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-0.1.1.tar.gz (4.3 kB view details)

Uploaded Source

Built Distribution

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

datachampsai-0.1.1-py3-none-any.whl (5.6 kB view details)

Uploaded Python 3

File details

Details for the file datachampsai-0.1.1.tar.gz.

File metadata

  • Download URL: datachampsai-0.1.1.tar.gz
  • Upload date:
  • Size: 4.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.3

File hashes

Hashes for datachampsai-0.1.1.tar.gz
Algorithm Hash digest
SHA256 50afdc10503faea5bebe38102b30faac2ffbd773d8b536abd6d2413288626c2a
MD5 247e12ed2c95b984707ac26693d1e704
BLAKE2b-256 16e3a92525741fabe832c31637236b28807ea15773980d925b43b5c3312ef85d

See more details on using hashes here.

File details

Details for the file datachampsai-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: datachampsai-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 5.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.3

File hashes

Hashes for datachampsai-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 2eb09ce364be76e15775c6d6f9474a22c6f6c7a8cc3f1110ce344b83f7b4cf27
MD5 f449ce38e00230caa1133b555302f2fd
BLAKE2b-256 0a0c98b8f537bb162def1b6f68f27af493fdb25332dc6c788674caebe3219353

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