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

Merge branch 'python_custom_node_component' into ChatWidgetAPI

Browse source
This commit is contained in:
Gabriel Luiz Freitas Almeida 2023-07-27 17:38:35 -03:00
commit 397c665536
102 changed files with 6034 additions and 671 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.gitignore vendored
View file

@ -251,3 +251,5 @@ langflow.db
# docusaurus
.docusaurus/
/tmp/*

3
.vscode/launch.json vendored
View file

@ -6,7 +6,8 @@
"request": "launch",
"module": "uvicorn",
"args": [
"langflow.main:app",
"--factory",
"langflow.main:create_app",
"--port",
"7860",
"--reload",

2
Makefile
View file

@ -46,7 +46,7 @@ install_backend:
backend:
make install_backend
poetry run uvicorn src.backend.langflow.main:app --port 7860 --reload --log-level debug
poetry run uvicorn --factory src.backend.langflow.main:create_app --port 7860 --reload --log-level debug
build_and_run:
echo 'Removing dist folder'

3
README.md
View file

@ -39,6 +39,8 @@
- [Deploy Langflow on Google Cloud Platform](#deploy-langflow-on-google-cloud-platform)
- [Deploy Langflow on Jina AI Cloud](#deploy-langflow-on-jina-ai-cloud)
- [API Usage](#api-usage)
- [Deploy on Railway](#deploy-on-railway)
- [Deploy on Render](#deploy-on-render)
- [🎨 Creating Flows](#-creating-flows)
- [👋 Contributing](#-contributing)
- [📄 License](#-license)
@ -87,6 +89,7 @@ Each option is detailed below:
- `--config`: Defines the path to the configuration file. The default is `config.yaml`.
- `--env-file`: Specifies the path to the .env file containing environment variables. The default is `.env`.
- `--log-level`: Defines the logging level. Can be set using the `LANGFLOW_LOG_LEVEL` environment variable. The default is `critical`.
- `component-path`: Specifies the path to the directory containing custom components. Can be set using the `LANGFLOW_COMPONENT_PATH` environment variable. The default is `langflow/components`.
- `--log-file`: Specifies the path to the log file. Can be set using the `LANGFLOW_LOG_FILE` environment variable. The default is `logs/langflow.log`.
- `--cache`: Selects the type of cache to use. Options are `InMemoryCache` and `SQLiteCache`. Can be set using the `LANGFLOW_LANGCHAIN_CACHE` environment variable. The default is `SQLiteCache`.
- `--jcloud/--no-jcloud`: Toggles the option to deploy on Jina AI Cloud. The default is `no-jcloud`.

41
docs/docs/components/chains.mdx
View file

@ -1,6 +1,7 @@
import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from "@docusaurus/useBaseUrl";
import ZoomableImage from "/src/theme/ZoomableImage.js";
import Admonition from "@theme/Admonition";
# Chains
@ -12,22 +13,23 @@ Chains, in the context of language models, refer to a series of calls made to a
The `CombineDocsChain` incorporates methods to combine or aggregate loaded documents for question-answering functionality.
:::info
<Admonition type="info">
Works as a proxy of LangChain’s [documents](https://python.langchain.com/docs/modules/chains/document/) chains generated by the `load_qa_chain` function.
:::
</Admonition>
**Params**
- **LLM:** Language Model to use in the chain.
- **chain_type:** The chain type to be used. Each one of them applies a different “combination strategy”.
- **stuff**: The stuff [documents](https://python.langchain.com/docs/modules/chains/document/stuff) chain (“stuff" as in "to stuff" or "to fill") is the most straightforward of *the* document chains. It takes a list of documents, inserts them all into a prompt, and passes that prompt to an LLM. This chain is well-suited for applications where documents are small and only a few are passed in for most calls.
- **map_reduce**: The map-reduce [documents](https://python.langchain.com/docs/modules/chains/document/map_reduce) chain first applies an LLM chain to each document individually (the Map step), treating the chain output as a new document. It then passes all the new documents to a separate combined documents chain to get a single output (the Reduce step). It can optionally first compress or collapse the mapped documents to make sure that they fit in the combined documents chain (which will often pass them to an LLM). This compression step is performed recursively if necessary.
- **map_rerank**: The map re-rank [documents](https://python.langchain.com/docs/modules/chains/document/map_rerank) chain runs an initial prompt on each document that not only tries to complete a task but also gives a score for how certain it is in its answer. The highest-scoring response is returned.
- **refine**: The refine [documents](https://python.langchain.com/docs/modules/chains/document/refine) chain constructs a response by looping over the input documents and iteratively updating its answer. For each document, it passes all non-document inputs, the current document, and the latest intermediate answer to an LLM chain to get a new answer.
Since the Refine chain only passes a single document to the LLM at a time, it is well-suited for tasks that require analyzing more documents than can fit in the model's context. The obvious tradeoff is that this chain will make far more LLM calls than, for example, the Stuff documents chain. There are also certain tasks that are difficult to accomplish iteratively. For example, the Refine chain can perform poorly when documents frequently cross-reference one another or when a task requires detailed information from many documents.
- **stuff**: The stuff [documents](https://python.langchain.com/docs/modules/chains/document/stuff) chain (“stuff" as in "to stuff" or "to fill") is the most straightforward of _the_ document chains. It takes a list of documents, inserts them all into a prompt, and passes that prompt to an LLM. This chain is well-suited for applications where documents are small and only a few are passed in for most calls.
- **map_reduce**: The map-reduce [documents](https://python.langchain.com/docs/modules/chains/document/map_reduce) chain first applies an LLM chain to each document individually (the Map step), treating the chain output as a new document. It then passes all the new documents to a separate combined documents chain to get a single output (the Reduce step). It can optionally first compress or collapse the mapped documents to make sure that they fit in the combined documents chain (which will often pass them to an LLM). This compression step is performed recursively if necessary.
- **map_rerank**: The map re-rank [documents](https://python.langchain.com/docs/modules/chains/document/map_rerank) chain runs an initial prompt on each document that not only tries to complete a task but also gives a score for how certain it is in its answer. The highest-scoring response is returned.
- **refine**: The refine [documents](https://python.langchain.com/docs/modules/chains/document/refine) chain constructs a response by looping over the input documents and iteratively updating its answer. For each document, it passes all non-document inputs, the current document, and the latest intermediate answer to an LLM chain to get a new answer.
Since the Refine chain only passes a single document to the LLM at a time, it is well-suited for tasks that require analyzing more documents than can fit in the model's context. The obvious tradeoff is that this chain will make far more LLM calls than, for example, the Stuff documents chain. There are also certain tasks that are difficult to accomplish iteratively. For example, the Refine chain can perform poorly when documents frequently cross-reference one another or when a task requires detailed information from many documents.
---
@ -41,7 +43,7 @@ The `ConversationChain` is a straightforward chain for interactive conversations
- **Memory:** Default memory store.
- **input_key:** Used to specify the key under which the user input will be stored in the conversation memory. It allows you to provide the user's input to the chain for processing and generating a response.
- **output_key:** Used to specify the key under which the generated response will be stored in the conversation memory. It allows you to retrieve the response using the specified key.
- **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 be helpful for debugging and understanding 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 be helpful for debugging and understanding the chain's behavior. If set to False, it will suppress the verbose output — defaults to `False`.
---
@ -49,11 +51,11 @@ The `ConversationChain` is a straightforward chain for interactive conversations
The `ConversationalRetrievalChain` extracts information and provides answers by combining document search and question-answering abilities.
:::info
<Admonition type="info">
A retriever is a component that finds documents based on a query. It doesn't store the documents themselves, but it returns the ones that match the query.
:::
</Admonition >
**Params**
@ -61,12 +63,13 @@ A retriever is a component that finds documents based on a query. It doesn't sto
- **Memory:** Default memory store.
- **Retriever:** The retriever used to fetch relevant documents.
- **chain_type:** The chain type to be used. Each one of them applies a different “combination strategy”.
- **stuff**: The stuff [documents](https://python.langchain.com/docs/modules/chains/document/stuff) chain (“stuff" as in "to stuff" or "to fill") is the most straightforward of *the* document chains. It takes a list of documents, inserts them all into a prompt, and passes that prompt to an LLM. This chain is well-suited for applications where documents are small and only a few are passed in for most calls.
- **map_reduce**: The map-reduce [documents](https://python.langchain.com/docs/modules/chains/document/map_reduce) chain first applies an LLM chain to each document individually (the Map step), treating the chain output as a new document. It then passes all the new documents to a separate combined documents chain to get a single output (the Reduce step). It can optionally first compress or collapse the mapped documents to make sure that they fit in the combined documents chain (which will often pass them to an LLM). This compression step is performed recursively if necessary.
- **map_rerank**: The map re-rank [documents](https://python.langchain.com/docs/modules/chains/document/map_rerank) chain runs an initial prompt on each document that not only tries to complete a task but also gives a score for how certain it is in its answer. The highest-scoring response is returned.
- **refine**: The refine [documents](https://python.langchain.com/docs/modules/chains/document/refine) chain constructs a response by looping over the input documents and iteratively updating its answer. For each document, it passes all non-document inputs, the current document, and the latest intermediate answer to an LLM chain to get a new answer.
Since the Refine chain only passes a single document to the LLM at a time, it is well-suited for tasks that require analyzing more documents than can fit in the model's context. The obvious tradeoff is that this chain will make far more LLM calls than, for example, the Stuff documents chain. There are also certain tasks that are difficult to accomplish iteratively. For example, the Refine chain can perform poorly when documents frequently cross-reference one another or when a task requires detailed information from many documents.
- **stuff**: The stuff [documents](https://python.langchain.com/docs/modules/chains/document/stuff) chain (“stuff" as in "to stuff" or "to fill") is the most straightforward of _the_ document chains. It takes a list of documents, inserts them all into a prompt, and passes that prompt to an LLM. This chain is well-suited for applications where documents are small and only a few are passed in for most calls.
- **map_reduce**: The map-reduce [documents](https://python.langchain.com/docs/modules/chains/document/map_reduce) chain first applies an LLM chain to each document individually (the Map step), treating the chain output as a new document. It then passes all the new documents to a separate combined documents chain to get a single output (the Reduce step). It can optionally first compress or collapse the mapped documents to make sure that they fit in the combined documents chain (which will often pass them to an LLM). This compression step is performed recursively if necessary.
- **map_rerank**: The map re-rank [documents](https://python.langchain.com/docs/modules/chains/document/map_rerank) chain runs an initial prompt on each document that not only tries to complete a task but also gives a score for how certain it is in its answer. The highest-scoring response is returned.
- **refine**: The refine [documents](https://python.langchain.com/docs/modules/chains/document/refine) chain constructs a response by looping over the input documents and iteratively updating its answer. For each document, it passes all non-document inputs, the current document, and the latest intermediate answer to an LLM chain to get a new answer.
Since the Refine chain only passes a single document to the LLM at a time, it is well-suited for tasks that require analyzing more documents than can fit in the model's context. The obvious tradeoff is that this chain will make far more LLM calls than, for example, the Stuff documents chain. There are also certain tasks that are difficult to accomplish iteratively. For example, the Refine chain can perform poorly when documents frequently cross-reference one another or when a task requires detailed information from many documents.
- **return_source_documents:** Used to specify whether or not to include the source documents that were used to answer the question in the output. When set to `True`, source documents will be included in the output along with the generated answer. This can be useful for providing additional context or references to the user — defaults to `True`.
- **verbose:** Whether or not to run in verbose mode. In verbose mode, intermediate logs will be printed to the console — defaults to `False`.
@ -108,17 +111,17 @@ The `LLMMathChain` works by using the language model with an `LLMChain` to under
`RetrievalQA` is a chain used to find relevant documents or information to answer a given query. The retriever is responsible for returning the relevant documents based on the query, and the QA component then extracts the answer from those documents. The retrieval QA system combines the capabilities of both the retriever and the QA component to provide accurate and relevant answers to user queries.
:::info
<Admonition type="info">
A retriever is a component that finds documents based on a query. It doesn't store the documents themselves, but it returns the ones that match the query.
:::
</Admonition >
**Params**
- **Combine Documents Chain:** Chain to use to combine the documents.
- **Memory:** Default memory store.
- **Retriever:** The retriever used to fetch relevant documents.
- **Retriever:** The retriever used to fetch relevant documents.
- **input_key:** This parameter is used to specify the key in the input data that contains the question. It is used to retrieve the question from the input data and pass it to the question-answering model for generating the answer — defaults to `query`.
- **output_key:** This parameter is used to specify the key in the output data where the generated answer will be stored. It is used to retrieve the answer from the output data after the question-answering model has generated it — defaults to `result`.
- **return_source_documents:** Used to specify whether or not to include the source documents that were used to answer the question in the output. When set to `True`, source documents will be included in the output along with the generated answer. This can be useful for providing additional context or references to the user — defaults to `True`.
@ -134,4 +137,4 @@ The `SQLDatabaseChain` finds answers to questions using a SQL database. It works
- **Db:** SQL Database to connect to.
- **LLM:** Language Model to use in the chain.
- **Prompt:** Prompt template to translate natural language to SQL.
- **Prompt:** Prompt template to translate natural language to SQL.

17
docs/docs/components/custom.mdx Normal file
View file

@ -0,0 +1,17 @@
import Admonition from "@theme/Admonition";
# Custom Component
---
Used to create a custom component. The code is the class that will be converted to a Custom Component with the fields and formatting you define.
**Params**
- **Code:** The code of the component.
<Admonition type="info" label="Tip">
[Learn more about Custom Components](../guidelines/custom-component)
</Admonition>

12
docs/docs/components/prompts.mdx
View file

@ -1,3 +1,5 @@
import Admonition from "@theme/Admonition";
# Prompts
A prompt refers to the input given to a language model. It is constructed from multiple components and can be parametrized using prompt templates. A prompt template is a reproducible way to generate prompts and allow for easy customization through input variables.
@ -8,8 +10,10 @@ A prompt refers to the input given to a language model. It is constructed from m
The `PromptTemplate` component allows users to create prompts and define variables that provide control over instructing the model. The template can take in a set of variables from the end user and generates the prompt once the conversation is initiated.
:::info
Once a variable is defined in the prompt template, it becomes a component input of its own. Check out [Prompt Customization](../guidelines/prompt-customization.mdx) to learn more.
:::
<Admonition type="info">
Once a variable is defined in the prompt template, it becomes a component
input of its own. Check out [Prompt
Customization](../guidelines/prompt-customization.mdx) to learn more.
</Admonition>
- **template:** Template used to format an individual request.
- **template:** Template used to format an individual request.

7
docs/docs/examples/buffer-memory.mdx
View file

@ -1,3 +1,5 @@
import Admonition from "@theme/Admonition";
# Buffer Memory
For certain applications, retaining past interactions is crucial. For that, chains and agents may accept a memory component as one of their input parameters. The `ConversationBufferMemory` component is one of them. It stores messages and extracts them into variables.
@ -17,9 +19,10 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
#### <a target="\_blank" href="json_files/Buffer_Memory.json" download>Download Flow</a>
:::note LangChain Components 🦜🔗
<Admonition type="note" title="LangChain Components 🦜🔗">
- [`ConversationBufferMemory`](https://python.langchain.com/docs/modules/memory/how_to/buffer)
- [`ConversationChain`](https://python.langchain.com/docs/modules/chains/)
- [`ChatOpenAI`](https://python.langchain.com/docs/modules/model_io/models/chat/integrations/openai)
:::
</Admonition>

13
docs/docs/examples/conversation-chain.mdx
View file

@ -1,10 +1,14 @@
import Admonition from "@theme/Admonition";
# Conversation Chain
This example shows how to instantiate a simple `ConversationChain` component using a Language Model (LLM). Once the Node Status turns green 🟢, the chat will be ready to take in user messages. Here, we used `ChatOpenAI` to act as the required LLM input, but you can use any LLM for this purpose.
:::info
<Admonition type="info">
Make sure to always get the API key from the provider.
:::
</Admonition>
## ⛓️ Langflow Example
@ -21,8 +25,9 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
#### <a target="\_blank" href="json_files/Basic_Chat.json" download>Download Flow</a>
:::note LangChain Components 🦜🔗
<Admonition type="note" title="LangChain Components 🦜🔗">
- [`ConversationChain`](https://python.langchain.com/docs/modules/chains/)
- [`ChatOpenAI`](https://python.langchain.com/docs/modules/model_io/models/chat/integrations/openai)
:::
</Admonition>

24
docs/docs/examples/csv-loader.mdx
View file

@ -1,3 +1,5 @@
import Admonition from "@theme/Admonition";
# CSV Loader
The `VectoStoreAgent` component retrieves information from one or more vector stores. This example shows a `VectoStoreAgent` connected to a CSV file through the `Chroma` vector store. Process description:
@ -7,13 +9,18 @@ The `VectoStoreAgent` component retrieves information from one or more vector st
- These chunks feed the `Chroma` vector store, which converts them into vectors and stores them for fast indexing.
- Finally, the agent accesses the information of the vector store through the `VectorStoreInfo` tool.
:::info
The vector store is used for efficient semantic search, while `VectorStoreInfo` carries information about it, such as its name and description. Embeddings are a way to represent words, phrases, or any entities in a vector space. Learn more about them [here](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings).
:::
<Admonition type="info">
The vector store is used for efficient semantic search, while
`VectorStoreInfo` carries information about it, such as its name and
description. Embeddings are a way to represent words, phrases, or any entities
in a vector space. Learn more about them
[here](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings).
</Admonition>
:::tip
Once you build this flow, ask questions about the data in the chat interface (e.g., number of rows or columns).
:::
<Admonition type="tip">
Once you build this flow, ask questions about the data in the chat interface
(e.g., number of rows or columns).
</Admonition>
## ⛓️ Langflow Example
@ -30,7 +37,7 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
#### <a target="\_blank" href="json_files/CSV_Loader.json" download>Download Flow</a>
:::note LangChain Components 🦜🔗
<Admonition type="note" title="LangChain Components 🦜🔗">
- [`CSVLoader`](https://python.langchain.com/docs/modules/data_connection/document_loaders/integrations/csv)
- [`CharacterTextSplitter`](https://python.langchain.com/docs/modules/data_connection/document_transformers/text_splitters/character_text_splitter)
@ -39,4 +46,5 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
- [`VectorStoreInfo`](https://python.langchain.com/docs/modules/data_connection/vectorstores/)
- [`OpenAI`](https://python.langchain.com/docs/modules/model_io/models/llms/integrations/openai)
- [`VectorStoreAgent`](https://python.langchain.com/docs/modules/agents/toolkits/vectorstore)
:::
</Admonition>

15
docs/docs/examples/midjourney-prompt-chain.mdx
View file

@ -1,3 +1,5 @@
import Admonition from "@theme/Admonition";
# MidJourney Prompt Chain
The `MidJourneyPromptChain` can be used to generate imaginative and detailed MidJourney prompts.
@ -14,9 +16,11 @@ And get a response such as:
Imagine a mysterious forest, the trees are tall and ancient, their branches reaching up to the sky. Through the darkness, a dragon emerges from the shadows, its scales shimmering in the moonlight. Its wingspan is immense, and its eyes glow with a fierce intensity. It is a majestic and powerful creature, one that commands both respect and fear.
```
:::tip
Notice that the `ConversationSummaryMemory` stores a summary of the conversation over time. Try using it to create better prompts as the conversation goes on.
:::
<Admonition type="tip">
Notice that the `ConversationSummaryMemory` stores a summary of the
conversation over time. Try using it to create better prompts as the
conversation goes on.
</Admonition>
## ⛓️ Langflow Example
@ -33,8 +37,9 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
#### <a target="\_blank" href="json_files/MidJourney_Prompt_Chain.json" download>Download Flow</a>
:::note LangChain Components 🦜🔗
<Admonition type="note" title="LangChain Components 🦜🔗">
- [`OpenAI`](https://python.langchain.com/docs/modules/model_io/models/llms/integrations/openai)
- [`ConversationSummaryMemory`](https://python.langchain.com/docs/modules/memory/how_to/summary)
:::
</Admonition>

27
docs/docs/examples/multiple-vectorstores.mdx
View file

@ -1,12 +1,15 @@
import Admonition from "@theme/Admonition";
# Multiple Vector Stores
The example below shows an agent operating with two vector stores built upon different data sources.
The `TextLoader` loads a TXT file, while the `WebBaseLoader` pulls text from webpages into a document format to accessed downstream. The `Chroma` vector stores are created analogous to what we have demonstrated in our [CSV Loader](/examples/csv-loader.mdx) example. Finally, the `VectorStoreRouterAgent` constructs an agent that routes between the vector stores.
:::info
Get the TXT file used [here](https://github.com/hwchase17/chat-your-data/blob/master/state_of_the_union.txt).
:::
<Admonition type="info">
Get the TXT file used
[here](https://github.com/hwchase17/chat-your-data/blob/master/state_of_the_union.txt).
</Admonition>
URL used by the `WebBaseLoader`:
@ -14,13 +17,15 @@ URL used by the `WebBaseLoader`:
https://pt.wikipedia.org/wiki/Harry_Potter
```
:::tip
When you build the flow, request information about one of the sources. The agent should be able to use the correct source to generate a response.
:::
<Admonition type="tip">
When you build the flow, request information about one of the sources. The
agent should be able to use the correct source to generate a response.
</Admonition>
:::info
Learn more about Multiple Vector Stores [here](https://python.langchain.com/docs/modules/agents/toolkits/vectorstore?highlight=Multiple%20Vector%20Stores#multiple-vectorstores).
:::
<Admonition type="info">
Learn more about Multiple Vector Stores
[here](https://python.langchain.com/docs/modules/agents/toolkits/vectorstore?highlight=Multiple%20Vector%20Stores#multiple-vectorstores).
</Admonition>
## ⛓️ Langflow Example
@ -37,7 +42,7 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
#### <a target="\_blank" href="json_files/Multiple_Vector_Stores.json" download>Download Flow</a>
:::note LangChain Components 🦜🔗
<Admonition type="note" title="LangChain Components 🦜🔗">
- [`WebBaseLoader`](https://python.langchain.com/docs/modules/data_connection/document_loaders/integrations/web_base)
- [`TextLoader`](https://python.langchain.com/docs/modules/data_connection/document_loaders/integrations/unstructured_file)
@ -49,4 +54,4 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
- [`VectorStoreRouterToolkit`](https://python.langchain.com/docs/modules/agents/toolkits/vectorstore)
- [`VectorStoreRouterAgent`](https://python.langchain.com/docs/modules/agents/toolkits/vectorstore)
:::
</Admonition>

