_type_from_generic_alias,
extract_union_types_from_generic_alias,
)
from langflow.services.database.models.flow import Flow
from langflow.services.database.utils import session_getter
from langflow.services.deps import get_db_service
from langflow.utils import validate
from langflow.services.database.utils import session_getter
from langflow.services.database.models.flow import Flow
from pydantic import Extra
import yaml
class CustomComponent(Component, extra=Extra.allow):
code: Optional[str]
class CustomComponent(Component):
display_name: Optional[str] = "Custom Component"
description: Optional[str] = "Custom Component"
code: Optional[str] = None
field_config: dict = {}
code_class_base_inheritance = "CustomComponent"
function_entrypoint_name = "build"
code_class_base_inheritance: ClassVar[str] = "CustomComponent"
function_entrypoint_name: ClassVar[str] = "build"
function: Optional[Callable] = None
return_type_valid_list = list(CUSTOM_COMPONENT_SUPPORTED_TYPES.keys())
repr_value: Optional[Any] = ""
user_id: Optional[Union[UUID, str]] = None
status: Optional[str] = None
def __init__(self, **data):
self.cache = TTLCache(maxsize=1024, ttl=60)
super().__init__(**data)
@property
def return_type_valid_list(self):
return list(CUSTOM_COMPONENT_SUPPORTED_TYPES.keys())
def custom_repr(self):
if self.status:
self.repr_value = self.status
if isinstance(self.repr_value, dict):
return yaml.dump(self.repr_value)
if isinstance(self.repr_value, str):
@ -53,47 +66,27 @@ class CustomComponent(Component, extra=Extra.allow):
reader = DirectoryReader("", False)
for type_hint in TYPE_HINT_LIST:
if reader._is_type_hint_used_in_args(
if reader._is_type_hint_used_in_args(type_hint, code) and not reader._is_type_hint_imported(
type_hint, code
) and not reader._is_type_hint_imported(type_hint, code):
):
error_detail = {
"error": "Type hint Error",
"traceback": f"Type hint '{type_hint}' is used but not imported in the code.",
}
raise HTTPException(status_code=400, detail=error_detail)
return True
def is_check_valid(self) -> bool:
def validate(self) -> bool:
return self._class_template_validation(self.code) if self.code else False
def get_code_tree(self, code: str):
return super().get_code_tree(code)
@property
def get_function_entrypoint_args(self) -> str:
if not self.code:
return ""
tree = self.get_code_tree(self.code)
component_classes = [
cls
for cls in tree["classes"]
if self.code_class_base_inheritance in cls["bases"]
]
if not component_classes:
return ""
# Assume the first Component class is the one we're interested in
component_class = component_classes[0]
build_methods = [
method
for method in component_class["methods"]
if method["name"] == self.function_entrypoint_name
]
if not build_methods:
return ""
build_method = build_methods[0]
def get_function_entrypoint_args(self) -> list:
build_method = self.get_build_method()
if not build_method:
return []
args = build_method["args"]
for arg in args:
@ -103,68 +96,70 @@ class CustomComponent(Component, extra=Extra.allow):
detail={
"error": "Type hint Error",
"traceback": (
"Prompt type is not supported in the build method."
" Try using PromptTemplate instead."
"Prompt type is not supported in the build method." " Try using PromptTemplate instead."
),
},
)
elif not arg.get("type"):
elif not arg.get("type") and arg.get("name") != "self":
# Set the type to Data
arg["type"] = "Data"
return args
@property
def get_function_entrypoint_return_type(self) -> List[str]:
@cachedmethod(operator.attrgetter("cache"))
def get_build_method(self):
if not self.code:
return []
tree = self.get_code_tree(self.code)
component_classes = [
cls
for cls in tree["classes"]
if self.code_class_base_inheritance in cls["bases"]
]
component_classes = [cls for cls in tree["classes"] if self.code_class_base_inheritance in cls["bases"]]
if not component_classes:
return []
# Assume the first Component class is the one we're interested in
component_class = component_classes[0]
build_methods = [
method
for method in component_class["methods"]
if method["name"] == self.function_entrypoint_name
method for method in component_class["methods"] if method["name"] == self.function_entrypoint_name
]
if not build_methods:
return []
build_method = build_methods[0]
return build_methods[0]
@property
def get_function_entrypoint_return_type(self) -> List[Any]:
build_method = self.get_build_method()
if not build_method:
return build_method
return_type = build_method["return_type"]
if not return_type:
return []
# If list or List is in the return type, then we remove it and return the inner type
if return_type.startswith("list") or return_type.startswith("List"):
return_type = extract_inner_type(return_type)
if hasattr(return_type, "__origin__") and return_type.__origin__ in [list, List]:
return_type = extract_inner_type_from_generic_alias(return_type)
# If the return type is not a Union, then we just return it as a list
if "Union" not in return_type:
return [return_type] if return_type in self.return_type_valid_list else []
if not hasattr(return_type, "__origin__") or return_type.__origin__ != Union:
if isinstance(return_type, list):
return return_type
return [return_type] # if return_type in self.return_type_valid_list else []
# If the return type is a Union, then we need to parse it
return_type = return_type.replace("Union", "").replace("[", "").replace("]", "")
return_type = return_type.split(",")
return_type = [item.strip() for item in return_type]
return [item for item in return_type if item in self.return_type_valid_list]
# If the return type is a Union, then we need to parse itx
return_type = extract_union_types_from_generic_alias(return_type)
# return [item for item in return_type if item in self.return_type_valid_list]
return return_type
@property
def get_main_class_name(self):
if not self.code:
return ""
tree = self.get_code_tree(self.code)
base_name = self.code_class_base_inheritance
method_name = self.function_entrypoint_name
classes = []
for item in tree.get("classes"):
for item in tree.get("classes", []):
if base_name in item["bases"]:
method_names = [method["name"] for method in item["methods"]]
if method_name in method_names:
@ -175,11 +170,13 @@ class CustomComponent(Component, extra=Extra.allow):
@property
def build_template_config(self):
if not self.code:
return {}
tree = self.get_code_tree(self.code)
attributes = [
main_class["attributes"]
for main_class in tree.get("classes")
for main_class in tree.get("classes", [])
if main_class["name"] == self.get_main_class_name
]
# Get just the first item
@ -191,9 +188,8 @@ class CustomComponent(Component, extra=Extra.allow):
def get_function(self):
return validate.create_function(self.code, self.function_entrypoint_name)
def load_flow(self, flow_id: str, tweaks: Optional[dict] = None) -> Any:
from langflow.processing.process import build_sorted_vertices
from langflow.processing.process import process_tweaks
async def load_flow(self, flow_id: str, tweaks: Optional[dict] = None) -> Any:
from langflow.processing.process import build_sorted_vertices, process_tweaks
db_service = get_db_service()
with session_getter(db_service) as session:
@ -202,7 +198,7 @@ class CustomComponent(Component, extra=Extra.allow):
raise ValueError(f"Flow {flow_id} not found")
if tweaks:
graph_data = process_tweaks(graph_data=graph_data, tweaks=tweaks)
return build_sorted_vertices(graph_data)
return await build_sorted_vertices(graph_data, self.user_id)
def list_flows(self, *, get_session: Optional[Callable] = None) -> List[Flow]:
if not self.user_id:
@ -216,7 +212,7 @@ class CustomComponent(Component, extra=Extra.allow):
except Exception as e:
raise ValueError("Session is invalid") from e
def get_flow(
async def get_flow(
self,
*,
flow_name: Optional[str] = None,
@ -230,17 +226,13 @@ class CustomComponent(Component, extra=Extra.allow):
if flow_id:
flow = session.query(Flow).get(flow_id)
elif flow_name:
flow = (
session.query(Flow)
.filter(Flow.name == flow_name)
.filter(Flow.user_id == self.user_id)
).first()
flow = (session.query(Flow).filter(Flow.name == flow_name).filter(Flow.user_id == self.user_id)).first()
else:
raise ValueError("Either flow_name or flow_id must be provided")
if not flow:
raise ValueError(f"Flow {flow_name or flow_id} not found")
return self.load_flow(flow.id, tweaks)
return await self.load_flow(flow.id, tweaks)
def build(self, *args: Any, **kwargs: Any) -> Any:
raise NotImplementedError

