feat(core): implement full memory pipeline #11

Merged
rock merged 2 commits from feat/full-pipeline into main 2026-08-24 01:37:17 +00:00
Owner

Squash merge of full pipeline implementation:

  • pgvector database schema (L0/L1/L2 memories)
  • Embeddings via api.riotpiao.com gateway
  • Async ingest worker
  • Semantic query with reranking
  • HTTP API endpoints wired to PostgreSQL
Squash merge of full pipeline implementation: - pgvector database schema (L0/L1/L2 memories) - Embeddings via api.riotpiao.com gateway - Async ingest worker - Semantic query with reranking - HTTP API endpoints wired to PostgreSQL
rock added 2 commits 2026-08-24 01:37:09 +00:00
- Add database schema with pgvector extension (L0/L1/L2 memories)
- Implement pgvector-backed vector store with similarity search
- Add Ollama embeddings client for 768-dim nomic embeddings
- Implement ingest worker to process records into L0/L1 memory
- Implement query worker with semantic search across memory tiers
- Rewrite HTTP server with database connection pooling
- Wire all endpoints to actual backend (ingest, query, projects, skills)
- Update main.rs to use DATABASE_URL from environment
- All code compiles, ready for Docker build and deployment
fix: wire all LLM clients to api.riotpiao.com gateway
Build and Push / Test (pull_request) Failing after 3s
Build and Push / Build and push image (pull_request) Skipped
70e3f7c9a5
- EmbeddingsClient: use /v1/embeddings from gateway (nomic-ai/nomic-embed-text-v2-moe)
- RerankClient: use /v1/rerank from gateway (BAAI/bge-reranker-base)
- ChatClient: support gateway without auth headers (future: Bearer token)
- All clients use LLM_API_BASE env var (default: https://api.riotpiao.com)
- Ready for Kubernetes deployment with proper API routing
rock merged commit e6e39cf6fd into main 2026-08-24 01:37:17 +00:00
Sign in to join this conversation.
No Reviewers
No labels
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: rock/poimen-memory#11