23
docs/docs/examples/python-function.mdx
View file

@ -1,3 +1,5 @@
import Admonition from "@theme/Admonition";
# Python Function
Langflow allows you to create a customized tool using the `PythonFunction` connected to a `Tool` component. In this example, Regex is used in Python to validate a pattern.
@ -15,15 +17,19 @@ def is_brazilian_zipcode(zipcode: str) -> bool:
return False
```
:::tip
When a tool is called, it is often desirable to have its output returned directly to the user. You can do this by setting the **return_direct** flag for a tool to be True.
:::
<Admonition type="tip">
When a tool is called, it is often desirable to have its output returned
directly to the user. You can do this by setting the **return_direct** flag
for a tool to be True.
</Admonition>
The `AgentInitializer` component is a quick way to construct an agent from the model and tools.
:::info
The `PythonFunction` is a custom component that uses the LangChain 🦜🔗 tool decorator. Learn more about it [here](https://python.langchain.com/docs/modules/agents/tools/how_to/custom_tools).
:::
<Admonition type="info">
The `PythonFunction` is a custom component that uses the LangChain 🦜🔗 tool
decorator. Learn more about it
[here](https://python.langchain.com/docs/modules/agents/tools/how_to/custom_tools).
</Admonition>
## ⛓️ Langflow Example
@ -40,9 +46,10 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
#### <a target="\_blank" href="json_files/Python_Function.json" download>Download Flow</a>
:::note LangChain Components 🦜🔗
<Admonition type="note" title="LangChain Components 🦜🔗">
- [`PythonFunctionTool`](https://python.langchain.com/docs/modules/agents/tools/how_to/custom_tools)
- [`ChatOpenAI`](https://python.langchain.com/docs/modules/model_io/models/chat/integrations/openai)
- [`AgentInitializer`](https://python.langchain.com/docs/modules/agents/)
:::
</Admonition>

28
docs/docs/examples/serp-api-tool.mdx
View file

@ -1,24 +1,29 @@
import Admonition from "@theme/Admonition";
# Serp API Tool
The [Serp API](https://serpapi.com/) (Search Engine Results Page) allows developers to scrape results from search engines such as Google, Bing and Yahoo, and can be used as in Langflow through the `Search` component.
:::info
To use the Serp API, you first need to sign up [Serp API](https://serpapi.com/) for an API key on the provider's website.
:::
<Admonition type="info">
To use the Serp API, you first need to sign up [Serp
API](https://serpapi.com/) for an API key on the provider's website.
</Admonition>
Here, the `ZeroShotPrompt` component specifies a prompt template for the `ZeroShotAgent`. Set a _Prefix_ and _Suffix_ with rules for the agent to obey. In the example, we used default templates.
The `LLMChain` is a simple chain that takes in a prompt template, formats it with the user input, and returns the response from an LLM.
:::tip
In this example, we used [`ChatOpenAI`](https://platform.openai.com/) as the LLM, but feel free to experiment with other Language Models!
:::
<Admonition type="tip">
In this example, we used [`ChatOpenAI`](https://platform.openai.com/) as the
LLM, but feel free to experiment with other Language Models!
</Admonition>
The `ZeroShotAgent` takes the `LLMChain` and the `Search` tool as inputs, using the tool to find information when necessary.
:::info
Learn more about the Serp API [here](https://python.langchain.com/docs/modules/agents/tools/integrations/serpapi).
:::
<Admonition type="info">
Learn more about the Serp API
[here](https://python.langchain.com/docs/modules/agents/tools/integrations/serpapi).
</Admonition>
## ⛓️ Langflow Example
@ -35,11 +40,12 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
#### <a target="\_blank" href="json_files/SerpAPI_Tool.json" download>Download Flow</a>
:::note LangChain Components 🦜🔗
<Admonition type="note" title="LangChain Components 🦜🔗">
- [`ZeroShotPrompt`](https://python.langchain.com/docs/modules/model_io/prompts/prompt_templates/)
- [`OpenAI`](https://python.langchain.com/docs/modules/model_io/models/llms/integrations/openai)
- [`LLMChain`](https://python.langchain.com/docs/modules/chains/foundational/llm_chain)
- [`Search`](https://python.langchain.com/docs/modules/agents/tools/integrations/serpapi)
- [`ZeroShotAgent`](https://python.langchain.com/docs/modules/agents/how_to/custom_mrkl_agent)
:::
</Admonition>

465
docs/docs/guidelines/custom-component.mdx Normal file
View file

@ -0,0 +1,465 @@
---
description: Custom Components
hide_table_of_contents: true
---
# Custom Components
A Custom Component has almost infinite possibilities. It can be a simple function that takes a string and returns a string,
or it can be a complex function that takes other components, calls APIs, and returns a custom object only you know how to use (which might not be ideal).
Let's take a look at the basic rules, then we'll talk about the ones that are not so basic.
## TL;DR
You need to create a class that inherits from _`CustomComponent`_ and has a _`build`_ method.
Use the type annotations of the _`build`_ method to create the fields of the component.
Use the _`build_config`_ method to create the config fields of the component (if any).
Here is an example:
<CH.Code linuNumbers={false}>
```python
from langflow import CustomComponent
from langchain.chains import LLMChain
from langchain.chains.base import Chain
from langchain import PromptTemplate
from langchain.llms.base import BaseLLM
from langchain import Tool
class BestComponent(CustomComponent):
display_name = "Best Component"
description = "This is the best component ever"
def build_config(self) -> dict:
cool_tool_names = ["Cool Tool",
"Cooler Tool",
"Coolest Tool"]
return {
"description": {"multiline": True},
"name": {"is_list": True,
"options": cool_tool_names}}
def build(self, name: str, description: str, chain: Chain) -> Tool:
return Tool(name=name,
description=description,
func=chain.run)
```
</CH.Code>
## Now, let's go over the rules one by one:
<CH.Scrollycoding rows={20} className={""}>
## Rule 1
The script must contain a **single class** that inherits from _`CustomComponent`_.
```python
# focus
from langflow import CustomComponent
from langchain.chains import LLMChain
from langchain.chains.base import Chain
from langchain import PromptTemplate
from langchain.llms.base import BaseLLM
from langchain import Tool
# focus
class BestComponent(CustomComponent):
display_name = "Custom Component"
description = "This is a custom component"
def build_config(self) -> dict:
...
def build(self):
...
```
---
## Rule 2
The class must have a _`build`_ method which defines the fields of the component and is used to run it.
```python
from langflow import CustomComponent
from langchain.chains import LLMChain
from langchain.chains.base import Chain
from langchain import PromptTemplate
from langchain.llms.base import BaseLLM
from langchain import Tool
class BestComponent(CustomComponent):
display_name = "Custom Component"
description = "This is a custom component"
def build_config(self) -> dict:
...
# focus[5:13]
def build(self):
...
```
---
## Rule 3
The type annotations of the _`build`_ method will be used to create the fields of the component.
The types supported are:
- _`str`_, _`int`_, _`float`_, _`bool`_, _`list`_, _`dict`_
- [_`langchain.chains.base.Chain`_](focus://3)
- [_`langchain.PromptTemplate`_](focus://4)
- [_`langchain.llms.base.BaseLLM`_](focus://5)
- [_`langchain.Tool`_](focus://6)
- _`langchain.document_loaders.base.BaseLoader`_
- _`langchain.schema.Document`_
- _`langchain.text_splitters.TextSplitter`_
- _`langchain.vectorstores.base.VectorStore`_
- _`langchain.embeddings.base.Embeddings`_
- _`langchain.schema.BaseRetriever`_
```python
from langflow import CustomComponent
from langchain.chains import LLMChain
from langchain.chains.base import Chain
from langchain import PromptTemplate
from langchain.llms.base import BaseLLM
from langchain import Tool
class BestComponent(CustomComponent):
display_name = "Custom Component"
description = "This is a custom component"
def build_config(self) -> dict:
...
# mark
def build(self):
...
```
---
```python
from langflow import CustomComponent
from langchain.chains import LLMChain
from langchain.chains.base import Chain
from langchain import PromptTemplate
from langchain.llms.base import BaseLLM
from langchain import Tool
class BestComponent(CustomComponent):
display_name = "Custom Component"
description = "This is a custom component"
# focus
def build_config(self) -> dict:
...
def build(self):
...
```
## Rule 4
The class can have a [_`build_config`_](focus://11:19) method
- The _`build_config`_ method will be used to create the config fields of the component (if any)
- It should always return a _`dict`_
The _`dict`_ should have the following format:
- The top level keys are the names of the fields
- The values are _`dict`_ with the following keys:
- _`field_type: str`_: The type of the field (can be any of the types supported by the _`build`_ method)
- _`is_list: bool`_: If the field is a list.
- _`options: List[str]`_: If the field is a list, the options that will be displayed.
- _`multiline: bool`_: If the field is a string, if it should be multiline.
- _`input_types: List[str]`_: To be used when you want a _`str`_ field to have connectable handles.
- _`display_name: str`_: To change the name of the field
- _`advanced: bool`_: To hide the field in the default view
- _`password: bool`_: To mask the input
- _`required: bool`_: To make the field required
- _`info: str`_: To add a tooltip to the field
- _`file_types: List[str]`_: This is a requirement if the _`field_type`_ is 'file'
(must be used in conjunction with _`suffixes`_)
Example: _`["json", "yaml", "yml"]`_
- _`suffixes: List[str]`_: This is a requirement if the _`field_type`_ is 'file' (must be used in conjunction with _`file_types`_, and it must be a list of strings like 'json')
Example: _`[".json", ".yaml", ".yml"]`_
---
```python
from langflow import CustomComponent
from langchain.chains import LLMChain
from langchain.chains.base import Chain
from langchain import PromptTemplate
from langchain.llms.base import BaseLLM
from langchain import Tool
class BestComponent(CustomComponent):
display_name = "Custom Component"
description = "This is a custom component"
# focus
def build_config(self) -> dict:
...
def build(self):
...
```
# Example
Now let's create a custom component that creates a Tool from a name, a description and a chain.
---
# Change the name
We can change the name of the component by adding a _`display_name`_ attribute.
```python focus=9
from langflow import CustomComponent
from langchain.chains import LLMChain
from langchain.chains.base import Chain
from langchain import PromptTemplate
from langchain.llms.base import BaseLLM
from langchain import Tool
class BestComponent(CustomComponent):
display_name = "Best Component"
description = "This is a custom component"
def build_config(self) -> dict:
...
def build(self):
...
```
---
# Change the description
We can change the description of the component by adding a _`description`_ attribute.
```python focus=10
from langflow import CustomComponent
from langchain.chains import LLMChain
from langchain.chains.base import Chain
from langchain import PromptTemplate
from langchain.llms.base import BaseLLM
from langchain import Tool
class BestComponent(CustomComponent):
display_name = "Best Component"
description = "This is the best component ever"
def build_config(self) -> dict:
...
def build(self):
...
```
---
# Add a config
The _`build_config`_ method will be used to configure the fields of the component.
- _`multiline`_ will add the possibility of editing text in a spaceous text editor.
- _`is_list`_ is a special option that allows you to add many values. When paired with _`options`_ it will transform it into a dropdown menu with the options you provide.
If you set the _`value`_ attribute to one of the options, it will be selected by default.
```python focus=12:19
from langflow import CustomComponent
from langchain.chains import LLMChain
from langchain.chains.base import Chain
from langchain import PromptTemplate
from langchain.llms.base import BaseLLM
from langchain import Tool
class BestComponent(CustomComponent):
display_name = "Best Component"
description = "This is the best component ever"
def build_config(self) -> dict:
cool_tool_names = ["Cool Tool",
"Cooler Tool",
"Coolest Tool"]
return {
"description": {"multiline": True},
"name": {"is_list": True,
"options": cool_tool_names}}
def build(self):
...
```
---
```python focus=21:25
from langflow import CustomComponent
from langchain.chains import LLMChain
from langchain.chains.base import Chain
from langchain import PromptTemplate
from langchain.llms.base import BaseLLM
from langchain import Tool
class BestComponent(CustomComponent):
display_name = "Best Component"
description = "This is the best component ever"
def build_config(self) -> dict:
cool_tool_names = ["Cool Tool",
"Cooler Tool",
"Coolest Tool"]
return {
"description": {"multiline": True},
"name": {"is_list": True,
"options": cool_tool_names}}
def build(self, name: str, description: str, chain: Chain) -> Tool:
return Tool(name=name,
description=description,
func=chain.run)
```
# Add the build method
The parameters used are:
- name is a string
- description is a string
- chain is a Chain
- The return type is Tool
We then instantiate a Tool and return it.
</CH.Scrollycoding>
## FlowRunner Example
Now let's see how to create a component that runs other flows.
<CH.Scrollycoding rows={20} className={""}>
```python
from langflow.interface.custom.custom_component import CustomComponent
class MyComponent(CustomComponent):
display_name = "Custom Component"
def build_config(self):
...
def build(self):
...
```
So, let's start by adding the _`display_name`_ and a _`description`_.
---
```python
from langflow.interface.custom.custom_component import CustomComponent
# focus
class FlowRunner(CustomComponent):
# focus
display_name = "Flow Runner"
# focus
description = "Run other flows"
def build_config(self):
...
def build(self):
...
```
That's better.
---
```python
from langflow.interface.custom.custom_component import CustomComponent
from langchain.schema import Document
# focus[6:16]
class FlowRunner(CustomComponent):
# focus[19:35]
display_name = "Flow Runner"
# focus[18:35]
description = "Run other flows"
def build_config(self):
...
def build(self):
...
```
Now let's import Document from the schema module which will be our return type for the _`build`_ method.
---
```python
from langflow.interface.custom.custom_component import CustomComponent
from langchain.schema import Document
class FlowRunner(CustomComponent):
display_name = "Flow Runner"
description = "Run other flows using a document as input."
def build_config(self):
...
# focus
def build(self, flow_name: str, document: Document) -> Document:
...
```
Let's add the parameters and the return type to the _`build`_ method.
---
```python
from langflow.interface.custom.custom_component import CustomComponent
from langchain.schema import Document
# focus
class FlowRunner(CustomComponent):
# focus
display_name = "Flow Runner"
# focus
description = "Run other flows using a document as input."
def build_config(self):
...
def build(self, flow_name: str, document: Document) -> Document:
...
```
---
</CH.Scrollycoding>

6
docs/docs/guidelines/features.mdx
View file

@ -2,6 +2,7 @@ import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from "@docusaurus/useBaseUrl";
import ZoomableImage from "/src/theme/ZoomableImage.js";
import ReactPlayer from "react-player";
import Admonition from "@theme/Admonition";
# Features
@ -34,9 +35,10 @@ import ReactPlayer from "react-player";
Flows can be exported and imported as JSON files.
:::caution
<Admonition type="caution">
Watch out for API keys being stored in local files.
:::
</Admonition>
---

252
docs/docusaurus.config.js
View file

@ -1,127 +1,141 @@
const lightCodeTheme = require("prism-react-renderer/themes/github");
const { remarkCodeHike } = require("@code-hike/mdx");
// With JSDoc @type annotations, IDEs can provide config autocompletion
/** @type {import('@docusaurus/types').DocusaurusConfig} */
(
module.exports = {
title: "Langflow Documentation",
tagline: "Langflow is a GUI for LangChain, designed with react-flow",
favicon: "img/favicon.ico",
url: "https://logspace-ai.github.io",
baseUrl: "/",
onBrokenLinks: "throw",
onBrokenMarkdownLinks: "warn",
organizationName: "logspace-ai",
projectName: "langflow",
trailingSlash: false,
customFields: {
mendableAnonKey: process.env.MENDABLE_ANON_KEY,
},
i18n: {
defaultLocale: "en",
locales: ["en"],
},
presets: [
[
"@docusaurus/preset-classic",
/** @type {import('@docusaurus/preset-classic').Options} */
({
docs: {
routeBasePath: "/",
sidebarPath: require.resolve("./sidebars.js"),
path: "docs",
// sidebarPath: 'sidebars.js',
},
theme: {
customCss: require.resolve("./src/css/custom.css"),
},
}),
],
],
plugins: [
["docusaurus-node-polyfills", { excludeAliases: ["console"] }],
"docusaurus-plugin-image-zoom",
// ....
async function myPlugin(context, options) {
return {
name: "docusaurus-tailwindcss",
configurePostCss(postcssOptions) {
// Appends TailwindCSS and AutoPrefixer.
postcssOptions.plugins.push(require("tailwindcss"));
postcssOptions.plugins.push(require("autoprefixer"));
return postcssOptions;
},
};
},
],
themeConfig:
/** @type {import('@docusaurus/preset-classic').ThemeConfig} */
module.exports = {
title: "Langflow Documentation",
tagline: "Langflow is a GUI for LangChain, designed with react-flow",
favicon: "img/favicon.ico",
url: "https://logspace-ai.github.io",
baseUrl: "/",
onBrokenLinks: "throw",
onBrokenMarkdownLinks: "warn",
organizationName: "logspace-ai",
projectName: "langflow",
trailingSlash: false,
customFields: {
mendableAnonKey: process.env.MENDABLE_ANON_KEY,
},
i18n: {
defaultLocale: "en",
locales: ["en"],
},
presets: [
[
"@docusaurus/preset-classic",
/** @type {import('@docusaurus/preset-classic').Options} */
({
navbar: {
hideOnScroll: true,
title: "Langflow",
logo: {
alt: "Langflow",
src: "img/chain.png",
},
items: [
// right
{
position: "right",
href: "https://github.com/logspace-ai/langflow",
position: "right",
className: "header-github-link",
target: "_blank",
rel: null,
},
{
position: "right",
href: "https://twitter.com/logspace_ai",
position: "right",
className: "header-twitter-link",
target: "_blank",
rel: null,
},
{
position: "right",
href: "https://discord.gg/EqksyE2EX9",
position: "right",
className: "header-discord-link",
target: "_blank",
rel: null,
},
docs: {
beforeDefaultRemarkPlugins: [
[
remarkCodeHike,
{ theme: "monokai", showCopyButton: true, lineNumbers: true },
],
],
routeBasePath: "/",
sidebarPath: require.resolve("./sidebars.js"),
path: "docs",
// sidebarPath: 'sidebars.js',
},
theme: {
customCss: [
require.resolve("@code-hike/mdx/styles.css"),
require.resolve("./src/css/custom.css"),
],
},
tableOfContents: {
minHeadingLevel: 2,
maxHeadingLevel: 5,
},
colorMode: {
defaultMode: "light",
disableSwitch: true,
respectPrefersColorScheme: false,
},
announcementBar: {
content:
'⭐️ If you like ⛓️Langflow, star it on <a target="_blank" rel="noopener noreferrer" href="https://github.com/logspace-ai/langflow">GitHub</a>! ⭐️',
backgroundColor: "#B53D38", //Mustard Yellow #D19900 #D4B20B - Salmon #E9967A
textColor: "#fff",
isCloseable: false,
},
footer: {
links: [],
copyright: `Copyright © ${new Date().getFullYear()} Logspace.`,
},
zoom: {
selector: ".markdown :not(a) > img:not(.no-zoom)",
background: {
light: "rgba(240, 240, 240, 0.9)",
},
config: {},
},
prism: {
theme: lightCodeTheme,
},
}),
}
);
],
],
plugins: [
["docusaurus-node-polyfills", { excludeAliases: ["console"] }],
"docusaurus-plugin-image-zoom",
// ....
async function myPlugin(context, options) {
return {
name: "docusaurus-tailwindcss",
configurePostCss(postcssOptions) {
// Appends TailwindCSS and AutoPrefixer.
postcssOptions.plugins.push(require("tailwindcss"));
postcssOptions.plugins.push(require("autoprefixer"));
return postcssOptions;
},
};
},
],
themes: ["mdx-v2"],
themeConfig:
/** @type {import('@docusaurus/preset-classic').ThemeConfig} */
({
navbar: {
hideOnScroll: true,
title: "Langflow",
logo: {
alt: "Langflow",
src: "img/chain.png",
},
items: [
// right
{
position: "right",
href: "https://github.com/logspace-ai/langflow",
position: "right",
className: "header-github-link",
target: "_blank",
rel: null,
},
{
position: "right",
href: "https://twitter.com/logspace_ai",
position: "right",
className: "header-twitter-link",
target: "_blank",
rel: null,
},
{
position: "right",
href: "https://discord.gg/EqksyE2EX9",
position: "right",
className: "header-discord-link",
target: "_blank",
rel: null,
},
],
},
tableOfContents: {
minHeadingLevel: 2,
maxHeadingLevel: 5,
},
colorMode: {
defaultMode: "light",
disableSwitch: true,
respectPrefersColorScheme: false,
},
announcementBar: {
content:
'⭐️ If you like ⛓️Langflow, star it on <a target="_blank" rel="noopener noreferrer" href="https://github.com/logspace-ai/langflow">GitHub</a>! ⭐️',
backgroundColor: "#B53D38", //Mustard Yellow #D19900 #D4B20B - Salmon #E9967A
textColor: "#fff",
isCloseable: false,
},
footer: {
links: [],
copyright: `Copyright © ${new Date().getFullYear()} Logspace.`,
},
zoom: {
selector: ".markdown :not(a) > img:not(.no-zoom)",
background: {
light: "rgba(240, 240, 240, 0.9)",
},
config: {},
},
// prism: {
// theme: require("prism-react-renderer/themes/dracula"),
// },
docs: {
sidebar: {
hideable: true,
},
},
}),
};

2033
docs/package-lock.json generated
View file

File diff suppressed because it is too large Load diff

6
docs/package.json
View file

@ -15,12 +15,13 @@
},
"dependencies": {
"@babel/preset-react": "^7.22.3",
"@code-hike/mdx": "^0.9.0",
"@docusaurus/core": "2.4.1",
"@docusaurus/plugin-ideal-image": "^2.4.1",
"@docusaurus/preset-classic": "2.4.1",
"@docusaurus/theme-classic": "^2.4.1",
"@docusaurus/theme-search-algolia": "^2.4.1",
"@mdx-js/react": "^1.6.22",
"@mdx-js/react": "^2.3.0",
"@mendable/search": "^0.0.114",
"@pbe/react-yandex-maps": "^1.2.4",
"@prismicio/client": "^7.0.1",
@ -28,6 +29,7 @@
"autoprefixer": "^10.4.14",
"clsx": "^1.2.1",
"docusaurus-plugin-image-zoom": "^0.1.4",
"docusaurus-theme-mdx-v2": "^0.1.2",
"jquery": "^3.7.0",
"medium-zoom": "^1.0.8",
"node-fetch": "^3.3.1",
@ -67,4 +69,4 @@
