Yes, Phoenix traces capture LLM parameters such as temperature, and you can inspect these parameters鈥攊ncluding temperature鈥攊n the trace details within the UI. This allows you to validate and debug the configuration used for each LLM call, as described in the documentation and shown in trace attribute examples (<https://arize.com/docs/phoenix/tracing/llm-traces#radix-芦R12r8ut1letrnb禄|source>, <https://github.com/Arize-ai/phoenix/blob/main/docs/tracing/llm-traces.md|source>, <https://github.com/Arize-ai/openinference/blob/main/spec/semantic_conventions.md|source>).
To view the temperature, open a trace in the Phoenix UI, select the relevant LLM span, and look for the `llm.invocation_parameters` or similar attribute, which will include the temperature value used for that call. Would you like more detail?
Sources:
- <https://arize.com/docs/phoenix/tracing/llm-traces#radix-芦R12r8ut1letrnb禄|Tracing Overview: Tracing>
- <https://github.com/Arize-ai/phoenix/blob/main/docs/tracing/llm-traces.md|docs/tracing/llm-traces.md>
- <https://github.com/Arize-ai/openinference/blob/main/spec/semantic_conventions.md|semantic_conventions.md>
