open-telemetry
/
semantic-conventions
mirror of https://github.com/open-telemetry/semantic-conventions.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
semantic-conventions/docs/attributes-registry/gen-ai.md

8.1 KiB
Raw Blame History

Gen AI

Gen AI Attributes

This document defines the attributes used to describe telemetry in the context of Generative Artificial Intelligence (GenAI) Models requests and responses.

Attribute Type Description Examples Stability
gen_ai.completion string The full response received from the GenAI model. [1] [{'role': 'assistant', 'content': 'The capital of France is Paris.'}] Experimental
gen_ai.operation.name string The name of the operation being performed. chat; completion Experimental
gen_ai.prompt string The full prompt sent to the GenAI model. [2] [{'role': 'user', 'content': 'What is the capital of France?'}] Experimental
gen_ai.request.frequency_penalty double The frequency penalty setting for the GenAI request. 0.1 Experimental
gen_ai.request.max_tokens int The maximum number of tokens the model generates for a request. 100 Experimental
gen_ai.request.model string The name of the GenAI model a request is being made to. gpt-4 Experimental
gen_ai.request.presence_penalty double The presence penalty setting for the GenAI request. 0.1 Experimental
gen_ai.request.stop_sequences string[] List of sequences that the model will use to stop generating further tokens. ["forest", "lived"] Experimental
gen_ai.request.temperature double The temperature setting for the GenAI request. 0.0 Experimental
gen_ai.request.top_k double The top_k sampling setting for the GenAI request. 1.0 Experimental
gen_ai.request.top_p double The top_p sampling setting for the GenAI request. 1.0 Experimental
gen_ai.response.finish_reasons string[] Array of reasons the model stopped generating tokens, corresponding to each generation received. ["stop"] Experimental
gen_ai.response.id string The unique identifier for the completion. chatcmpl-123 Experimental
gen_ai.response.model string The name of the model that generated the response. gpt-4-0613 Experimental
gen_ai.system string The Generative AI product as identified by the client or server instrumentation. [3] openai Experimental
gen_ai.token.type string The type of token being counted. input; output Experimental
gen_ai.usage.completion_tokens int The number of tokens used in the GenAI response (completion). 180 Experimental
gen_ai.usage.prompt_tokens int The number of tokens used in the GenAI input or prompt. 100 Experimental

[1]: It's RECOMMENDED to format completions as JSON string matching OpenAI messages format

[2]: It's RECOMMENDED to format prompts as JSON string matching OpenAI messages format

[3]: The actual GenAI product may differ from the one identified by the client. For example, when using OpenAI client libraries to communicate with Mistral, the gen_ai.system is set to openai based on the instrumentation's best knowledge. For custom model, a custom friendly name SHOULD be used. If none of these options apply, the gen_ai.system SHOULD be set to _OTHER.

gen_ai.system has the following list of well-known values. If one of them applies, then the respective value MUST be used; otherwise, a custom value MAY be used.

Value Description Stability
anthropic Anthropic Experimental
cohere Cohere Experimental
openai OpenAI Experimental
vertex_ai Vertex AI Experimental

gen_ai.token.type has the following list of well-known values. If one of them applies, then the respective value MUST be used; otherwise, a custom value MAY be used.

Value Description Stability
input Input tokens (prompt, input, etc.) Experimental
output Output tokens (completion, response, etc.) Experimental