langflow-streamlit 0.1.8

No project description provided

Langflow Streamlit Integration

Table of Contents

1. Introduction
2. Installation
3. How to run
4. Starter Projects
   1. How to get Streamlit's Flows from the store
   2. Using Streamlit Components in Langflow
   3. Streamlit Components
5. Contributing
6. License
7. Contact

Introduction

langflow-streamlit is a powerful API that bridges the gap between Langflow and Streamlit applications. This library seamlessly integrates Langflow's advanced language processing capabilities with Streamlit's user-friendly interface, enabling developers to create interactive applications that harness the power of sophisticated language models.

Important: To use this library effectively, you need to set up a Langflow Store Key. This key allows you to access and use flows and components from the Langflow Store. For more information on setting up your Langflow Store Key, please refer to the Langflow documentation.

Features

• Seamless Integration: Effortlessly establish communication between Langflow and Streamlit with minimal configuration.
• Streamlined Deployment: Quickly install and run the API using either pip or poetry.
• Flexible Execution Options: Choose to run the full stack (Langflow + Streamlit API) or just the Streamlit backend with API.
• Langflow Store Integration: Access and utilize pre-built flows and Streamlit components from the Langflow Store to enhance your applications.

Requirements

• Python 3.10 or higher

Installation

Option 1: Install via pip

python3 -m venv env
source env/bin/activate
pip install langflow-streamlit==0.1.8

Option 2: Clone the repository and use Poetry

1. Clone the repository:

   git clone https://github.com/yaitec/langflow-streamlit.git
   cd langflow-streamlit
   

2. Install Poetry if you haven't already:

   pip install poetry
   

3. Install the project dependencies:

   poetry install
   

How to run

If choose pip installation option

1. Run the full stack (Langflow, API, and Streamlit):

   python -m langflow-streamlit run
   

2. Run only the Streamlit backend and API:

   python -m langflow-streamlit run --streamlit-only
   

If choose clone the repository option

1. Run the full stack (Langflow, API, and Streamlit):

   make start
   

2. Run only the Streamlit backend and API:

   make start-streamlit-only
   

Note: Running only the Streamlit backend is useful when you want to use Langflow-created flows in your Streamlit application without running the full Langflow instance.

How to open each aplication(after running the project)

Open the URLs below in your browser

• Streamlit Chat:: Available at http://localhost:5001.
• Streamlit API: The API Documentation can abe accessed at http://localhost:7881/docs.
• Langflow: Available at http://localhost:7860.

---

Starter Projects

How to get Streamlit's Flows from the store

The gif below shows how to search, download, and run Streamlit's flow:

Using Streamlit Components in Langflow

The gif below shows how to use Listen and Send components:

Streamlit Components

Langflow provides pre-built Streamlit components that can be accessed through the Langflow store. These components enhance your Streamlit applications with powerful functionality:

• Send: Send messages to a Streamlit chat session.
• Listen: Listen for incoming messages in a Streamlit chat, dynamically updating the layout of the Streamlit application.

To use these components:

1. Access the Langflow store within your Langflow instance.
2. Search for and download the desired Streamlit component.
3. Integrate the component into your Langflow workflow.
4. Connect the component to your Streamlit application using the langflow-streamlit API.

For detailed instructions on using Streamlit components, refer to the Usage section below.

---

Environment Variables

Variable	Description	Default
STREAMLIT_ONLY	If True, runs only Streamlit and Streamlit API; else, runs Langflow too	False
LOG_LEVEL	Defines log level of library	"info"
LOG_FILE_GENERATION	If True, creates a langflow-streamlit.log file for debug purpose and overrides LOG_LEVEL to 'debug'	False

Setting Environment Variables

You can learn how to set environment variables for each alternative bellow, click in the arrow that correlated to installation option that you choosed and check how to setup it properly.

If you choose pip installation option

these are the options that you can set:

langflow-streamlit --streamlit-only --log-level error --log-file-generation

If you choose clone the repository option

• Setting it in zsh or bash

  export STREAMLIT_ONLY=True LOG_LEVEL=debug LOG_FILE_GENERATION=True
  

• Setting it in PowerShell

  $env:STREAMLIT_ONLY = "True"
  $env:LOG_LEVEL = "debug"
  $env:LOG_FILE_GENERATION = "True"
  

Using Poetry (after cloning the repository)

1. Run the full stack:

   poetry run langflow-streamlit run
   

2. Run only the Streamlit frontend and API backend:

   poetry run langflow-streamlit run --streamlit-only
   

Using Make Commands

1. Run the full stack:

   make start
   

2. Run only the Streamlit frontend and API backend:

   make start-streamlit-only
   

3. Check the other available commands:

   make help
   

Development

To set up the development environment:

1. Clone the repository (if you haven't already).

2. Enter inside the cloned repository directory.

   cd <repository_path>
   

3. Install development dependencies:

   poetry install --with dev
   

4. Run tests:

   make test
   

5. Check code style:

   make lint
   

Contributing

We welcome contributions! Please feel free to submit a Pull Request or open an Issue on the GitHub repository.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

License

This project is licensed under the MIT License. See the LICENSE file for details.

Contact

YAITEC - [e-mail]

Project Link: https://github.com/yaitec/langflow-streamlit