Skip to content

Streamlit app to query tabular data with natural language. Upload CSV/XLSX, use a LangChain Pandas DataFrame agent + OpenAI for conversational Q&A and chat history.

Notifications You must be signed in to change notification settings

logicblocker/streamlit-data-chat

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 

Repository files navigation

streamlit-data-chat

Description

Python Streamlit web application that lets you chat with your data. Upload a CSV or XLSX file and ask questions in natural language; the app uses an LLM-powered agent to answer using your data.

The app uses Streamlit for the UI, pandas for data handling, and LangChain (with the OpenAI API) to run a Pandas DataFrame agent. You load your API key via environment variables, upload a file, and get a data preview plus a chat interface to query it.

App V3 Improvements

  1. API key via .env (e.g. OPENAI_API_KEY).
  2. Improved prompt for the agent, including prior chat context.
  3. Improved CSS.
  4. CSV and XLSX support.
  5. LLM temperature slider.

App V3 Screenshot

image

App V2 Improvements

Conversational memory and continuous chat instead of single Q&A.

Example Screenshots App V2

image

Example Screenshots App V1

image

Contact

About

Streamlit app to query tabular data with natural language. Upload CSV/XLSX, use a LangChain Pandas DataFrame agent + OpenAI for conversational Q&A and chat history.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages