Search without a second system.
One Postgres for your application data, full-text search, vector retrieval, and aggregations.
The official SQLAlchemy integration for ParadeDB (powered by the pg_search Postgres extension), including first-class support for managing ParadeDB indexes with Alembic and running queries using the full ParadeDB API. The integration covers both full-text search and vector search over pgvector vector types. Follow the getting started guide to begin.
| Component | Supported |
|---|---|
| Python | 3.10+ |
| SQLAlchemy | 2.0.32+ |
| ParadeDB | 0.25.0+ |
| PostgreSQL | 15+ (with the ParadeDB pg_search extension) |
| pgvector | Required for vector search (included in the ParadeDB Docker image) |
- Quickstart
- Vector Search
- Faceted Search
- Hybrid Search (RRF)
- Retrieval-Augmented Generation (RAG)
- Autocomplete
- More Like This
See examples/README.md for setup instructions and a description of each example.
See CONTRIBUTING.md for development setup, running tests, linting, and the PR workflow.
If you're missing a feature or have found a bug, please open a GitHub Issue.
To get community support, you can:
- Post a question in the ParadeDB Slack Community
- Ask for help on our GitHub Discussions
If you need commercial support, please contact the ParadeDB team.
ParadeDB for SQLAlchemy is licensed under the MIT License.