36
src/backend/langflow/interface/custom/directory_reader.py
View file

@ -76,9 +76,7 @@ class DirectoryReader:
for menu in data["menu"]
]
filtered = [menu for menu in items if menu["components"]]
logger.debug(
f'Filtered components {"with errors" if with_errors else ""}: {len(filtered)}'
)
logger.debug(f'Filtered components {"with errors" if with_errors else ""}: {len(filtered)}')
return {"menu": filtered}
def validate_code(self, file_content):
@ -111,9 +109,7 @@ class DirectoryReader:
Walk through the directory path and return a list of all .py files.
"""
if not (safe_path := self.get_safe_path()):
raise CustomComponentPathValueError(
f"The path needs to start with '{self.base_path}'."
)
raise CustomComponentPathValueError(f"The path needs to start with '{self.base_path}'.")
file_list = []
for root, _, files in os.walk(safe_path):
@ -158,9 +154,7 @@ class DirectoryReader:
for node in ast.walk(module):
if isinstance(node, ast.FunctionDef):
for arg in node.args.args:
if self._is_type_hint_in_arg_annotation(
arg.annotation, type_hint_name
):
if self._is_type_hint_in_arg_annotation(arg.annotation, type_hint_name):
return True
except SyntaxError:
# Returns False if the code is not valid Python
@ -178,16 +172,14 @@ class DirectoryReader:
and annotation.value.id == type_hint_name
)
def is_type_hint_used_but_not_imported(
self, type_hint_name: str, code: str
) -> bool:
def is_type_hint_used_but_not_imported(self, type_hint_name: str, code: str) -> bool:
"""
Check if a type hint is used but not imported in the given code.
"""
try:
return self._is_type_hint_used_in_args(
return self._is_type_hint_used_in_args(type_hint_name, code) and not self._is_type_hint_imported(
type_hint_name, code
) and not self._is_type_hint_imported(type_hint_name, code)
)
except SyntaxError:
# Returns True if there's something wrong with the code
# TODO : Find a better way to handle this
@ -208,9 +200,9 @@ class DirectoryReader:
return False, "Syntax error"
elif not self.validate_build(file_content):
return False, "Missing build function"
elif self._is_type_hint_used_in_args(
elif self._is_type_hint_used_in_args("Optional", file_content) and not self._is_type_hint_imported(
"Optional", file_content
) and not self._is_type_hint_imported("Optional", file_content):
):
return (
False,
"Type hint 'Optional' is used but not imported in the code.",
@ -226,9 +218,7 @@ class DirectoryReader:
from the .py files in the directory.
"""
response = {"menu": []}
logger.debug(
"-------------------- Building component menu list --------------------"
)
logger.debug("-------------------- Building component menu list --------------------")
for file_path in file_paths:
menu_name = os.path.basename(os.path.dirname(file_path))
@ -248,9 +238,7 @@ class DirectoryReader:
# first check if it's already CamelCase
if "_" in component_name:
component_name_camelcase = " ".join(
word.title() for word in component_name.split("_")
)
component_name_camelcase = " ".join(word.title() for word in component_name.split("_"))
else:
component_name_camelcase = component_name
@ -266,7 +254,5 @@ class DirectoryReader:
logger.debug(f"Component info: {component_info}")
if menu_result not in response["menu"]:
response["menu"].append(menu_result)
logger.debug(
"-------------------- Component menu list built --------------------"
)
logger.debug("-------------------- Component menu list built --------------------")
return response

