kreuzberg-dev/kreuzberg-surrealdb
Extract, chunk, and embed documents from 88+ formats directly into SurrealDB.
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.
Stars
3
Forks
—
Language
Python
License
MIT
Category
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.
Related tools
LLM-Implementation/private-rag-embeddinggemma
🔒 100% Private RAG Stack with EmbeddingGemma, SQLite-vec & Ollama - Zero Cost, Offline Capable
sudhanshug16/chromadb-cli
CLI to interact with ChromaDB (https://github.com/chroma-core/chroma)
jmiba/zotero-redisearch-rag
An Obsidian plugin that synchronizes selected Zotero full-text items with your vault in...
sanketvagal/rag-notes
RAG system that lets you chat with your Obsidian/Markdown notes — chunks by headers, embeds with...
Vatsal-Founder/Hybrid-Search-with-LangChain-and-Pinecone
Hybrid search RAG system combining BM25 sparse + dense embeddings via LangChain and Pinecone 35%...