"engines": {
"node": ">=16.14"
}
}
}

2
docs/sidebars.js
View file

@ -22,6 +22,7 @@ module.exports = {
"guidelines/prompt-customization",
"guidelines/chat-interface",
"guidelines/chat-widget",
"guidelines/custom-component",
],
},
{
@ -31,6 +32,7 @@ module.exports = {
items: [
"components/agents",
"components/chains",
"components/custom",
"components/embeddings",
"components/llms",
"components/loaders",

41
docs/src/css/custom.css
View file

@ -3,17 +3,19 @@
* bundles Infima by default. Infima is a CSS framework designed to
* work well for content-centric websites.
*/
:root {
:root {
--ifm-background-color: var(--token-primary-bg-c);
--ifm-navbar-link-hover-color: initial;
--ifm-navbar-padding-vertical: 0;
--ifm-navbar-item-padding-vertical: 0;
--ifm-font-family-base: -apple-system, BlinkMacSystemFont, Inter, Helvetica, Arial, sans-serif, 'Apple Color Emoji', 'Segoe UI emoji';
--ifm-font-family-monospace: 'SFMono-Regular', 'Roboto Mono', Consolas, 'Liberation Mono', Menlo, Courier, monospace;
--ifm-font-family-base: -apple-system, BlinkMacSystemFont, Inter, Helvetica,
Arial, sans-serif, "Apple Color Emoji", "Segoe UI emoji";
--ifm-font-family-monospace: "SFMono-Regular", "Roboto Mono", Consolas,
"Liberation Mono", Menlo, Courier, monospace;
}
.theme-doc-sidebar-item-category.menu__list-item:not(:first-child) {
margin-top: 1.5rem!important;
margin-top: 1.5rem !important;
}
.docusaurus-highlight-code-line {
@ -31,7 +33,7 @@
transform: skewY(6deg);
}
[class^='announcementBar'] {
[class^="announcementBar"] {
z-index: 10;
}
@ -112,7 +114,7 @@ body {
}
.header-github-link:before {
content: '';
content: "";
width: 24px;
height: 24px;
display: flex;
@ -126,7 +128,7 @@ body {
}
.header-twitter-link::before {
content: '';
content: "";
width: 24px;
height: 24px;
display: flex;
@ -140,7 +142,7 @@ body {
}
.header-discord-link::before {
content: '';
content: "";
width: 24px;
height: 24px;
display: flex;
@ -148,7 +150,6 @@ body {
background-size: contain;
}
/* Images */
.image-rendering-crisp {
image-rendering: crisp-edges;
@ -164,7 +165,7 @@ body {
.img-center {
display: flex;
justify-content: center;
width: 100%,
width: 100%;
}
.resized-image {
@ -188,4 +189,22 @@ body {
.mendable-search {
width: 140px;
}
}
}
/*
.ch-scrollycoding {
gap: 10rem !important;
} */
.ch-scrollycoding-content {
max-width: 55% !important;
min-width: 40% !important;
}
.ch-scrollycoding-sticker {
max-width: 60% !important;
min-width: 45% !important;
}
.ch-scrollycoding-step-content {
min-height: 70px;
}

8
src/backend/langflow/__init__.py
View file

@ -1,6 +1,7 @@
from importlib import metadata
from langflow.cache import cache_manager # noqa: E402
from langflow.processing.process import load_flow_from_json # noqa: E402
from langflow.cache import cache_manager
from langflow.processing.process import load_flow_from_json
from langflow.interface.custom.custom_component import CustomComponent
try:
__version__ = metadata.version(__package__)
@ -9,5 +10,4 @@ except metadata.PackageNotFoundError:
__version__ = ""
del metadata # optional, avoids polluting the results of dir(__package__)
__all__ = ["load_flow_from_json", "cache_manager"]
__all__ = ["load_flow_from_json", "cache_manager", "CustomComponent"]

28
src/backend/langflow/__main__.py
View file

@ -2,7 +2,8 @@ import os
import sys
import time
import httpx
from multiprocess import Process, cpu_count # type: ignore
from langflow.utils.util import get_number_of_workers
from multiprocess import Process # type: ignore
import platform
from pathlib import Path
from typing import Optional
@ -20,18 +21,13 @@ from dotenv import load_dotenv
app = typer.Typer()
def get_number_of_workers(workers=None):
if workers == -1:
workers = (cpu_count() * 2) + 1
return workers
def update_settings(
config: str,
cache: str,
dev: bool = False,
database_url: Optional[str] = None,
remove_api_keys: bool = False,
component_path: Optional[Path] = None,
):
"""Update the settings from a config file."""
@ -39,13 +35,19 @@ def update_settings(
database_url = database_url or os.getenv("langflow_database_url")
if config:
logger.debug(f"Loading settings from {config}")
settings.update_from_yaml(config, dev=dev)
if database_url:
settings.update_settings(database_url=database_url)
if remove_api_keys:
logger.debug(f"Setting remove_api_keys to {remove_api_keys}")
settings.update_settings(remove_api_keys=remove_api_keys)
if cache:
logger.debug(f"Setting cache to {cache}")
settings.update_settings(cache=cache)
if component_path:
logger.debug(f"Adding component path {component_path}")
settings.update_settings(component_path=component_path)
def load_params():
@ -120,10 +122,15 @@ def serve(
"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"
-1, help="Number of worker processes.", envvar="LANGFLOW_WORKERS"
),
timeout: int = typer.Option(60, help="Worker timeout in seconds."),
timeout: int = typer.Option(300, help="Worker timeout in seconds."),
port: int = typer.Option(7860, help="Port to listen on.", envvar="LANGFLOW_PORT"),
component_path: Optional[Path] = typer.Option(
Path(__file__).parent,
help="Path to the directory containing custom components.",
envvar="LANGFLOW_COMPONENT_PATH",
),
config: str = typer.Option("config.yaml", help="Path to the configuration file."),
# .env file param
env_file: Path = typer.Option(
@ -181,6 +188,7 @@ def serve(
database_url=database_url,
remove_api_keys=remove_api_keys,
cache=cache,
component_path=component_path,
)
# create path object if path is provided
static_files_dir: Optional[Path] = Path(path) if path else None
@ -298,7 +306,7 @@ def run_langflow(host, port, log_level, options, app):
Run Langflow server on localhost
"""
try:
if platform.system() in ["Darwin", "Windows"]:
if platform.system() in ["Windows"]:
# Run using uvicorn on MacOS and Windows
# Windows doesn't support gunicorn
# MacOS requires an env variable to be set to use gunicorn

2
src/backend/langflow/api/router.py
View file

@ -6,6 +6,7 @@ from langflow.api.v1 import (
validate_router,
flows_router,
flow_styles_router,
component_router,
)
router = APIRouter(
@ -14,5 +15,6 @@ 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(flows_router)
router.include_router(flow_styles_router)

9
src/backend/langflow/api/utils.py
View file

@ -57,3 +57,12 @@ def build_input_keys_response(langchain_object, artifacts):
input_keys_response["template"] = langchain_object.prompt.template
return input_keys_response
def merge_nested_dicts(dict1, dict2):
for key, value in dict2.items():
if isinstance(value, dict) and isinstance(dict1.get(key), dict):
dict1[key] = merge_nested_dicts(dict1[key], value)
else:
dict1[key] = value
return dict1

2
src/backend/langflow/api/v1/__init__.py
View file

@ -3,10 +3,12 @@ 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.flow_styles import router as flow_styles_router
from langflow.api.v1.components import router as component_router
__all__ = [
"chat_router",
"endpoints_router",
"component_router",
"validate_router",
"flows_router",
"flow_styles_router",

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

@ -91,8 +91,8 @@ class AsyncStreamingLLMCallbackHandler(AsyncCallbackHandler):
# This is to emulate the stream of tokens
for resp in resps:
await self.websocket.send_json(resp.dict())
except Exception as e:
logger.error(e)
except Exception as exc:
logger.error(f"Error sending response: {exc}")
async def on_tool_error(
self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any

8
src/backend/langflow/api/v1/chat.py
View file

@ -26,7 +26,7 @@ async def chat(client_id: str, websocket: WebSocket):
message = "Please, build the flow before sending messages"
await websocket.close(code=status.WS_1011_INTERNAL_ERROR, reason=message)
except WebSocketException as exc:
logger.error(exc)
logger.error(f"Websocket error: {exc}")
await websocket.close(code=status.WS_1011_INTERNAL_ERROR, reason=str(exc))
@ -56,7 +56,7 @@ async def init_build(graph_data: dict, flow_id: str):
return InitResponse(flowId=flow_id)
except Exception as exc:
logger.error(exc)
logger.error(f"Error initializing build: {exc}")
return HTTPException(status_code=500, detail=str(exc))
@ -74,7 +74,7 @@ async def build_status(flow_id: str):
)
except Exception as exc:
logger.error(exc)
logger.error(f"Error checking build status: {exc}")
return HTTPException(status_code=500, detail=str(exc))
@ -177,5 +177,5 @@ async def stream_build(flow_id: str):
try:
return StreamingResponse(event_stream(flow_id), media_type="text/event-stream")
except Exception as exc:
logger.error(exc)
logger.error(f"Error streaming build: {exc}")
raise HTTPException(status_code=500, detail=str(exc))

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

@ -0,0 +1,77 @@
from datetime import timezone
from typing import List
from uuid import UUID
from langflow.database.models.component import Component, ComponentModel
from langflow.database.base 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}

84
src/backend/langflow/api/v1/endpoints.py
View file

@ -1,17 +1,34 @@
from typing import Optional
from http import HTTPStatus
from typing import Annotated, Optional
from langflow.cache.utils import save_uploaded_file
from langflow.database.models.flow import Flow
from langflow.processing.process import process_graph_cached, process_tweaks
from langflow.utils.logger import logger
from langflow.settings import settings
from fastapi import APIRouter, Depends, HTTPException, UploadFile
from fastapi import APIRouter, Depends, HTTPException, UploadFile, Body
from langflow.interface.custom.custom_component import CustomComponent
from langflow.interface.custom.directory_reader import (
CustomComponentPathValueError,
)
from langflow.api.v1.schemas import (
ProcessResponse,
UploadFileResponse,
CustomComponentCode,
)
from langflow.api.utils import merge_nested_dicts
from langflow.interface.types import (
build_langchain_types_dict,
build_langchain_template_custom_component,
build_langchain_custom_component_list_from_path,
)
from langflow.interface.types import langchain_types_dict
from langflow.database.base import get_session
from sqlmodel import Session
@ -21,7 +38,47 @@ router = APIRouter(tags=["Base"])
@router.get("/all")
def get_all():
return langchain_types_dict
native_components = build_langchain_types_dict()
# custom_components is a list of dicts
# need to merge all the keys into one dict
custom_components_from_file = {}
if settings.component_path:
custom_component_dicts = [
build_langchain_custom_component_list_from_path(str(path))
for path in settings.component_path
]
for custom_component_dict in custom_component_dicts:
custom_components_from_file = merge_nested_dicts(
custom_components_from_file, custom_component_dict
)
return merge_nested_dicts(native_components, custom_components_from_file)
@router.get("/load_custom_component_from_path")
def get_load_custom_component_from_path(path: str):
try:
data = build_langchain_custom_component_list_from_path(path)
except CustomComponentPathValueError as err:
raise HTTPException(
status_code=400,
detail={"error": type(err).__name__, "traceback": str(err)},
) from err
return data
@router.get("/load_custom_component_from_path_TEST")
def get_load_custom_component_from_path_test(path: str):
from langflow.interface.custom.directory_reader import (
DirectoryReader,
)
reader = DirectoryReader(path, False)
file_list = reader.get_files()
data = reader.build_component_menu_list(file_list)
return reader.filter_loaded_components(data, True)
# For backwards compatibility we will keep the old endpoint
@ -31,6 +88,7 @@ async def process_flow(
flow_id: str,
inputs: Optional[dict] = None,
tweaks: Optional[dict] = None,
clear_cache: Annotated[bool, Body(embed=True)] = False, # noqa: F821
session: Session = Depends(get_session),
):
"""
@ -50,7 +108,7 @@ async def process_flow(
graph_data = process_tweaks(graph_data, tweaks)
except Exception as exc:
logger.error(f"Error processing tweaks: {exc}")
response = process_graph_cached(graph_data, inputs)
response = process_graph_cached(graph_data, inputs, clear_cache)
return ProcessResponse(
result=response,
)
@ -60,7 +118,11 @@ async def process_flow(
raise HTTPException(status_code=500, detail=str(e)) from e
@router.post("/upload/{flow_id}", response_model=UploadFileResponse, status_code=201)
@router.post(
"/upload/{flow_id}",
response_model=UploadFileResponse,
status_code=HTTPStatus.CREATED,
)
async def create_upload_file(file: UploadFile, flow_id: str):
# Cache file
try:
@ -81,3 +143,13 @@ def get_version():
from langflow import __version__
return {"version": __version__}
@router.post("/custom_component", status_code=HTTPStatus.OK)
async def custom_component(
raw_code: CustomComponentCode,
):
extractor = CustomComponent(code=raw_code.code)
extractor.is_check_valid()
return build_langchain_template_custom_component(extractor)

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

@ -116,3 +116,20 @@ class StreamData(BaseModel):
def __str__(self) -> str:
return f"event: {self.event}\ndata: {json.dumps(self.data)}\n\n"
class CustomComponentCode(BaseModel):
code: str
class CustomComponentResponseError(BaseModel):
detail: str
traceback: str
class ComponentListCreate(BaseModel):
flows: List[FlowCreate]
class ComponentListRead(BaseModel):
flows: List[FlowRead]

12
src/backend/langflow/chat/manager.py
View file

@ -111,7 +111,7 @@ class ChatManager:
# This is to catch the following error:
# Unexpected ASGI message 'websocket.close', after sending 'websocket.close'
if "after sending" in str(exc):
logger.error(exc)
logger.error(f"Error closing connection: {exc}")
async def process_message(
self, client_id: str, payload: Dict, langchain_object: Any
@ -197,13 +197,13 @@ class ChatManager:
langchain_object = self.in_memory_cache.get(client_id)
await self.process_message(client_id, payload, langchain_object)
except Exception as e:
except Exception as exc:
# Handle any exceptions that might occur
logger.error(e)
logger.error(f"Error handling websocket: {exc}")
await self.close_connection(
client_id=client_id,
code=status.WS_1011_INTERNAL_ERROR,
reason=str(e)[:120],
reason=str(exc)[:120],
)
finally:
try:
@ -212,6 +212,6 @@ class ChatManager:
code=status.WS_1000_NORMAL_CLOSURE,
reason="Client disconnected",
)
except Exception as e:
logger.error(e)
except Exception as exc:
logger.error(f"Error closing connection: {exc}")
self.disconnect(client_id)

3
src/backend/langflow/config.yaml
View file

@ -290,3 +290,6 @@ output_parsers:
documentation: "https://python.langchain.com/docs/modules/model_io/output_parsers/structured"
ResponseSchema:
documentation: "https://python.langchain.com/docs/modules/model_io/output_parsers/structured"
custom_components:
CustomComponent:
documentation: ""

3
src/backend/langflow/custom/customs.py
View file

@ -31,6 +31,9 @@ CUSTOM_NODES = {
"MidJourneyPromptChain": frontend_node.chains.MidJourneyPromptChainNode(),
"load_qa_chain": frontend_node.chains.CombineDocsChainNode(),
},
"custom_components": {
"CustomComponent": frontend_node.custom_components.CustomComponentFrontendNode(),
},
}

18
src/backend/langflow/database/base.py
View file

@ -1,3 +1,4 @@
from contextlib import contextmanager
from langflow.settings import settings
from sqlmodel import SQLModel, Session, create_engine
from langflow.utils.logger import logger
@ -32,6 +33,19 @@ def create_db_and_tables():
logger.debug("Database and tables created successfully")
def get_session():
with Session(engine) as session:
@contextmanager
def session_getter():
try:
session = Session(engine)
yield session
except Exception as e:
print("Session rollback because of exception:", e)
session.rollback()
raise
finally:
session.close()
def get_session():
with session_getter() as session:
yield session

29
src/backend/langflow/database/models/component.py Normal file
View file

@ -0,0 +1,29 @@
from langflow.database.models.base import SQLModelSerializable, SQLModel
from sqlmodel import Field
from typing import Optional
from datetime import datetime
import uuid
class Component(SQLModelSerializable, table=True):
id: uuid.UUID = Field(default_factory=uuid.uuid4, primary_key=True)
frontend_node_id: uuid.UUID = Field(index=True)
name: str = Field(index=True)
description: Optional[str] = Field(default=None)
python_code: Optional[str] = Field(default=None)
return_type: Optional[str] = Field(default=None)
is_disabled: bool = Field(default=False)
is_read_only: bool = Field(default=False)
create_at: datetime = Field(default_factory=datetime.utcnow)
update_at: datetime = Field(default_factory=datetime.utcnow)
class ComponentModel(SQLModel):
id: uuid.UUID = Field(default_factory=uuid.uuid4)
frontend_node_id: uuid.UUID = Field(default=uuid.uuid4())
name: str = Field(default="")
description: Optional[str] = None
python_code: Optional[str] = None
return_type: Optional[str] = None
is_disabled: bool = False
is_read_only: bool = False

2
src/backend/langflow/graph/graph/base.py
View file

@ -77,6 +77,8 @@ class Graph:
def _validate_nodes(self) -> None:
"""Check that all nodes have edges"""
if len(self.nodes) == 1:
return
for node in self.nodes:
if not self._validate_node(node):
raise ValueError(

3
src/backend/langflow/graph/graph/constants.py
View file

@ -14,7 +14,7 @@ from langflow.interface.vector_store.base import vectorstore_creator
from langflow.interface.wrappers.base import wrapper_creator
from langflow.interface.output_parsers.base import output_parser_creator
from langflow.interface.retrievers.base import retriever_creator
from langflow.interface.custom.base import custom_component_creator
from typing import Dict, Type
@ -32,5 +32,6 @@ VERTEX_TYPE_MAP: Dict[str, Type[Vertex]] = {
**{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.RetrieverVertex for t in retriever_creator.to_list()},
}

9
src/backend/langflow/graph/vertex/types.py
View file

@ -239,3 +239,12 @@ class PromptVertex(Vertex):
class OutputParserVertex(Vertex):
def __init__(self, data: Dict):
super().__init__(data, base_type="output_parsers")
class CustomComponentVertex(Vertex):
def __init__(self, data: Dict):
super().__init__(data, base_type="custom_components")
def _built_object_repr(self):
if self.artifacts and "repr" in self.artifacts:
return self.artifacts["repr"] or super()._built_object_repr()

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

@ -34,7 +34,7 @@ class LangChainTypeCreator(BaseModel, ABC):
for name, value_dict in type_settings.items()
}
except AttributeError as exc:
logger.error(exc)
logger.error(f"Error getting settings for {self.type_name}: {exc}")
self.name_docs_dict = {}
return self.name_docs_dict

4
src/backend/langflow/interface/custom/__init__.py Normal file
View file

@ -0,0 +1,4 @@
from langflow.interface.custom.base import CustomComponentCreator
from langflow.interface.custom.custom_component import CustomComponent
__all__ = ["CustomComponentCreator", "CustomComponent"]

48
src/backend/langflow/interface/custom/base.py Normal file
View file

@ -0,0 +1,48 @@
from typing import Any, Dict, List, Optional, Type
from langflow.interface.base import LangChainTypeCreator
# from langflow.interface.custom.custom import CustomComponent
from langflow.interface.custom.custom_component import CustomComponent
from langflow.template.frontend_node.custom_components import (
CustomComponentFrontendNode,
)
from langflow.utils.logger import logger
# Assuming necessary imports for Field, Template, and FrontendNode classes
class CustomComponentCreator(LangChainTypeCreator):
type_name: str = "custom_components"
@property
def frontend_node_class(self) -> Type[CustomComponentFrontendNode]:
return CustomComponentFrontendNode
@property
def type_to_loader_dict(self) -> Dict:
if self.type_dict is None:
self.type_dict: dict[str, Any] = {
"CustomComponent": CustomComponent,
}
return self.type_dict
def get_signature(self, name: str) -> Optional[Dict]:
from langflow.custom.customs import get_custom_nodes
try:
if name in get_custom_nodes(self.type_name).keys():
return get_custom_nodes(self.type_name)[name]
except ValueError as exc:
raise ValueError(f"CustomComponent {name} not found: {exc}") from exc
except AttributeError as exc:
logger.error(f"CustomComponent {name} not loaded: {exc}")
return None
return None
def to_list(self) -> List[str]:
return list(self.type_to_loader_dict.keys())
custom_component_creator = CustomComponentCreator()

272
src/backend/langflow/interface/custom/code_parser.py Normal file
View file

@ -0,0 +1,272 @@
import ast
import inspect
import traceback
from typing import Dict, Any, List, Type, Union
from fastapi import HTTPException
from langflow.interface.custom.schema import CallableCodeDetails, ClassCodeDetails
class CodeSyntaxError(HTTPException):
pass
class CodeParser:
"""
A parser for Python source code, extracting code details.
"""
def __init__(self, code: Union[str, Type]) -> None:
"""
Initializes the parser with the provided code.
"""
if isinstance(code, type):
if not inspect.isclass(code):
raise ValueError("The provided code must be a class.")
# If the code is a class, get its source code
code = inspect.getsource(code)
self.code = code
self.data: Dict[str, Any] = {
"imports": [],
"functions": [],
"classes": [],
"global_vars": [],
}
self.handlers = {
ast.Import: self.parse_imports,
ast.ImportFrom: self.parse_imports,
ast.FunctionDef: self.parse_functions,
ast.ClassDef: self.parse_classes,
ast.Assign: self.parse_global_vars,
}
def __get_tree(self):
"""
Parses the provided code to validate its syntax.
It tries to parse the code into an abstract syntax tree (AST).
"""
try:
tree = ast.parse(self.code)
except SyntaxError as err:
raise CodeSyntaxError(
status_code=400,
detail={"error": err.msg, "traceback": traceback.format_exc()},
) from err
return tree
def parse_node(self, node: Union[ast.stmt, ast.AST]) -> None:
"""
Parses an AST node and updates the data
dictionary with the relevant information.
"""
if handler := self.handlers.get(type(node)): # type: ignore
handler(node) # type: ignore
def parse_imports(self, node: Union[ast.Import, ast.ImportFrom]) -> None:
"""
Extracts "imports" from the code.
"""
if isinstance(node, ast.Import):
for alias in node.names:
self.data["imports"].append(alias.name)
elif isinstance(node, ast.ImportFrom):
for alias in node.names:
self.data["imports"].append((node.module, alias.name))
def parse_functions(self, node: ast.FunctionDef) -> None:
"""
Extracts "functions" from the code.
"""