11
src/backend/langflow/interface/custom/schema.py
View file

@ -1,16 +1,15 @@
from typing import Any, Optional
from pydantic import BaseModel, Field
from typing import Optional
class ClassCodeDetails(BaseModel):
"""
A dataclass for storing details about a class.
"""
name: str
doc: Optional[str]
doc: Optional[str] = None
bases: list
attributes: list
methods: list
@ -23,7 +22,7 @@ class CallableCodeDetails(BaseModel):
"""
name: str
doc: Optional[str]
doc: Optional[str] = None
args: list
body: list
return_type: Optional[str]
return_type: Optional[Any] = None

30
src/backend/langflow/interface/custom/utils.py
View file

@ -1,4 +1,6 @@
import re
from types import GenericAlias
from typing import Any
def extract_inner_type(return_type: str) -> str:
@ -8,3 +10,31 @@ def extract_inner_type(return_type: str) -> str:
if match := re.match(r"list\[(.*)\]", return_type, re.IGNORECASE):
return match[1]
return return_type
def extract_inner_type_from_generic_alias(return_type: GenericAlias) -> Any:
"""
Extracts the inner type from a type hint that is a list.
"""
if return_type.__origin__ == list:
return list(return_type.__args__)
return return_type
def extract_union_types_from_generic_alias(return_type: GenericAlias) -> list:
"""
Extracts the inner type from a type hint that is a Union.
"""
return list(return_type.__args__)
def extract_union_types(return_type: str) -> list[str]:
"""
Extracts the inner type from a type hint that is a list.
"""
# If the return type is a Union, then we need to parse it
return_type = return_type.replace("Union", "").replace("[", "").replace("]", "")
return_types = return_type.split(",")
return_types = [item.strip() for item in return_types]
return return_types

18
src/backend/langflow/interface/custom_lists.py
View file

@ -46,34 +46,26 @@ toolkit_type_to_cls_dict: dict[str, Any] = {
# Memories
memory_type_to_cls_dict: dict[str, Any] = {
memory_name: import_class(f"langchain.memory.{memory_name}")
for memory_name in memory.__all__
memory_name: import_class(f"langchain.memory.{memory_name}") for memory_name in memory.__all__
}
# Wrappers
wrapper_type_to_cls_dict: dict[str, Any] = {
wrapper.__name__: wrapper for wrapper in [requests.RequestsWrapper]
}
wrapper_type_to_cls_dict: dict[str, Any] = {wrapper.__name__: wrapper for wrapper in [requests.RequestsWrapper]}
# Embeddings
embedding_type_to_cls_dict: dict[str, Any] = {
embedding_name: import_class(f"langchain.embeddings.{embedding_name}")
for embedding_name in embeddings.__all__
embedding_name: import_class(f"langchain.embeddings.{embedding_name}") for embedding_name in embeddings.__all__
}
# Document Loaders
documentloaders_type_to_cls_dict: dict[str, Any] = {
documentloader_name: import_class(
f"langchain.document_loaders.{documentloader_name}"
)
documentloader_name: import_class(f"langchain.document_loaders.{documentloader_name}")
for documentloader_name in document_loaders.__all__
}
# Text Splitters
textsplitter_type_to_cls_dict: dict[str, Any] = dict(
inspect.getmembers(text_splitter, inspect.isclass)
)
textsplitter_type_to_cls_dict: dict[str, Any] = dict(inspect.getmembers(text_splitter, inspect.isclass))
# merge CUSTOM_AGENTS and CUSTOM_CHAINS
CUSTOM_NODES = {**CUSTOM_AGENTS, **CUSTOM_CHAINS} # type: ignore

5
src/backend/langflow/interface/document_loaders/base.py
View file

@ -1,7 +1,7 @@
from typing import Dict, List, Optional, Type
from langflow.interface.base import LangChainTypeCreator
from langflow.services.getters import get_settings_service
from langflow.services.deps import get_settings_service
from langflow.template.frontend_node.documentloaders import DocumentLoaderFrontNode
from langflow.interface.custom_lists import documentloaders_type_to_cls_dict
@ -35,8 +35,7 @@ class DocumentLoaderCreator(LangChainTypeCreator):
return [
documentloader.__name__
for documentloader in self.type_to_loader_dict.values()
if documentloader.__name__ in settings_service.settings.DOCUMENTLOADERS
or settings_service.settings.DEV
if documentloader.__name__ in settings_service.settings.DOCUMENTLOADERS or settings_service.settings.DEV
]

5
src/backend/langflow/interface/embeddings/base.py
View file

@ -2,7 +2,7 @@ from typing import Dict, List, Optional, Type
from langflow.interface.base import LangChainTypeCreator
from langflow.interface.custom_lists import embedding_type_to_cls_dict
from langflow.services.getters import get_settings_service
from langflow.services.deps import get_settings_service
from langflow.template.frontend_node.base import FrontendNode
from langflow.template.frontend_node.embeddings import EmbeddingFrontendNode
@ -37,8 +37,7 @@ class EmbeddingCreator(LangChainTypeCreator):
return [
embedding.__name__
for embedding in self.type_to_loader_dict.values()
if embedding.__name__ in settings_service.settings.EMBEDDINGS
or settings_service.settings.DEV
if embedding.__name__ in settings_service.settings.EMBEDDINGS or settings_service.settings.DEV
]

