Repository files navigation

🤖Note: This project was fully generated and developed using GitHub Copilot.

Are you looking for a simple way to asks question to your codebase using the inference provider you want without to be locked to a specific service?This tool is a way to achieve this!

Check theblogpost about the project that has more info!

• Production-ready RAG backend with per-project persistent storage
• PyCharm/IDE integration via REST API (seeREST_API.md)
• Per-project databases: Each project gets isolated SQLite database
• Indexes files, computes embeddings using an OpenAI-compatible embedding endpoint
• Stores vector embeddings in SQLite using sqlite-vector for fast semantic search
• Analysis runs asynchronously (FastAPI BackgroundTasks) so the UI remains responsive
• Minimal web UI for starting analysis and asking questions (semantic search + coding model)
• Health check and monitoring endpoints for production deployment

A full-featured PyCharm/IntelliJ IDEA plugin is available:

• Download: Get the latest plugin fromReleases
• Per-Project Indexing: Automatically indexes current project
• Secure API Keys: Stores credentials in IDE password safe
• Real-time Responses: Streams answers from your coding model
• File Navigation: Click retrieved files to open in editor
• Progress Indicators: Visual feedback during indexing

Seeide-plugins/README.md for building and installation instructions.

• Python 3.8+ (3.11+ recommended for builtin tomllib)
• Git (optional, if you clone the repo)
• If you use Astraluv, install/configureuv according to the official docs:https://docs.astral.sh/uv/

First step: Example .env (copy.env.example ->.env and edit)

• Follow Astral uv installation instructions first:https://docs.astral.sh/uv/
• Typical flow (afteruv is installed and you are in the project directory):

  uv pip install -r pyproject.toml  uv run python ./main.py

Notes:

• The exactuv subcommands depend on the uv version/configuration. Check the Astral uv docs for the exact syntax for your uv CLI release. The analyzer only needs a Python executable in the venv to runpython -m pip list --format=json;uv typically provides or creates that venv.

• Create a virtual environment and install dependencies listed inpyproject.toml with your preferred tool.

  # create venv  python -m venv .venv  # activate (UNIX)  source .venv/bin/activate  # activate (Windows PowerShell)  .venv\Scripts\Activate.ps1  uv pip install -r pyproject.toml  # run the server  python ./main.py

  poetry install  poetry run main.py