Knowledge

Ground answers with uploaded documents and sources.

Assistant Knowledge (/app/assistants/{id}/knowledge) ingests files and websites into pgvector chunks. Embeddings use local sentence-transformers/all-MiniLM-L6-v2 (not OpenAI embeddings). Knowledge nodes on the flow canvas and runtime fallback path query these chunks.

Sources

  • Upload PDF, DOCX, TXT, or website URLs — max file size from knowledge_max_file_size_mb.
  • Per-source status — indexing, ready, failed with error_message.
  • chunk_count, embedding_model stored on KnowledgeSource.
  • Intent bindings — attach sources to specific intents for scoped retrieval.
  • Test retrieval — query box with combined vector + keyword scores.

Ingestion pipeline

  1. Parse document or crawl URL.
  2. Chunk with overlap (knowledge_chunk_size / knowledge_chunk_overlap).
  3. Embed with MiniLM; store in knowledge_chunks with tsvector keywords.
  4. Synthesis optional — synthesize_answer uses extraction LLM when building answers from chunks.

AI Agent Knowledge (/app/agents/{slug}/knowledge) is a separate RAG store for the agentic runtime — same embedding approach, different API namespace.