12
src/backend/langflow/interface/importing/utils.py
View file

@ -3,15 +3,15 @@
import importlib
from typing import Any, Type
from langchain.prompts import PromptTemplate
from langchain.agents import Agent
from langchain.base_language import BaseLanguageModel
from langchain.chains.base import Chain
from langchain.chat_models.base import BaseChatModel
from langchain.prompts import PromptTemplate
from langchain.tools import BaseTool
from langflow.interface.custom.custom_component import CustomComponent
from langflow.utils import validate
from langflow.interface.wrappers.base import wrapper_creator
from langflow.utils import validate
def import_module(module_path: str) -> Any:
@ -104,10 +104,7 @@ def import_prompt(prompt: str) -> Type[PromptTemplate]:
def import_wrapper(wrapper: str) -> Any:
"""Import wrapper from wrapper name"""
if (
isinstance(wrapper_creator.type_dict, dict)
and wrapper in wrapper_creator.type_dict
):
if isinstance(wrapper_creator.type_dict, dict) and wrapper in wrapper_creator.type_dict:
return wrapper_creator.type_dict.get(wrapper)
@ -183,6 +180,7 @@ def get_function(code):
return validate.create_function(code, function_name)
def get_function_custom(code):
def eval_custom_component_code(code: str) -> Type[CustomComponent]:
"""Evaluate custom component code"""
class_name = validate.extract_class_name(code)
return validate.create_class(code, class_name)

4
src/backend/langflow/interface/initialize/llm.py
View file

@ -2,8 +2,6 @@ def initialize_vertexai(class_object, params):
if credentials_path := params.get("credentials"):
from google.oauth2 import service_account # type: ignore
credentials_object = service_account.Credentials.from_service_account_file(
filename=credentials_path
)
credentials_object = service_account.Credentials.from_service_account_file(filename=credentials_path)
params["credentials"] = credentials_object
return class_object(**params)