self.data["functions"].append(self.parse_callable_details(node))
def parse_arg(self, arg, default):
"""
Parses an argument and its default value.
"""
arg_dict = {"name": arg.arg, "default": default}
if arg.annotation:
arg_dict["type"] = ast.unparse(arg.annotation)
return arg_dict
def parse_callable_details(self, node: ast.FunctionDef) -> Dict[str, Any]:
"""
Extracts details from a single function or method node.
"""
func = CallableCodeDetails(
name=node.name,
doc=ast.get_docstring(node),
args=[],
body=[],
return_type=ast.unparse(node.returns) if node.returns else None,
)
func.args = self.parse_function_args(node)
func.body = self.parse_function_body(node)
return func.dict()
def parse_function_args(self, node: ast.FunctionDef) -> List[Dict[str, Any]]:
"""
Parses the arguments of a function or method node.
"""
args = []
args += self.parse_positional_args(node)
args += self.parse_varargs(node)
args += self.parse_keyword_args(node)
args += self.parse_kwargs(node)
return args
def parse_positional_args(self, node: ast.FunctionDef) -> List[Dict[str, Any]]:
"""
Parses the positional arguments of a function or method node.
"""
num_args = len(node.args.args)
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
]
# 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
]
defaults = missing_defaults + default_values
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]]:
"""
Parses the *args argument of a function or method node.
"""
args = []
if node.args.vararg:
args.append(self.parse_arg(node.args.vararg, None))
return args
def parse_keyword_args(self, node: ast.FunctionDef) -> List[Dict[str, Any]]:
"""
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
]
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]]:
"""
Parses the **kwargs argument of a function or method node.
"""
args = []
if node.args.kwarg:
args.append(self.parse_arg(node.args.kwarg, None))
return args
def parse_function_body(self, node: ast.FunctionDef) -> List[str]:
"""
Parses the body of a function or method node.
"""
return [ast.unparse(line) for line in node.body]
def parse_assign(self, stmt):
"""
Parses an Assign statement and returns a dictionary
with the target's name and value.
"""
for target in stmt.targets:
if isinstance(target, ast.Name):
return {"name": target.id, "value": ast.unparse(stmt.value)}
def parse_ann_assign(self, stmt):
"""
Parses an AnnAssign statement and returns a dictionary
with the target's name, value, and annotation.
"""
if isinstance(stmt.target, ast.Name):
return {
"name": stmt.target.id,
"value": ast.unparse(stmt.value) if stmt.value else None,
"annotation": ast.unparse(stmt.annotation),
}
def parse_function_def(self, stmt):
"""
Parses a FunctionDef statement and returns the parsed
method and a boolean indicating if it's an __init__ method.
"""
method = self.parse_callable_details(stmt)
return (method, True) if stmt.name == "__init__" else (method, False)
def parse_classes(self, node: ast.ClassDef) -> None:
"""
Extracts "classes" from the code, including inheritance and init methods.
"""
class_details = ClassCodeDetails(
name=node.name,
doc=ast.get_docstring(node),
bases=[ast.unparse(base) for base in node.bases],
attributes=[],
methods=[],
init=None,
)
for stmt in node.body:
if isinstance(stmt, ast.Assign):
if attr := self.parse_assign(stmt):
class_details.attributes.append(attr)
elif isinstance(stmt, ast.AnnAssign):
if attr := self.parse_ann_assign(stmt):
class_details.attributes.append(attr)
elif isinstance(stmt, ast.FunctionDef):
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())
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
],
"value": ast.unparse(node.value),
}
self.data["global_vars"].append(global_var)
def parse_code(self) -> Dict[str, Any]:
"""
Runs all parsing operations and returns the resulting data.
"""
tree = self.__get_tree()
for node in ast.walk(tree):
self.parse_node(node)
return self.data

72
src/backend/langflow/interface/custom/component.py Normal file
View file

@ -0,0 +1,72 @@
import ast
from typing import Optional
from pydantic import BaseModel
from fastapi import HTTPException
from langflow.utils import validate
from langflow.interface.custom.code_parser import CodeParser
class ComponentCodeNullError(HTTPException):
pass
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."
)
code: Optional[str]
function_entrypoint_name = "build"
field_config: dict = {}
def __init__(self, **data):
super().__init__(**data)
def get_code_tree(self, code: str):
parser = CodeParser(code)
return parser.parse_code()
def get_function(self):
if not self.code:
raise ComponentCodeNullError(
status_code=400,
detail={"error": self.ERROR_CODE_NULL, "traceback": ""},
)
if not self.function_entrypoint_name:
raise ComponentFunctionEntrypointNameNullError(
status_code=400,
detail={
"error": self.ERROR_FUNCTION_ENTRYPOINT_NAME_NULL,
"traceback": "",
},
)
return validate.create_function(self.code, self.function_entrypoint_name)
def build_template_config(self, attributes) -> dict:
template_config = {}
for item in attributes:
item_name = item.get("name")
if item_value := item.get("value"):
if "display_name" in item_name:
template_config["display_name"] = ast.literal_eval(item_value)
elif "description" in item_name:
template_config["description"] = ast.literal_eval(item_value)
elif "field_config" in item_name:
template_config["field_config"] = ast.literal_eval(item_value)
return template_config
def build(self):
raise NotImplementedError

59
src/backend/langflow/interface/custom/constants.py Normal file
View file

@ -0,0 +1,59 @@
from langchain import PromptTemplate
from langchain.chains.base import Chain
from langchain.document_loaders.base import BaseLoader
from langchain.embeddings.base import Embeddings
from langchain.llms.base import BaseLLM
from langchain.schema import BaseRetriever, Document
from langchain.text_splitter import TextSplitter
from langchain.tools import Tool
from langchain.vectorstores.base import VectorStore
LANGCHAIN_BASE_TYPES = {
"Chain": Chain,
"Tool": Tool,
"BaseLLM": BaseLLM,
"PromptTemplate": PromptTemplate,
"BaseLoader": BaseLoader,
"Document": Document,
"TextSplitter": TextSplitter,
"VectorStore": VectorStore,
"Embeddings": Embeddings,
"BaseRetriever": BaseRetriever,
}
# Langchain base types plus Python base types
CUSTOM_COMPONENT_SUPPORTED_TYPES = {
**LANGCHAIN_BASE_TYPES,
"str": str,
"int": int,
"float": float,
"bool": bool,
"list": list,
"dict": dict,
}
DEFAULT_CUSTOM_COMPONENT_CODE = """
from langflow import CustomComponent
from langchain.llms.base import BaseLLM
from langchain.chains import LLMChain
from langchain import PromptTemplate
from langchain.schema import Document
import requests
class YourComponent(CustomComponent):
display_name: str = "Your Component"
description: str = "Your description"
def build_config(self):
return { "url": { "multiline": True, "required": True } }
def build(self, url: str, llm: BaseLLM, prompt: PromptTemplate) -> Document:
response = requests.get(url)
chain = LLMChain(llm=llm, prompt=prompt)
result = chain.run(response.text[:300])
return Document(page_content=str(result))
"""

162
src/backend/langflow/interface/custom/custom_component.py Normal file
View file

@ -0,0 +1,162 @@
from typing import Callable, Optional
from fastapi import HTTPException
from langflow.interface.custom.constants import CUSTOM_COMPONENT_SUPPORTED_TYPES
from langflow.interface.custom.component import Component
from langflow.utils import validate
from langflow.database.base import session_getter
from langflow.database.models.flow import Flow
from pydantic import Extra
class CustomComponent(Component, extra=Extra.allow):
code: Optional[str]
field_config: dict = {}
code_class_base_inheritance = "CustomComponent"
function_entrypoint_name = "build"
function: Optional[Callable] = None
return_type_valid_list = list(CUSTOM_COMPONENT_SUPPORTED_TYPES.keys())
repr_value: Optional[str] = ""
def __init__(self, **data):
super().__init__(**data)
def custom_repr(self):
return str(self.repr_value)
def build_config(self):
return self.field_config
def _class_template_validation(self, code: str) -> bool:
if not code:
raise HTTPException(
status_code=400,
detail={
"error": self.ERROR_CODE_NULL,
"traceback": "",
},
)
# TODO: Create the logic to validate what the Custom Component
# should have as a prerequisite to be able to execute
return True
def is_check_valid(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]
return build_method["args"]
@property
def get_function_entrypoint_return_type(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]
return build_method["return_type"]
@property
def get_main_class_name(self):
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"):
if base_name in item["bases"]:
method_names = [method["name"] for method in item["methods"]]
if method_name in method_names:
classes.append(item["name"])
# Get just the first item
return next(iter(classes), "")
@property
def build_template_config(self):
tree = self.get_code_tree(self.code)
attributes = [
main_class["attributes"]
for main_class in tree.get("classes")
if main_class["name"] == self.get_main_class_name
]
# Get just the first item
attributes = next(iter(attributes), [])
return super().build_template_config(attributes)
@property
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):
from langflow.processing.process import build_sorted_vertices_with_caching
from langflow.processing.process import process_tweaks
with session_getter() as session:
graph_data = flow.data if (flow := session.get(Flow, flow_id)) else None
if not graph_data:
raise ValueError(f"Flow {flow_id} not found")
if tweaks:
graph_data = process_tweaks(graph_data=graph_data, tweaks=tweaks)
return build_sorted_vertices_with_caching(graph_data)
def list_flows(self):
with session_getter() as session:
flows = session.query(Flow).all()
return flows
def build(self):
raise NotImplementedError

181
src/backend/langflow/interface/custom/directory_reader.py Normal file
View file

@ -0,0 +1,181 @@
import os
import ast
import zlib
class CustomComponentPathValueError(ValueError):
pass
class StringCompressor:
def __init__(self, input_string):
"""Initialize StringCompressor with a string to compress."""
self.input_string = input_string
def compress_string(self):
"""
Compress the initial string and return the compressed data.
"""
# Convert string to bytes
byte_data = self.input_string.encode("utf-8")
# Compress the bytes
self.compressed_data = zlib.compress(byte_data)
return self.compressed_data
def decompress_string(self):
"""
Decompress the compressed data and return the original string.
"""
# Decompress the bytes
decompressed_data = zlib.decompress(self.compressed_data)
# Convert bytes back to string
return decompressed_data.decode("utf-8")
class DirectoryReader:
# Ensure the base path to read the files that contain
# the custom components from this directory.
base_path = ""
def __init__(self, directory_path, compress_code_field=False):
"""
Initialize DirectoryReader with a directory path
and a flag indicating whether to compress the code.
"""
self.directory_path = directory_path
self.compress_code_field = compress_code_field
def get_safe_path(self):
"""Check if the path is valid and return it, or None if it's not."""
return self.directory_path if self.is_valid_path() else None
def is_valid_path(self) -> bool:
"""Check if the directory path is valid by comparing it to the base path."""
fullpath = os.path.normpath(os.path.join(self.directory_path))
return fullpath.startswith(self.base_path)
def is_empty_file(self, file_content):
"""
Check if the file content is empty.
"""
return len(file_content.strip()) == 0
def filter_loaded_components(self, data: dict, with_errors: bool) -> dict:
items = [
{
"name": menu["name"],
"path": menu["path"],
"components": [
component
for component in menu["components"]
if (component["error"] if with_errors else not component["error"])
],
}
for menu in data["menu"]
]
filtred = [menu for menu in items if menu["components"]]
return {"menu": filtred}
def validate_code(self, file_content):
"""
Validate the Python code by trying to parse it with ast.parse.
"""
try:
ast.parse(file_content)
return True
except SyntaxError:
return False
def validate_build(self, file_content):
"""
Check if the file content contains a function named 'build'.
"""
return "def build" in file_content
def read_file_content(self, file_path):
"""
Read and return the content of a file.
"""
if not os.path.isfile(file_path):
return None
with open(file_path, "r") as file:
return file.read()
def get_files(self):
"""
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}'."
)
file_list = []
for root, _, files in os.walk(safe_path):
file_list.extend(
os.path.join(root, filename)
for filename in files
if filename.endswith(".py")
)
return file_list
def find_menu(self, response, menu_name):
"""
Find and return a menu by its name in the response.
"""
return next(
(menu for menu in response["menu"] if menu["name"] == menu_name),
None,
)
def process_file(self, file_path):
"""
Process a file by validating its content and
returning the result and content/error message.
"""
file_content = self.read_file_content(file_path)
if file_content is None:
return False, f"Could not read {file_path}"
if self.is_empty_file(file_content):
return False, "Empty file"
elif not self.validate_code(file_content):
return False, "Syntax error"
elif not self.validate_build(file_content):
return False, "Missing build function"
else:
if self.compress_code_field:
file_content = str(StringCompressor(file_content).compress_string())
return True, file_content
def build_component_menu_list(self, file_paths):
"""
Build a list of menus with their components
from the .py files in the directory.
"""
response = {"menu": []}
for file_path in file_paths:
menu_name = os.path.basename(os.path.dirname(file_path))
filename = os.path.basename(file_path)
validation_result, result_content = self.process_file(file_path)
menu_result = self.find_menu(response, menu_name) or {
"name": menu_name,
"path": os.path.dirname(file_path),
"components": [],
}
component_info = {
"name": filename.split(".")[0],
"file": filename,
"code": result_content if validation_result else "",
"error": "" if validation_result else result_content,
}
menu_result["components"].append(component_info)
if menu_result not in response["menu"]:
response["menu"].append(menu_result)
return response

29
src/backend/langflow/interface/custom/schema.py Normal file
View file

@ -0,0 +1,29 @@
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]
bases: list
attributes: list
methods: list
init: Optional[dict] = Field(default_factory=dict)
class CallableCodeDetails(BaseModel):
"""
A dataclass for storing details about a callable.
"""
name: str
doc: Optional[str]
args: list
body: list
return_type: Optional[str]

14
src/backend/langflow/interface/importing/utils.py
View file

@ -9,6 +9,7 @@ from langchain.base_language import BaseLanguageModel
from langchain.chains.base import Chain
from langchain.chat_models.base import BaseChatModel
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
@ -47,6 +48,7 @@ def import_by_type(_type: str, name: str) -> Any:
"utilities": import_utility,
"output_parsers": import_output_parser,
"retrievers": import_retriever,
"custom_components": import_custom_component,
}
if _type == "llms":
key = "chat" if "chat" in name.lower() else "llm"
@ -57,6 +59,13 @@ def import_by_type(_type: str, name: str) -> Any:
return loaded_func(name)
def import_custom_component(custom_component: str) -> CustomComponent:
"""Import custom component from custom component name"""
return import_class(
f"langflow.interface.custom.custom_component.{custom_component}"
)
def import_output_parser(output_parser: str) -> Any:
"""Import output parser from output parser name"""
return import_module(f"from langchain.output_parsers import {output_parser}")
@ -172,3 +181,8 @@ def get_function(code):
function_name = validate.extract_function_name(code)
return validate.create_function(code, function_name)
def get_function_custom(code):
class_name = validate.extract_class_name(code)
return validate.create_class(code, class_name)

87
src/backend/langflow/interface/initialize/loading.py
View file

@ -1,21 +1,23 @@
import contextlib
import json
from typing import Any, Callable, Dict, List, Sequence, Type
from typing import Any, Callable, Dict, Sequence, Type
from langchain.agents import ZeroShotAgent
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
from langflow.interface.initialize.vector_store import vecstore_initializer
from langchain.schema import Document, BaseOutputParser
from pydantic import ValidationError
from langflow.interface.importing.utils import (
get_function,
get_function_custom,
import_by_type,
)
from langflow.interface.custom_lists import CUSTOM_NODES
from langflow.interface.importing.utils import get_function, import_by_type
from langflow.interface.agents.base import agent_creator
from langflow.interface.toolkits.base import toolkits_creator
from langflow.interface.chains.base import chain_creator
@ -95,12 +97,21 @@ def instantiate_based_on_type(class_object, base_type, node_type, params):
return instantiate_retriever(node_type, class_object, params)
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)
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):
class_object = get_function_custom(params.pop("code"))
custom_component = class_object()
built_object = custom_component.build(**params)
return built_object, {"repr": custom_component.custom_repr()}
def instantiate_wrapper(node_type, class_object, params):
if node_type in wrapper_creator.from_method_nodes:
method = wrapper_creator.from_method_nodes[node_type]
@ -199,68 +210,8 @@ def instantiate_agent(node_type, class_object: Type[agent_module.Agent], params:
def instantiate_prompt(node_type, class_object, params: Dict):
if node_type == "ZeroShotPrompt":
if "tools" not in params:
params["tools"] = []
return ZeroShotAgent.create_prompt(**params)
elif "MessagePromptTemplate" in node_type:
# Then we only need the template
from_template_params = {
"template": params.pop("prompt", params.pop("template", ""))
}
if not from_template_params.get("template"):
raise ValueError("Prompt template is required")
prompt = class_object.from_template(**from_template_params)
elif node_type == "ChatPromptTemplate":
prompt = class_object.from_messages(**params)
else:
prompt = class_object(**params)
format_kwargs: Dict[str, Any] = {}
for input_variable in prompt.input_variables:
if input_variable in params:
variable = params[input_variable]
if isinstance(variable, str):
format_kwargs[input_variable] = variable
elif isinstance(variable, BaseOutputParser) and hasattr(
variable, "get_format_instructions"
):
format_kwargs[input_variable] = variable.get_format_instructions()
elif isinstance(variable, List) and all(
isinstance(item, Document) for item in variable
):
# Format document to contain page_content and metadata
# as one string separated by a newline
if len(variable) > 1:
content = "\n".join(
[item.page_content for item in variable if item.page_content]
)
else:
content = variable[0].page_content
# content could be a json list of strings
with contextlib.suppress(json.JSONDecodeError):
content = json.loads(content)
if isinstance(content, list):
content = ",".join([str(item) for item in content])
format_kwargs[input_variable] = content
# handle_keys will be a list but it does not exist yet
# so we need to create it
if (
isinstance(variable, List)
and all(isinstance(item, Document) for item in variable)
) or (
isinstance(variable, BaseOutputParser)
and hasattr(variable, "get_format_instructions")
):
if "handle_keys" not in format_kwargs:
format_kwargs["handle_keys"] = []
# Add the handle_keys to the list
format_kwargs["handle_keys"].append(input_variable)
params, prompt = handle_node_type(node_type, class_object, params)
format_kwargs = handle_format_kwargs(prompt, params)
return prompt, format_kwargs
@ -363,6 +314,8 @@ def instantiate_textsplitter(
):
try:
documents = params.pop("documents")
if not isinstance(documents, list):
documents = [documents]
except KeyError as exc:
raise ValueError(
"The source you provided did not load correctly or was empty."

103
src/backend/langflow/interface/initialize/utils.py Normal file
View file

@ -0,0 +1,103 @@
import contextlib
import json
from typing import Any, Dict, List
from langchain.agents import ZeroShotAgent
from langchain.schema import Document, BaseOutputParser
def handle_node_type(node_type, class_object, params: Dict):
if node_type == "ZeroShotPrompt":
params = check_tools_in_params(params)
prompt = ZeroShotAgent.create_prompt(**params)
elif "MessagePromptTemplate" in node_type:
prompt = instantiate_from_template(class_object, params)
elif node_type == "ChatPromptTemplate":
prompt = class_object.from_messages(**params)
else:
prompt = class_object(**params)
return params, prompt
def check_tools_in_params(params: Dict):
if "tools" not in params:
params["tools"] = []
return params
def instantiate_from_template(class_object, params: Dict):
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)
def handle_format_kwargs(prompt, params: Dict):
format_kwargs: Dict[str, Any] = {}
for input_variable in prompt.input_variables:
if input_variable in params:
format_kwargs = handle_variable(params, input_variable, format_kwargs)
return format_kwargs
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"
):
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)
if needs_handle_keys(variable):
format_kwargs = add_handle_keys(input_variable, format_kwargs)
return format_kwargs
def is_instance_of_list_or_document(variable):
return (
isinstance(variable, List)
and all(isinstance(item, Document) for item in variable)
or isinstance(variable, Document)
)
def format_document(variable, input_variable: str, format_kwargs: Dict):
variable = variable if isinstance(variable, List) else [variable]
content = format_content(variable)
format_kwargs[input_variable] = content
return format_kwargs
def format_content(variable):
if len(variable) > 1:
return "\n".join([item.page_content for item in variable if item.page_content])
content = variable[0].page_content
return try_to_load_json(content)
def try_to_load_json(content):
with contextlib.suppress(json.JSONDecodeError):
content = json.loads(content)
if isinstance(content, list):
