semantic-conventions/docs/gen-ai
Riccardo Magliocchetti 520702f155
genai: add system_fingerprint attribute (#1355)
Co-authored-by: Liudmila Molkova <limolkova@microsoft.com>
2024-11-01 03:00:09 +00:00
..
README.md Add genai system-specific conventions for Azure AI Inference (#1393) 2024-10-10 10:39:22 -07:00
azure-ai-inference.md [chore] Remove empty lines in generated markdown (#1477) 2024-10-15 08:52:26 -07:00
gen-ai-events.md [chore] Remove empty lines in generated markdown (#1477) 2024-10-15 08:52:26 -07:00
gen-ai-metrics.md [chore] Remove empty lines in generated markdown (#1477) 2024-10-15 08:52:26 -07:00
gen-ai-spans.md Use `SHOULD` instead of `MUST` for span kinds on DB, GenAI and FaaS (#1506) 2024-10-24 15:02:45 +02:00
openai.md genai: add system_fingerprint attribute (#1355) 2024-11-01 03:00:09 +00:00

README.md

Semantic Conventions for Generative AI systems

Status: Experimental

Warning: The semantic conventions for GenAI and LLM are currently in development. We encourage instrumentation libraries and telemetry consumers developers to use the conventions in limited non-critical workloads and share the feedback

Semantic conventions for Generative AI operations are defined for the following signals:

  • Events: Semantic Conventions for Generative AI inputs and outputs - events.
  • Metrics: Semantic Conventions for Generative AI operations - metrics.
  • Spans: Semantic Conventions for Generative AI requests - spans.

Technology specific semantic conventions are defined for the following GenAI system: