Skip to main content

AI-powered chat application with multi-provider support and embedded web UI

Project description

AIDiscuss

AI-powered chat application with multi-provider support and embedded web UI

AIDiscuss is a modern, production-ready AI chat application that supports multiple LLM providers (Anthropic, OpenAI, Google, Groq) with advanced features like RAG, memory management, and multi-agent conversations. Built with FastAPI and React, distributed as a PyPI package.

Features

  • Multi-Provider Support: Anthropic Claude, OpenAI, Google Gemini, Groq
  • Advanced AI Features: RAG (Retrieval-Augmented Generation), conversation memory, multi-agent orchestration
  • Embedded Web UI: Beautiful React interface bundled with the Python package
  • Multi-Environment Isolation: Automatic data separation for virtual environments vs global installs
  • Secure by Default: Local-only storage, localhost binding, bytecode distribution
  • Production Ready: Structured logging, version checking, graceful error handling

Installation

pip install aidiscuss

Requires Python 3.11+

Usage

aidiscuss

Opens the web UI at http://127.0.0.1:8000

Configuration

On first run, AIDiscuss creates a config file:

  • Virtual env: {venv}/.aidiscuss_data/.env
  • Global: ~/.aidiscuss/.env

API keys are configured through the web UI.

Environment Isolation

Each installation maintains separate data:

venv1/bin/aidiscuss  # Data in venv1/.aidiscuss_data/
venv2/bin/aidiscuss  # Data in venv2/.aidiscuss_data/
aidiscuss            # Global data in ~/.aidiscuss/

API

Key Endpoints

Endpoint Description
GET /health Health check
POST /api/chat/stream Streaming chat
GET /api/providers List LLM providers
POST /api/rag/upload Upload documents

Troubleshooting

Port in use: AIDiscuss auto-finds ports 8000-8100, or set PORT=8080

Custom data dir: Set AIDISCUSS_DATA_DIR=/path/to/data

Logs: ~/.aidiscuss/logs/aidiscuss.log or {venv}/.aidiscuss_data/logs/

Security

Report vulnerabilities via GitHub Security Advisories. Do not open public issues.

License

MIT License - see LICENSE

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

aidiscuss-0.1.0.tar.gz (484.8 kB view details)

Uploaded Source

Built Distribution

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

aidiscuss-0.1.0-py3-none-any.whl (514.6 kB view details)

Uploaded Python 3

File details

Details for the file aidiscuss-0.1.0.tar.gz.

File metadata

  • Download URL: aidiscuss-0.1.0.tar.gz
  • Upload date:
  • Size: 484.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.5

File hashes

Hashes for aidiscuss-0.1.0.tar.gz
Algorithm Hash digest
SHA256 c2d8934495d7fec83baf349ba2b35ba4fe04b41a52f3cf1e1688cf5e5154b48b
MD5 3b46377f33eaab9af567eec306fcbd91
BLAKE2b-256 901b3c322ca02e32ce6c9c26d31d728ae6c52035a277fcff01a439c1dfecaf28

See more details on using hashes here.

File details

Details for the file aidiscuss-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: aidiscuss-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 514.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.5

File hashes

Hashes for aidiscuss-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3c4db85feda97d1ffbb3e610e4cceba8cf98a8cfe57beb96b9ef6f9bb4c2cc66
MD5 1f60b3843a5694f4013b7a127fa8fa90
BLAKE2b-256 cea6d98a46534d8276b1d473adb0a4a1a0b24cd685ce5df4c79e175ed0a3bff6

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