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

fix: LangFlow -> Langflow

Browse source
This commit is contained in:
Gabriel Luiz Freitas Almeida 2023-07-12 19:30:37 -03:00
commit 049ba108bb
20 changed files with 196 additions and 177 deletions
Download patch file Download diff file Expand all files Collapse all files

14
docs/docs/contributing/community.md
View file

@ -1,23 +1,23 @@
# Community # Community
## 🤖 Join **LangFlow** Discord server ## 🤖 Join **Langflow** Discord server
Join us to ask questions and showcase your projects. Join us to ask questions and showcase your projects.
Let's bring together the building blocks of AI integration! Let's bring together the building blocks of AI integration!
LangFlow [Discord](https://discord.gg/EqksyE2EX9) server. Langflow [Discord](https://discord.gg/EqksyE2EX9) server.
--- ---
## 🐦 Stay tunned for **LangFlow** on Twitter ## 🐦 Stay tunned for **Langflow** on Twitter
Follow [@logspace_ai](https://twitter.com/logspace_ai) on **Twitter** to get the latest news about **LangFlow**. Follow [@logspace_ai](https://twitter.com/logspace_ai) on **Twitter** to get the latest news about **Langflow**.
--- ---
## ⭐️ Star **LangFlow** on GitHub ## ⭐️ Star **Langflow** on GitHub
You can "star" **LangFlow** in [GitHub](https://github.com/logspace-ai/langflow). You can "star" **Langflow** in [GitHub](https://github.com/logspace-ai/langflow).
By adding a star, other users will be able to find it more easily and see that it has been already useful for others. By adding a star, other users will be able to find it more easily and see that it has been already useful for others.
@ -25,7 +25,7 @@ By adding a star, other users will be able to find it more easily and see that i
## 👀 Watch the GitHub repository for releases ## 👀 Watch the GitHub repository for releases
You can "watch" **LangFlow** in [GitHub](https://github.com/logspace-ai/langflow). You can "watch" **Langflow** in [GitHub](https://github.com/logspace-ai/langflow).
If you select "Watching" instead of "Releases only" you will receive notifications when someone creates a new issue or question. You can also specify that you only want to be notified about new issues, discussions, PRs, etc. If you select "Watching" instead of "Releases only" you will receive notifications when someone creates a new issue or question. You can also specify that you only want to be notified about new issues, discussions, PRs, etc.

6
docs/docs/contributing/how-contribute.md
View file

@ -1,6 +1,6 @@
# How to contribute? # How to contribute?
👋 Hello there! We welcome contributions from developers of all levels to our open-source project on [GitHub](https://github.com/logspace-ai/langflow). If you'd like to contribute, please check our contributing guidelines and help make LangFlow more accessible. 👋 Hello there! We welcome contributions from developers of all levels to our open-source project on [GitHub](https://github.com/logspace-ai/langflow). If you'd like to contribute, please check our contributing guidelines and help make Langflow more accessible.
As an open-source project in a rapidly developing field, we are extremely open As an open-source project in a rapidly developing field, we are extremely open
to contributions, whether in the form of a new feature, improved infra, or better documentation. to contributions, whether in the form of a new feature, improved infra, or better documentation.
@ -12,7 +12,7 @@ Please do not try to push directly to this repo unless you are a maintainer.
--- ---
## Local development ## Local development
You can develop LangFlow using docker compose, or locally. You can develop Langflow using docker compose, or locally.
We provide a .vscode/launch.json file for debugging the backend in VSCode, which is a lot faster than using docker compose. We provide a .vscode/launch.json file for debugging the backend in VSCode, which is a lot faster than using docker compose.
@ -29,7 +29,7 @@ It is advised to run `make lint` before pushing to the repository.
## Run locally ## Run locally
LangFlow can run locally by cloning the repository and installing the dependencies. We recommend using a virtual environment to isolate the dependencies from your system. Langflow can run locally by cloning the repository and installing the dependencies. We recommend using a virtual environment to isolate the dependencies from your system.
Before you start, make sure you have the following installed: Before you start, make sure you have the following installed:

