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/registry/attributes/gen-ai.md

34 KiB
Raw Blame History

Gen AI

GenAI 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.agent.description string Free-form description of the GenAI agent provided by the application. Helps with math problems; Generates fiction stories Development
gen_ai.agent.id string The unique identifier of the GenAI agent. asst_5j66UpCpwteGg4YSxUnt7lPY Development
gen_ai.agent.name string Human-readable name of the GenAI agent provided by the application. Math Tutor; Fiction Writer Development
gen_ai.conversation.id string The unique identifier for a conversation (session, thread), used to store and correlate messages within this conversation. conv_5j66UpCpwteGg4YSxUnt7lPY Development
gen_ai.data_source.id string The data source identifier. [1] H7STPQYOND Development
gen_ai.embeddings.dimension.count int The number of dimensions the resulting output embeddings should have. 512; 1024 Development
gen_ai.evaluation.explanation string A free-form explanation for the assigned score provided by the evaluator. The response is factually accurate but lacks sufficient detail to fully address the question. Development
gen_ai.evaluation.name string The name of the evaluation metric used for the GenAI response. Relevance; IntentResolution Development
gen_ai.evaluation.score.label string Human readable label for evaluation. [2] relevant; not_relevant; correct; incorrect; pass; fail Development
gen_ai.evaluation.score.value double The evaluation score returned by the evaluator. 4.0 Development
gen_ai.input.messages any The chat history provided to the model as an input. [3] [
  {
    "role": "user",
    "parts": [
      {
        "type": "text",
        "content": "Weather in Paris?"
      }
    ]
  },
  {
    "role": "assistant",
    "parts": [
      {
        "type": "tool_call",
        "id": "call_VSPygqKTWdrhaFErNvMV18Yl",
        "name": "get_weather",
        "arguments": {
          "location": "Paris"
        }
      }
    ]
  },
  {
    "role": "tool",
    "parts": [
      {
        "type": "tool_call_response",
        "id": " call_VSPygqKTWdrhaFErNvMV18Yl",
        "result": "rainy, 57°F"
      }
    ]
  }
]		 Development
gen_ai.operation.name string The name of the operation being performed. [4] chat; generate_content; text_completion Development
gen_ai.output.messages any Messages returned by the model where each message represents a specific model response (choice, candidate). [5] [
  {
    "role": "assistant",
    "parts": [
      {
        "type": "text",
        "content": "The weather in Paris is currently rainy with a temperature of 57°F."
      }
    ],
    "finish_reason": "stop"
  }
]		 Development
gen_ai.output.type string Represents the content type requested by the client. [6] text; json; image Development
gen_ai.provider.name string The Generative AI provider as identified by the client or server instrumentation. [7] openai; gcp.gen_ai; gcp.vertex_ai Development
gen_ai.request.choice.count int The target number of candidate completions to return. 3 Development
gen_ai.request.encoding_formats string[] The encoding formats requested in an embeddings operation, if specified. [8] ["base64"]; ["float", "binary"] Development
gen_ai.request.frequency_penalty double The frequency penalty setting for the GenAI request. 0.1 Development
gen_ai.request.max_tokens int The maximum number of tokens the model generates for a request. 100 Development
gen_ai.request.model string The name of the GenAI model a request is being made to. gpt-4 Development
gen_ai.request.presence_penalty double The presence penalty setting for the GenAI request. 0.1 Development
gen_ai.request.seed int Requests with same seed value more likely to return same result. 100 Development
gen_ai.request.stop_sequences string[] List of sequences that the model will use to stop generating further tokens. ["forest", "lived"] Development
gen_ai.request.temperature double The temperature setting for the GenAI request. 0.0 Development
gen_ai.request.top_k double The top_k sampling setting for the GenAI request. 1.0 Development
gen_ai.request.top_p double The top_p sampling setting for the GenAI request. 1.0 Development
gen_ai.response.finish_reasons string[] Array of reasons the model stopped generating tokens, corresponding to each generation received. ["stop"]; ["stop", "length"] Development
gen_ai.response.id string The unique identifier for the completion. chatcmpl-123 Development
gen_ai.response.model string The name of the model that generated the response. gpt-4-0613 Development
gen_ai.system_instructions any The system message or instructions provided to the GenAI model separately from the chat history. [9] [
  {
    "type": "text",
    "content": "You are an Agent that greet users, always use greetings tool to respond"
  }
]; [
  {
    "type": "text",
    "content": "You are a language translator."
  },
  {
    "type": "text",
    "content": "Your mission is to translate text in English to French."
  }
]		 Development
gen_ai.token.type string The type of token being counted. input; output Development
gen_ai.tool.call.arguments any Parameters passed to the tool call. [10] {
    "location": "San Francisco?",
    "date": "2025-10-01"
}		 Development
gen_ai.tool.call.id string The tool call identifier. call_mszuSIzqtI65i1wAUOE8w5H4 Development
gen_ai.tool.call.result any The result returned by the tool call (if any and if execution was successful). [11] {
  "temperature_range": {
    "high": 75,
    "low": 60
  },
  "conditions": "sunny"
}		 Development
gen_ai.tool.definitions any The list of source system tool definitions available to the GenAI agent or model. [12] [
  {
    "type": "function",
    "name": "get_current_weather",
    "description": "Get the current weather in a given location",
    "parameters": {
      "type": "object",
      "properties": {
        "location": {
          "type": "string",
          "description": "The city and state, e.g. San Francisco, CA"
        },
        "unit": {
          "type": "string",
          "enum": [
            "celsius",
            "fahrenheit"
          ]
        }
      },
      "required": [
        "location",
        "unit"
      ]
    }
  }
]		 Development
gen_ai.tool.description string The tool description. Multiply two numbers Development
gen_ai.tool.name string Name of the tool utilized by the agent. Flights Development
gen_ai.tool.type string Type of the tool utilized by the agent [13] function; extension; datastore Development
gen_ai.usage.input_tokens int The number of tokens used in the GenAI input (prompt). 100 Development
gen_ai.usage.output_tokens int The number of tokens used in the GenAI response (completion). 180 Development