133
src/backend/langflow/interface/initialize/loading.py
View file

@ -1,40 +1,29 @@
import inspect
import json
from typing import TYPE_CHECKING, Any, Callable, Dict, Sequence, Type
import orjson
from typing import Any, Callable, Dict, Sequence, Type, TYPE_CHECKING
from langchain.schema import Document
from langchain.agents import agent as agent_module
from langchain.agents.agent import AgentExecutor
from langchain.agents.agent_toolkits.base import BaseToolkit
from langchain.agents.tools import BaseTool
from langflow.interface.initialize.llm import initialize_vertexai
from langflow.interface.initialize.utils import (
handle_format_kwargs,
handle_node_type,
handle_partial_variables,
)
from langflow.interface.initialize.vector_store import vecstore_initializer
from pydantic import ValidationError
from langflow.interface.importing.utils import (
get_function,
get_function_custom,
import_by_type,
)
from langchain.chains.base import Chain
from langchain.document_loaders.base import BaseLoader
from langchain.schema import Document
from langchain.vectorstores.base import VectorStore
from langflow.interface.custom_lists import CUSTOM_NODES
from langflow.interface.agents.base import agent_creator
from langflow.interface.toolkits.base import toolkits_creator
from langflow.interface.chains.base import chain_creator
from langflow.interface.importing.utils import eval_custom_component_code, get_function, import_by_type
from langflow.interface.initialize.llm import initialize_vertexai
from langflow.interface.initialize.utils import handle_format_kwargs, handle_node_type, handle_partial_variables
from langflow.interface.initialize.vector_store import vecstore_initializer
from langflow.interface.output_parsers.base import output_parser_creator
from langflow.interface.retrievers.base import retriever_creator
from langflow.interface.wrappers.base import wrapper_creator
from langflow.interface.toolkits.base import toolkits_creator
from langflow.interface.utils import load_file_into_dict
from langflow.interface.wrappers.base import wrapper_creator
from langflow.utils import validate
from langchain.chains.base import Chain
from langchain.vectorstores.base import VectorStore
from langchain.document_loaders.base import BaseLoader
from loguru import logger
from pydantic import ValidationError
if TYPE_CHECKING:
from langflow import CustomComponent
@ -44,15 +33,10 @@ def build_vertex_in_params(params: Dict) -> Dict:
from langflow.graph.vertex.base import Vertex
# If any of the values in params is a Vertex, we will build it
return {
key: value.build() if isinstance(value, Vertex) else value
for key, value in params.items()
}
return {key: value.build() if isinstance(value, Vertex) else value for key, value in params.items()}
def instantiate_class(
node_type: str, base_type: str, params: Dict, user_id=None
) -> Any:
async def instantiate_class(node_type: str, base_type: str, params: Dict, user_id=None) -> Any:
"""Instantiate class from module type and key, and params"""
params = convert_params_to_sets(params)
params = convert_kwargs(params)
@ -64,9 +48,7 @@ def instantiate_class(
return custom_node(**params)
logger.debug(f"Instantiating {node_type} of type {base_type}")
class_object = import_by_type(_type=base_type, name=node_type)
return instantiate_based_on_type(
class_object, base_type, node_type, params, user_id=user_id
)
return await instantiate_based_on_type(class_object, base_type, node_type, params, user_id=user_id)
def convert_params_to_sets(params):
@ -93,7 +75,7 @@ def convert_kwargs(params):
return params
def instantiate_based_on_type(class_object, base_type, node_type, params, user_id):
async def instantiate_based_on_type(class_object, base_type, node_type, params, user_id):
if base_type == "agents":
return instantiate_agent(node_type, class_object, params)
elif base_type == "prompts":
@ -127,20 +109,28 @@ def instantiate_based_on_type(class_object, base_type, node_type, params, user_i
elif base_type == "memory":
return instantiate_memory(node_type, class_object, params)
elif base_type == "custom_components":
return instantiate_custom_component(node_type, class_object, params, user_id)
return await instantiate_custom_component(node_type, class_object, params, user_id)
elif base_type == "wrappers":
return instantiate_wrapper(node_type, class_object, params)
else:
return class_object(**params)
def instantiate_custom_component(node_type, class_object, params, user_id):
# we need to make a copy of the params because we will be
# modifying it
async def instantiate_custom_component(node_type, class_object, params, user_id):
params_copy = params.copy()
class_object: "CustomComponent" = get_function_custom(params_copy.pop("code"))
class_object: "CustomComponent" = eval_custom_component_code(params_copy.pop("code"))
custom_component = class_object(user_id=user_id)
built_object = custom_component.build(**params_copy)
# Determine if the build method is asynchronous
is_async = inspect.iscoroutinefunction(custom_component.build)
if is_async:
# Await the build method directly if it's async
built_object = await custom_component.build(**params_copy)
else:
# Call the build method directly if it's sync
built_object = custom_component.build(**params_copy)
return built_object, {"repr": custom_component.custom_repr()}
@ -194,9 +184,7 @@ def instantiate_memory(node_type, class_object, params):
# I want to catch a specific attribute error that happens
# when the object does not have a cursor attribute
except Exception as exc:
if "object has no attribute 'cursor'" in str(
exc
) or 'object has no field "conn"' in str(exc):
if "object has no attribute 'cursor'" in str(exc) or 'object has no field "conn"' in str(exc):
raise AttributeError(
(
"Failed to build connection to database."
@ -218,6 +206,8 @@ def instantiate_retriever(node_type, class_object, params):
def instantiate_chains(node_type, class_object: Type[Chain], params: Dict):
from langflow.interface.chains.base import chain_creator
if "retriever" in params and hasattr(params["retriever"], "as_retriever"):
params["retriever"] = params["retriever"].as_retriever()
if node_type in chain_creator.from_method_nodes:
@ -230,14 +220,14 @@ def instantiate_chains(node_type, class_object: Type[Chain], params: Dict):
def instantiate_agent(node_type, class_object: Type[agent_module.Agent], params: Dict):
from langflow.interface.agents.base import agent_creator
if node_type in agent_creator.from_method_nodes:
method = agent_creator.from_method_nodes[node_type]
if class_method := getattr(class_object, method, None):
agent = class_method(**params)
tools = params.get("tools", [])
return AgentExecutor.from_agent_and_tools(
agent=agent, tools=tools, handle_parsing_errors=True
)
return AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, handle_parsing_errors=True)
return load_agent_executor(class_object, params)
@ -287,26 +277,25 @@ def instantiate_embedding(node_type, class_object, params: Dict):
if "VertexAI" in node_type:
return initialize_vertexai(class_object=class_object, params=params)
if "OpenAIEmbedding" in node_type:
params["disallowed_special"] = ()
try:
return class_object(**params)
except ValidationError:
params = {
key: value
for key, value in params.items()
if key in class_object.__fields__
}
params = {key: value for key, value in params.items() if key in class_object.model_fields}
return class_object(**params)
def instantiate_vectorstore(class_object: Type[VectorStore], params: Dict):
search_kwargs = params.pop("search_kwargs", {})
if search_kwargs == {"yourkey": "value"}:
search_kwargs = {}
# clean up docs or texts to have only documents
if "texts" in params:
params["documents"] = params.pop("texts")
if "documents" in params:
params["documents"] = [
doc for doc in params["documents"] if isinstance(doc, Document)
]
params["documents"] = [doc for doc in params["documents"] if isinstance(doc, Document)]
if initializer := vecstore_initializer.get(class_object.__name__):
vecstore = initializer(class_object, params)
else:
@ -321,9 +310,7 @@ def instantiate_vectorstore(class_object: Type[VectorStore], params: Dict):
return vecstore
def instantiate_documentloader(
node_type: str, class_object: Type[BaseLoader], params: Dict
):
def instantiate_documentloader(node_type: str, class_object: Type[BaseLoader], params: Dict):
if "file_filter" in params:
# file_filter will be a string but we need a function
# that will be used to filter the files using file_filter
@ -332,17 +319,13 @@ def instantiate_documentloader(
# in x and if it is, we will return True
file_filter = params.pop("file_filter")
extensions = file_filter.split(",")
params["file_filter"] = lambda x: any(
extension.strip() in x for extension in extensions
)
params["file_filter"] = lambda x: any(extension.strip() in x for extension in extensions)
metadata = params.pop("metadata", None)
if metadata and isinstance(metadata, str):
try:
metadata = orjson.loads(metadata)
except json.JSONDecodeError as exc:
raise ValueError(
"The metadata you provided is not a valid JSON string."
) from exc
raise ValueError("The metadata you provided is not a valid JSON string.") from exc
if node_type == "WebBaseLoader":
if web_path := params.pop("web_path", None):
@ -375,16 +358,12 @@ def instantiate_textsplitter(
"Try changing the chunk_size of the Text Splitter."
) from exc
if (
"separator_type" in params and params["separator_type"] == "Text"
) or "separator_type" not in params:
if ("separator_type" in params and params["separator_type"] == "Text") or "separator_type" not in params:
params.pop("separator_type", None)
# separators might come in as an escaped string like \\n
# so we need to convert it to a string
if "separators" in params:
params["separators"] = (
params["separators"].encode().decode("unicode-escape")
)
params["separators"] = params["separators"].encode().decode("unicode-escape")
text_splitter = class_object(**params)
else:
from langchain.text_splitter import Language
@ -411,8 +390,7 @@ def replace_zero_shot_prompt_with_prompt_template(nodes):
tools = [
tool
for tool in nodes
if tool["type"] != "chatOutputNode"
and "Tool" in tool["data"]["node"]["base_classes"]
if tool["type"] != "chatOutputNode" and "Tool" in tool["data"]["node"]["base_classes"]
]
node["data"] = build_prompt_template(prompt=node["data"], tools=tools)
break
@ -426,9 +404,7 @@ def load_agent_executor(agent_class: type[agent_module.Agent], params, **kwargs)
# agent has hidden args for memory. might need to be support
# memory = params["memory"]
# if allowed_tools is not a list or set, make it a list
if not isinstance(allowed_tools, (list, set)) and isinstance(
allowed_tools, BaseTool
):
if not isinstance(allowed_tools, (list, set)) and isinstance(allowed_tools, BaseTool):
allowed_tools = [allowed_tools]
tool_names = [tool.name for tool in allowed_tools]
# Agent class requires an output_parser but Agent classes
@ -456,10 +432,7 @@ def build_prompt_template(prompt, tools):
format_instructions = prompt["node"]["template"]["format_instructions"]["value"]
tool_strings = "\n".join(
[
f"{tool['data']['node']['name']}: {tool['data']['node']['description']}"
for tool in tools
]
[f"{tool['data']['node']['name']}: {tool['data']['node']['description']}" for tool in tools]
)
tool_names = ", ".join([tool["data"]["node"]["name"] for tool in tools])
format_instructions = format_instructions.format(tool_names=tool_names)

15
src/backend/langflow/interface/initialize/utils.py
View file

@ -30,9 +30,7 @@ def check_tools_in_params(params: Dict):
def instantiate_from_template(class_object, params: Dict):
from_template_params = {
"template": params.pop("prompt", params.pop("template", ""))
}
from_template_params = {"template": params.pop("prompt", params.pop("template", ""))}
if not from_template_params.get("template"):
raise ValueError("Prompt template is required")
return class_object.from_template(**from_template_params)
@ -48,9 +46,7 @@ def handle_format_kwargs(prompt, params: Dict):
def handle_partial_variables(prompt, format_kwargs: Dict):
partial_variables = format_kwargs.copy()
partial_variables = {
key: value for key, value in partial_variables.items() if value
}
partial_variables = {key: value for key, value in partial_variables.items() if value}
# Remove handle_keys otherwise LangChain raises an error
partial_variables.pop("handle_keys", None)
if partial_variables and hasattr(prompt, "partial"):
@ -62,9 +58,7 @@ def handle_variable(params: Dict, input_variable: str, format_kwargs: Dict):
variable = params[input_variable]
if isinstance(variable, str):
format_kwargs[input_variable] = variable
elif isinstance(variable, BaseOutputParser) and hasattr(
variable, "get_format_instructions"
):
elif isinstance(variable, BaseOutputParser) and hasattr(variable, "get_format_instructions"):
format_kwargs[input_variable] = variable.get_format_instructions()
elif is_instance_of_list_or_document(variable):
format_kwargs = format_document(variable, input_variable, format_kwargs)
@ -107,8 +101,7 @@ def try_to_load_json(content):
def needs_handle_keys(variable):
return is_instance_of_list_or_document(variable) or (
isinstance(variable, BaseOutputParser)
and hasattr(variable, "get_format_instructions")
isinstance(variable, BaseOutputParser) and hasattr(variable, "get_format_instructions")
)

30
src/backend/langflow/interface/initialize/vector_store.py
View file

@ -17,9 +17,7 @@ import orjson
def docs_in_params(params: dict) -> bool:
"""Check if params has documents OR texts and one of them is not an empty list,
If any of them is not an empty list, return True, else return False"""
return ("documents" in params and params["documents"]) or (
"texts" in params and params["texts"]
)
return ("documents" in params and params["documents"]) or ("texts" in params and params["texts"])
def initialize_mongodb(class_object: Type[MongoDBAtlasVectorSearch], params: dict):
@ -31,9 +29,7 @@ def initialize_mongodb(class_object: Type[MongoDBAtlasVectorSearch], params: dic
from pymongo import MongoClient
import certifi
client: MongoClient = MongoClient(
MONGODB_ATLAS_CLUSTER_URI, tlsCAFile=certifi.where()
)
client: MongoClient = MongoClient(MONGODB_ATLAS_CLUSTER_URI, tlsCAFile=certifi.where())
db_name = params.pop("db_name", None)
collection_name = params.pop("collection_name", None)
if not db_name or not collection_name:
@ -141,9 +137,7 @@ def initialize_pinecone(class_object: Type[Pinecone], params: dict):
pinecone_env = os.getenv("PINECONE_ENV")
if pinecone_api_key is None or pinecone_env is None:
raise ValueError(
"Pinecone API key and environment must be provided in the params"
)
raise ValueError("Pinecone API key and environment must be provided in the params")
# initialize pinecone
pinecone.init(
@ -177,26 +171,20 @@ def initialize_chroma(class_object: Type[Chroma], params: dict):
import chromadb # type: ignore
settings_params = {
key: params[key]
for key, value_ in params.items()
if key.startswith("chroma_server_") and value_
key: params[key] for key, value_ in params.items() if key.startswith("chroma_server_") and value_
}
chroma_settings = chromadb.config.Settings(**settings_params)
params["client_settings"] = chroma_settings
else:
# remove all chroma_server_ keys from params
params = {
key: value
for key, value in params.items()
if not key.startswith("chroma_server_")
}
params = {key: value for key, value in params.items() if not key.startswith("chroma_server_")}
persist = params.pop("persist", False)
if not docs_in_params(params):
params.pop("documents", None)
params.pop("texts", None)
params["embedding_function"] = params.pop("embedding")
chromadb = class_object(**params)
chromadb_instance = class_object(**params)
else:
if "texts" in params:
params["documents"] = params.pop("texts")
@ -211,10 +199,10 @@ def initialize_chroma(class_object: Type[Chroma], params: dict):
if value is None:
doc.metadata[key] = ""
chromadb = class_object.from_documents(**params)
chromadb_instance = class_object.from_documents(**params)
if persist:
chromadb.persist()
return chromadb
chromadb_instance.persist()
return chromadb_instance
def initialize_qdrant(class_object: Type[Qdrant], params: dict):

