# FiddlerGeneration

Wrapper for LLM generation spans with semantic convention helpers.

Initialize LLM generation wrapper.

## **enter**()

Enter context and set LLM type.

**Return type:** [*FiddlerGeneration*](#fiddlergeneration)

## set\_model()

Set the LLM model name (gen\_ai.request.model).

**Return type:** None

## set\_system()

Set the LLM system/provider (gen\_ai.system).

**Return type:** None

## set\_system\_prompt()

Set the system prompt (gen\_ai.llm.input.system).

**Return type:** None

## set\_user\_prompt()

Set the user prompt (gen\_ai.llm.input.user).

**Return type:** None

## set\_completion()

Set the LLM completion/output (gen\_ai.llm.output).

**Return type:** None

## set\_usage()

Set token usage information (gen\_ai.usage.\*).

**Return type:** None

## set\_context()

Set additional context (gen\_ai.llm.context).

**Return type:** None

## set\_messages()

Set input messages in OpenAI chat format (gen\_ai.input.messages).

Accepts simple format: \[{'role': 'user', 'content': '...'}] Auto-converts to OTel format: \[{'role': 'user', 'parts': \[{'type': 'text', 'content': '...'}]}]

**Return type:** None

## set\_output\_messages()

Set output messages in OpenAI chat format (gen\_ai.output.messages).

Accepts simple format: \[{'role': 'assistant', 'content': '...'}] Auto-converts to OTel format: \[{'role': 'assistant', 'parts': \[{'type': 'text', 'content': '...'}]}]

**Return type:** None

## set\_tool\_definitions()

Set available tool definitions for this LLM call (gen\_ai.tool.definitions).

**Return type:** None