content = ",".join([str(item) for item in content])
return content
def needs_handle_keys(variable):
return is_instance_of_list_or_document(variable) or (
isinstance(variable, BaseOutputParser)
and hasattr(variable, "get_format_instructions")
)
def add_handle_keys(input_variable: str, format_kwargs: Dict):
if "handle_keys" not in format_kwargs:
format_kwargs["handle_keys"] = []
format_kwargs["handle_keys"].append(input_variable)
return format_kwargs

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

@ -13,6 +13,7 @@ from langflow.interface.vector_store.base import vectorstore_creator
from langflow.interface.wrappers.base import wrapper_creator
from langflow.interface.output_parsers.base import output_parser_creator
from langflow.interface.retrievers.base import retriever_creator
from langflow.interface.custom.base import custom_component_creator
def get_type_dict():
@ -32,6 +33,7 @@ def get_type_dict():
"utilities": utility_creator.to_list(),
"outputParsers": output_parser_creator.to_list(),
"retrievers": retriever_creator.to_list(),
"custom_components": custom_component_creator.to_list(),
}

2
src/backend/langflow/interface/tools/base.py
View file

@ -55,7 +55,7 @@ TOOL_INPUTS = {
show=True,
value="",
suffixes=[".json", ".yaml", ".yml"],
fileTypes=["json", "yaml", "yml"],
file_types=["json", "yaml", "yml"],
),
}

5
src/backend/langflow/interface/tools/constants.py
View file

@ -9,7 +9,10 @@ from langchain.agents.load_tools import (
from langchain.tools.json.tool import JsonSpec
from langflow.interface.importing.utils import import_class
from langflow.interface.tools.custom import PythonFunctionTool, PythonFunction
from langflow.interface.tools.custom import (
PythonFunctionTool,
PythonFunction,
)
FILE_TOOLS = {"JsonSpec": JsonSpec}
CUSTOM_TOOLS = {

4
src/backend/langflow/interface/tools/custom.py
View file

@ -34,8 +34,6 @@ class Function(BaseModel):
class PythonFunctionTool(Function, Tool):
"""Python function"""
name: str = "Custom Tool"
description: str
code: str
@ -49,6 +47,4 @@ class PythonFunctionTool(Function, Tool):
class PythonFunction(Function):
"""Python function"""
code: str

316
src/backend/langflow/interface/types.py
View file

@ -1,7 +1,9 @@
from langflow.interface.agents.base import agent_creator
from langflow.interface.chains.base import chain_creator
from langflow.interface.custom.constants import CUSTOM_COMPONENT_SUPPORTED_TYPES
from langflow.interface.document_loaders.base import documentloader_creator
from langflow.interface.embeddings.base import embedding_creator
from langflow.interface.importing.utils import get_function_custom
from langflow.interface.llms.base import llm_creator
from langflow.interface.memories.base import memory_creator
from langflow.interface.prompts.base import prompt_creator
@ -12,9 +14,28 @@ from langflow.interface.utilities.base import utility_creator
from langflow.interface.vector_store.base import vectorstore_creator
from langflow.interface.wrappers.base import wrapper_creator
from langflow.interface.output_parsers.base import output_parser_creator
from langflow.interface.custom.base import custom_component_creator
from langflow.interface.custom.custom_component import CustomComponent
from langflow.template.field.base import TemplateField
from langflow.template.frontend_node.constants import CLASSES_TO_REMOVE
from langflow.template.frontend_node.custom_components import (
CustomComponentFrontendNode,
)
from langflow.interface.retrievers.base import retriever_creator
from langflow.interface.custom.directory_reader import DirectoryReader
from langflow.utils.logger import logger
from langflow.utils.util import get_base_classes
from langflow.api.utils import merge_nested_dicts
import re
import warnings
import traceback
from fastapi import HTTPException
# Used to get the base_classes list
def get_type_list():
"""Get a list of all langchain types"""
all_types = build_langchain_types_dict()
@ -29,7 +50,6 @@ def get_type_list():
def build_langchain_types_dict(): # sourcery skip: dict-assign-update-to-union
"""Build a dictionary of all langchain types"""
all_types = {}
creators = [
@ -48,6 +68,7 @@ def build_langchain_types_dict(): # sourcery skip: dict-assign-update-to-union
utility_creator,
output_parser_creator,
retriever_creator,
custom_component_creator,
]
all_types = {}
@ -55,7 +76,298 @@ def build_langchain_types_dict(): # sourcery skip: dict-assign-update-to-union
created_types = creator.to_dict()
if created_types[creator.type_name].values():
all_types.update(created_types)
return all_types
langchain_types_dict = build_langchain_types_dict()
def process_type(field_type: str):
return "prompt" if field_type == "Prompt" else field_type
# TODO: Move to correct place
def add_new_custom_field(
template,
field_name: str,
field_type: str,
field_value: str,
field_required: bool,
field_config: dict,
):
# Check field_config if any of the keys are in it
# if it is, update the value
display_name = field_config.pop("display_name", field_name)
field_type = field_config.pop("field_type", field_type)
field_type = process_type(field_type)
field_value = field_config.pop("value", field_value)
field_advanced = field_config.pop("advanced", False)
if "name" in field_config:
warnings.warn(
"The 'name' key in field_config is used to build the object and can't be changed."
)
field_config.pop("name", None)
required = field_config.pop("required", field_required)
placeholder = field_config.pop("placeholder", "")
new_field = TemplateField(
name=field_name,
field_type=field_type,
value=field_value,
show=True,
required=required,
advanced=field_advanced,
placeholder=placeholder,
display_name=display_name,
**field_config,
)
template.get("template")[field_name] = new_field.to_dict()
template.get("custom_fields")[field_name] = None
return template
# TODO: Move to correct place
def add_code_field(template, raw_code, field_config):
# Field with the Python code to allow update
code_field = {
"code": {
"dynamic": True,
"required": True,
"placeholder": "",
"show": True,
"multiline": True,
"value": raw_code,
"password": False,
"name": "code",
"advanced": field_config.pop("advanced", False),
"type": "code",
"list": False,
}
}
template.get("template")["code"] = code_field.get("code")
return template
def extract_type_from_optional(field_type):
"""
Extract the type from a string formatted as "Optional[<type>]".
Parameters:
field_type (str): The string from which to extract the type.
Returns:
str: The extracted type, or an empty string if no type was found.
"""
match = re.search(r"\[(.*?)\]", field_type)
return match[1] if match else None
def build_frontend_node(custom_component: CustomComponent):
"""Build a frontend node for a custom component"""
try:
return (
CustomComponentFrontendNode().to_dict().get(type(custom_component).__name__)
)
except Exception as exc:
logger.error(f"Error while building base frontend node: {exc}")
return None
def update_display_name_and_description(frontend_node, template_config):
"""Update the display name and description of a frontend node"""
if "display_name" in template_config:
frontend_node["display_name"] = template_config["display_name"]
if "description" in template_config:
frontend_node["description"] = template_config["description"]
def build_field_config(custom_component):
"""Build the field configuration for a custom component"""
try:
custom_class = get_function_custom(custom_component.code)
return custom_class().build_config()
except Exception as exc:
logger.error(f"Error while building field config: {exc}")
return {}
def add_extra_fields(frontend_node, field_config, function_args):
"""Add extra fields to the frontend node"""
if function_args is None:
return
# sort function_args which is a list of dicts
function_args.sort(key=lambda x: x["name"])
for extra_field in function_args:
if "name" not in extra_field or extra_field["name"] == "self":
continue
field_name, field_type, field_value, field_required = get_field_properties(
extra_field
)
config = field_config.get(field_name, {})
frontend_node = add_new_custom_field(
frontend_node,
field_name,
field_type,
field_value,
field_required,
config,
)
def get_field_properties(extra_field):
"""Get the properties of an extra field"""
field_name = extra_field["name"]
field_type = extra_field.get("type", "str")
field_value = extra_field.get("default", "")
field_required = "optional" not in field_type.lower()
if not field_required:
field_type = extract_type_from_optional(field_type)
return field_name, field_type, field_value, field_required
def add_base_classes(frontend_node, return_type):
"""Add base classes to the frontend node"""
if return_type not in CUSTOM_COMPONENT_SUPPORTED_TYPES or return_type is None:
raise HTTPException(
status_code=400,
detail={
"error": (
"Invalid return type should be one of: "
f"{list(CUSTOM_COMPONENT_SUPPORTED_TYPES.keys())}"
),
"traceback": traceback.format_exc(),
},
)
return_type_instance = CUSTOM_COMPONENT_SUPPORTED_TYPES.get(return_type)
base_classes = get_base_classes(return_type_instance)
for base_class in base_classes:
if base_class not in CLASSES_TO_REMOVE:
frontend_node.get("base_classes").append(base_class)
def build_langchain_template_custom_component(custom_component: CustomComponent):
"""Build a custom component template for the langchain"""
frontend_node = build_frontend_node(custom_component)
if frontend_node is None:
return None
template_config = custom_component.build_template_config
update_display_name_and_description(frontend_node, template_config)
field_config = build_field_config(custom_component)
add_extra_fields(
frontend_node, field_config, custom_component.get_function_entrypoint_args
)
frontend_node = add_code_field(
frontend_node, custom_component.code, field_config.get("code", {})
)
add_base_classes(
frontend_node, custom_component.get_function_entrypoint_return_type
)
return frontend_node
def load_files_from_path(path: str):
"""Load all files from a given path"""
reader = DirectoryReader(path, False)
return reader.get_files()
def build_and_validate_all_files(reader, file_list):
"""Build and validate all files"""
data = reader.build_component_menu_list(file_list)
valid_components = reader.filter_loaded_components(data=data, with_errors=False)
invalid_components = reader.filter_loaded_components(data=data, with_errors=True)
return valid_components, invalid_components
def build_valid_menu(valid_components):
"""Build the valid menu"""
valid_menu = {}
for menu_item in valid_components["menu"]:
menu_name = menu_item["name"]
valid_menu[menu_name] = {}
for component in menu_item["components"]:
try:
component_name = component["name"]
component_code = component["code"]
component_extractor = CustomComponent(code=component_code)
component_extractor.is_check_valid()
component_template = build_langchain_template_custom_component(
component_extractor
)
valid_menu[menu_name][component_name] = component_template
except Exception as exc:
logger.error(f"Error while building custom component: {exc}")
return valid_menu
def build_invalid_menu(invalid_components):
"""Build the invalid menu"""
invalid_menu = {}
for menu_item in invalid_components["menu"]:
menu_name = menu_item["name"]
invalid_menu[menu_name] = {}
for component in menu_item["components"]:
try:
component_name = component["name"]
component_code = component["code"]
component_template = (
CustomComponentFrontendNode(
description="ERROR - Check your Python Code",
display_name=f"ERROR - {component_name}",
)
.to_dict()
.get(type(CustomComponent()).__name__)
)
component_template.get("template").get("code")["value"] = component_code
invalid_menu[menu_name][component_name] = component_template
except Exception as exc:
logger.error(f"Error while creating custom component: {exc}")
return invalid_menu
def build_langchain_custom_component_list_from_path(path: str):
"""Build a list of custom components for the langchain from a given path"""
file_list = load_files_from_path(path)
reader = DirectoryReader(path, False)
valid_components, invalid_components = build_and_validate_all_files(
reader, file_list
)
valid_menu = build_valid_menu(valid_components)
invalid_menu = build_invalid_menu(invalid_components)
return merge_nested_dicts(valid_menu, invalid_menu)

16
src/backend/langflow/main.py
View file

@ -8,10 +8,12 @@ from fastapi.staticfiles import StaticFiles
from langflow.api import router
from langflow.database.base import create_db_and_tables
from langflow.interface.utils import setup_llm_caching
from langflow.utils.logger import configure
def create_app():
"""Create the FastAPI app and include the router."""
configure()
app = FastAPI()
@ -78,10 +80,16 @@ def setup_app(static_files_dir: Optional[Path] = None) -> FastAPI:
return app
app = create_app()
if __name__ == "__main__":
import uvicorn
from langflow.utils.util import get_number_of_workers
uvicorn.run(app, host="127.0.0.1", port=7860)
configure()
uvicorn.run(
create_app,
host="127.0.0.1",
port=7860,
workers=get_number_of_workers(),
log_level="debug",
reload=True,
)

2
src/backend/langflow/processing/base.py
View file

@ -22,7 +22,7 @@ async def get_result_and_steps(langchain_object, inputs: Union[dict, str], **kwa
try:
fix_memory_inputs(langchain_object)
except Exception as exc:
logger.error(exc)
logger.error(f"Error fixing memory inputs: {exc}")
try:
async_callbacks = [AsyncStreamingLLMCallbackHandler(**kwargs)]

7
src/backend/langflow/processing/process.py
View file

@ -85,12 +85,17 @@ def get_input_str_if_only_one_input(inputs: dict) -> Optional[str]:
return list(inputs.values())[0] if len(inputs) == 1 else None
def process_graph_cached(data_graph: Dict[str, Any], inputs: Optional[dict] = None):
def process_graph_cached(
data_graph: Dict[str, Any], inputs: Optional[dict] = None, clear_cache=False
):
"""
Process graph by extracting input variables and replacing ZeroShotPrompt
with PromptTemplate,then run the graph and return the result and thought.
"""
# Load langchain object
if clear_cache:
build_sorted_vertices_with_caching.clear_cache()
logger.debug("Cleared cache")
langchain_object, artifacts = build_sorted_vertices_with_caching(data_graph)
logger.debug("Loaded LangChain object")
if inputs is None:

33
src/backend/langflow/settings.py
View file

@ -1,10 +1,13 @@
import os
from typing import Optional
from typing import Optional, List
from pathlib import Path
import yaml
from pydantic import BaseSettings, root_validator
from langflow.utils.logger import logger
BASE_COMPONENTS_PATH = Path(__file__).parent / "components"
class Settings(BaseSettings):
chains: dict = {}
@ -22,13 +25,16 @@ class Settings(BaseSettings):
textsplitters: dict = {}
utilities: dict = {}
output_parsers: dict = {}
custom_components: dict = {}
dev: bool = False
database_url: Optional[str] = None
cache: str = "InMemoryCache"
remove_api_keys: bool = False
component_path: List[Path]
@root_validator(pre=True)
def set_database_url(cls, values):
def set_env_variables(cls, values):
if "database_url" not in values:
logger.debug(
"No database_url provided, trying LANGFLOW_DATABASE_URL env variable"
@ -38,6 +44,19 @@ class Settings(BaseSettings):
else:
logger.debug("No DATABASE_URL env variable, using sqlite database")
values["database_url"] = "sqlite:///./langflow.db"
if not values.get("component_path"):
values["component_path"] = [BASE_COMPONENTS_PATH]
elif BASE_COMPONENTS_PATH not in values["component_path"]:
values["component_path"].append(BASE_COMPONENTS_PATH)
if os.getenv("LANGFLOW_COMPONENT_PATH"):
langflow_component_path = Path(os.getenv("LANGFLOW_COMPONENT_PATH"))
if (
langflow_component_path.exists()
and langflow_component_path not in values["component_path"]
):
values["component_path"].append(langflow_component_path)
return values
class Config:
@ -68,12 +87,20 @@ class Settings(BaseSettings):
self.documentloaders = new_settings.documentloaders or {}
self.retrievers = new_settings.retrievers or {}
self.output_parsers = new_settings.output_parsers or {}
self.custom_components = new_settings.custom_components or {}
self.component_path = new_settings.component_path or []
self.dev = dev
def update_settings(self, **kwargs):
for key, value in kwargs.items():
if hasattr(self, key):
setattr(self, key, value)
if isinstance(getattr(self, key), list):
if isinstance(value, list):
getattr(self, key).extend(value)
else:
getattr(self, key).append(value)
else:
setattr(self, key, value)
def save_settings_to_yaml(settings: Settings, file_path: str):

37
src/backend/langflow/template/field/base.py
View file

@ -6,23 +6,58 @@ from pydantic import BaseModel
class TemplateFieldCreator(BaseModel, ABC):
field_type: str = "str"
"""The type of field this is. Default is a string."""
required: bool = False
"""Specifies if the field is required. Defaults to False."""
placeholder: str = ""
"""A placeholder string for the field. Default is an empty string."""
is_list: bool = False
"""Defines if the field is a list. Default is False."""
show: bool = True
"""Should the field be shown. Defaults to True."""
multiline: bool = False
"""Defines if the field will allow the user to open a text editor. Default is False."""
value: Any = None
"""The value of the field. Default is None."""
suffixes: list[str] = []
fileTypes: list[str] = []
"""List of suffixes for a file field. Default is an empty list."""
file_types: list[str] = []
"""List of file types associated with the field. Default is an empty list. (duplicate)"""
file_path: Union[str, None] = None
"""The file path of the field if it is a file. Defaults to None."""
password: bool = False
"""Specifies if the field is a password. Defaults to False."""
options: list[str] = []
"""List of options for the field. Only used when is_list=True. Default is an empty list."""
name: str = ""
"""Name of the field. Default is an empty string."""
display_name: Optional[str] = None
"""Display name of the field. Defaults to None."""
advanced: bool = False
"""Specifies if the field will an advanced parameter (hidden). Defaults to False."""
input_types: list[str] = []
"""List of input types for the handle when the field has more than one type. Default is an empty list."""
dynamic: bool = False
"""Specifies if the field is dynamic. Defaults to False."""
info: Optional[str] = ""
"""Additional information about the field to be shown in the tooltip. Defaults to an empty string."""
def to_dict(self):
result = self.dict()

2
src/backend/langflow/template/frontend_node/__init__.py
View file

@ -9,6 +9,7 @@ from langflow.template.frontend_node import (
vectorstores,
documentloaders,
textsplitters,
custom_components,
)
__all__ = [
@ -22,4 +23,5 @@ __all__ = [
"vectorstores",
"documentloaders",
"textsplitters",
"custom_components",
]

2
src/backend/langflow/template/frontend_node/agents.py
View file

@ -145,7 +145,7 @@ class CSVAgentNode(FrontendNode):
name="path",
value="",
suffixes=[".csv"],
fileTypes=["csv"],
file_types=["csv"],
),
TemplateField(
field_type="BaseLanguageModel",

25
src/backend/langflow/template/frontend_node/base.py
View file

@ -5,13 +5,14 @@ from typing import List, Optional
from pydantic import BaseModel, Field
from langflow.template.frontend_node.formatter import field_formatters
from langflow.template.frontend_node.constants import FORCE_SHOW_FIELDS
from langflow.template.frontend_node.constants import (
CLASSES_TO_REMOVE,
FORCE_SHOW_FIELDS,
)
from langflow.template.field.base import TemplateField
from langflow.template.template.base import Template
from langflow.utils import constants
CLASSES_TO_REMOVE = ["Serializable", "BaseModel", "object"]
class FieldFormatters(BaseModel):
formatters = {
@ -51,14 +52,7 @@ class FrontendNode(BaseModel):
custom_fields: defaultdict = defaultdict(list)
output_types: List[str] = []
field_formatters: FieldFormatters = Field(default_factory=FieldFormatters)
def process_base_classes(self) -> None:
"""Removes unwanted base classes from the list of base classes."""
self.base_classes = [
base_class
for base_class in self.base_classes
if base_class not in CLASSES_TO_REMOVE
]
beta: bool = False
# field formatters is an instance attribute but it is not used in the class
# so we need to create a method to get it
@ -70,6 +64,14 @@ class FrontendNode(BaseModel):
"""Sets the documentation of the frontend node."""
self.documentation = documentation
def process_base_classes(self) -> None:
"""Removes unwanted base classes from the list of base classes."""
self.base_classes = [
base_class
for base_class in self.base_classes
if base_class not in CLASSES_TO_REMOVE
]
def to_dict(self) -> dict:
"""Returns a dict representation of the frontend node."""
self.process_base_classes()
@ -82,6 +84,7 @@ class FrontendNode(BaseModel):
"custom_fields": self.custom_fields,
"output_types": self.output_types,
"documentation": self.documentation,
"beta": self.beta,
},
}

3
src/backend/langflow/template/frontend_node/constants.py
View file

@ -63,3 +63,6 @@ You can change this to use other APIs like JinaChat, LocalAI and Prem.
INPUT_KEY_INFO = """The variable to be used as Chat Input when more than one variable is available."""
OUTPUT_KEY_INFO = """The variable to be used as Chat Output (e.g. answer in a ConversationalRetrievalChain)"""
CLASSES_TO_REMOVE = ["Serializable", "BaseModel", "object"]

31
src/backend/langflow/template/frontend_node/custom_components.py Normal file
View file

@ -0,0 +1,31 @@
from langflow.template.field.base import TemplateField
from langflow.template.frontend_node.base import FrontendNode
from langflow.template.template.base import Template
from langflow.interface.custom.constants import DEFAULT_CUSTOM_COMPONENT_CODE
class CustomComponentFrontendNode(FrontendNode):
name: str = "CustomComponent"
display_name: str = "Custom Component"
beta: bool = True
template: Template = Template(
type_name="CustomComponent",
fields=[
TemplateField(
field_type="code",
required=True,
placeholder="",
is_list=False,
show=True,
value=DEFAULT_CUSTOM_COMPONENT_CODE,
name="code",
advanced=False,
dynamic=True,
)
],
)
description: str = "Create any custom component you want!"
base_classes: list[str] = []
def to_dict(self):
return super().to_dict()

2
src/backend/langflow/template/frontend_node/documentloaders.py
View file

@ -14,7 +14,7 @@ def build_file_field(
name=name,
value="",
suffixes=suffixes,
fileTypes=fileTypes,
file_types=fileTypes,
)

2
src/backend/langflow/template/frontend_node/llms.py
View file

@ -19,7 +19,7 @@ class LLMFrontendNode(FrontendNode):
name="credentials",
value="",
suffixes=[".json"],
fileTypes=["json"],
file_types=["json"],
)
)

4
src/backend/langflow/template/frontend_node/tools.py
View file

@ -1,7 +1,9 @@
from langflow.template.field.base import TemplateField
from langflow.template.frontend_node.base import FrontendNode
from langflow.template.template.base import Template
from langflow.utils.constants import DEFAULT_PYTHON_FUNCTION
from langflow.utils.constants import (
DEFAULT_PYTHON_FUNCTION,
)
class ToolNode(FrontendNode):

34
src/backend/langflow/utils/constants.py
View file

@ -17,18 +17,29 @@ CHAT_OPENAI_MODELS = [
]
ANTHROPIC_MODELS = [
"claude-v1", # largest model, ideal for a wide range of more complex tasks.
"claude-v1-100k", # An enhanced version of claude-v1 with a 100,000 token (roughly 75,000 word) context window.
"claude-instant-v1", # A smaller model with far lower latency, sampling at roughly 40 words/sec!
"claude-instant-v1-100k", # Like claude-instant-v1 with a 100,000 token context window but retains its performance.
# largest model, ideal for a wide range of more complex tasks.
"claude-v1",
# An enhanced version of claude-v1 with a 100,000 token (roughly 75,000 word) context window.
"claude-v1-100k",
# A smaller model with far lower latency, sampling at roughly 40 words/sec!
"claude-instant-v1",
# Like claude-instant-v1 with a 100,000 token context window but retains its performance.
"claude-instant-v1-100k",
# Specific sub-versions of the above models:
"claude-v1.3", # Vs claude-v1.2: better instruction-following, code, and non-English dialogue and writing.
"claude-v1.3-100k", # An enhanced version of claude-v1.3 with a 100,000 token (roughly 75,000 word) context window.
"claude-v1.2", # Vs claude-v1.1: small adv in general helpfulness, instruction following, coding, and other tasks.
"claude-v1.0", # An earlier version of claude-v1.
"claude-instant-v1.1", # Latest version of claude-instant-v1. Better than claude-instant-v1.0 at most tasks.
"claude-instant-v1.1-100k", # Version of claude-instant-v1.1 with a 100K token context window.
"claude-instant-v1.0", # An earlier version of claude-instant-v1.
# Vs claude-v1.2: better instruction-following, code, and non-English dialogue and writing.
"claude-v1.3",
# An enhanced version of claude-v1.3 with a 100,000 token (roughly 75,000 word) context window.
"claude-v1.3-100k",
# Vs claude-v1.1: small adv in general helpfulness, instruction following, coding, and other tasks.
"claude-v1.2",
# An earlier version of claude-v1.
"claude-v1.0",
# Latest version of claude-instant-v1. Better than claude-instant-v1.0 at most tasks.
"claude-instant-v1.1",
# Version of claude-instant-v1.1 with a 100K token context window.
"claude-instant-v1.1-100k",
# An earlier version of claude-instant-v1.
"claude-instant-v1.0",
]
DEFAULT_PYTHON_FUNCTION = """
@ -36,4 +47,5 @@ def python_function(text: str) -> str:
\"\"\"This is a default python function that returns the input text\"\"\"
return text
"""
DIRECT_TYPES = ["str", "bool", "code", "int", "float", "Any", "prompt"]

2
src/backend/langflow/utils/logger.py
View file

@ -6,7 +6,7 @@ from rich.logging import RichHandler
logger = logging.getLogger("langflow")
def configure(log_level: str = "INFO", log_file: Path = None): # type: ignore
def configure(log_level: str = "DEBUG", log_file: Path = None): # type: ignore
log_format = "%(asctime)s - %(levelname)s - %(message)s"
log_level_value = getattr(logging, log_level.upper(), logging.INFO)

2
src/backend/langflow/utils/types.py Normal file
View file

@ -0,0 +1,2 @@
class Prompt:
pass

329
src/backend/langflow/utils/util.py
View file

@ -1,13 +1,15 @@
import importlib
import inspect
import re
import inspect
import importlib
from functools import wraps
from typing import Dict, Optional
from typing import Optional, Dict, Any, Union
from docstring_parser import parse # type: ignore
from langflow.template.frontend_node.constants import FORCE_SHOW_FIELDS
from langflow.utils import constants
from langflow.utils.logger import logger
from multiprocess import cpu_count # type: ignore
def build_template_from_function(
@ -214,111 +216,6 @@ def get_default_factory(module: str, function: str):
return None
def format_dict(d, name: Optional[str] = None):
"""
Formats a dictionary by removing certain keys and modifying the
values of other keys.
Args:
d: the dictionary to format
name: the name of the class to format
Returns:
A new dictionary with the desired modifications applied.
"""
# Process remaining keys
for key, value in d.items():
if key == "_type":
continue
_type = value["type"]
if not isinstance(_type, str):
_type = _type.__name__
# Remove 'Optional' wrapper
if "Optional" in _type:
_type = _type.replace("Optional[", "")[:-1]
# Check for list type
if "List" in _type or "Sequence" in _type or "Set" in _type:
_type = (
_type.replace("List[", "")
.replace("Sequence[", "")
.replace("Set[", "")[:-1]
)
value["list"] = True
else:
value["list"] = False
# Replace 'Mapping' with 'dict'
if "Mapping" in _type:
_type = _type.replace("Mapping", "dict")
# Change type from str to Tool
value["type"] = "Tool" if key in ["allowed_tools"] else _type
value["type"] = "int" if key in ["max_value_length"] else value["type"]
# Show or not field
value["show"] = bool(
(value["required"] and key not in ["input_variables"])
or key in FORCE_SHOW_FIELDS
or "api_key" in key
)
# Add password field
value["password"] = any(
text in key.lower() for text in ["password", "token", "api", "key"]
)
# Add multline
value["multiline"] = key in [
"suffix",
"prefix",
"template",
"examples",
"code",
"headers",
"format_instructions",
]
# Replace dict type with str
if "dict" in value["type"].lower():
value["type"] = "code"
if key == "dict_":
value["type"] = "file"
value["suffixes"] = [".json", ".yaml", ".yml"]
value["fileTypes"] = ["json", "yaml", "yml"]
# Replace default value with actual value
if "default" in value:
value["value"] = value["default"]
value.pop("default")
if key == "headers":
value[
"value"
] = """{'Authorization':
'Bearer <token>'}"""
# Add options to openai
if name == "OpenAI" and key == "model_name":
value["options"] = constants.OPENAI_MODELS
value["list"] = True
value["value"] = constants.OPENAI_MODELS[0]
elif name == "ChatOpenAI" and key == "model_name":
value["options"] = constants.CHAT_OPENAI_MODELS
value["list"] = True
value["value"] = constants.CHAT_OPENAI_MODELS[0]
elif (name == "Anthropic" or name == "ChatAnthropic") and key == "model_name":
value["options"] = constants.ANTHROPIC_MODELS
value["list"] = True
value["value"] = constants.ANTHROPIC_MODELS[0]
return d
def update_verbose(d: dict, new_value: bool) -> dict:
"""
Recursively updates the value of the 'verbose' key in a dictionary.
@ -349,3 +246,219 @@ def sync_to_async(func):
return func(*args, **kwargs)
return async_wrapper
def format_dict(
dictionary: Dict[str, Any], class_name: Optional[str] = None
) -> Dict[str, Any]:
"""
Formats a dictionary by removing certain keys and modifying the
values of other keys.
Returns:
A new dictionary with the desired modifications applied.
"""
for key, value in dictionary.items():
if key == "_type":
continue
_type: Union[str, type] = get_type(value)
_type = remove_optional_wrapper(_type)
_type = check_list_type(_type, value)
_type = replace_mapping_with_dict(_type)
value["type"] = get_formatted_type(key, _type)
value["show"] = should_show_field(value, key)
value["password"] = is_password_field(key)
value["multiline"] = is_multiline_field(key)
replace_dict_type_with_code(value)
if key == "dict_":
set_dict_file_attributes(value)
replace_default_value_with_actual(value)
if key == "headers":
set_headers_value(value)
add_options_to_field(value, class_name, key)
return dictionary
def get_type(value: Any) -> Union[str, type]:
"""
Retrieves the type value from the dictionary.
Returns:
The type value.
"""
_type = value["type"]
return _type if isinstance(_type, str) else _type.__name__
def remove_optional_wrapper(_type: Union[str, type]) -> str:
"""
Removes the 'Optional' wrapper from the type string.
Returns:
The type string with the 'Optional' wrapper removed.
"""
if isinstance(_type, type):
_type = str(_type)
if "Optional" in _type:
_type = _type.replace("Optional[", "")[:-1]
return _type
def check_list_type(_type: str, value: Dict[str, Any]) -> str:
"""
Checks if the type is a list type and modifies the value accordingly.
Returns:
The modified type string.
"""
if any(list_type in _type for list_type in ["List", "Sequence", "Set"]):
_type = (
_type.replace("List[", "").replace("Sequence[", "").replace("Set[", "")[:-1]
)
value["list"] = True
else:
value["list"] = False
return _type
def replace_mapping_with_dict(_type: str) -> str:
"""
Replaces 'Mapping' with 'dict' in the type string.
Returns:
The modified type string.
"""
if "Mapping" in _type:
_type = _type.replace("Mapping", "dict")
return _type
def get_formatted_type(key: str, _type: str) -> str:
"""
Formats the type value based on the given key.
Returns:
The formatted type value.
"""
if key == "allowed_tools":
return "Tool"
elif key == "max_value_length":
return "int"
return _type
def should_show_field(value: Dict[str, Any], key: str) -> bool:
"""
Determines if the field should be shown or not.
Returns:
True if the field should be shown, False otherwise.
"""
return (
(value["required"] and key != "input_variables")
or key in FORCE_SHOW_FIELDS
or any(text in key.lower() for text in ["password", "token", "api", "key"])
)
def is_password_field(key: str) -> bool:
"""
Determines if the field is a password field.
Returns:
True if the field is a password field, False otherwise.
"""
return any(text in key.lower() for text in ["password", "token", "api", "key"])
def is_multiline_field(key: str) -> bool:
"""
Determines if the field is a multiline field.
Returns:
True if the field is a multiline field, False otherwise.
"""
return key in {
"suffix",
"prefix",
"template",
"examples",
"code",
"headers",
"format_instructions",
}
def replace_dict_type_with_code(value: Dict[str, Any]) -> None:
"""
Replaces the type value with 'code' if the type is a dict.
"""
if "dict" in value["type"].lower():
value["type"] = "code"
def set_dict_file_attributes(value: Dict[str, Any]) -> None:
"""
Sets the file attributes for the 'dict_' key.
"""
value["type"] = "file"
value["suffixes"] = [".json", ".yaml", ".yml"]
value["fileTypes"] = ["json", "yaml", "yml"]
def replace_default_value_with_actual(value: Dict[str, Any]) -> None:
"""
Replaces the default value with the actual value.
"""
if "default" in value:
value["value"] = value["default"]
value.pop("default")
def set_headers_value(value: Dict[str, Any]) -> None:
"""
Sets the value for the 'headers' key.
"""
value["value"] = """{'Authorization': 'Bearer <token>'}"""
def add_options_to_field(
value: Dict[str, Any], class_name: Optional[str], key: str
) -> None:
"""
Adds options to the field based on the class name and key.
"""
options_map = {
"OpenAI": constants.OPENAI_MODELS,
"ChatOpenAI": constants.CHAT_OPENAI_MODELS,
"Anthropic": constants.ANTHROPIC_MODELS,
"ChatAnthropic": constants.ANTHROPIC_MODELS,
}
if class_name in options_map and key == "model_name":
value["options"] = options_map[class_name]
value["list"] = True
value["value"] = options_map[class_name][0]
def get_number_of_workers(workers=None):
if workers == -1 or workers is None:
workers = (cpu_count() * 2) + 1
logger.debug(f"Number of workers: {workers}")
return workers

68
src/backend/langflow/utils/validate.py
View file

@ -163,9 +163,77 @@ def create_function(code, function_name):
return wrapped_function
def create_class(code, class_name):
if not hasattr(ast, "TypeIgnore"):
class TypeIgnore(ast.AST):
_fields = ()
ast.TypeIgnore = TypeIgnore
module = ast.parse(code)
exec_globals = globals().copy()
for node in module.body:
if isinstance(node, ast.Import):
for alias in node.names:
try:
exec_globals[alias.asname or alias.name] = importlib.import_module(
alias.name
)
except ModuleNotFoundError as e:
raise ModuleNotFoundError(
f"Module {alias.name} not found. Please install it and try again."
) from e
elif isinstance(node, ast.ImportFrom):
try:
imported_module = importlib.import_module(node.module)
for alias in node.names:
exec_globals[alias.name] = getattr(imported_module, alias.name)
except ModuleNotFoundError as e:
raise ModuleNotFoundError(
f"Module {node.module} not found. Please install it and try again."
) from e
class_code = next(
node
for node in module.body
if isinstance(node, ast.ClassDef) and node.name == class_name
)
class_code.parent = None
code_obj = compile(
ast.Module(body=[class_code], type_ignores=[]), "<string>", "exec"
)
# This suppresses import errors
# with contextlib.suppress(Exception):
exec(code_obj, exec_globals, locals())
exec_globals[class_name] = locals()[class_name]
# Return a function that imports necessary modules and creates an instance of the target class
def build_my_class(*args, **kwargs):
for module_name, module in exec_globals.items():
if isinstance(module, type(importlib)):
globals()[module_name] = module
instance = exec_globals[class_name](*args, **kwargs)
return instance
build_my_class.__globals__.update(exec_globals)
return build_my_class
def extract_function_name(code):
module = ast.parse(code)
for node in module.body:
if isinstance(node, ast.FunctionDef):
return node.name
raise ValueError("No function definition found in the code string")
def extract_class_name(code):
module = ast.parse(code)
for node in module.body:
if isinstance(node, ast.ClassDef):
return node.name
raise ValueError("No class definition found in the code string")

111
src/frontend/src/CustomNodes/GenericNode/components/parameterComponent/index.tsx
View file

@ -27,6 +27,7 @@ import {
classNames,
getRandomKeyByssmm,
groupByFamily,
groupByFamilyCustom,
} from "../../../../utils/utils";
export default function ParameterComponent({
@ -49,7 +50,9 @@ export default function ParameterComponent({
const infoHtml = useRef(null);
const updateNodeInternals = useUpdateNodeInternals();
const [position, setPosition] = useState(0);
const { setTabsState, tabId, save } = useContext(TabsContext);
const { setTabsState, tabId, save, flows } = useContext(TabsContext);
const flow = flows.find((f) => f.id === tabId).data?.nodes ?? null;
// Update component position
useEffect(() => {
@ -80,9 +83,11 @@ export default function ParameterComponent({
[tabId]: {
...prev[tabId],
isPending: true,
formKeysData: prev[tabId].formKeysData,
},
};
});
renderTooltips();
};
useEffect(() => {
@ -98,57 +103,76 @@ export default function ParameterComponent({
);
}, [info]);
useEffect(() => {
const groupedObj = groupByFamily(myData, tooltipTitle, left, data.type);
function renderTooltips() {
let groupedObj = groupByFamily(myData, tooltipTitle, left, data.type, flow);
refNumberComponents.current = groupedObj[0]?.type?.length;
if (groupedObj?.length === 0 && flow && flow.length > 0) {
groupedObj = groupByFamilyCustom(
myData,
tooltipTitle,
left,
data.type,
flow
);
}
refHtml.current = groupedObj.map((item, i) => {
const Icon: any = nodeIconsLucide[item.family];
if (groupedObj) {
refNumberComponents.current = groupedObj[0]?.type?.length;
return (
<span
key={getRandomKeyByssmm() + item.family + i}
className={classNames(
i > 0 ? "mt-2 flex items-center" : "flex items-center"
)}
>
<div
className="h-5 w-5"
style={{
color: nodeColors[item.family],
}}
refHtml.current = groupedObj.map((item, i) => {
const Icon: any = nodeIconsLucide[item.family];
return (
<span
key={getRandomKeyByssmm() + item.family + i}
className={classNames(
i > 0 ? "mt-2 flex items-center" : "flex items-center"
)}
>
<Icon
<div
className="h-5 w-5"
strokeWidth={1.5}
style={{
color: nodeColors[item.family] ?? nodeColors.unknown,
color: nodeColors[item.family],
}}
/>
</div>
<span className="ps-2 text-xs text-foreground">
{nodeNames[item.family] ?? ""}{" "}
<span className="text-xs">
{" "}
{item.type === "" ? "" : " - "}
{item.type.split(", ").length > 2
? item.type.split(", ").map((el, i) => (
<React.Fragment key={el + i}>
<span>
{i === item.type.split(", ").length - 1
? el
: (el += `, `)}
</span>
</React.Fragment>
))
: item.type}
>
<Icon
className="h-5 w-5"
strokeWidth={1.5}
style={{
color: nodeColors[item.family] ?? nodeColors.unknown,
}}
/>
</div>
<span className="ps-2 text-xs text-foreground">
{item.family !== "custom_components"
? nodeNames[item.family]
: item.component ?? ""}{" "}
<span className="text-xs">
{" "}
{item.type === "" ? "" : " - "}
{item.type.split(", ").length > 2
? item.type.split(", ").map((el, i) => (
<React.Fragment key={el + i}>
<span>
{i === item.type.split(", ").length - 1
? el
: (el += `, `)}
</span>
</React.Fragment>
))
: item.type}
</span>
</span>
</span>
</span>
);
});
}, [tooltipTitle]);
);
});
}
}
useEffect(() => {
renderTooltips();
}, [tooltipTitle, flow]);
return (
<div
ref={ref}
@ -280,6 +304,7 @@ export default function ParameterComponent({
) : left === true && type === "code" ? (
<div className="mt-2 w-full">
<CodeAreaComponent
dynamic={data.node.template[name].dynamic ?? false}
setNodeClass={(nodeClass) => {
data.node = nodeClass;
}}

16
src/frontend/src/CustomNodes/GenericNode/index.tsx
View file

@ -95,6 +95,11 @@ export default function GenericNode({
"generic-node-div"
)}
>
{data.node.beta && (
<div className="beta-badge-wrapper">
<div className="beta-badge-content">BETA</div>
</div>
)}
<div className="generic-node-div-title">
<div className="generic-node-title-arrangement">
<IconComponent
@ -127,7 +132,7 @@ export default function GenericNode({
</span>
) : (
<div className="max-h-96 overflow-auto">
{validationStatus.params
{typeof validationStatus.params === "string"
? validationStatus.params
.split("\n")
.map((line, index) => <div key={index}>{line}</div>)
@ -178,6 +183,14 @@ export default function GenericNode({
{data.node.template[t].show &&
!data.node.template[t].advanced ? (
<ParameterComponent
key={
(data.node.template[t].input_types?.join(";") ??
data.node.template[t].type) +
"|" +
t +
"|" +
data.id
}
data={data}
setData={setData}
color={
@ -225,6 +238,7 @@ export default function GenericNode({
{" "}
</div>
<ParameterComponent
key={[data.type, data.id, ...data.node.base_classes].join("|")}
data={data}
setData={setData}
color={nodeColors[types[data.type]] ?? nodeColors.unknown}

24
src/frontend/src/components/EditFlowSettingsComponent/index.tsx
View file

@ -1,7 +1,8 @@
import React, { ChangeEvent, useState } from "react";
import React, { ChangeEvent, useEffect, useRef, useState } from "react";
import { Input } from "../../components/ui/input";
import { Label } from "../../components/ui/label";
import { Textarea } from "../../components/ui/textarea";
import { readFlowsFromDatabase } from "../../controllers/API";
type InputProps = {
name: string | null;
@ -9,6 +10,8 @@ type InputProps = {
maxLength?: number;
flows: Array<{ id: string; name: string; description: string }>;
tabId: string;
invalidName: boolean;
setInvalidName: (invalidName: boolean) => void;
setName: (name: string) => void;
setDescription: (description: string) => void;
updateFlow: (flow: { id: string; name: string }) => void;
@ -16,6 +19,8 @@ type InputProps = {
export const EditFlowSettings: React.FC<InputProps> = ({
name,
invalidName,
setInvalidName,
description,
maxLength = 50,
flows,
@ -25,6 +30,14 @@ export const EditFlowSettings: React.FC<InputProps> = ({
updateFlow,
}) => {
const [isMaxLength, setIsMaxLength] = useState(false);
const nameLists = useRef([]);
useEffect(() => {
readFlowsFromDatabase().then((flows) => {
flows.forEach((flow) => {
nameLists.current.push(flow.name);
});
});
}, []);
const handleNameChange = (event: ChangeEvent<HTMLInputElement>) => {
const { value } = event.target;
@ -33,7 +46,11 @@ export const EditFlowSettings: React.FC<InputProps> = ({
} else {
setIsMaxLength(false);
}
if (!nameLists.current.includes(value)) {
setInvalidName(false);
} else {
setInvalidName(true);
}
setName(value);
};
@ -55,6 +72,9 @@ export const EditFlowSettings: React.FC<InputProps> = ({
{isMaxLength && (
<span className="edit-flow-span">Character limit reached</span>
)}
{invalidName && (
<span className="edit-flow-span">Name already in use</span>
)}
</div>
<Input
className="nopan nodrag noundo nocopy mt-2 font-normal"

6
src/frontend/src/components/codeAreaComponent/index.tsx
View file

@ -1,6 +1,6 @@
import { useEffect, useState } from "react";
import CodeAreaModal from "../../modals/codeAreaModal";
import { TextAreaComponentType } from "../../types/components";
import { CodeAreaComponentType } from "../../types/components";
import IconComponent from "../genericIconComponent";
@ -10,8 +10,9 @@ export default function CodeAreaComponent({
disabled,
editNode = false,
nodeClass,
dynamic,
setNodeClass,
}: TextAreaComponentType) {
}: CodeAreaComponentType) {
const [myValue, setMyValue] = useState(
typeof value == "string" ? value : JSON.stringify(value)
);
@ -29,6 +30,7 @@ export default function CodeAreaComponent({
return (
<div className={disabled ? "pointer-events-none w-full " : " w-full"}>
<CodeAreaModal
dynamic={dynamic}
value={myValue}
nodeClass={nodeClass}
setNodeClass={setNodeClass}

11
src/frontend/src/constants/constants.ts
View file

@ -491,3 +491,14 @@ export const NOUNS: string[] = [
*
*/
export const USER_PROJECTS_HEADER = "My Collection";
/**
* URLs excluded from error retries.
* @constant
*
*/
export const URL_EXCLUDED_FROM_ERROR_RETRIES = [
"/api/v1/validate/code",
"/api/v1/custom_component",
"/api/v1/validate/prompt",
];

6
src/frontend/src/controllers/API/api.tsx
View file

@ -1,5 +1,6 @@
import axios, { AxiosError, AxiosInstance } from "axios";
import { useContext, useEffect, useRef } from "react";
import { URL_EXCLUDED_FROM_ERROR_RETRIES } from "../../constants/constants";
import { alertContext } from "../../contexts/alertContext";
// Create a new Axios instance
@ -15,6 +16,9 @@ function ApiInterceptor() {
const interceptor = api.interceptors.response.use(
(response) => response,
async (error: AxiosError) => {
if (URL_EXCLUDED_FROM_ERROR_RETRIES.includes(error.config?.url)) {
return Promise.reject(error);
}
let retryCount = 0;
while (retryCount < 4) {
@ -31,7 +35,7 @@ function ApiInterceptor() {
"Refresh the page",
"Use a new flow tab",
"Check if the backend is up",
"Endpoint: " + error.config.url,
"Endpoint: " + error.config?.url,
],
});
return Promise.reject(error);

7
src/frontend/src/controllers/API/index.ts
View file

@ -339,3 +339,10 @@ export async function uploadFile(
formData.append("file", file);
return await api.post(`/api/v1/upload/${id}`, formData);
}
export async function postCustomComponent(
code: string,
apiClass: APIClassType
): Promise<AxiosResponse<APIClassType>> {
return await api.post(`/api/v1/custom_component`, { code });
}

22
src/frontend/src/icons/GradientSparkles/index.tsx Normal file
View file

@ -0,0 +1,22 @@
import { Infinity } from "lucide-react";
import { forwardRef } from "react";
const GradientSparkles = forwardRef<SVGSVGElement, React.PropsWithChildren<{}>>(
(props, ref) => {
return (
<>
<svg width="0" height="0" style={{ position: "absolute" }}>
<defs>
<linearGradient id="grad1" x1="0%" y1="0%" x2="100%" y2="0%">
<stop className="gradient-start" offset="0%" />
<stop className="gradient-end" offset="100%" />
</linearGradient>
</defs>
</svg>
<Infinity stroke="url(#grad1)" ref={ref} {...props} />
</>
);
}
);
export default GradientSparkles;

7
src/frontend/src/modals/EditNodeModal/index.tsx
View file

@ -261,6 +261,13 @@ const EditNodeModal = forwardRef(
) : myData.node.template[n].type === "code" ? (
<div className="mx-auto">
<CodeAreaComponent
dynamic={
data.node.template[n].dynamic ?? false
}
setNodeClass={(nodeClass) => {
data.node = nodeClass;
}}
nodeClass={data.node}
disabled={disabled}
editNode={true}
value={myData.node.template[n].value ?? ""}

5
src/frontend/src/modals/NodeModal/components/ModalField/index.tsx
View file

@ -160,6 +160,11 @@ export default function ModalField({
) : type === "code" ? (
<div className="w-1/2">
<CodeAreaComponent
dynamic={data.node.template[name].dynamic ?? false}
setNodeClass={(nodeClass) => {
data.node = nodeClass;
}}
nodeClass={data.node}
disabled={false}
value={data.node.template[name].value ?? ""}
onChange={(t: string) => {

5
src/frontend/src/modals/baseModal/index.tsx
View file

@ -112,8 +112,9 @@ function BaseModal({
<div className={`mt-2 flex flex-col ${height} w-full `}>
{ContentChild}
</div>
<div className="flex flex-row-reverse">{ContentFooter}</div>
{ContentFooter && (
<div className="flex flex-row-reverse">{ContentFooter}</div>
)}
</DialogContent>
</Dialog>
);

95
src/frontend/src/modals/codeAreaModal/index.tsx
View file

@ -3,14 +3,16 @@ import "ace-builds/src-noconflict/ext-language_tools";
import "ace-builds/src-noconflict/mode-python";
import "ace-builds/src-noconflict/theme-github";
import "ace-builds/src-noconflict/theme-twilight";
import { ReactNode, useContext, useState } from "react";
// import "ace-builds/webpack-resolver";
import { ReactNode, useContext, useEffect, useState } from "react";
import AceEditor from "react-ace";
import IconComponent from "../../components/genericIconComponent";
import { Button } from "../../components/ui/button";
import { CODE_PROMPT_DIALOG_SUBTITLE } from "../../constants/constants";
import { alertContext } from "../../contexts/alertContext";
import { darkContext } from "../../contexts/darkContext";
import { postValidateCode } from "../../controllers/API";
import { typesContext } from "../../contexts/typesContext";
import { postCustomComponent, postValidateCode } from "../../controllers/API";
import { APIClassType } from "../../types/api";
import BaseModal from "../baseModal";
@ -20,18 +22,34 @@ export default function CodeAreaModal({
nodeClass,
setNodeClass,
children,
dynamic,
}: {
setValue: (value: string) => void;
value: string;
nodeClass: APIClassType;
nodeClass?: APIClassType;
children: ReactNode;
setNodeClass: (Class: APIClassType) => void;
setNodeClass?: (Class: APIClassType) => void;
dynamic?: boolean;
}) {
const [code, setCode] = useState(value);
const { dark } = useContext(darkContext);
const { reactFlowInstance } = useContext(typesContext);
const [height, setHeight] = useState(null);
const { setErrorData, setSuccessData } = useContext(alertContext);
const [error, setError] = useState<{
detail: { error: string; traceback: string };
}>(null);
function handleClick() {
useEffect(() => {
// if nodeClass.template has more fields other than code and dynamic is true
// do not run handleClick
if (dynamic && Object.keys(nodeClass.template).length > 2) {
return;
}
processCode();
}, []);
function processNonDynamicField() {
postValidateCode(code)
.then((apiReturn) => {
if (apiReturn.data) {
@ -41,8 +59,9 @@ export default function CodeAreaModal({
setSuccessData({
title: "Code is ready to run",
});
setValue(code);
setOpen(false);
setValue(code);
// setValue(code);
} else {
if (funcErrors.length !== 0) {
setErrorData({
@ -70,6 +89,50 @@ export default function CodeAreaModal({
});
}
function processDynamicField() {
postCustomComponent(code, nodeClass)
.then((apiReturn) => {
const { data } = apiReturn;
if (data) {
setNodeClass(data);
setValue(code);
setError({ detail: { error: undefined, traceback: undefined } });
setOpen(false);
}
})
.catch((err) => {
setError(err.response.data);
});
}
function processCode() {
if (!dynamic) {
processNonDynamicField();
} else {
processDynamicField();
}
}
function handleClick() {
processCode();
}
useEffect(() => {
// Function to be executed after the state changes
const delayedFunction = setTimeout(() => {
if (error?.detail.error !== undefined) {
//trigger to update the height, does not really apply any height
setHeight("90%");
}
//600 to happen after the transition of 500ms
}, 600);
// Cleanup function to clear the timeout if the component unmounts or the state changes again
return () => {
clearTimeout(delayedFunction);
};
}, [error, setHeight]);
const [open, setOpen] = useState(false);
return (
@ -89,6 +152,7 @@ export default function CodeAreaModal({
<AceEditor
value={code}
mode="python"
height={height ?? "100%"}
highlightActiveLine={true}
showPrintMargin={false}
fontSize={14}
@ -99,9 +163,26 @@ export default function CodeAreaModal({
onChange={(value) => {
setCode(value);
}}
className="h-full w-full rounded-lg border-[1px] border-border custom-scroll"
className="h-full w-full rounded-lg border-[1px] border-gray-300 custom-scroll dark:border-gray-600"
/>
</div>
<div
className={
"w-full transition-all delay-500 " +
(error?.detail.error !== undefined ? "h-2/6" : "h-0")
}
>
<div className="mt-1 h-full w-full overflow-y-auto overflow-x-clip text-left custom-scroll">
<h1 className="text-lg text-destructive">
{error?.detail?.error}
</h1>
<div className="ml-2 w-full break-all text-sm text-status-red">
<pre className="w-full whitespace-pre-wrap break-all">
{error?.detail?.traceback}
</pre>
</div>
</div>
</div>
<div className="flex h-fit w-full justify-end">
<Button className="mt-3" onClick={handleClick} type="submit">
Check & Save

6
src/frontend/src/modals/flowSettingsModal/index.tsx
View file

@ -23,6 +23,8 @@ export default function FlowSettingsModal({
const [description, setDescription] = useState(
flows.find((f) => f.id === tabId).description
);
const [invalidName, setInvalidName] = useState(false);
function handleClick() {
let savedFlow = flows.find((f) => f.id === tabId);
savedFlow.name = name;
@ -39,6 +41,8 @@ export default function FlowSettingsModal({
</BaseModal.Header>
<BaseModal.Content>
<EditFlowSettings
invalidName={invalidName}
setInvalidName={setInvalidName}
name={name}
description={description}
flows={flows}
@ -50,7 +54,7 @@ export default function FlowSettingsModal({
</BaseModal.Content>
<BaseModal.Footer>
<Button onClick={handleClick} type="submit">
<Button disabled={invalidName} onClick={handleClick} type="submit">
Save
</Button>
</BaseModal.Footer>

37
src/frontend/src/style/applies.css
View file

@ -31,6 +31,36 @@
}
}
@keyframes gradient-motion-start {
0% {
stop-color: rgb(156, 138, 236);
}
50% {
stop-color: rgb(255, 130, 184);
}
80% {
stop-color: rgb(255, 165, 100);
}
100% {
stop-color: rgb(156, 138, 236);
}
}
@keyframes gradient-motion-end {
0% {
stop-color: rgb(156, 138, 236);
}
50% {
stop-color: rgb(255, 165, 100);
}
80% {
stop-color: rgb(255, 130, 184);
}
100% {
stop-color: rgb(156, 138, 236);
}
}
@layer components {
.round-buttons-position {
@apply fixed right-4;
@ -979,6 +1009,13 @@
@apply font-medium leading-none peer-disabled:cursor-not-allowed peer-disabled:opacity-70;
}
.beta-badge-wrapper {
@apply absolute right-0 top-0 h-16 w-16 overflow-hidden rounded-tr-lg;
}
.beta-badge-content {
@apply mt-2 w-24 rotate-45 bg-beta-background text-center text-xs font-semibold text-beta-foreground;
}
.chat-message-highlight {
@apply rounded-md bg-indigo-100 px-0.5 dark:bg-indigo-900;
}

44
src/frontend/src/style/classes.css
View file

@ -1,30 +1,38 @@
body {
margin: 0;
font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Roboto", "Oxygen",
"Ubuntu", "Cantarell", "Fira Sans", "Droid Sans", "Helvetica Neue",
sans-serif;
-webkit-font-smoothing: antialiased;
-moz-osx-font-smoothing: grayscale;
margin: 0;
font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", "Roboto", "Oxygen",
"Ubuntu", "Cantarell", "Fira Sans", "Droid Sans", "Helvetica Neue",
sans-serif;
-webkit-font-smoothing: antialiased;
-moz-osx-font-smoothing: grayscale;
}
code {
font-family: source-code-pro, Menlo, Monaco, Consolas, "Courier New",
monospace;
font-family: source-code-pro, Menlo, Monaco, Consolas, "Courier New",
monospace;
}
pre {
font-family: inherit;
font-family: inherit;
}
.react-flow__pane {
cursor: default;
cursor: default;
}
.AccordionContent {
overflow: hidden;
overflow: hidden;
}
.AccordionContent[data-state='open'] {
animation: slideDown 300ms ease-out;
.AccordionContent[data-state="open"] {
animation: slideDown 300ms ease-out;
}
.AccordionContent[data-state="closed"] {
animation: slideUp 300ms ease-out;
}
.gradient-end {
animation: gradient-motion-end 3s infinite forwards;
}
.gradient-start {
animation: gradient-motion-start 4s infinite forwards;
}
.AccordionContent[data-state='closed'] {
animation: slideUp 300ms ease-out;
}

228
src/frontend/src/style/index.css
View file

@ -2,125 +2,127 @@
@tailwind components;
@tailwind utilities;
/* TODO: Confirm that all colors here are found in tailwind config */
@layer base {
:root {
--background: 0 0% 100%; /* hsl(0 0% 100%) */
--foreground: 222.2 47.4% 11.2%; /* hsl(222 47% 11%) */
--muted: 210 40% 98%; /* hsl(210 40% 98%) */
--muted-foreground: 215.4 16.3% 46.9%; /* hsl(215 16% 46%) */
--popover: 0 0% 100%; /* hsl(0 0% 100%) */
--popover-foreground: 222.2 47.4% 11.2%; /* hsl(222 47% 11%) */
--card: 0 0% 100%; /* hsl(0 0% 100%) */
--card-foreground: 222.2 47.4% 11.2%; /* hsl(222 47% 11%) */
--border: 214.3 21.8% 91.4%; /* hsl(214 32% 91%) */
--input: 214.3 21.8% 91.4%; /* hsl(214 32% 91%) */
--primary: 222.2 27% 11.2%; /* hsl(222 27% 18%) */
--primary-foreground: 210 40% 98%; /* hsl(210 40% 98%) */
--secondary: 210 40% 96.1%; /* hsl(210 40% 96%) */
--secondary-foreground: 222.2 47.4% 11.2%; /* hsl(222 47% 11%) */
--accent: 210 30% 96.1%; /* hsl(210 30% 96%) */
--accent-foreground: 222.2 47.4% 11.2%; /* hsl(222 47% 11%) */
--destructive: 0 100% 50%; /* hsl(0 100% 50%) */
--destructive-foreground: 210 40% 98%; /* hsl(210 40% 98%) */
--radius: 0.5rem;
--ring: 215 20.2% 65.1%; /* hsl(215 20% 65%) */
--round-btn-shadow: #00000063;
--error-background: #fef2f2;
--error-foreground: #991b1b;
--success-background: #f0fdf4;
--success-foreground: #14532d;
--background: 0 0% 100%; /* hsl(0 0% 100%) */
--foreground: 222.2 47.4% 11.2%; /* hsl(222 47% 11%) */
--muted: 210 40% 98%; /* hsl(210 40% 98%) */
--muted-foreground: 215.4 16.3% 46.9%; /* hsl(215 16% 46%) */
--popover: 0 0% 100%; /* hsl(0 0% 100%) */
--popover-foreground: 222.2 47.4% 11.2%; /* hsl(222 47% 11%) */
--card: 0 0% 100%; /* hsl(0 0% 100%) */
--card-foreground: 222.2 47.4% 11.2%; /* hsl(222 47% 11%) */
--border: 214.3 21.8% 91.4%; /* hsl(214 32% 91%) */
--input: 214.3 21.8% 91.4%; /* hsl(214 32% 91%) */
--primary: 222.2 27% 11.2%; /* hsl(222 27% 18%) */
--primary-foreground: 210 40% 98%; /* hsl(210 40% 98%) */
--secondary: 210 40% 96.1%; /* hsl(210 40% 96%) */
--secondary-foreground: 222.2 47.4% 11.2%; /* hsl(222 47% 11%) */
--accent: 210 30% 96.1%; /* hsl(210 30% 96%) */
--accent-foreground: 222.2 47.4% 11.2%; /* hsl(222 47% 11%) */
--destructive: 0 100% 50%; /* hsl(0 100% 50%) */
--destructive-foreground: 210 40% 98%; /* hsl(210 40% 98%) */
--radius: 0.5rem;
--ring: 215 20.2% 65.1%; /* hsl(215 20% 65%) */
--round-btn-shadow: #00000063;
--info-background: #f0f4fd;
--info-foreground: #141653;
--error-background: #fef2f2;
--error-foreground: #991b1b;
--high-indigo: #4338ca;
--medium-indigo: #6366f1;
--low-indigo: #e0e7ff;
--success-background: #f0fdf4;
--success-foreground: #14532d;
--chat-bot-icon: #afe6ef;
--chat-user-icon: #aface9;
/* Colors that are shared in dark and light mode */
--blur-shared: #151923de;
--build-trigger: #dc735b;
--chat-trigger: #5c8be1;
--chat-trigger-disabled: #b4c3da;
--status-red: #ef4444;
--status-yellow: #eab308;
--chat-send: #059669;
--status-green: #4ade80;
--status-blue:#2563eb;
--connection: #555;
--info-background: #f0f4fd;
--info-foreground: #141653;
--high-indigo: #4338ca;
--medium-indigo: #6366f1;
--low-indigo: #e0e7ff;
--beta-background: rgb(219 234 254);
--beta-foreground: rgb(37 99 235);
--chat-bot-icon: #afe6ef;
--chat-user-icon: #aface9;
/* Colors that are shared in dark and light mode */
--blur-shared: #151923de;
--build-trigger: #dc735b;
--chat-trigger: #5c8be1;
--chat-trigger-disabled: #b4c3da;
--status-red: #ef4444;
--status-yellow: #eab308;
--chat-send: #059669;
--status-green: #4ade80;
--status-blue: #2563eb;
--connection: #555;
}
.dark {
--background: 224 35% 7.5%; /* hsl(224 40% 10%) */
--foreground: 213 31% 80%; /* hsl(213 31% 91%) */
--muted: 223 27% 11%; /* hsl(223 27% 11%) */
--muted-foreground: 215.4 16.3% 56.9%; /* hsl(215 16% 56%) */
--popover: 224 71% 4%; /* hsl(224 71% 4%) */
--popover-foreground: 215 20.2% 65.1%; /* hsl(215 20% 65%) */
--card: 224 25% 15.5%; /* hsl(224 71% 4%) */
--card-foreground: 213 31% 80%; /* hsl(213 31% 91%) */
--border: 216 24% 17%; /* hsl(216 34% 17%) */
--input: 216 24% 17%; /* hsl(216 34% 17%) */
--primary: 210 20% 80%; /* hsl(210 20% 80%) */
--primary-foreground: 222.2 27.4% 1.2%; /* hsl(222 47% 1%) */
--secondary: 222.2 37.4% 7.2%; /* hsl(222 47% 11%) */
--secondary-foreground: 210 40% 80%; /* hsl(210 40% 80%) */
--accent: 216 24% 20%; /* hsl(216 34% 17%) */
--accent-foreground: 210 30% 98%; /* hsl(210 40% 98%) */
--destructive: 0 63% 31%; /* hsl(0 63% 31%) */
--destructive-foreground: 210 40% 98%; /* hsl(210 40% 98%) */
--ring: 216 24% 30%; /* hsl(216 24% 30%) */
--radius: 0.5rem;
--round-btn-shadow: #00000063;
--success-background: #022c22;
--success-foreground: #ecfdf5;
--error-foreground: #fef2f2;
--error-background: #450a0a;
--info-foreground: #eff6ff;
--info-background: #172554;
--high-indigo: #4338ca;
--medium-indigo: #6366f1;
--low-indigo: #e0e7ff;
/* Colors that are shared in dark and light mode */
--blur-shared: #151923d2;
--build-trigger: #dc735b;
--chat-trigger: #5c8be1;
--chat-trigger-disabled: #2d3b54;
--status-red: #ef4444;
--status-yellow: #eab308;
--chat-send: #059669;
--status-green: #4ade80;
--status-blue: #2563eb;
--connection: #555;
--beta-background: rgb(37 99 235);
--beta-foreground: rgb(219 234 254);
--chat-bot-icon: #235d70;
--chat-user-icon: #4f3d6e;
}
}
.dark {
--background: 224 35% 7.5%; /* hsl(224 40% 10%) */
--foreground: 213 31% 80%; /* hsl(213 31% 91%) */
--muted: 223 27% 11%; /* hsl(223 27% 11%) */
--muted-foreground: 215.4 16.3% 56.9%; /* hsl(215 16% 56%) */
--popover: 224 71% 4%; /* hsl(224 71% 4%) */
--popover-foreground: 215 20.2% 65.1%; /* hsl(215 20% 65%) */
--card: 224 25% 15.5%; /* hsl(224 71% 4%) */
--card-foreground: 213 31% 80%; /* hsl(213 31% 91%) */
--border: 216 24% 17%; /* hsl(216 34% 17%) */
--input: 216 24% 17%; /* hsl(216 34% 17%) */
--primary: 210 20% 80%; /* hsl(210 20% 80%) */
--primary-foreground: 222.2 27.4% 1.2%; /* hsl(222 47% 1%) */
--secondary: 222.2 37.4% 7.2%; /* hsl(222 47% 11%) */
--secondary-foreground: 210 40% 80%; /* hsl(210 40% 80%) */
--accent: 216 24% 20%; /* hsl(216 34% 17%) */
--accent-foreground: 210 30% 98%; /* hsl(210 40% 98%) */
--destructive: 0 63% 31%; /* hsl(0 63% 31%) */
--destructive-foreground: 210 40% 98%; /* hsl(210 40% 98%) */
--ring: 216 24% 30%; /* hsl(216 24% 30%) */
--radius: 0.5rem;
--round-btn-shadow: #00000063;
--success-background: #022c22;
--success-foreground: #ecfdf5;
--error-foreground: #fef2f2;
--error-background: #450a0a;
--info-foreground: #eff6ff;
--info-background: #172554;
--high-indigo: #4338ca;
--medium-indigo: #6366f1;
--low-indigo: #e0e7ff;
/* Colors that are shared in dark and light mode */
--blur-shared: #151923d2;
--build-trigger: #dc735b;
--chat-trigger: #5c8be1;
--chat-trigger-disabled: #2d3b54;
--status-red: #ef4444;
--status-yellow: #eab308;
--chat-send: #059669;
--status-green: #4ade80;
--status-blue: #2563eb;
--connection: #555;
--chat-bot-icon: #235d70;
--chat-user-icon: #4f3d6e;
}}

3
src/frontend/src/types/api/index.ts
View file

@ -14,8 +14,9 @@ export type APIClassType = {
display_name: string;
input_types?: Array<string>;
output_types?: Array<string>;
beta?: boolean;
documentation: string;
[key: string]: Array<string> | string | APITemplateType;
[key: string]: Array<string> | string | APITemplateType | boolean;
};
export type TemplateVariableType = {

5
src/frontend/src/types/components/index.ts
View file

@ -62,8 +62,9 @@ export type CodeAreaComponentType = {
onChange: (value: string[] | string) => void;
value: string;
editNode?: boolean;
nodeClass: APIClassType;
setNodeClass: (value: APIClassType) => void;
nodeClass?: APIClassType;
setNodeClass?: (value: APIClassType) => void;
dynamic?: boolean;
};
export type FileComponentType = {

6
src/frontend/src/utils/styleUtils.ts
View file

@ -14,6 +14,7 @@ import {
Cpu,
Download,
DownloadCloud,
Edit,
Eraser,
ExternalLink,
File,
@ -74,6 +75,7 @@ import { EvernoteIcon } from "../icons/Evernote";
import { FBIcon } from "../icons/FacebookMessenger";
import { GitBookIcon } from "../icons/GitBook";
import { GoogleIcon } from "../icons/Google";
import GradientSparkles from "../icons/GradientSparkles";
import { HuggingFaceIcon } from "../icons/HuggingFace";
import { IFixIcon } from "../icons/IFixIt";
import { MetaIcon } from "../icons/Meta";
@ -146,6 +148,7 @@ export const nodeColors: { [char: string]: string } = {
str: "#049524",
retrievers: "#e6b25a",
unknown: "#9CA3AF",
custom_components: "#ab11ab",
};
export const nodeNames: { [char: string]: string } = {
@ -166,6 +169,7 @@ export const nodeNames: { [char: string]: string } = {
retrievers: "Retrievers",
utilities: "Utilities",
output_parsers: "Output Parsers",
custom_components: "Custom",
unknown: "Unknown",
};
@ -224,6 +228,8 @@ export const nodeIconsLucide = {
unknown: HelpCircle,
WikipediaQueryRun: SvgWikipedia,
WolframAlphaQueryRun: SvgWolfram,
custom_components: GradientSparkles,
custom: Edit,
Trash2,
X,
XCircle,

107
src/frontend/src/utils/utils.ts
View file

@ -5,6 +5,7 @@ import { IVarHighlightType } from "../types/components";
import { FlowType } from "../types/flow";
import { TabsState } from "../types/tabs";
import { buildTweaks } from "./reactflowUtils";
import { nodeNames } from "./styleUtils";
export function classNames(...classes: Array<string>) {
return classes.filter(Boolean).join(" ");
@ -88,12 +89,13 @@ export function checkUpperWords(str: string) {
export const isWrappedWithClass = (event: any, className: string | undefined) =>
event.target.closest(`.${className}`);
export function groupByFamily(data, baseClasses, left, type) {
export function groupByFamily(data, baseClasses, left, type, flow) {
let parentOutput: string;
let arrOfParent: string[] = [];
let arrOfType: { family: string; type: string; component: string }[] = [];
let arrOfLength: { length: number; type: string }[] = [];
let lastType = "";
Object.keys(data).forEach((d) => {
Object.keys(data[d]).forEach((n) => {
try {
@ -165,7 +167,7 @@ export function groupByFamily(data, baseClasses, left, type) {
});
}
if (left === false) {
if (parentOutput !== "custom_components") {
let resFil = result.filter((group) => group.family === parentOutput);
result = resFil;
}
@ -203,6 +205,107 @@ export function groupByFamily(data, baseClasses, left, type) {
}
}
export function groupByFamilyCustom(data, baseClasses, left, type, flow) {
let arrOfParentCustom: string[] = [];
let arrOfType: { family: string; type: string; component: string }[] = [];
if (type === "CustomComponent") {
const uniqueValuesSet = new Set();
flow.forEach((element) => {
element["data"]["node"]["base_classes"].forEach((el) => {
if (!uniqueValuesSet.has(el)) {
arrOfParentCustom.push(el);
uniqueValuesSet.add(el);
}
});
});
}
if (left === false) {
arrOfParentCustom.map((n) => {
try {
arrOfType.push({
family: "custom_components",
type: n,
component: nodeNames["custom_components"],
});
} catch (e) {
console.log(e);
}
});
} else {
flow.forEach((element) => {
Object.keys(element["data"]["node"]["template"]).map((el) => {
if (
element["data"]["node"]["template"][el].input_types &&
element["data"]["node"]["template"][el].input_types.length > 0
) {
element["data"]["node"]["template"][el].input_types.map((n) => {
try {
arrOfType.push({
family: "custom_components",
type: n,
component: nodeNames["custom_components"],
});
} catch (e) {
console.log(e);
}
});
}
});
});
}
const groupedResult = {};
arrOfType.forEach((item) => {
const { family, type, component } = item;
if (groupedResult.hasOwnProperty(family)) {
if (!groupedResult[family].type.includes(type)) {
groupedResult[family].type += `, ${type}`;
}
} else {
groupedResult[family] = { family, type, component };
}
});
const result = Object.values(groupedResult);
if (left === false) {
let resultFiltered = [];
flow.forEach((element) => {
Object.keys(element["data"]["node"]["template"]).map((el) => {
if (
element["data"]["node"]["template"][el].input_types &&
element["data"]["node"]["template"][el].input_types.length > 0
) {
element["data"]["node"]["template"][el].input_types.map((n) => {
resultFiltered.push({
family: "custom_components",
type: n,
component: element["data"]["node"]["display_name"],
});
});
}
});
});
if (resultFiltered.length === 0) {
Object.keys(groupedResult).forEach((el) => {
resultFiltered.push({
family: "custom_components",
type: groupedResult[el].type,
component: nodeNames["custom_components"],
});
});
}
return resultFiltered;
} else {
return result;
}
}