8
docs/docs/deployment/gcp-deployment.md
View file

@ -1,8 +1,8 @@
# Deploy on Google Cloud Platform # Deploy on Google Cloud Platform
## Run LangFlow from a New Google Cloud Project ## Run Langflow from a New Google Cloud Project
This guide will help you set up a LangFlow development VM in a Google Cloud Platform project using Google Cloud Shell. This guide will help you set up a Langflow development VM in a Google Cloud Platform project using Google Cloud Shell.
:::note :::note
When Cloud Shell opens, be sure to select **Trust repo**. Some `gcloud` commands might not run in an ephemeral Cloud Shell environment. When Cloud Shell opens, be sure to select **Trust repo**. Some `gcloud` commands might not run in an ephemeral Cloud Shell environment.
@ -12,7 +12,7 @@ When Cloud Shell opens, be sure to select **Trust repo**. Some `gcloud` commands
## Standard VM ## Standard VM
[![Open in Cloud Shell](https://gstatic.com/cloudssh/images/open-btn.svg)](https://console.cloud.google.com/cloudshell/open?git_repo=https://github.com/logspace-ai/langflow&working_dir=scripts&shellonly=true&tutorial=walkthroughtutorial.md) [![Open in Cloud Shell](https://gstatic.com/cloudssh/images/open-btn.svg)](https://console.cloud.google.com/cloudshell/open?git_repo=https://github.com/logspace-ai/langflow&working_dir=scripts&shellonly=true&tutorial=walkthroughtutorial.md)
This script sets up a Debian-based VM with the LangFlow package, Nginx, and the necessary configurations to run the LangFlow Dev environment. This script sets up a Debian-based VM with the Langflow package, Nginx, and the necessary configurations to run the Langflow Dev environment.
--- ---
@ -20,7 +20,7 @@ This script sets up a Debian-based VM with the LangFlow package, Nginx, and the
[![Open in Cloud Shell - Spot Instance](https://gstatic.com/cloudssh/images/open-btn.svg)](https://console.cloud.google.com/cloudshell/open?git_repo=https://github.com/genome21/langflow&working_dir=scripts&shellonly=true&tutorial=walkthroughtutorial_spot.md) [![Open in Cloud Shell - Spot Instance](https://gstatic.com/cloudssh/images/open-btn.svg)](https://console.cloud.google.com/cloudshell/open?git_repo=https://github.com/genome21/langflow&working_dir=scripts&shellonly=true&tutorial=walkthroughtutorial_spot.md)
When running as a [spot (preemptible) instance](https://cloud.google.com/compute/docs/instances/preemptible), the code and VM will behave the same way as in a regular instance, executing the startup script to configure the environment, install necessary dependencies, and run the LangFlow application. However, **due to the nature of spot instances, the VM may be terminated at any time if Google Cloud needs to reclaim the resources**. This makes spot instances suitable for fault-tolerant, stateless, or interruptible workloads that can handle unexpected terminations and restarts. When running as a [spot (preemptible) instance](https://cloud.google.com/compute/docs/instances/preemptible), the code and VM will behave the same way as in a regular instance, executing the startup script to configure the environment, install necessary dependencies, and run the Langflow application. However, **due to the nature of spot instances, the VM may be terminated at any time if Google Cloud needs to reclaim the resources**. This makes spot instances suitable for fault-tolerant, stateless, or interruptible workloads that can handle unexpected terminations and restarts.
--- ---

6
docs/docs/deployment/jina-deployment.md
View file

@ -1,6 +1,6 @@
# Deploy on Jina AI Cloud # Deploy on Jina AI Cloud
LangFlow integrates with langchain-serve to provide a one-command deployment to [Jina AI Cloud](https://github.com/jina-ai/langchain-serve). Langflow integrates with langchain-serve to provide a one-command deployment to [Jina AI Cloud](https://github.com/jina-ai/langchain-serve).
Start by installing `langchain-serve` with Start by installing `langchain-serve` with
@ -51,7 +51,7 @@ langflow --jcloud
``` ```
## API Usage (with python) ## API Usage (with python)
You can use LangFlow directly on your browser or the API endpoints on Jina AI Cloud to interact with the server. You can use Langflow directly on your browser or the API endpoints on Jina AI Cloud to interact with the server.
```python ```python
import requests import requests
@ -96,6 +96,6 @@ print(run_flow("Your message", flow_id=FLOW_ID, tweaks=TWEAKS))
:::info :::info
Read more about resource customization, cost, and management of LangFlow apps on Jina AI Cloud in the **[langchain-serve](https://github.com/jina-ai/langchain-serve)** repository. Read more about resource customization, cost, and management of Langflow apps on Jina AI Cloud in the **[langchain-serve](https://github.com/jina-ai/langchain-serve)** repository.
::: :::

16
docs/docs/examples/buffer-memory.mdx
View file

@ -2,24 +2,24 @@
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. 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.
## ⛓️ LangFlow Example ## ⛓️ Langflow Example
import ThemedImage from '@theme/ThemedImage';
import useBaseUrl from '@docusaurus/useBaseUrl';
import ZoomableImage from '/src/theme/ZoomableImage.js';
import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from "@docusaurus/useBaseUrl";
import ZoomableImage from "/src/theme/ZoomableImage.js";
<ZoomableImage <ZoomableImage
alt="Docusaurus themed image" alt="Docusaurus themed image"
sources={{ sources={{
light: 'img/buffer-memory.png', light: "img/buffer-memory.png",
}} }}
/> />
#### <a target="\_blank" href="json_files/Buffer_Memory.json" download>Download Flow</a> #### <a target="\_blank" href="json_files/Buffer_Memory.json" download>Download Flow</a>
:::note LangChain Components 🦜🔗 :::note LangChain Components 🦜🔗
- [`ConversationBufferMemory`](https://python.langchain.com/docs/modules/memory/how_to/buffer) - [`ConversationBufferMemory`](https://python.langchain.com/docs/modules/memory/how_to/buffer)
- [`ConversationChain`](https://python.langchain.com/docs/modules/chains/) - [`ConversationChain`](https://python.langchain.com/docs/modules/chains/)
- [`ChatOpenAI`](https://python.langchain.com/docs/modules/model_io/models/chat/integrations/openai) - [`ChatOpenAI`](https://python.langchain.com/docs/modules/model_io/models/chat/integrations/openai)
::: :::

