Skip to main content

Generative UI and copilot stack

The GenUI stack is defined in compose-genui.yaml and contains two services: the Chainlit copilot and Open-Intelligent-UI.

GENUI & AIOPS COPILOT STACKcompose-genuiSRE Operator"Diagnose CPU load &render remediation tool"Chainlit AIOps CopilotPort :8050 • chainlit-genuiStep 1: pgvector RAG LookupEmbedding cosine similarityStep 2: MCP Tool InvocationQuery PromQL & Loki logsStep 3: Streaming ReasoningOpenUI Lang component streamInteractive Preview iframe Embedpgvector RAG Store (PostgreSQL 17)Database: rag_storage • Table: operational_runbooksHNSW Cosine Vector Index (<=>)vector(768) • Matches nomic-embed-textObservability MCP ServersHTTP / Server-Sent Events (SSE)Grafana MCP:8000/ssePrometheus MCP:8080/sseEnvoy Gateway & Host Ollamahttp://ollama-gateway:11435 -> 0.0.0.0:1143432k Context Window (OLLAMA_CONTEXT_LENGTH=32768)Llama 3.2 • nomic-embed-text • Streamed TokensOpen-Intelligent-UI CanvasPort :3001 • Container: open-intelligent-ui • Next.js + @openuidev/reactContainer CPU Usage92.4%Threshold ExceededSuggested SRE ActionRestart high-consumer container:⚡ Restart ContainerLive PromQL Telemetryrate(container_cpu[1m])

Request flow​

  1. An operator submits a question to Chainlit on port 8050.
  2. Chainlit asks Ollama to embed the question.
  3. The embedding is compared with operational_runbooks in pgvector.
  4. Chainlit sends the retrieved evidence and question to the configured Ollama model.
  5. The streamed response appears in Chainlit, with a link to Open-Intelligent-UI when UI-oriented content is detected.

Current integration boundary​

The Compose service provides Grafana and Prometheus MCP endpoint variables, but genui/chainlit/app.py does not yet invoke MCP tools. Live telemetry retrieval must be implemented and tested before responses can claim to include current Grafana or Prometheus data.

See README_GENUI.md for the deployment procedure and security notes.