Dynamic Hybrid Search That Beats Pure Dense and Fixed Hybrid
Per-query α fusion beats fixed hybrid weights on FiQA and FEVER benchmarks.
Dasein managed vector index service - Python SDK
Hybrid search toggle per query when Pinecone charges for everything.
Developers building RAG applications and semantic search
Pinecone · Weaviate · Qdrant
this week you can checkout the sdk and get an api key issued through github oauth. No card needed. Immediate free trial.[1]
What we built:
- 1M Vectors (100k on Free) - Low latency hybrid search - 1k Metadata filters - 50M embedding tokens monthly (1M on Free) - Build times that don't blow
if you are looking for an index that doesn't have a huge minimum fee or spiky/confusing usage based pricing it's only $10 a month. See if you can't cost us more than that!
[0] https://results.daseinai.ai/ [1] https://github.com/nickswami/dasein-python-sdk
Per-query α fusion beats fixed hybrid weights on FiQA and FEVER benchmarks.
Single-binary Rust DB fusing HNSW and BM25 without cloud dependencies or API keys.
Hybrid search over 5,600 papers when Elicit and Semantic Scholar already exist.
Native MLX-Swift transformer port with no Python when every alternative needs cloud APIs.
Hybrid BM25 + vector search via MCP beats pure keyword or pure semantic for API docs.
Local semantic search beats Everything and ripgrep; adds OCR, GPS reversal, MCP agents.