17
docs/docs/examples/conversation-chain.mdx
View file

@ -6,24 +6,23 @@ This example shows how to instantiate a simple `ConversationChain` component usi
Make sure to always get the API key from the provider. Make sure to always get the API key from the provider.
::: :::
## ⛓️ Langflow Example
## ⛓️ LangFlow Example import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from "@docusaurus/useBaseUrl";
import ThemedImage from '@theme/ThemedImage'; import ZoomableImage from "/src/theme/ZoomableImage.js";
import useBaseUrl from '@docusaurus/useBaseUrl';
import ZoomableImage from '/src/theme/ZoomableImage.js';
<ZoomableImage <ZoomableImage
alt="Docusaurus themed image" alt="Docusaurus themed image"
sources={{ sources={{
light: 'img/basic-chat.png', light: "img/basic-chat.png",
}} }}
/> />
#### <a target="\_blank" href="json_files/Basic_Chat.json" download>Download Flow</a> #### <a target="\_blank" href="json_files/Basic_Chat.json" download>Download Flow</a>
:::note LangChain Components 🦜🔗 :::note LangChain Components 🦜🔗
- [`ConversationChain`](https://python.langchain.com/docs/modules/chains/) - [`ConversationChain`](https://python.langchain.com/docs/modules/chains/)
- [`ChatOpenAI`](https://python.langchain.com/docs/modules/model_io/models/chat/integrations/openai) - [`ChatOpenAI`](https://python.langchain.com/docs/modules/model_io/models/chat/integrations/openai)
::: :::

17
docs/docs/examples/csv-loader.mdx
View file

@ -15,24 +15,23 @@ The vector store is used for efficient semantic search, while `VectorStoreInfo`
Once you build this flow, ask questions about the data in the chat interface (e.g., number of rows or columns). Once you build this flow, ask questions about the data in the chat interface (e.g., number of rows or columns).
::: :::
## ⛓️ Langflow Example
## ⛓️ LangFlow Example import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from "@docusaurus/useBaseUrl";
import ThemedImage from '@theme/ThemedImage'; import ZoomableImage from "/src/theme/ZoomableImage.js";
import useBaseUrl from '@docusaurus/useBaseUrl';
import ZoomableImage from '/src/theme/ZoomableImage.js';
<ZoomableImage <ZoomableImage
alt="Docusaurus themed image" alt="Docusaurus themed image"
sources={{ sources={{
light: 'img/csv-loader.png', light: "img/csv-loader.png",
}} }}
/> />
#### <a target="\_blank" href="json_files/CSV_Loader.json" download>Download Flow</a> #### <a target="\_blank" href="json_files/CSV_Loader.json" download>Download Flow</a>
:::note LangChain Components 🦜🔗 :::note LangChain Components 🦜🔗
- [`CSVLoader`](https://python.langchain.com/docs/modules/data_connection/document_loaders/integrations/csv) - [`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) - [`CharacterTextSplitter`](https://python.langchain.com/docs/modules/data_connection/document_transformers/text_splitters/character_text_splitter)
- [`OpenAIEmbedding`](https://python.langchain.com/docs/modules/data_connection/text_embedding/integrations/openai) - [`OpenAIEmbedding`](https://python.langchain.com/docs/modules/data_connection/text_embedding/integrations/openai)
@ -40,4 +39,4 @@ import ZoomableImage from '/src/theme/ZoomableImage.js';
- [`VectorStoreInfo`](https://python.langchain.com/docs/modules/data_connection/vectorstores/) - [`VectorStoreInfo`](https://python.langchain.com/docs/modules/data_connection/vectorstores/)
- [`OpenAI`](https://python.langchain.com/docs/modules/model_io/models/llms/integrations/openai) - [`OpenAI`](https://python.langchain.com/docs/modules/model_io/models/llms/integrations/openai)
- [`VectorStoreAgent`](https://python.langchain.com/docs/modules/agents/toolkits/vectorstore) - [`VectorStoreAgent`](https://python.langchain.com/docs/modules/agents/toolkits/vectorstore)
::: :::

