feat(vector-store): Implement pgvector adapter for self-hosted RAG (#1211)

* Add conditional migration for vector_store_chunks table

Creates the pgvector-backed chunks table when VECTOR_STORE_PROVIDER=pgvector.
Enables the vector extension, adds store_id/file_id indexes, and uses
vector(1024) column type for embeddings.

* Add VectorStore::Embeddable concern for text extraction and embedding

Shared concern providing extract_text (PDF via pdf-reader, plain-text as-is),
paragraph-boundary chunking (~2000 chars, ~200 overlap), and embed/embed_batch
via OpenAI-compatible /v1/embeddings endpoint using Faraday. Configurable via
EMBEDDING_MODEL, EMBEDDING_URI_BASE, with fallback to OPENAI_* env vars.

* Implement VectorStore::Pgvector adapter with raw SQL

Replaces the stub with a full implementation using
ActiveRecord::Base.connection with parameterized binds. Supports
create_store, delete_store, upload_file (extract+chunk+embed+insert),
remove_file, and cosine-similarity search via the <=> operator.

* Add registry test for pgvector adapter selection

* Configure pgvector in compose.example.ai.yml

Switch db image to pgvector/pgvector:pg16, add VECTOR_STORE_PROVIDER,
EMBEDDING_MODEL, and EMBEDDING_DIMENSIONS env vars, and include
nomic-embed-text in Ollama's pre-loaded models.

* Update pgvector docs from scaffolded to ready

Document env vars, embedding model setup, pgvector Docker image
requirement, and Ollama pull instructions.

* Address PR review feedback

- Migration: remove env guard, use pgvector_available? check so it runs
  on plain Postgres (CI) but creates the table on pgvector-capable servers.
  Add NOT NULL constraints on content/embedding/metadata, unique index on
  (store_id, file_id, chunk_index).
- Pgvector adapter: wrap chunk inserts in a DB transaction to prevent
  partial file writes. Override supported_extensions to match formats
  that extract_text can actually parse.
- Embeddable: add hard_split fallback for paragraphs exceeding CHUNK_SIZE
  to avoid overflowing embedding model token limits.

* Bump schema version to include vector_store_chunks migration

CI uses db:schema:load which checks the version — without this bump,
the migration is detected as pending and tests fail to start.

* Update 20260316120000_create_vector_store_chunks.rb

---------

Co-authored-by: sokiee <sokysrm@gmail.com>

compose.example.ai.yml

@@ -69,6 +69,10 @@ x-rails-env: &rails_env
   OPENAI_ACCESS_TOKEN: token-can-be-any-value-for-ollama
   OPENAI_MODEL: llama3.1:8b # Note: Use tool-enabled model
   OPENAI_URI_BASE: http://ollama:11434/v1
+  # Vector store — pgvector keeps all data local (requires pgvector/pgvector Docker image for db)
+  VECTOR_STORE_PROVIDER: pgvector
+  EMBEDDING_MODEL: nomic-embed-text
+  EMBEDDING_DIMENSIONS: "1024"
   # NOTE: enabling OpenAI will incur costs when you use AI-related features in the app (chat, rules).  Make sure you have set appropriate spend limits on your account before adding this.
   #  OPENAI_ACCESS_TOKEN: ${OPENAI_ACCESS_TOKEN}
   # External AI Assistant — delegates chat to a remote AI agent (e.g., OpenClaw).
@@ -128,7 +132,7 @@ services:
       - "11434:11434"
     environment:
       - OLLAMA_KEEP_ALIVE=1h
-      - OLLAMA_MODELS=deepseek-r1:8b,llama3.1:8b # Pre-load model on startup, you can change this to your preferred model
+      - OLLAMA_MODELS=deepseek-r1:8b,llama3.1:8b,nomic-embed-text # Pre-load model on startup, you can change this to your preferred model
     networks:
       - sure_net
     # Recommended: Enable GPU support
@@ -213,7 +217,7 @@ services:
       - sure_net
 
   db:
-    image: postgres:16
+    image: pgvector/pgvector:pg16
     restart: unless-stopped
     volumes:
       - postgres-data:/var/lib/postgresql/data