https://github.com/CharlyWargnier/LangchainRAG-Trubrics-Langsmith

https://github.com/CharlyWargnier/LangchainRAG-Trubrics-Langsmith

Last synced: 3 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/CharlyWargnier/LangchainRAG-Trubrics-Langsmith
• Owner: CharlyWargnier
• License: apache-2.0
• Created: 2023-09-17T20:21:25.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2023-11-12T13:17:47.000Z (about 1 year ago)
• Last Synced: 2024-07-05T22:14:57.990Z (5 months ago)
• Language: Python
• Homepage: https://langchain-rag-trubrics-langsmith.vercel.app
• Size: 834 KB
• Stars: 18
• Watchers: 3
• Forks: 13
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Chat with the Streamlit docs, collect feedback with Trubrics & LangSmith.









  









✨ Chat with the [Streamlit docs](https://docs.streamlit.io/) using [LangChain](https://www.langchain.com/) and collect feedback with [Trubrics](https://github.com/trubrics/streamlit-feedback) and [LangSmith](https://www.langchain.com/langsmith).

📖 To find out how to build this app and chat with your own docs, check our [blog post](https://blog.streamlit.io/how-in-app-feedback-can-increase-your-chatbots-performance/).

## Overview of the App



  



This demo app made with [Streamlit](https://streamlit.io/) allows users to chat with the [Streamlit docs](https://docs.streamlit.io/) using [LangChain](https://www.langchain.com/)'s Retrieval-Augmented Generation (RAG) capabilities. By integrating the [Trubrics' Feedback component](https://github.com/trubrics/streamlit-feedback), the app provides a dynamic way to capture user feedback, which is then monitored in [LangSmith](https://www.langchain.com/langsmith) for further analyses and improvements.

## Demo App

You can try out the demo on Streamlit Community Cloud

[![Streamlit App](https://static.streamlit.io/badges/streamlit_badge_black_white.svg)](https://rag-chatbot-with-user-feedback.streamlit.app/)

## Prerequisites

Ensure you have the necessary API keys:

### Get a LangSmith API key

Sign up for LangSmith at [smith.langchain.com](https://smith.langchain.com/) and generate an API Key.

To do this, click on the `API Key` icon and then click on `Create API Key` (make sure to copy it).



  



### Get an OpenAI API key

You can get your own OpenAI API key by following these instructions:

1. Go to https://platform.openai.com/account/api-keys.

2. Click on the `+ Create new secret key` button.

3. Next, enter an identifier name (optional) and click on the `Create secret key` button.

## Need Support?

If you require assistance or have any questions, feel free to reach out to me on X (formerly Twitter) at [@datachaz](https://twitter.com/datachaz) or on the [Streamlit forums](https://discuss.streamlit.io/)!