16
docs/docs/examples/how-upload-examples.mdx
View file

@ -1,17 +1,19 @@
import ThemedImage from '@theme/ThemedImage'; import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from '@docusaurus/useBaseUrl'; import useBaseUrl from "@docusaurus/useBaseUrl";
import ZoomableImage from '/src/theme/ZoomableImage.js'; import ZoomableImage from "/src/theme/ZoomableImage.js";
# 📚 How to Upload Examples? # 📚 How to Upload Examples?
We welcome all examples that can help our community learn and explore LangFlow's capabilities. We welcome all examples that can help our community learn and explore Langflow's capabilities.
Langflow Examples is a repository on [GitHub](https://github.com/logspace-ai/langflow_examples) that contains examples of flows that people can use for inspiration and learning. Langflow Examples is a repository on [GitHub](https://github.com/logspace-ai/langflow_examples) that contains examples of flows that people can use for inspiration and learning.
<div style={{ marginBottom: '20px', display: 'flex', justifyContent: 'center' }}> <div
<ZoomableImage style={{ marginBottom: "20px", display: "flex", justifyContent: "center" }}
>
<ZoomableImage
alt="Docusaurus themed image" alt="Docusaurus themed image"
sources={{ sources={{
light: 'img/community-examples.png', light: "img/community-examples.png",
}} }}
/> />
</div> </div>

16
docs/docs/examples/midjourney-prompt-chain.mdx
View file

@ -18,23 +18,23 @@ Imagine a mysterious forest, the trees are tall and ancient, their branches reac
Notice that the `ConversationSummaryMemory` stores a summary of the conversation over time. Try using it to create better prompts as the conversation goes on. Notice that the `ConversationSummaryMemory` stores a summary of the conversation over time. Try using it to create better prompts as the conversation goes on.
::: :::
## ⛓️ LangFlow Example ## ⛓️ Langflow Example
import ThemedImage from '@theme/ThemedImage';
import useBaseUrl from '@docusaurus/useBaseUrl';
import ZoomableImage from '/src/theme/ZoomableImage.js';
import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from "@docusaurus/useBaseUrl";
import ZoomableImage from "/src/theme/ZoomableImage.js";
<ZoomableImage <ZoomableImage
alt="Docusaurus themed image" alt="Docusaurus themed image"
sources={{ sources={{
light: 'img/midjourney-prompt-chain.png', light: "img/midjourney-prompt-chain.png",
}} }}
/> />
#### <a target="\_blank" href="json_files/MidJourney_Prompt_Chain.json" download>Download Flow</a> #### <a target="\_blank" href="json_files/MidJourney_Prompt_Chain.json" download>Download Flow</a>
:::note LangChain Components 🦜🔗 :::note LangChain Components 🦜🔗
- [`OpenAI`](https://python.langchain.com/docs/modules/model_io/models/llms/integrations/openai) - [`OpenAI`](https://python.langchain.com/docs/modules/model_io/models/llms/integrations/openai)
- [`ConversationSummaryMemory`](https://python.langchain.com/docs/modules/memory/how_to/summary) - [`ConversationSummaryMemory`](https://python.langchain.com/docs/modules/memory/how_to/summary)
::: :::

18
docs/docs/examples/multiple-vectorstores.mdx
View file

@ -1,16 +1,15 @@
# Multiple Vector Stores # Multiple Vector Stores
The example below shows an agent operating with two vector stores built upon different data sources. 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. 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 :::info
Get the TXT file used [here](https://github.com/hwchase17/chat-your-data/blob/master/state_of_the_union.txt). Get the TXT file used [here](https://github.com/hwchase17/chat-your-data/blob/master/state_of_the_union.txt).
::: :::
URL used by the `WebBaseLoader`: URL used by the `WebBaseLoader`:
```txt ```txt
https://pt.wikipedia.org/wiki/Harry_Potter https://pt.wikipedia.org/wiki/Harry_Potter
``` ```
@ -23,24 +22,23 @@ When you build the flow, request information about one of the sources. The agent
Learn more about Multiple Vector Stores [here](https://python.langchain.com/docs/modules/agents/toolkits/vectorstore?highlight=Multiple%20Vector%20Stores#multiple-vectorstores). Learn more about Multiple Vector Stores [here](https://python.langchain.com/docs/modules/agents/toolkits/vectorstore?highlight=Multiple%20Vector%20Stores#multiple-vectorstores).
::: :::
## ⛓️ Langflow Example
## ⛓️ LangFlow Example import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from "@docusaurus/useBaseUrl";
import ThemedImage from '@theme/ThemedImage'; import ZoomableImage from "/src/theme/ZoomableImage.js";
import useBaseUrl from '@docusaurus/useBaseUrl';
import ZoomableImage from '/src/theme/ZoomableImage.js';
<ZoomableImage <ZoomableImage
alt="Docusaurus themed image" alt="Docusaurus themed image"
sources={{ sources={{
light: 'img/multiple-vectorstores.png', light: "img/multiple-vectorstores.png",
}} }}
/> />
#### <a target="\_blank" href="json_files/Multiple_Vector_Stores.json" download>Download Flow</a> #### <a target="\_blank" href="json_files/Multiple_Vector_Stores.json" download>Download Flow</a>
:::note LangChain Components 🦜🔗 :::note LangChain Components 🦜🔗
- [`WebBaseLoader`](https://python.langchain.com/docs/modules/data_connection/document_loaders/integrations/web_base) - [`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) - [`TextLoader`](https://python.langchain.com/docs/modules/data_connection/document_loaders/integrations/unstructured_file)
- [`CharacterTextSplitter`](https://python.langchain.com/docs/modules/data_connection/document_transformers/text_splitters/character_text_splitter) - [`CharacterTextSplitter`](https://python.langchain.com/docs/modules/data_connection/document_transformers/text_splitters/character_text_splitter)

