Рабочий вариант

README.md

@@ -1,3 +1,6 @@
+
+
+
 # RAG Agent (Postgres)
 
 Custom RAG agent that indexes text files from a git repository into Postgres
@@ -14,7 +17,7 @@ and answers queries using retrieval + LLM generation. **Changes are always in th
 2. Configure environment variables:
    - `RAG_REPO_PATH` — path to git repo with text files
    - `RAG_DB_DSN` — Postgres DSN (e.g. `postgresql://rag:rag_secret@localhost:5432/rag`)
-   - `RAG_EMBEDDINGS_DIM` — embedding vector dimension (e.g. `1536`)
+   - `RAG_EMBEDDINGS_DIM` — embedding vector dimension: **1024** for GigaChat Embeddings (default), 1536 for OpenAI
 3. Create DB schema (only if not using Docker, or if init was disabled):
    - `python scripts/create_db.py` (or `psql "$RAG_DB_DSN" -f scripts/schema.sql`)
 4. Index files for a story (e.g. branch name as story slug). Use the **full story range** so all commits in the story are included:
@@ -40,6 +43,35 @@ When the app runs as a service in Docker, it can start a **webhook server** so t
 
 Health check: `GET http://<host>:8000/health` → `ok`. Port is configurable via `WEBHOOK_PORT` (default 8000) in docker-compose.
 
+### Webhook diagnostics (202 Accepted but no new rows in DB)
+
+1. **Logs** — After a push, check app logs. Each webhook logs `pull_and_index started branch=… repo_path=…`; then one of:
+   - `not a git repo or missing` — `/data` in the container is not a git clone; clone the repo into the mounted dir.
+   - `git fetch failed` — SSH/network (see `docker/ssh/README.md`) or wrong remote.
+   - `git checkout … failed` — branch missing in the clone.
+   - `git merge --ff-only failed` — non–fast-forward (e.g. force-push); index is skipped. Use a normal push or re-clone.
+   - `no new commits for branch=…` — merge was a no-op (already up to date); nothing to index.
+   - `running index story=…` then `index completed` — index ran; check tables for that story.
+   - `index failed` — stderr shows the `rag-agent index` error (e.g. DB, embeddings, repo path).
+
+   ```bash
+   docker compose logs -f app
+   # or: docker logs -f rag-agent
+   ```
+   Trigger a push and watch for the lines above.
+
+2. **Story and tables** — Rows are per **story** (branch name). Query by story, e.g. `SELECT * FROM stories;` then `SELECT * FROM chunks WHERE story_id = (SELECT id FROM stories WHERE slug = 'main');`.
+
+3. **Manual index** — Run index inside the container to confirm DB and repo work:
+   ```bash
+   docker compose exec app rag-agent index --story main --changed --base-ref main --head-ref HEAD
+   ```
+   If this inserts rows, the issue is in the webhook path (fetch/merge/refs).
+
+4. **Allowed extensions** — Only `.md`, `.txt`, `.rst` (or `RAG_ALLOWED_EXTENSIONS`) are indexed; other files are skipped.
+
+5. **"expected 1536 dimensions, not 1024"** — GigaChat Embeddings returns 1024-dim vectors; the default is now 1024. If the DB was created earlier with vector(1536), drop and recreate the tables so the app can create them with 1024: `psql "$RAG_DB_DSN" -c "DROP TABLE IF EXISTS chunks; DROP TABLE IF EXISTS documents;"` then restart the app (ensure_schema will recreate the tables).
+
 ## Git hook (index on commit)
 
 Install the post-commit hook so changed files are indexed after each commit:

docker-compose.yml

@@ -42,13 +42,17 @@ services:
       RAG_DB_DSN: "postgresql://${POSTGRES_USER:-rag}:${POSTGRES_PASSWORD:-rag_secret}@postgres:5432/${POSTGRES_DB:-rag}"
       # In container repo is always at /data (mounted below). Use RAG_REPO_HOST in .env for host path.
       RAG_REPO_PATH: "/data"
-      RAG_EMBEDDINGS_DIM: ${RAG_EMBEDDINGS_DIM:-1536}
+      # Accept host key on first connect; git fetch uses SSH from /root/.ssh (mounted below).
+      GIT_SSH_COMMAND: "ssh -o StrictHostKeyChecking=accept-new"
+      RAG_EMBEDDINGS_DIM: ${RAG_EMBEDDINGS_DIM:-1024}
       GIGACHAT_CREDENTIALS: ${GIGACHAT_CREDENTIALS:-}
       GIGACHAT_EMBEDDINGS_MODEL: ${GIGACHAT_EMBEDDINGS_MODEL:-Embeddings}
       WEBHOOK_SECRET: ${WEBHOOK_SECRET:-}
     volumes:
       # Host path: set RAG_REPO_HOST in .env (e.g. /Users/you/repo). Falls back to RAG_REPO_PATH then ./data.
       - ${RAG_REPO_HOST:-${RAG_REPO_PATH:-./data}}:/data
+      # SSH for git fetch (webhook): put deploy key and known_hosts in RAG_SSH_DIR. See docker/ssh/README.md.
+      - ${RAG_SSH_DIR:-./docker/ssh}:/root/.ssh:ro
     entrypoint: ["rag-agent"]
     command: ["serve", "--host", "0.0.0.0", "--port", "8000"]
     networks:

docker/postgres-init/01-schema.sql

@@ -1,5 +1,5 @@
 -- RAG vector DB schema (runs automatically on first Postgres init).
--- If RAG_EMBEDDINGS_DIM is not 1536, change vector(1536) below.
+-- GigaChat Embeddings = 1024; for OpenAI use vector(1536).
 
 CREATE EXTENSION IF NOT EXISTS vector;
 
@@ -27,7 +27,7 @@ CREATE TABLE IF NOT EXISTS chunks (
     chunk_index INTEGER NOT NULL,
     hash TEXT NOT NULL,
     content TEXT NOT NULL,
-    embedding vector(1536) NOT NULL,
+    embedding vector(1024) NOT NULL,
     start_line INTEGER,
     end_line INTEGER,
     change_type TEXT NOT NULL DEFAULT 'added'

docker/postgres_test_data/18/docker/PG_VERSION

@@ -0,0 +1 @@
+18