Postgres Hybrid Text Search

What it does

When your agent uses it

• Implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF)
• User asks to: - Combine keyword and semantic search - Implement hybrid search
• Reciprocal rank fusion
• Full-text search

Example prompts

• “/postgres-hybrid-text-search”

Requirements

• Python 3
• A credential in COHERE_API_KEY
• Compatibility (from SKILL.md): Requires PostgreSQL 15+ with pgvector and pg_textsearch extensions

What it can do on your machine

Read from SKILL.md and the folder at commit 187be00. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are sql, python and typescript).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com
  • postgresql.org

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • COHERE_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Requires PostgreSQL 15+ with pgvector and pg_textsearch extensions

  From compatibility in the SKILL.md frontmatter.

Context cost

Postgres Hybrid Text Search loads about 3.1k tokens when it runs. Until then it costs about 185 tokens; SKILL.md has 746 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~185

When it runs · the whole SKILL.md, loaded when a task matches

~3.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from timescale/pg-aiguide at commit 187be00, republished under its Apache-2.0 licence (© timescale). 746 words, ~3,147 tokens.

name

postgres-hybrid-text-search

description

Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). **Trigger when user asks to:** - Combine keyword and semantic search - Implement hybrid search or multi-modal retrieval - Use BM25/pg_textsearch with pgvector together - Implement RRF (Reciprocal Rank Fusion) for search - Build search that handles both exact terms and meaning **Keywords:** hybrid search, BM25, pg_textsearch, RRF, reciprocal rank fusion, keyword search, full-text search, reranking, cross-encoder Covers: pg_textsearch BM25 index setup, parallel query patterns, client-side RRF fusion (Python/TypeScript), weighting strategies, and optional ML reranking.

compatibility

Requires PostgreSQL 15+ with pgvector and pg_textsearch extensions

license

Apache-2.0

metadata.author

tigerdata

-- Enable extensions
CREATE EXTENSION IF NOT EXISTS vector;
CREATE EXTENSION IF NOT EXISTS pg_textsearch;

-- Table with both indexes
CREATE TABLE documents (
  id BIGINT GENERATED ALWAYS AS IDENTITY PRIMARY KEY,
  content TEXT NOT NULL,
  embedding halfvec(1536) NOT NULL
);

-- BM25 index for keyword search
CREATE INDEX ON documents USING bm25 (content) WITH (text_config = 'english');

-- HNSW index for semantic search
CREATE INDEX ON documents USING hnsw (embedding halfvec_cosine_ops);

-- Query 1: Keyword search (BM25)
-- $1: search text
SELECT id, content FROM documents ORDER BY content <@> $1 LIMIT 50;

-- Query 2: Semantic search (separate query, run in parallel)
-- $1: embedding of your search text as halfvec(1536)
SELECT id, content FROM documents ORDER BY embedding <=> $1::halfvec(1536) LIMIT 50;

# Client-side RRF fusion (Python)
def rrf_fusion(keyword_results, semantic_results, k=60, limit=10):
    scores = {}
    content_map = {}

    for rank, row in enumerate(keyword_results, start=1):
        scores[row['id']] = scores.get(row['id'], 0) + 1 / (k + rank)
        content_map[row['id']] = row['content']

    for rank, row in enumerate(semantic_results, start=1):
        scores[row['id']] = scores.get(row['id'], 0) + 1 / (k + rank)
        content_map[row['id']] = row['content']

    sorted_ids = sorted(scores, key=scores.get, reverse=True)[:limit]
    return [{'id': id, 'content': content_map[id], 'score': scores[id]} for id in sorted_ids]

// Client-side RRF fusion (TypeScript)
type Row = { id: number; content: string };
type Result = Row & { score: number };

function rrfFusion(keywordResults: Row[], semanticResults: Row[], k = 60, limit = 10): Result[] {
  const scores = new Map<number, number>();
  const contentMap = new Map<number, string>();

  keywordResults.forEach((row, i) => {
    scores.set(row.id, (scores.get(row.id) ?? 0) + 1 / (k + i + 1));
    contentMap.set(row.id, row.content);
  });

  semanticResults.forEach((row, i) => {
    scores.set(row.id, (scores.get(row.id) ?? 0) + 1 / (k + i + 1));
    contentMap.set(row.id, row.content);
  });

  return [...scores.entries()]
    .sort((a, b) => b[1] - a[1])
    .slice(0, limit)
    .map(([id, score]) => ({ id, content: contentMap.get(id)!, score }));
}