22
docs/docs/examples/python-function.mdx
View file

@ -1,7 +1,6 @@
# Python Function # 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.
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.
```python ```python
import re import re
@ -17,34 +16,33 @@ def is_brazilian_zipcode(zipcode: str) -> bool:
``` ```
:::tip :::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. 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.
::: :::
The `AgentInitializer` component is a quick way to construct an agent from the model and tools. The `AgentInitializer` component is a quick way to construct an agent from the model and tools.
:::info :::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). 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).
::: :::
## ⛓️ Langflow Example
## ⛓️ LangFlow Example import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from "@docusaurus/useBaseUrl";
import ThemedImage from '@theme/ThemedImage'; import ZoomableImage from "/src/theme/ZoomableImage.js";
import useBaseUrl from '@docusaurus/useBaseUrl';
import ZoomableImage from '/src/theme/ZoomableImage.js';
<ZoomableImage <ZoomableImage
alt="Docusaurus themed image" alt="Docusaurus themed image"
sources={{ sources={{
light: 'img/python-function.png', light: "img/python-function.png",
}} }}
/> />
#### <a target="\_blank" href="json_files/Python_Function.json" download>Download Flow</a> #### <a target="\_blank" href="json_files/Python_Function.json" download>Download Flow</a>
:::note LangChain Components 🦜🔗 :::note LangChain Components 🦜🔗
- [`PythonFunctionTool`](https://python.langchain.com/docs/modules/agents/tools/how_to/custom_tools) - [`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) - [`ChatOpenAI`](https://python.langchain.com/docs/modules/model_io/models/chat/integrations/openai)
- [`AgentInitializer`](https://python.langchain.com/docs/modules/agents/) - [`AgentInitializer`](https://python.langchain.com/docs/modules/agents/)
::: :::

21
docs/docs/examples/serp-api-tool.mdx
View file

@ -1,9 +1,9 @@
# Serp API Tool # 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. 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 :::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. 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.
::: :::
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. 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.
@ -14,33 +14,32 @@ The `LLMChain` is a simple chain that takes in a prompt template, formats it wit
In this example, we used [`ChatOpenAI`](https://platform.openai.com/) as the LLM, but feel free to experiment with other Language Models! In this example, we used [`ChatOpenAI`](https://platform.openai.com/) as the LLM, but feel free to experiment with other Language Models!
::: :::
The `ZeroShotAgent` takes the `LLMChain` and the `Search` tool as inputs, using the tool to find information when necessary. The `ZeroShotAgent` takes the `LLMChain` and the `Search` tool as inputs, using the tool to find information when necessary.
:::info :::info
Learn more about the Serp API [here](https://python.langchain.com/docs/modules/agents/tools/integrations/serpapi). Learn more about the Serp API [here](https://python.langchain.com/docs/modules/agents/tools/integrations/serpapi).
::: :::
## ⛓️ LangFlow Example ## ⛓️ Langflow Example
import ThemedImage from '@theme/ThemedImage'; import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from '@docusaurus/useBaseUrl'; import useBaseUrl from "@docusaurus/useBaseUrl";
import ZoomableImage from '/src/theme/ZoomableImage.js'; import ZoomableImage from "/src/theme/ZoomableImage.js";
<ZoomableImage <ZoomableImage
alt="Docusaurus themed image" alt="Docusaurus themed image"
sources={{ sources={{
light: 'img/serp-api-tool.png', light: "img/serp-api-tool.png",
}} }}
/> />
#### <a target="\_blank" href="json_files/SerpAPI_Tool.json" download>Download Flow</a> #### <a target="\_blank" href="json_files/SerpAPI_Tool.json" download>Download Flow</a>
:::note LangChain Components 🦜🔗 :::note LangChain Components 🦜🔗
- [`ZeroShotPrompt`](https://python.langchain.com/docs/modules/model_io/prompts/prompt_templates/) - [`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) - [`OpenAI`](https://python.langchain.com/docs/modules/model_io/models/llms/integrations/openai)
- [`LLMChain`](https://python.langchain.com/docs/modules/chains/foundational/llm_chain) - [`LLMChain`](https://python.langchain.com/docs/modules/chains/foundational/llm_chain)
- [`Search`](https://python.langchain.com/docs/modules/agents/tools/integrations/serpapi) - [`Search`](https://python.langchain.com/docs/modules/agents/tools/integrations/serpapi)
- [`ZeroShotAgent`](https://python.langchain.com/docs/modules/agents/how_to/custom_mrkl_agent) - [`ZeroShotAgent`](https://python.langchain.com/docs/modules/agents/how_to/custom_mrkl_agent)
::: :::

