cim_summary/backend/vector_function.sql

-- Enable pgvector extension (if not already enabled)
CREATE EXTENSION IF NOT EXISTS vector;

-- Create vector similarity search function
CREATE OR REPLACE FUNCTION match_document_chunks(
    query_embedding VECTOR(1536),
    match_threshold FLOAT DEFAULT 0.7,
    match_count INTEGER DEFAULT 10
)
RETURNS TABLE (
    id UUID,
    document_id TEXT,
    content TEXT,
    metadata JSONB,
    chunk_index INTEGER,
    similarity FLOAT
)
LANGUAGE SQL STABLE
AS $$
    SELECT
        document_chunks.id,
        document_chunks.document_id,
        document_chunks.content,
        document_chunks.metadata,
        document_chunks.chunk_index,
        1 - (document_chunks.embedding <=> query_embedding) AS similarity
    FROM document_chunks
    WHERE document_chunks.embedding IS NOT NULL
    AND 1 - (document_chunks.embedding <=> query_embedding) > match_threshold
    ORDER BY document_chunks.embedding <=> query_embedding
    LIMIT match_count;
$$;