AI Observability

Since Camel 4.23

The camel-ai-observability module provides GenAI observability for Camel AI components following the OpenTelemetry semantic conventions for GenAI (stable subset aligned with Spring AI).

AI producers depend on the lightweight camel-ai-observability-api module. Add camel-ai-observability to your application classpath together with a tracing or metrics backend to enable span and metric emission.

When camel-opentelemetry2 and/or camel-micrometer is on the classpath, langchain4j and OpenAI producers emit child spans and metrics per LLM call with attributes such as gen_ai.operation.name, gen_ai.system, gen_ai.request.model, gen_ai.usage.input_tokens, and gen_ai.usage.output_tokens.

Global toggle: set camel.ai.observability.enabled=false to disable GenAI observability across all AI components (default is true when a tracing or metrics backend is present).

Phase 1 coverage: langchain4j-chat, langchain4j-tools, langchain4j-agent, langchain4j-embeddings, and openai.

New exchange headers for model identification on langchain4j components:

  • CamelLangChain4jChatRequestModel / CamelLangChain4jChatResponseModel

  • CamelLangChain4jToolsRequestModel / CamelLangChain4jToolsResponseModel

  • CamelLangChain4jAgentRequestModel / CamelLangChain4jAgentResponseModel

  • CamelLangChain4jEmbeddingsRequestModel / CamelLangChain4jEmbeddingsResponseModel

Metrics recorded (when Micrometer is available):

  • gen_ai.client.operation — operation duration timer

  • gen_ai.client.token.usage — token usage counter (tags: gen_ai.token.type=input|output)

Camel TUI integration (Phase 2)

When monitoring a running integration with camel tui and observability enabled, the AI panel usage view (Ctrl+U while the AI panel is open) combines:

  • TUI ask token usage from camel ask / the embedded AI prompt

  • Route GenAI usage extracted from exported OpenTelemetry spans with gen_ai.* attributes

This gives a single dashboard for developer CLI usage and production route LLM calls.

Back to top