Skip to main content

A Streamlit app that refines data queries using chat context and reference instructions.

Project description

ChatApp

ChatApp is a lightweight Python package that powers a Streamlit-based chatbot interface designed to refine user queries using prior chat history and a reference document.

The app uses OpenAI's GPT-4 model (via LangChain) to return:

  • A refined query, and
  • Additional context or logic to help with analysis or automation

🚀 Features

  • 🧠 Maintains full chat history across turns
  • 📄 Incorporates a static reference document with example queries and hints
  • 🤖 Integrates with OpenAI GPT-4 via LangChain
  • 📦 Package-style installation for easy sharing or deployment
  • ✅ Clean XML-style formatted response:
    <refined_query>
    ...
    </refined_query>
    
    <additional_info>
    ...
    </additional_info>
    

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

datachampsai-0.1.7.tar.gz (8.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

datachampsai-0.1.7-py3-none-any.whl (9.9 kB view details)

Uploaded Python 3

File details

Details for the file datachampsai-0.1.7.tar.gz.

File metadata

  • Download URL: datachampsai-0.1.7.tar.gz
  • Upload date:
  • Size: 8.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.3

File hashes

Hashes for datachampsai-0.1.7.tar.gz
Algorithm Hash digest
SHA256 8a78f83a65de736dbc22495e3781f0dd8cc4370d414a4bfc7754e7ad34eb5de6
MD5 7bb59262a2de7d0a7bc6d03817222d72
BLAKE2b-256 5c81a9400088ff5a8ce97fb381b5deb801c1bd0c25fce945399259fed32f9005

See more details on using hashes here.

File details

Details for the file datachampsai-0.1.7-py3-none-any.whl.

File metadata

  • Download URL: datachampsai-0.1.7-py3-none-any.whl
  • Upload date:
  • Size: 9.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.3

File hashes

Hashes for datachampsai-0.1.7-py3-none-any.whl
Algorithm Hash digest
SHA256 a00ae50fba39d0f4a6ded5162fd99be49f7cc5e85af798d005f4cc23909ba221
MD5 bc27ece4563e5cbf7b8f8b759265af76
BLAKE2b-256 b1df29275848ce63f1f9e0051f004d6ffd376f912a736e770973f5cd08cf3d87

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page