export function buildInputs(tabsState, id) {
return tabsState &&
tabsState[id] &&

2
src/frontend/tailwind.config.js
View file

@ -71,6 +71,8 @@ module.exports = {
"status-yellow": "var(--status-yellow)",
"success-background": "var(--success-background)",
"success-foreground": "var(--success-foreground)",
"beta-background": "var(--beta-background)",
"beta-foreground": "var(--beta-foreground)",
"chat-bot-icon": "var(--chat-bot-icon)",
"chat-user-icon": "var(--chat-user-icon)",

14
tests/conftest.py
View file

@ -93,8 +93,8 @@ def json_flow():
return f.read()
@pytest.fixture(name="session") #
def session_fixture(): #
@pytest.fixture(name="session")
def session_fixture():
engine = create_engine(
"sqlite://", connect_args={"check_same_thread": False}, poolclass=StaticPool
)
@ -103,16 +103,16 @@ def session_fixture(): #
yield session
@pytest.fixture(name="client") #
def client_fixture(session: Session): #
def get_session_override(): #
@pytest.fixture(name="client")
def client_fixture(session: Session):
def get_session_override():
return session
from langflow.main import create_app
app = create_app()
app.dependency_overrides[get_session] = get_session_override #
app.dependency_overrides[get_session] = get_session_override
yield TestClient(app)
app.dependency_overrides.clear() #
app.dependency_overrides.clear()

15
tests/test_agents_template.py
View file

@ -18,6 +18,7 @@ def test_zero_shot_agent(client: TestClient):
assert template["tools"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -32,6 +33,7 @@ def test_zero_shot_agent(client: TestClient):
# Additional assertions for other template variables
assert template["callback_manager"] == {
"required": False,
"dynamic": False,
"placeholder": "",
"show": False,
"multiline": False,
@ -44,6 +46,7 @@ def test_zero_shot_agent(client: TestClient):
}
assert template["llm"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -56,6 +59,7 @@ def test_zero_shot_agent(client: TestClient):
}
assert template["output_parser"] == {
"required": False,
"dynamic": False,
"placeholder": "",
"show": False,
"multiline": False,
@ -68,6 +72,7 @@ def test_zero_shot_agent(client: TestClient):
}
assert template["input_variables"] == {
"required": False,
"dynamic": False,
"placeholder": "",
"show": False,
"multiline": False,
@ -80,6 +85,7 @@ def test_zero_shot_agent(client: TestClient):
}
assert template["prefix"] == {
"required": False,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": True,
@ -93,6 +99,7 @@ def test_zero_shot_agent(client: TestClient):
}
assert template["suffix"] == {
"required": False,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": True,
@ -118,6 +125,7 @@ def test_json_agent(client: TestClient):
assert template["toolkit"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -130,6 +138,7 @@ def test_json_agent(client: TestClient):
}
assert template["llm"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -155,6 +164,7 @@ def test_csv_agent(client: TestClient):
assert template["path"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -171,6 +181,7 @@ def test_csv_agent(client: TestClient):
}
assert template["llm"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -196,6 +207,7 @@ def test_initialize_agent(client: TestClient):
assert template["agent"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -217,6 +229,7 @@ def test_initialize_agent(client: TestClient):
}
assert template["memory"] == {
"required": False,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -229,6 +242,7 @@ def test_initialize_agent(client: TestClient):
}
assert template["tools"] == {
"required": False,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -241,6 +255,7 @@ def test_initialize_agent(client: TestClient):
}
assert template["llm"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,

21
tests/test_chains_template.py
View file

@ -29,6 +29,7 @@ def test_conversation_chain(client: TestClient):
template = chain["template"]
assert template["memory"] == {
"required": False,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -41,6 +42,7 @@ def test_conversation_chain(client: TestClient):
}
assert template["verbose"] == {
"required": False,
"dynamic": False,
"placeholder": "",
"show": False,
"multiline": False,
@ -53,6 +55,7 @@ def test_conversation_chain(client: TestClient):
}
assert template["llm"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -65,6 +68,7 @@ def test_conversation_chain(client: TestClient):
}
assert template["input_key"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -78,6 +82,7 @@ def test_conversation_chain(client: TestClient):
}
assert template["output_key"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -115,6 +120,7 @@ def test_llm_chain(client: TestClient):
template = chain["template"]
assert template["memory"] == {
"required": False,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -127,6 +133,7 @@ def test_llm_chain(client: TestClient):
}
assert template["verbose"] == {
"required": False,
"dynamic": False,
"placeholder": "",
"show": False,
"multiline": False,
@ -140,6 +147,7 @@ def test_llm_chain(client: TestClient):
}
assert template["llm"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -152,6 +160,7 @@ def test_llm_chain(client: TestClient):
}
assert template["output_key"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -182,6 +191,7 @@ def test_llm_checker_chain(client: TestClient):
template = chain["template"]
assert template["llm"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -215,6 +225,7 @@ def test_llm_math_chain(client: TestClient):
template = chain["template"]
assert template["memory"] == {
"required": False,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -227,6 +238,7 @@ def test_llm_math_chain(client: TestClient):
}
assert template["verbose"] == {
"required": False,
"dynamic": False,
"placeholder": "",
"show": False,
"multiline": False,
@ -240,6 +252,7 @@ def test_llm_math_chain(client: TestClient):
}
assert template["llm"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -252,6 +265,7 @@ def test_llm_math_chain(client: TestClient):
}
assert template["input_key"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -265,6 +279,7 @@ def test_llm_math_chain(client: TestClient):
}
assert template["output_key"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -306,6 +321,7 @@ def test_series_character_chain(client: TestClient):
assert template["llm"] == {
"required": True,
"dynamic": False,
"display_name": "LLM",
"placeholder": "",
"show": True,
@ -319,6 +335,7 @@ def test_series_character_chain(client: TestClient):
}
assert template["character"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -331,6 +348,7 @@ def test_series_character_chain(client: TestClient):
}
assert template["series"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,
@ -372,6 +390,7 @@ def test_mid_journey_prompt_chain(client: TestClient):
assert template["llm"] == {
"required": True,
"dynamic": False,
"display_name": "LLM",
"placeholder": "",
"show": True,
@ -412,6 +431,7 @@ def test_time_travel_guide_chain(client: TestClient):
assert template["llm"] == {
"required": True,
"dynamic": False,
"placeholder": "",
"display_name": "LLM",
"show": True,
@ -425,6 +445,7 @@ def test_time_travel_guide_chain(client: TestClient):
}
assert template["memory"] == {
"required": False,
"dynamic": False,
"placeholder": "",
"show": True,
"multiline": False,

1
tests/test_creators.py
View file

@ -35,6 +35,7 @@ def test_lang_chain_type_creator_to_dict(
sample_lang_chain_type_creator: LangChainTypeCreator,
):
type_dict = sample_lang_chain_type_creator.to_dict()
assert len(type_dict) == 1
assert "test_type" in type_dict
assert "node1" in type_dict["test_type"]

558
tests/test_custom_component.py Normal file
View file

@ -0,0 +1,558 @@
import ast
import pytest
import types
from uuid import uuid4
from fastapi import HTTPException
from langflow.database.models.flow import Flow, FlowCreate
from langflow.interface.custom.base import CustomComponent
from langflow.interface.custom.component import (
Component,
ComponentCodeNullError,
ComponentFunctionEntrypointNameNullError,
)
from langflow.interface.custom.code_parser import CodeParser, CodeSyntaxError
code_default = """
from langflow import Prompt
from langflow.interface.custom.custom_component import CustomComponent
from langchain.llms.base import BaseLLM
from langchain.chains import LLMChain
from langchain import PromptTemplate
from langchain.schema import Document
import requests
class YourComponent(CustomComponent):
display_name: str = "Your Component"
description: str = "Your description"
field_config = { "url": { "multiline": True, "required": True } }
def build(self, url: str, llm: BaseLLM, template: Prompt) -> Document:
response = requests.get(url)
prompt = PromptTemplate.from_template(template)
chain = LLMChain(llm=llm, prompt=prompt)
result = chain.run(response.text[:300])
return Document(page_content=str(result))
"""
def test_code_parser_init():
"""
Test the initialization of the CodeParser class.
"""
parser = CodeParser(code_default)
assert parser.code == code_default
def test_code_parser_get_tree():
"""
Test the __get_tree method of the CodeParser class.
"""
parser = CodeParser(code_default)
tree = parser._CodeParser__get_tree()
assert isinstance(tree, ast.AST)
def test_code_parser_syntax_error():
"""
Test the __get_tree method raises the
CodeSyntaxError when given incorrect syntax.
"""
code_syntax_error = "zzz import os"
parser = CodeParser(code_syntax_error)
with pytest.raises(CodeSyntaxError):
parser._CodeParser__get_tree()
def test_component_init():
"""
Test the initialization of the Component class.
"""
component = Component(code=code_default, function_entrypoint_name="build")
assert component.code == code_default
assert component.function_entrypoint_name == "build"
def test_component_get_code_tree():
"""
Test the get_code_tree method of the Component class.
"""
component = Component(code=code_default, function_entrypoint_name="build")
tree = component.get_code_tree(component.code)
assert "imports" in tree
def test_component_code_null_error():
"""
Test the get_function method raises the
ComponentCodeNullError when the code is empty.
"""
component = Component(code="", function_entrypoint_name="")
with pytest.raises(ComponentCodeNullError):
component.get_function()
def test_component_function_entrypoint_name_null_error():
"""
Test the get_function method raises the ComponentFunctionEntrypointNameNullError
when the function_entrypoint_name is empty.
"""
component = Component(code=code_default, function_entrypoint_name="")
with pytest.raises(ComponentFunctionEntrypointNameNullError):
component.get_function()
def test_custom_component_init():
"""
Test the initialization of the CustomComponent class.
"""
function_entrypoint_name = "build"
custom_component = CustomComponent(
code=code_default, function_entrypoint_name=function_entrypoint_name
)
assert custom_component.code == code_default
assert custom_component.function_entrypoint_name == function_entrypoint_name
def test_custom_component_build_template_config():
"""
Test the build_template_config property of the CustomComponent class.
"""
custom_component = CustomComponent(
code=code_default, function_entrypoint_name="build"
)
config = custom_component.build_template_config
assert isinstance(config, dict)
def test_custom_component_get_function():
"""
Test the get_function property of the CustomComponent class.
"""
custom_component = CustomComponent(
code="def build(): pass", function_entrypoint_name="build"
)
my_function = custom_component.get_function
assert isinstance(my_function, types.FunctionType)
def test_code_parser_parse_imports_import():
"""
Test the parse_imports method of the CodeParser
class with an import statement.
"""
parser = CodeParser(code_default)
tree = parser._CodeParser__get_tree()
for node in ast.walk(tree):
if isinstance(node, ast.Import):
parser.parse_imports(node)
assert "requests" in parser.data["imports"]
def test_code_parser_parse_imports_importfrom():
"""
Test the parse_imports method of the CodeParser
class with an import from statement.
"""
parser = CodeParser("from os import path")
tree = parser._CodeParser__get_tree()
for node in ast.walk(tree):
if isinstance(node, ast.ImportFrom):
parser.parse_imports(node)
assert ("os", "path") in parser.data["imports"]
def test_code_parser_parse_functions():
"""
Test the parse_functions method of the CodeParser class.
"""
parser = CodeParser("def test(): pass")
tree = parser._CodeParser__get_tree()
for node in ast.walk(tree):
if isinstance(node, ast.FunctionDef):
parser.parse_functions(node)
assert len(parser.data["functions"]) == 1
assert parser.data["functions"][0]["name"] == "test"
def test_code_parser_parse_classes():
"""
Test the parse_classes method of the CodeParser class.
"""
parser = CodeParser("class Test: pass")
tree = parser._CodeParser__get_tree()
for node in ast.walk(tree):
if isinstance(node, ast.ClassDef):
parser.parse_classes(node)
assert len(parser.data["classes"]) == 1
assert parser.data["classes"][0]["name"] == "Test"
def test_code_parser_parse_global_vars():
"""
Test the parse_global_vars method of the CodeParser class.
"""
parser = CodeParser("x = 1")
tree = parser._CodeParser__get_tree()
for node in ast.walk(tree):
if isinstance(node, ast.Assign):
parser.parse_global_vars(node)
assert len(parser.data["global_vars"]) == 1
assert parser.data["global_vars"][0]["targets"] == ["x"]
def test_component_get_function_valid():
"""
Test the get_function method of the Component
class with valid code and function_entrypoint_name.
"""
component = Component(code="def build(): pass", function_entrypoint_name="build")
my_function = component.get_function()
assert callable(my_function)
def test_custom_component_get_function_entrypoint_args():
"""
Test the get_function_entrypoint_args
property of the CustomComponent class.
"""
custom_component = CustomComponent(
code=code_default, function_entrypoint_name="build"
)
args = custom_component.get_function_entrypoint_args
assert len(args) == 4
assert args[0]["name"] == "self"
assert args[1]["name"] == "url"
assert args[2]["name"] == "llm"
def test_custom_component_get_function_entrypoint_return_type():
"""
Test the get_function_entrypoint_return_type
property of the CustomComponent class.
"""
custom_component = CustomComponent(
code=code_default, function_entrypoint_name="build"
)
return_type = custom_component.get_function_entrypoint_return_type
assert return_type == "Document"
def test_custom_component_get_main_class_name():
"""
Test the get_main_class_name property of the CustomComponent class.
"""
custom_component = CustomComponent(
code=code_default, function_entrypoint_name="build"
)
class_name = custom_component.get_main_class_name
assert class_name == "YourComponent"
def test_custom_component_get_function_valid():
"""
Test the get_function property of the CustomComponent
class with valid code and function_entrypoint_name.
"""
custom_component = CustomComponent(
code="def build(): pass", function_entrypoint_name="build"
)
my_function = custom_component.get_function
assert callable(my_function)
def test_code_parser_parse_arg_no_annotation():
"""
Test the parse_arg method of the CodeParser class without an annotation.
"""
parser = CodeParser("")
arg = ast.arg(arg="x", annotation=None)
result = parser.parse_arg(arg, None)
assert result["name"] == "x"
assert "type" not in result
def test_code_parser_parse_arg_with_annotation():
"""
Test the parse_arg method of the CodeParser class with an annotation.
"""
parser = CodeParser("")
arg = ast.arg(arg="x", annotation=ast.Name(id="int", ctx=ast.Load()))
result = parser.parse_arg(arg, None)
assert result["name"] == "x"
assert result["type"] == "int"
def test_code_parser_parse_callable_details_no_args():
"""
Test the parse_callable_details method of the
CodeParser class with a function with no arguments.
"""
parser = CodeParser("")
node = ast.FunctionDef(
name="test",
args=ast.arguments(
args=[], vararg=None, kwonlyargs=[], kw_defaults=[], kwarg=None, defaults=[]
),
body=[],
decorator_list=[],
returns=None,
)
result = parser.parse_callable_details(node)
assert result["name"] == "test"
assert len(result["args"]) == 0
def test_code_parser_parse_assign():
"""
Test the parse_assign method of the CodeParser class.
"""
parser = CodeParser("")
stmt = ast.Assign(targets=[ast.Name(id="x", ctx=ast.Store())], value=ast.Num(n=1))
result = parser.parse_assign(stmt)
assert result["name"] == "x"
assert result["value"] == "1"
def test_code_parser_parse_ann_assign():
"""
Test the parse_ann_assign method of the CodeParser class.
"""
parser = CodeParser("")
stmt = ast.AnnAssign(
target=ast.Name(id="x", ctx=ast.Store()),
annotation=ast.Name(id="int", ctx=ast.Load()),
value=ast.Num(n=1),
simple=1,
)
result = parser.parse_ann_assign(stmt)
assert result["name"] == "x"
assert result["value"] == "1"
assert result["annotation"] == "int"
def test_code_parser_parse_function_def_not_init():
"""
Test the parse_function_def method of the
CodeParser class with a function that is not __init__.
"""
parser = CodeParser("")
stmt = ast.FunctionDef(
name="test",
args=ast.arguments(
args=[], vararg=None, kwonlyargs=[], kw_defaults=[], kwarg=None, defaults=[]
),
body=[],
decorator_list=[],
returns=None,
)
result, is_init = parser.parse_function_def(stmt)
assert result["name"] == "test"
assert not is_init
def test_code_parser_parse_function_def_init():
"""
Test the parse_function_def method of the
CodeParser class with an __init__ function.
"""
parser = CodeParser("")
stmt = ast.FunctionDef(
name="__init__",
args=ast.arguments(
args=[], vararg=None, kwonlyargs=[], kw_defaults=[], kwarg=None, defaults=[]
),
body=[],
decorator_list=[],
returns=None,
)
result, is_init = parser.parse_function_def(stmt)
assert result["name"] == "__init__"
assert is_init
def test_component_get_code_tree_syntax_error():
"""
Test the get_code_tree method of the Component class
raises the CodeSyntaxError when given incorrect syntax.
"""
component = Component(code="import os as", function_entrypoint_name="build")
with pytest.raises(CodeSyntaxError):
component.get_code_tree(component.code)
def test_custom_component_class_template_validation_no_code():
"""
Test the _class_template_validation method of the CustomComponent class
raises the HTTPException when the code is None.
"""
custom_component = CustomComponent(code=None, function_entrypoint_name="build")
with pytest.raises(HTTPException):
custom_component._class_template_validation(custom_component.code)
def test_custom_component_get_code_tree_syntax_error():
"""
Test the get_code_tree method of the CustomComponent class
raises the CodeSyntaxError when given incorrect syntax.
"""
custom_component = CustomComponent(
code="import os as", function_entrypoint_name="build"
)
with pytest.raises(CodeSyntaxError):
custom_component.get_code_tree(custom_component.code)
def test_custom_component_get_function_entrypoint_args_no_args():
"""
Test the get_function_entrypoint_args property of
the CustomComponent class with a build method with no arguments.
"""
my_code = """
class MyMainClass(CustomComponent):
def build():
pass"""
custom_component = CustomComponent(code=my_code, function_entrypoint_name="build")
args = custom_component.get_function_entrypoint_args
assert len(args) == 0
def test_custom_component_get_function_entrypoint_return_type_no_return_type():
"""
Test the get_function_entrypoint_return_type property of the
CustomComponent class with a build method with no return type.
"""
my_code = """
class MyClass(CustomComponent):
def build():
pass"""
custom_component = CustomComponent(code=my_code, function_entrypoint_name="build")
return_type = custom_component.get_function_entrypoint_return_type
assert return_type is None
def test_custom_component_get_main_class_name_no_main_class():
"""
Test the get_main_class_name property of the
CustomComponent class when there is no main class.
"""
my_code = """
def build():
pass"""
custom_component = CustomComponent(code=my_code, function_entrypoint_name="build")
class_name = custom_component.get_main_class_name
assert class_name == ""
def test_custom_component_build_not_implemented():
"""
Test the build method of the CustomComponent
class raises the NotImplementedError.
"""
custom_component = CustomComponent(
code="def build(): pass", function_entrypoint_name="build"
)
with pytest.raises(NotImplementedError):
custom_component.build()
def test_build_config_no_code():
component = CustomComponent(code=None)
assert component.get_function_entrypoint_args == ""
assert component.get_function_entrypoint_return_type == ""
@pytest.fixture
def component():
return CustomComponent(
field_config={
"fields": {
"llm": {"type": "str"},
"url": {"type": "str"},
"year": {"type": "int"},
}
}
)
@pytest.fixture(scope="session")
def test_flow(db):
flow_data = {
"nodes": [{"id": "1"}, {"id": "2"}],
"edges": [{"source": "1", "target": "2"}],
}
# Create flow
flow = FlowCreate(
id=uuid4(), name="Test Flow", description="Fixture flow", data=flow_data
)
# Add to database
db.add(flow)
db.commit()
yield flow
# Clean up
db.delete(flow)
db.commit()
@pytest.fixture(scope="session")
def db(app):
# Setup database for tests
yield app.db
# Teardown
app.db.drop_all()
def test_list_flows_return_type(component):
flows = component.list_flows()
assert isinstance(flows, list)
def test_list_flows_flow_objects(component):
flows = component.list_flows()
assert all(isinstance(flow, Flow) for flow in flows)
def test_build_config_return_type(component):
config = component.build_config()
assert isinstance(config, dict)
def test_build_config_has_fields(component):
config = component.build_config()
assert "fields" in config
def test_build_config_fields_dict(component):
config = component.build_config()
assert isinstance(config["fields"], dict)
def test_build_config_field_keys(component):
config = component.build_config()
assert all(isinstance(key, str) for key in config["fields"])
def test_build_config_field_values_dict(component):
config = component.build_config()
assert all(isinstance(value, dict) for value in config["fields"].values())
def test_build_config_field_value_keys(component):
config = component.build_config()
field_values = config["fields"].values()
assert all("type" in value for value in field_values)

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