Lower embedding batch size to 8 to match model backend limit
The TEI backend forces max_batch_requests=8 regardless of client config. Batches of 32 were still failing with connection errors.
Batch embedding requests to respect model's max batch size of 32
The embedding model rejects requests with more than 32 inputs, but articles with large content produce 46-198 chunks. All embedding attempts were failing with 4...
Add audience-scoped AI visibility filtering to RAG pipeline
Store **************** in Qdrant payload, filter search results by memberType, skip indexing when aiEnabled is false, and add visibility index creation for exis...
Full chunk text storage, configurable vector size, and permission-aware retrieval in Qdrant
Add note embedding support to RAG pipeline
Add NoteEventConsumer for NOTE_EVENTS NATS stream and NoteEmbeddingPipelineService for processing notes. Update Qdrant to store sourceType, memberId, noteId. Se...
Update version ID references from Long to UUID
Article IDs remain Long. Version IDs now use UUID.
Handle unpublished events by removing vectors from Qdrant
When an article is unpublished, delete its vectors from Qdrant so the AI chat no longer references it.
Add search request/response logging to RagSearchController
Log orgId, query, result count, and full stack traces on error to diagnose 500 responses seen from AIService.
Reduce chunk size to fit all-MiniLM-L6-v2 token limit (256 max)
Chunk target was 2000 chars (~512 tokens) but the embedding model only accepts 256 tokens, causing 413 validation errors. Reduce to 800 chars (~200 tokens) with...
Use integer match filter for Qdrant searches instead of matchKeyword
The orgId and articleId payload fields are stored as integers via value(Long), but search and delete filters used matchKeyword() which only matches string/keywo...
Index KB articles for RAG on creation, not just when published
Previously the RAG pipeline only indexed PUBLISHED articles, requiring the full review/approval cycle before the AI chat could reference them. Now indexes all a...
Grant all rights when rights list is empty (rights system not yet enforced)
Rename qdrant config properties to avoid K8s env var collision
Kubernetes auto-creates QDRANT_PORT env var from the qdrant Service, which overrides the Spring property with 'tcp://ip:port' instead of an integer. Renamed to ...
Make NATS consumer startup resilient with retry logic
Consumer now retries subscription in a background thread with backoff if KB_EVENTS stream doesn't exist yet. Prevents crash loop when KBService hasn't published...
Scaffold RAGService - NATS consumer, embedding pipeline, Qdrant vector store, semantic search API
Like what you see shipping?
All of it arrives in your workspace on its own. Start on the free plan and read this page again in a month.