39 lines
1.6 KiB
SQL
39 lines
1.6 KiB
SQL
|
-- Unified Search: Document chunks table for RAG indexing
|
||
|
|
-- Creates document_chunks table with HNSW index on embedding,
|
||
|
|
-- and adds content_text/content_tsv columns to files if missing.
|
||
|
|
|
||
|
|
CREATE EXTENSION IF NOT EXISTS vector;
|
||
|
|
|
||
|
|
-- ─── Document Chunks Table ───
|
||
|
|
CREATE TABLE IF NOT EXISTS document_chunks (
|
||
|
|
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
|
||
|
|
tenant_id UUID NOT NULL,
|
||
|
|
file_id UUID NOT NULL REFERENCES files(id) ON DELETE CASCADE,
|
||
|
|
chunk_index INTEGER NOT NULL,
|
||
|
|
chunk_text TEXT NOT NULL,
|
||
|
|
chunk_hash VARCHAR(64) NOT NULL,
|
||
|
|
embedding vector(768),
|
||
|
|
deleted_at TIMESTAMPTZ,
|
||
|
|
created_at TIMESTAMPTZ NOT NULL DEFAULT now(),
|
||
|
|
updated_at TIMESTAMPTZ NOT NULL DEFAULT now()
|
||
|
|
);
|
||
|
|
|
||
|
|
CREATE INDEX IF NOT EXISTS ix_document_chunks_tenant ON document_chunks(tenant_id);
|
||
|
|
CREATE INDEX IF NOT EXISTS ix_document_chunks_file ON document_chunks(file_id);
|
||
|
|
CREATE INDEX IF NOT EXISTS ix_document_chunks_tenant_file ON document_chunks(tenant_id, file_id);
|
||
|
|
|
||
|
|
-- HNSW index for fast cosine similarity search on chunk embeddings
|
||
|
|
CREATE INDEX IF NOT EXISTS ix_document_chunks_embedding
|
||
|
|
ON document_chunks USING hnsw(embedding vector_cosine_ops);
|
||
|
|
|
||
|
|
-- ─── Files: content_text and content_tsv (idempotent) ───
|
||
|
|
DO $$ BEGIN
|
||
|
|
IF EXISTS (SELECT 1 FROM information_schema.tables WHERE table_name = 'files') THEN
|
||
|
|
ALTER TABLE files ADD COLUMN IF NOT EXISTS content_text text;
|
||
|
|
ALTER TABLE files ADD COLUMN IF NOT EXISTS content_tsv tsvector;
|
||
|
|
|
||
|
|
-- GIN index for full-text search on file content
|
||
|
|
CREATE INDEX IF NOT EXISTS ix_files_content_tsv ON files USING gin(content_tsv);
|
||
|
|
END IF;
|
||
|
|
END $$;
|