Ahsan Hadi: Hybrid Search in PostgreSQL: BM25, Sparse Vectors, and Reciprocal Rank Fusion
In my previous blog on the pgEdge Vectorizer and RAG Server, I showed how to build a semantic search pipeline using dense vector embeddings. The RAG Server already did hybrid search, combining vector similarity with BM25 keyword matching, but BM25 was handled at the application layer, not inside PostgreSQL.That changes now. The pgedge-vectorizer extension adds BM25 sparse vector generation directly into the vectorizer, running inside PostgreSQL alongside the dense embeddings.
- ▪In my previous blog on the pgEdge Vectorizer and RAG Server, I showed how to build a semantic search pipeline using dense vector embeddings.
- ▪The RAG Server already did hybrid search, combining vector similarity with BM25 keyword matching, but BM25 was handled at the application layer, not inside PostgreSQL.That changes now.
- ▪The pgedge-vectorizer extension adds BM25 sparse vector generation directly into the vectorizer, running inside PostgreSQL alongside the dense embeddings.
Planet PostgreSQL files mainly under programming. We currently carry 28 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Postgr |
| Canonical URL | https://postgr.es/p/9qm |
| Publication time | Wed, 22 Jul 2026 11:19:03 +0000 |
| Retrieval time | 2026-07-26T10:01:46.574Z |
| Last seen | 2026-07-26T10:01:46.574Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | pjzIsE1hx-zS · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
In my previous blog on the pgEdge Vectorizer and RAG Server, I showed how to build a semantic search pipeline using dense vector embeddings. The RAG Server already did hybrid search, combining vector similarity with BM25 keyword matching, but BM25 was handled at the application layer, not inside PostgreSQL.That changes now. The pgedge-vectorizer extension adds BM25 sparse vector generation directly into the vectorizer, running inside PostgreSQL alongside the dense embeddings. Results are fused using reciprocal rank fusion (RRF). In this blog I will show you what this means in practice.I am using the same Rocky Linux ARM64 VM and testdb configuration from the previous blog: two pgEdge nodes, n1 on port 5432 and n2 on port 5433, using Ollama with nomic-embed-text.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Postgr.
Discussion
0 commentsMore from Postgr