30
docs/docs/getting-started/creating-flows.mdx
View file

@ -1,37 +1,37 @@
import ThemedImage from '@theme/ThemedImage'; import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from '@docusaurus/useBaseUrl'; import useBaseUrl from "@docusaurus/useBaseUrl";
import ZoomableImage from '/src/theme/ZoomableImage.js'; import ZoomableImage from "/src/theme/ZoomableImage.js";
import ReactPlayer from 'react-player'; import ReactPlayer from "react-player";
# 🎨 Creating Flows # 🎨 Creating Flows
## Compose ## Compose
Creating flows with LangFlow is easy. Drag sidebar components onto the canvas and connect them together to create your pipeline. LangFlow provides a range of [LangChain components](https://python.langchain.com/docs/modules/) to choose from, including LLMs, prompt serializers, agents, and chains. Creating flows with Langflow is easy. Drag sidebar components onto the canvas and connect them together to create your pipeline. Langflow provides a range of [LangChain components](https://python.langchain.com/docs/modules/) to choose from, including LLMs, prompt serializers, agents, and chains.
<ZoomableImage <ZoomableImage
alt="Docusaurus themed image" alt="Docusaurus themed image"
sources={{ sources={{
light: 'img/langflow_canvas.png', light: "img/langflow_canvas.png",
}} }}
/> />
## Fork ## Fork
The easiest way to start with LangFlow is by forking a **community example**. Forking an example stores a copy in your project collection, allowing you to edit and save the modified version as a new flow. The easiest way to start with Langflow is by forking a **community example**. Forking an example stores a copy in your project collection, allowing you to edit and save the modified version as a new flow.
<div style={{ marginBottom: '20px', display: 'flex', justifyContent: 'center' }}> <div
<ReactPlayer playing controls url='/videos/langflow_fork.mp4' style={{ marginBottom: "20px", display: "flex", justifyContent: "center" }}
/> >
<ReactPlayer playing controls url="/videos/langflow_fork.mp4" />
</div> </div>
## Build ## Build
Building a flow means validating if the components have prerequisites fulfilled and are properly instantiated. When a chat message is sent, the flow will run for the first time, executing the pipeline. Building a flow means validating if the components have prerequisites fulfilled and are properly instantiated. When a chat message is sent, the flow will run for the first time, executing the pipeline.
<div style={{ marginBottom: '20px', display: 'flex', justifyContent: 'center' }}> <div
<ReactPlayer playing controls url='/videos/langflow_build.mp4' style={{ marginBottom: "20px", display: "flex", justifyContent: "center" }}
/> >
<ReactPlayer playing controls url="/videos/langflow_build.mp4" />
</div> </div>

18
docs/docs/getting-started/hugging-face-spaces.mdx
View file

@ -1,18 +1,20 @@
# 🤗 HuggingFace Spaces # 🤗 HuggingFace Spaces
A fully featured version of LangFlow can be accessed via HuggingFace spaces with no installation required. A fully featured version of Langflow can be accessed via HuggingFace spaces with no installation required.
import ThemedImage from '@theme/ThemedImage'; import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from '@docusaurus/useBaseUrl'; import useBaseUrl from "@docusaurus/useBaseUrl";
import ZoomableImage from '/src/theme/ZoomableImage.js'; import ZoomableImage from "/src/theme/ZoomableImage.js";
<div style={{ marginBottom: '20px', display: 'flex', justifyContent: 'center' }}> <div
<ZoomableImage style={{ marginBottom: "20px", display: "flex", justifyContent: "center" }}
>
<ZoomableImage
alt="Docusaurus themed image" alt="Docusaurus themed image"
sources={{ sources={{
light: 'img/hugging-face.png', light: "img/hugging-face.png",
}} }}
/> />
</div> </div>
Check out LangFlow on [HuggingFace Spaces](https://huggingface.co/spaces/Logspace/LangFlow). Check out Langflow on [HuggingFace Spaces](https://huggingface.co/spaces/Logspace/Langflow).

