Meridian

The problem

Meridian is a semantic search product built on Exa with a shared Python core, FastAPI web API, React app, and Typer CLI.

What I built

Meridian is a semantic search product built on Exa with a shared Python core, FastAPI web API, React app, and Typer CLI.

How it works

• The Exa Python SDK remains the live provider boundary. Tests use mocked clients and fixtures, so CI never spends quota.
• The default answer provider is extractive and keyless. Set LLM_API_KEY and swap to OpenAICompatibleProvider for model synthesis.
• Local SQLite files under MERIDIAN_HOME hold cache, quota, history, and collections. On Windows the default is %LOCALAPPDATA%\Meridian; no telemetry is sent by default.

Tradeoffs and limits

This project does not currently have a hosted demo. Run and verification instructions live in the repository when available.

What I learned

It turns the single-query Exa tutorial into a reusable product surface: neural, keyword, and auto search; full-content retrieval; similarity search; cited answer synthesis; saved history and collections; quota-aware caching; and Markdown, JSON, and CSV exports.