Скелет проекта

scripts/create_db.py

@@ -0,0 +1,29 @@
+#!/usr/bin/env python3
+"""
+Create RAG vector DB schema in Postgres (extension + stories, documents, chunks).
+Requires RAG_DB_DSN and RAG_EMBEDDINGS_DIM (optional, default 1536).
+Run from repo root with package installed: pip install -e . && python scripts/create_db.py
+"""
+from __future__ import annotations
+
+import sys
+from pathlib import Path
+
+# Allow importing rag_agent when run as scripts/create_db.py
+repo_root = Path(__file__).resolve().parent.parent
+sys.path.insert(0, str(repo_root / "src"))
+
+from rag_agent.config import load_config
+from rag_agent.index.postgres import connect, ensure_schema
+
+
+def main() -> None:
+    config = load_config()
+    conn = connect(config.db_dsn)
+    ensure_schema(conn, config.embeddings_dim)
+    conn.close()
+    print("Schema created successfully.")
+
+
+if __name__ == "__main__":
+    main()

scripts/post-commit

@@ -0,0 +1,35 @@
+#!/usr/bin/env sh
+# Git post-commit hook: index changed files into RAG vector DB for the current story.
+# Install: cp scripts/post-commit .git/hooks/post-commit && chmod +x .git/hooks/post-commit
+# Requires: RAG_REPO_PATH, RAG_DB_DSN, RAG_EMBEDDINGS_DIM; story from RAG_STORY or .rag-story or current branch name.
+
+set -e
+cd "$(git rev-parse --show-toplevel)"
+
+# Resolve story: env RAG_STORY > file .rag-story > current branch name
+if [ -n "${RAG_STORY}" ]; then
+  STORY="${RAG_STORY}"
+elif [ -f .rag-story ]; then
+  STORY=$(head -n1 .rag-story | tr -d '\n\r')
+else
+  STORY=$(git branch --show-current)
+fi
+
+if [ -z "$STORY" ]; then
+  echo "post-commit: RAG_STORY or .rag-story or branch name required for indexing."
+  exit 0
+fi
+
+# Run index (changed files only: previous commit -> HEAD)
+if command -v rag-agent >/dev/null 2>&1; then
+  rag-agent index --changed --base-ref HEAD~1 --head-ref HEAD --story "$STORY"
+elif [ -n "${VIRTUAL_ENV}" ]; then
+  rag-agent index --changed --base-ref HEAD~1 --head-ref HEAD --story "$STORY"
+else
+  # Try repo venv or python -m
+  if [ -f "venv/bin/rag-agent" ]; then
+    venv/bin/rag-agent index --changed --base-ref HEAD~1 --head-ref HEAD --story "$STORY"
+  else
+    PYTHONPATH=src python -m rag_agent.cli index --changed --base-ref HEAD~1 --head-ref HEAD --story "$STORY" 2>/dev/null || true
+  fi
+fi

scripts/schema.sql

@@ -0,0 +1,33 @@
+-- RAG vector DB schema for Postgres (pgvector).
+-- Run once against an empty DB. If RAG_EMBEDDINGS_DIM is not 1536, change vector(1536) below.
+-- Usage: psql "$RAG_DB_DSN" -f scripts/schema.sql
+
+CREATE EXTENSION IF NOT EXISTS vector;
+
+CREATE TABLE IF NOT EXISTS stories (
+    id SERIAL PRIMARY KEY,
+    slug TEXT UNIQUE NOT NULL,
+    created_at TIMESTAMPTZ NOT NULL DEFAULT (NOW() AT TIME ZONE 'utc')
+);
+
+CREATE TABLE IF NOT EXISTS documents (
+    id SERIAL PRIMARY KEY,
+    story_id INTEGER NOT NULL REFERENCES stories(id) ON DELETE CASCADE,
+    path TEXT NOT NULL,
+    version TEXT NOT NULL,
+    updated_at TIMESTAMPTZ NOT NULL,
+    UNIQUE(story_id, path)
+);
+
+CREATE TABLE IF NOT EXISTS chunks (
+    id SERIAL PRIMARY KEY,
+    document_id INTEGER NOT NULL REFERENCES documents(id) ON DELETE CASCADE,
+    chunk_index INTEGER NOT NULL,
+    hash TEXT NOT NULL,
+    content TEXT NOT NULL,
+    embedding vector(1536) NOT NULL
+);
+
+CREATE INDEX IF NOT EXISTS idx_documents_story_id ON documents(story_id);
+CREATE INDEX IF NOT EXISTS idx_chunks_document_id ON chunks(document_id);
+CREATE INDEX IF NOT EXISTS idx_chunks_embedding ON chunks USING ivfflat (embedding vector_cosine_ops);