2
docs/docs/getting-started/installation.md
View file

@ -2,7 +2,7 @@
## Installation ## Installation
You can install LangFlow from pip: You can install Langflow from pip:
```bash ```bash
pip install langflow pip install langflow

55
docs/docs/guidelines/components.mdx
View file

@ -1,44 +1,59 @@
import ThemedImage from '@theme/ThemedImage'; import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from '@docusaurus/useBaseUrl'; import useBaseUrl from "@docusaurus/useBaseUrl";
import ZoomableImage from '/src/theme/ZoomableImage.js'; import ZoomableImage from "/src/theme/ZoomableImage.js";
import ReactPlayer from 'react-player'; import ReactPlayer from "react-player";
# Component # Component
Components are the building blocks of the flows. They are made of inputs, outputs, and parameters that define their functionality, providing a convenient and straightforward way to compose LLM-based applications. Learn more about components and how they work in the LangChain [documentation](https://docs.langchain.com/docs/category/components) section. Components are the building blocks of the flows. They are made of inputs, outputs, and parameters that define their functionality, providing a convenient and straightforward way to compose LLM-based applications. Learn more about components and how they work in the LangChain [documentation](https://docs.langchain.com/docs/category/components) section.
### Component's Features ### Component's Features
<div style={{ marginBottom: '20px' }}> <div style={{ marginBottom: "20px" }}>
During the flow creation process, you will notice handles (colored circles) attached to one or both sides of a component. These handles represent the availability to connect to other components, while their colors are type hints (hover over a handle to see connection details).</div> During the flow creation process, you will notice handles (colored circles)
attached to one or both sides of a component. These handles represent the
<div style={{ marginBottom: '20px' }}> availability to connect to other components, while their colors are type hints
For example, if you select a <code>ConversationChain</code> component, you will see orange <span style={{ color: 'orange' }}>o</span> and purple <span style={{ color: 'purple' }}>o</span> input handles. They indicate that this component accepts an LLM and a Memory component as inputs. The red asterisk <span style={{ color: 'red' }}>*</span> means that at least one input of that type is required. (hover over a handle to see connection details).
</div> </div>
<div style={{ marginBottom: '20px', display: 'flex', justifyContent: 'center' }}> <div style={{ marginBottom: "20px" }}>
For example, if you select a <code>ConversationChain</code> component, you
will see orange <span style={{ color: "orange" }}>o</span> and purple{" "}
<span style={{ color: "purple" }}>o</span> input handles. They indicate that
this component accepts an LLM and a Memory component as inputs. The red
asterisk <span style={{ color: "red" }}>*</span> means that at least one input
of that type is required.
</div>
<div
style={{ marginBottom: "20px", display: "flex", justifyContent: "center" }}
>
<ZoomableImage <ZoomableImage
alt="Docusaurus themed image" alt="Docusaurus themed image"
sources={{ sources={{
light: useBaseUrl('img/single-compenent.png'), light: useBaseUrl("img/single-compenent.png"),
}} }}
style={{ width: '100%', maxWidth: '800px', margin: '0 auto' }} style={{ width: "100%", maxWidth: "800px", margin: "0 auto" }}
/> />
</div> </div>
<div style={{ marginBottom: "20px" }}>
<div style={{ marginBottom: '20px' }}> On the top right corner, you will find the component status icon 🔴. Make the
On the top right corner, you will find the component status icon 🔴. Make the necessary connections, build the flow (⚡ zap icon on the bottom right of the canvas) and once the validation is completed, the status of each validated component should light green 🟢. Hover over the component status to reveal the outputs going through it in case of success, or the detected error in case of failure. necessary connections, build the flow (⚡ zap icon on the bottom right of the
canvas) and once the validation is completed, the status of each validated
component should light green 🟢. Hover over the component status to reveal the
outputs going through it in case of success, or the detected error in case of
failure.
</div> </div>
--- ---
### Component's Parameters ### Component's Parameters
LangFlow components can be edited in the component settings button. Hide parameters to reduce complexity and keep the canvas clean and intuitive for experimentation. Langflow components can be edited in the component settings button. Hide parameters to reduce complexity and keep the canvas clean and intuitive for experimentation.
<div style={{ marginBottom: '20px', display: 'flex', justifyContent: 'center' }}> <div
<ReactPlayer playing controls url='/videos/langflow_parameters.mp4' style={{ marginBottom: "20px", display: "flex", justifyContent: "center" }}
/> >
<ReactPlayer playing controls url="/videos/langflow_parameters.mp4" />
</div> </div>

39
docs/docs/guidelines/features.mdx
View file

@ -1,27 +1,31 @@
import ThemedImage from '@theme/ThemedImage'; import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from '@docusaurus/useBaseUrl'; import useBaseUrl from "@docusaurus/useBaseUrl";
import ZoomableImage from '/src/theme/ZoomableImage.js'; import ZoomableImage from "/src/theme/ZoomableImage.js";