2
src/backend/langflow/interface/listing.py
View file

@ -1,4 +1,4 @@
from langflow.services.getters import get_settings_service
from langflow.services.deps import get_settings_service
from langflow.utils.lazy_load import LazyLoadDictBase

5
src/backend/langflow/interface/llms/base.py
View file

@ -2,7 +2,7 @@ from typing import Dict, List, Optional, Type
from langflow.interface.base import LangChainTypeCreator
from langflow.interface.custom_lists import llm_type_to_cls_dict
from langflow.services.getters import get_settings_service
from langflow.services.deps import get_settings_service
from langflow.template.frontend_node.llms import LLMFrontendNode
from loguru import logger
@ -38,8 +38,7 @@ class LLMCreator(LangChainTypeCreator):
return [
llm.__name__
for llm in self.type_to_loader_dict.values()
if llm.__name__ in settings_service.settings.LLMS
or settings_service.settings.DEV
if llm.__name__ in settings_service.settings.LLMS or settings_service.settings.DEV
]

9
src/backend/langflow/interface/memories/base.py
View file

@ -1,8 +1,8 @@
from typing import Dict, List, Optional, Type
from typing import ClassVar, Dict, List, Optional, Type
from langflow.interface.base import LangChainTypeCreator
from langflow.interface.custom_lists import memory_type_to_cls_dict
from langflow.services.getters import get_settings_service
from langflow.services.deps import get_settings_service
from langflow.template.frontend_node.base import FrontendNode
from langflow.template.frontend_node.memories import MemoryFrontendNode
@ -14,7 +14,7 @@ from langflow.custom.customs import get_custom_nodes
class MemoryCreator(LangChainTypeCreator):
type_name: str = "memories"
from_method_nodes = {
from_method_nodes: ClassVar[Dict] = {
"ZepChatMessageHistory": "__init__",
"SQLiteEntityStore": "__init__",
}
@ -53,8 +53,7 @@ class MemoryCreator(LangChainTypeCreator):
return [
memory.__name__
for memory in self.type_to_loader_dict.values()
if memory.__name__ in settings_service.settings.MEMORIES
or settings_service.settings.DEV
if memory.__name__ in settings_service.settings.MEMORIES or settings_service.settings.DEV
]

13
src/backend/langflow/interface/output_parsers/base.py
View file

@ -1,10 +1,10 @@
from typing import Dict, List, Optional, Type
from typing import ClassVar, Dict, List, Optional, Type
from langchain import output_parsers
from langflow.interface.base import LangChainTypeCreator
from langflow.interface.importing.utils import import_class
from langflow.services.getters import get_settings_service
from langflow.services.deps import get_settings_service
from langflow.template.frontend_node.output_parsers import OutputParserFrontendNode
from loguru import logger
@ -13,7 +13,7 @@ from langflow.utils.util import build_template_from_class, build_template_from_m
class OutputParserCreator(LangChainTypeCreator):
type_name: str = "output_parsers"
from_method_nodes = {
from_method_nodes: ClassVar[Dict] = {
"StructuredOutputParser": "from_response_schemas",
}
@ -26,17 +26,14 @@ class OutputParserCreator(LangChainTypeCreator):
if self.type_dict is None:
settings_service = get_settings_service()
self.type_dict = {
output_parser_name: import_class(
f"langchain.output_parsers.{output_parser_name}"
)
output_parser_name: import_class(f"langchain.output_parsers.{output_parser_name}")
# if output_parser_name is not lower case it is a class
for output_parser_name in output_parsers.__all__
}
self.type_dict = {
name: output_parser
for name, output_parser in self.type_dict.items()
if name in settings_service.settings.OUTPUT_PARSERS
or settings_service.settings.DEV
if name in settings_service.settings.OUTPUT_PARSERS or settings_service.settings.DEV
}
return self.type_dict

5
src/backend/langflow/interface/prompts/base.py
View file

@ -5,7 +5,7 @@ from langchain import prompts
from langflow.custom.customs import get_custom_nodes
from langflow.interface.base import LangChainTypeCreator
from langflow.interface.importing.utils import import_class
from langflow.services.getters import get_settings_service
from langflow.services.deps import get_settings_service
from langflow.template.frontend_node.prompts import PromptFrontendNode
from loguru import logger
@ -36,8 +36,7 @@ class PromptCreator(LangChainTypeCreator):
self.type_dict = {
name: prompt
for name, prompt in self.type_dict.items()
if name in settings_service.settings.PROMPTS
or settings_service.settings.DEV
if name in settings_service.settings.PROMPTS or settings_service.settings.DEV
}
return self.type_dict