# Weight semantic search 2x higher than keyword
keyword_weight = 1.0
semantic_weight = 2.0

for rank, row in enumerate(keyword_results, start=1):
    scores[row['id']] = scores.get(row['id'], 0) + keyword_weight / (k + rank)

for rank, row in enumerate(semantic_results, start=1):
    scores[row['id']] = scores.get(row['id'], 0) + semantic_weight / (k + rank)

// Weight semantic search 2x higher than keyword
const keywordWeight = 1.0;
const semanticWeight = 2.0;

keywordResults.forEach((row, i) => {
  scores.set(row.id, (scores.get(row.id) ?? 0) + keywordWeight / (k + i + 1));
});

semanticResults.forEach((row, i) => {
  scores.set(row.id, (scores.get(row.id) ?? 0) + semanticWeight / (k + i + 1));
});

# 1. Fuse results with RRF (more candidates for reranking)
candidates = rrf_fusion(keyword_results, semantic_results, limit=100)

# 2. Rerank with cross-encoder
from sentence_transformers import CrossEncoder
reranker = CrossEncoder('cross-encoder/ms-marco-MiniLM-L-6-v2')

pairs = [(query_text, doc['content']) for doc in candidates]
scores = reranker.predict(pairs)

# 3. Return top 10 by reranker score
reranked = sorted(zip(candidates, scores), key=lambda x: x[1], reverse=True)[:10]

import { CohereClientV2 } from 'cohere-ai';

// 1. Fuse results with RRF (more candidates for reranking)
const candidates = rrfFusion(keywordResults, semanticResults, 60, 100);

// 2. Rerank via API (example uses Cohere SDK; Jina, Voyage, and others work similarly)
const cohere = new CohereClientV2({ token: COHERE_API_KEY });

const reranked = await cohere.rerank({
  model: 'rerank-v3.5',
  query: queryText,
  documents: candidates.map(c => c.content),
  topN: 10
});

// 3. Map back to original documents
const results = reranked.results.map(r => candidates[r.index]);

-- Enable pgvectorscale (in addition to pgvector)
CREATE EXTENSION IF NOT EXISTS vectorscale;

-- Table with label column for filtering
CREATE TABLE documents (
  id BIGINT GENERATED ALWAYS AS IDENTITY PRIMARY KEY,
  content TEXT NOT NULL,
  embedding halfvec(1536) NOT NULL,
  labels smallint[] NOT NULL  -- e.g., category IDs, tenant IDs
);

-- StreamingDiskANN index with label filtering
CREATE INDEX ON documents USING diskann (embedding vector_cosine_ops, labels);

-- BM25 index for keyword search
CREATE INDEX ON documents USING bm25 (content) WITH (text_config = 'english');

-- Filtered semantic search using && (array overlap)
SELECT id, content FROM documents
WHERE labels && ARRAY[1, 3]::smallint[]
ORDER BY embedding <=> $1::halfvec(1536) LIMIT 50;

-- Force index usage for verification (planner may prefer seqscan on small tables)
SET enable_seqscan = off;

-- Verify BM25 index is used
EXPLAIN SELECT id, content FROM documents ORDER BY content <@> 'search text' LIMIT 10;
-- Look for: Index Scan using ... (bm25)

-- Verify HNSW index is used
EXPLAIN SELECT id, content FROM documents ORDER BY embedding <=> '[0.1, 0.2, ...]'::halfvec(1536) LIMIT 10;
-- Look for: Index Scan using ... (hnsw)

SET enable_seqscan = on;  -- Re-enable for normal operation

-- Check index sizes
SELECT indexname, pg_size_pretty(pg_relation_size(indexname::regclass)) AS size
FROM pg_indexes WHERE tablename = 'documents';

© timescale, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/postgres-hybrid-text-search of timescale/pg-aiguide.

Open the folder on GitHubat commit 187be00