WikiSearch
A sample project demonstrating hybrid search in PostgreSQL. It combines BM25 keyword retrieval with vector-based semantic retrieval and supports comparison of the results.
Timeline (last 90 days)
The example project WikiSearch's keyword index covers about 242,000 Simple English Wikipedia articles, while semantic search covers only about 25,000.
The execution plan of the hybrid query in the course shows: 20 rows from keywords and 20 rows from vectors, which after aggregation deduplicate 40 records into 32 articles, i.e. 8 articles were found by both methods.
The application adjusts the weights of the keyword and semantic paths via the semantic_weight parameter, where 0 means pure keyword, 1 means pure semantic, and intermediate values are allocated proportionally.
All Facts (3)
The example project WikiSearch's keyword index covers about 242,000 Simple English Wikipedia articles, while semantic search covers only about 25,000.
50%UnverifiedThe execution plan of the hybrid query in the course shows: 20 rows from keywords and 20 rows from vectors, which after aggregation deduplicate 40 records into 32 articles, i.e. 8 articles were found by both methods.
50%UnverifiedThe application adjusts the weights of the keyword and semantic paths via the semantic_weight parameter, where 0 means pure keyword, 1 means pure semantic, and intermediate values are allocated proportionally.
50%