kreuzberg-dev/kreuzberg-surrealdb

Extract, chunk, and embed documents from 88+ formats directly into SurrealDB.

39
/ 100
Emerging

Provides automated schema generation with SHA-256 deduplication to prevent duplicate ingestion across runs, and supports two distinct architectures: `DocumentConnector` for full-document BM25 search, and `DocumentPipeline` for chunked documents with optional ONNX embedding models and hybrid vector+BM25 search via Reciprocal Rank Fusion. Chunks maintain parent document links via SurrealDB record references, enabling relational traversal in SurQL queries with tunable BM25 and HNSW index parameters.

Available on PyPI.

Maintenance 13 / 25
Adoption 8 / 25
Maturity 18 / 25
Community 0 / 25

How are scores calculated?

Stars

3

Forks

Language

Python

License

MIT

Last pushed

Mar 13, 2026

Monthly downloads

231

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/kreuzberg-dev/kreuzberg-surrealdb"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.