Hugging Face's logo

Spaces:
joshuasundance
/
langchain-streamlit-demo
Running

App Files Community
langchain-streamlit-demo / README.md
Joshua Sundance Bailey
add gpt-4 to roadmap
9f78133
preview code
|
raw
history blame
3.46 kB
metadata
title: langchain-streamlit-demo
emoji: 🦜
colorFrom: green
colorTo: red
sdk: docker
app_port: 7860
pinned: true
tags:
  - langchain
  - streamlit
  - docker

langchain-streamlit-demo

License: MIT python security: bandit Ruff Code style: black pre-commit Checked with mypy

Docker Docker Image Size (tag) Open HuggingFace Space

This project shows how to build a simple chatbot UI with Streamlit and LangChain.

This README was written by Claude 2, an LLM from Anthropic.

Features

  • Chat interface for talking to AI assistant
  • Streaming output of assistant responses
  • Leverages LangChain for dialogue management
  • Integrates with LangSmith for tracing conversations
  • Allows giving feedback on assistant's responses

Usage

With Docker (pull from Docker Hub)

  1. Run in terminal: docker run -p 7860:7860 joshuasundance/langchain-streamlit-demo:latest
  2. Open http://localhost:7860 in your browser.

Docker Compose

  1. Clone the repo. Navigate to cloned repo directory.
  2. Run in terminal: docker-compose up
  3. Then open http://localhost:7860 in your browser.

Configuration

  • Enter your OpenAI API key to power the assistant
  • Optionally enter a LangSmith API key to enable conversation tracing
  • Customize the assistant prompt and temperature

Code Overview

  • app.py - Main Streamlit app definition
  • llm_stuff.py - LangChain helper functions

Deployment

The app is packaged as a Docker image for easy deployment. It is published to Docker Hub and Hugging Face Spaces:

CI workflows in .github/workflows handle building and publishing the image.

Links

TODO

  1. Let user choose between gpt-3.5-turbo and gpt-4
  2. Add support for Anthropic and Anyscale chat models
  3. More customization / parameterization in sidebar