all AI news
Using DuckDB for Embeddings and Vector Search
June 15, 2024, 2:39 p.m. |
Simon Willison's Weblog simonwillison.net
Using DuckDB for Embeddings and Vector Search
Sören Brunk's comprehensive tutorial combining DuckDB 1.0, a subset of German Wikipedia from Hugging Face (loaded using Parquet), the BGE M3 embedding model and DuckDB's new vss extension for implementing an HNSW vector index.
Via @soebrunk
ai duckdb embedding embeddings extension face german hnsw hugging face index parquet search tutorial vector vector search via wikipedia
More from simonwillison.net / Simon Willison's Weblog
Wikipedia Manual of Style: Linking
1 day, 4 hours ago |
simonwillison.net
Quoting Matt Levine
2 days, 13 hours ago |
simonwillison.net
Val Vibes: Semantic search in Val Town
2 days, 16 hours ago |
simonwillison.net
Jobs in AI, ML, Big Data
Senior Data Engineer
@ Displate | Warsaw
Director of Data Science (f/m/x)
@ AUTO1 Group | Berlin, Germany
Business Intelligence Analyst I [BI Analyst I]
@ Capitec Bank | Stellenbosch, Western Cape, ZA
Data Governance Associate Director
@ Publicis Groupe | London, United Kingdom
Technical Lead - Power BI
@ Birlasoft | INDIA - PUNE - BIRLASOFT OFFICE - HINJAWADI, IN
Data Analyst
@ FirstRand Corporate Centre | 1 First Place, Cnr Simmonds & Pritchard Streets, Johannesburg, 2001