import ReactPlayer from 'react-player'; import ReactPlayer from "react-player";
# Features # Features
<div style={{ marginBottom: '20px' }}> <div style={{ marginBottom: "20px" }}>
When you click for New Project, you will see on the top left corner of the screen, some options such as <strong>Import</strong>, <strong>Export</strong>, <strong>Code</strong> and <strong>Save</strong>, as displayed in the image below: When you click for New Project, you will see on the top left corner of the
screen, some options such as <strong>Import</strong>, <strong>Export</strong>,{" "}
<strong>Code</strong> and <strong>Save</strong>, as displayed in the image
below:
</div> </div>
<div
<div style={{ marginBottom: '20px', display: 'flex', justifyContent: 'center' }}> style={{ marginBottom: "20px", display: "flex", justifyContent: "center" }}
>
<ZoomableImage <ZoomableImage
alt="Docusaurus themed image" alt="Docusaurus themed image"
sources={{ sources={{
light: useBaseUrl('img/features.png'), light: useBaseUrl("img/features.png"),
}} }}
style={{ width: '100%', maxWidth: '800px', margin: '0 auto' }} style={{ width: "100%", maxWidth: "800px", margin: "0 auto" }}
/> />
</div> </div>
<div style={{ marginBottom: '20px' }}> <div style={{ marginBottom: "20px" }}>
Further down, we will explain each of these options. Further down, we will explain each of these options.
</div> </div>
--- ---
@ -42,14 +46,14 @@ The Code button shows snippets to use your flow as a Python object or an API.
**Python Code** **Python Code**
Through the LangFlow package, you can load a flow from a JSON file and use it as a LangChain object. Through the Langflow package, you can load a flow from a JSON file and use it as a LangChain object.
```py ```py
from langflow import load_flow_from_json from langflow import load_flow_from_json
flow = load_flow_from_json("path/to/flow.json") flow = load_flow_from_json("path/to/flow.json")
# Now you can use it like any chain # Now you can use it like any chain
flow("Hey, have you heard of LangFlow?") flow("Hey, have you heard of Langflow?")
``` ```
**API** **API**
@ -58,7 +62,8 @@ Once you save a flow, the API endpoint is created with your latest changes. Clic
The example below shows a Python script making a POST request to a local API endpoint, which gets a prediction based on the message input. The example below shows a Python script making a POST request to a local API endpoint, which gets a prediction based on the message input.
<div style={{ marginBottom: '20px', display: 'flex', justifyContent: 'center' }}> <div
<ReactPlayer playing controls url='/videos/langflow_api.mp4' style={{ marginBottom: "20px", display: "flex", justifyContent: "center" }}
/> >
<ReactPlayer playing controls url="/videos/langflow_api.mp4" />
</div> </div>

18
docs/docs/index.mdx
View file

@ -1,16 +1,18 @@
# 👋 Welcome to LangFlow # 👋 Welcome to Langflow
LangFlow is an easy way to prototype [LangChain](https://github.com/hwchase17/langchain) flows. The drag-and-drop feature allows quick and effortless experimentation, while the built-in chat interface facilitates real-time interaction. It provides options to edit prompt parameters, create chains and agents, track thought processes, and export flows. Langflow is an easy way to prototype [LangChain](https://github.com/hwchase17/langchain) flows. The drag-and-drop feature allows quick and effortless experimentation, while the built-in chat interface facilitates real-time interaction. It provides options to edit prompt parameters, create chains and agents, track thought processes, and export flows.
import ThemedImage from '@theme/ThemedImage'; import ThemedImage from "@theme/ThemedImage";
import useBaseUrl from '@docusaurus/useBaseUrl'; import useBaseUrl from "@docusaurus/useBaseUrl";
import ZoomableImage from '/src/theme/ZoomableImage.js'; import ZoomableImage from "/src/theme/ZoomableImage.js";
<div style={{ marginBottom: '20px', display: 'flex', justifyContent: 'center' }}> <div
<ZoomableImage style={{ marginBottom: "20px", display: "flex", justifyContent: "center" }}
>
<ZoomableImage
alt="Docusaurus themed image" alt="Docusaurus themed image"
sources={{ sources={{
light: 'img/new_langflow2.gif', light: "img/new_langflow2.gif",
}} }}
/> />
</div> </div>

4
src/frontend/src/constants.tsx
View file

@ -236,13 +236,13 @@ export const DESCRIPTIONS: string[] = [
"Your Hub for Text Generation.", "Your Hub for Text Generation.",
"Promptly Ingenious!", "Promptly Ingenious!",
"Building Linguistic Labyrinths.", "Building Linguistic Labyrinths.",
"LangFlow: Create, Chain, Communicate.", "Langflow: Create, Chain, Communicate.",
"Connect the Dots, Craft Language.", "Connect the Dots, Craft Language.",
"Interactive Language Weaving.", "Interactive Language Weaving.",
"Generate, Innovate, Communicate.", "Generate, Innovate, Communicate.",
"Conversation Catalyst Engine.", "Conversation Catalyst Engine.",
"Language Chainlink Master.", "Language Chainlink Master.",
"Design Dialogues with LangFlow.", "Design Dialogues with Langflow.",
"Nurture NLP Nodes Here.", "Nurture NLP Nodes Here.",
"Conversational Cartography Unlocked.", "Conversational Cartography Unlocked.",
"Design, Develop, Dialogize.", "Design, Develop, Dialogize.",

2
src/frontend/src/modals/formModal/index.tsx
View file

@ -529,7 +529,7 @@ export default function FormModal({
<span> <span>
👋{" "} 👋{" "}
<span className="langflow-chat-span"> <span className="langflow-chat-span">
LangFlow Chat Langflow Chat
</span> </span>
</span> </span>
<br /> <br />