14
src/backend/langflow/interface/prompts/custom.py
View file

@ -1,7 +1,7 @@
from typing import Dict, List, Optional, Type
from langchain.prompts import PromptTemplate
from pydantic import root_validator
from pydantic.v1 import root_validator
from langflow.interface.utils import extract_input_variables_from_prompt
@ -42,17 +42,13 @@ class BaseCustomPrompt(PromptTemplate):
values["template"] = values["template"].format(**format_dict)
values["template"] = values["template"]
values["input_variables"] = extract_input_variables_from_prompt(
values["template"]
)
values["input_variables"] = extract_input_variables_from_prompt(values["template"])
return values
class SeriesCharacterPrompt(BaseCustomPrompt):
# Add a very descriptive description for the prompt generator
description: Optional[
str
] = "A prompt that asks the AI to act like a character from a series."
description: Optional[str] = "A prompt that asks the AI to act like a character from a series."
character: str
series: str
template: str = """I want you to act like {character} from {series}.
@ -68,6 +64,4 @@ Human: {input}
input_variables: List[str] = ["character", "series"]
CUSTOM_PROMPTS: Dict[str, Type[BaseCustomPrompt]] = {
"SeriesCharacterPrompt": SeriesCharacterPrompt
}
CUSTOM_PROMPTS: Dict[str, Type[BaseCustomPrompt]] = {"SeriesCharacterPrompt": SeriesCharacterPrompt}

16
src/backend/langflow/interface/retrievers/base.py
View file

@ -1,10 +1,10 @@
from typing import Any, Dict, List, Optional, Type
from typing import Any, ClassVar, Dict, List, Optional, Type
from langchain import retrievers
from langflow.interface.base import LangChainTypeCreator
from langflow.interface.importing.utils import import_class
from langflow.services.getters import get_settings_service
from langflow.services.deps import get_settings_service
from langflow.template.frontend_node.retrievers import RetrieverFrontendNode
from loguru import logger
@ -14,7 +14,10 @@ from langflow.utils.util import build_template_from_method, build_template_from_
class RetrieverCreator(LangChainTypeCreator):
type_name: str = "retrievers"
from_method_nodes = {"MultiQueryRetriever": "from_llm", "ZepRetriever": "__init__"}
from_method_nodes: ClassVar[Dict] = {
"MultiQueryRetriever": "from_llm",
"ZepRetriever": "__init__",
}
@property
def frontend_node_class(self) -> Type[RetrieverFrontendNode]:
@ -39,9 +42,7 @@ class RetrieverCreator(LangChainTypeCreator):
method_name=self.from_method_nodes[name],
)
else:
return build_template_from_class(
name, type_to_cls_dict=self.type_to_loader_dict
)
return build_template_from_class(name, type_to_cls_dict=self.type_to_loader_dict)
except ValueError as exc:
raise ValueError(f"Retriever {name} not found") from exc
except AttributeError as exc:
@ -53,8 +54,7 @@ class RetrieverCreator(LangChainTypeCreator):
return [
retriever
for retriever in self.type_to_loader_dict.keys()
if retriever in settings_service.settings.RETRIEVERS
or settings_service.settings.DEV
if retriever in settings_service.settings.RETRIEVERS or settings_service.settings.DEV
]

27
src/backend/langflow/interface/run.py
View file

@ -1,9 +1,12 @@
from typing import Dict, Tuple
from langflow.graph import Graph
from typing import Dict, Optional, Tuple, Union
from uuid import UUID
from loguru import logger
from langflow.graph import Graph
def build_sorted_vertices(data_graph) -> Tuple[Graph, Dict]:
async def build_sorted_vertices(data_graph, user_id: Optional[Union[str, UUID]] = None) -> Tuple[Graph, Dict]:
"""
Build langchain object from data_graph.
"""
@ -13,28 +16,12 @@ def build_sorted_vertices(data_graph) -> Tuple[Graph, Dict]:
sorted_vertices = graph.topological_sort()
artifacts = {}
for vertex in sorted_vertices:
vertex.build()
await vertex.build(user_id=user_id)
if vertex.artifacts:
artifacts.update(vertex.artifacts)
return graph, artifacts
def build_langchain_object(data_graph):
"""
Build langchain object from data_graph.
"""
logger.debug("Building langchain object")
nodes = data_graph["nodes"]
# Add input variables
# nodes = payload.extract_input_variables(nodes)
# Nodes, edges and root node
edges = data_graph["edges"]
graph = Graph(nodes, edges)
return graph.build()
def get_memory_key(langchain_object):
"""
Given a LangChain object, this function retrieves the current memory key from the object's memory attribute.

5
src/backend/langflow/interface/text_splitters/base.py
View file

@ -1,7 +1,7 @@
from typing import Dict, List, Optional, Type
from langflow.interface.base import LangChainTypeCreator
from langflow.services.getters import get_settings_service
from langflow.services.deps import get_settings_service
from langflow.template.frontend_node.textsplitters import TextSplittersFrontendNode
from langflow.interface.custom_lists import textsplitter_type_to_cls_dict
@ -35,8 +35,7 @@ class TextSplitterCreator(LangChainTypeCreator):
return [
textsplitter.__name__
for textsplitter in self.type_to_loader_dict.values()
if textsplitter.__name__ in settings_service.settings.TEXTSPLITTERS
or settings_service.settings.DEV
if textsplitter.__name__ in settings_service.settings.TEXTSPLITTERS or settings_service.settings.DEV
]

Some files were not shown because too many files have changed in this diff Show more