// what it does

  1. 01

    Hybrid Search with RRF Fusion

    Combines BM25 keyword search and vector similarity for superior retrieval quality.

  2. 02

    Multi-Tenant Document Isolation

    Document-level access control via Qdrant payload filtering with pre-filter ACLs.

  3. 03

    Semantic Caching

    Qdrant dual-use for vector storage and query caching, reducing LLM costs.

  4. 04

    LiteLLM Provider Abstraction

    Same code for Ollama (local) or any cloud LLM provider — no vendor lock-in.

  5. 05

    Langfuse Observability

    Self-hosted tracing and monitoring for the entire RAG pipeline.

// how it gets used

01

Upload and Query

Upload documents via API gateway

Ask natural language questions

01

Upload documents via API gateway

02

Documents chunked and embedded automatically

03

Ask natural language questions

04

Get sourced answers with citations

Documents chunked and embedded automatically

Get sourced answers with citations

🧠

Phoenix

Ready when you are

Hey! I'm Phoenix — I know Titas's work, projects, and experience. Ask me anything — from distributed systems to production RAG, or what it's like building at Tesco and VMware.