[1] gen_ai.data_source.id: Data sources are used by AI agents and RAG applications to store grounding data. A data source may be an external database, object store, document collection, website, or any other storage system used by the GenAI agent or application. The gen_ai.data_source.id SHOULD match the identifier used by the GenAI system rather than a name specific to the external storage, such as a database or object store. Semantic conventions referencing gen_ai.data_source.id MAY also leverage additional attributes, such as db.*, to further identify and describe the data source.

[2] gen_ai.evaluation.score.label: This attribute provides a human-readable interpretation of the evaluation score produced by an evaluator. For example, a score value of 1 could mean "relevant" in one evaluation system and "not relevant" in another, depending on the scoring range and evaluator. The label SHOULD have low cardinality. Possible values depend on the evaluation metric and evaluator used; implementations SHOULD document the possible values.

[3] gen_ai.input.messages: Instrumentations MUST follow Input messages JSON schema. When the attribute is recorded on events, it MUST be recorded in structured form. When recorded on spans, it MAY be recorded as a JSON string if structured format is not supported and SHOULD be recorded in structured form otherwise.

Messages MUST be provided in the order they were sent to the model. Instrumentations MAY provide a way for users to filter or truncate input messages.

[!Warning] This attribute is likely to contain sensitive information including user/PII data.

See Recording content on attributes section for more details.

[4] gen_ai.operation.name: If one of the predefined values applies, but specific system uses a different name it's RECOMMENDED to document it in the semantic conventions for specific GenAI system and use system-specific name in the instrumentation. If a different name is not documented, instrumentation libraries SHOULD use applicable predefined value.

[5] gen_ai.output.messages: Instrumentations MUST follow Output messages JSON schema

Each message represents a single output choice/candidate generated by the model. Each message corresponds to exactly one generation (choice/candidate) and vice versa - one choice cannot be split across multiple messages or one message cannot contain parts from multiple choices.

When the attribute is recorded on events, it MUST be recorded in structured form. When recorded on spans, it MAY be recorded as a JSON string if structured format is not supported and SHOULD be recorded in structured form otherwise.

Instrumentations MAY provide a way for users to filter or truncate output messages.

[!Warning] This attribute is likely to contain sensitive information including user/PII data.

See Recording content on attributes section for more details.

[6] gen_ai.output.type: This attribute SHOULD be used when the client requests output of a specific type. The model may return zero or more outputs of this type. This attribute specifies the output modality and not the actual output format. For example, if an image is requested, the actual output could be a URL pointing to an image file. Additional output format details may be recorded in the future in the gen_ai.output.{type}.* attributes.

[7] gen_ai.provider.name: The attribute SHOULD be set based on the instrumentation's best knowledge and may differ from the actual model provider.

Multiple providers, including Azure OpenAI, Gemini, and AI hosting platforms are accessible using the OpenAI REST API and corresponding client libraries, but may proxy or host models from different providers.

The gen_ai.request.model, gen_ai.response.model, and server.address attributes may help identify the actual system in use.

The gen_ai.provider.name attribute acts as a discriminator that identifies the GenAI telemetry format flavor specific to that provider within GenAI semantic conventions. It SHOULD be set consistently with provider-specific attributes and signals. For example, GenAI spans, metrics, and events related to AWS Bedrock should have the gen_ai.provider.name set to aws.bedrock and include applicable aws.bedrock.* attributes and are not expected to include openai.* attributes.

[8] gen_ai.request.encoding_formats: In some GenAI systems the encoding formats are called embedding types. Also, some GenAI systems only accept a single format per request.

[9] gen_ai.system_instructions: This attribute SHOULD be used when the corresponding provider or API allows to provide system instructions or messages separately from the chat history.

Instructions that are part of the chat history SHOULD be recorded in gen_ai.input.messages attribute instead.

Instrumentations MUST follow System instructions JSON schema.

When recorded on spans, it MAY be recorded as a JSON string if structured format is not supported and SHOULD be recorded in structured form otherwise.

Instrumentations MAY provide a way for users to filter or truncate system instructions.

[!Warning] This attribute may contain sensitive information.

See Recording content on attributes section for more details.

[10] gen_ai.tool.call.arguments: > [!WARNING]

This attribute may contain sensitive information.

It's expected to be an object - in case a serialized string is available to the instrumentation, the instrumentation SHOULD do the best effort to deserialize it to an object. When recorded on spans, it MAY be recorded as a JSON string if structured format is not supported and SHOULD be recorded in structured form otherwise.

[11] gen_ai.tool.call.result: > [!WARNING]

This attribute may contain sensitive information.

It's expected to be an object - in case a serialized string is available to the instrumentation, the instrumentation SHOULD do the best effort to deserialize it to an object. When recorded on spans, it MAY be recorded as a JSON string if structured format is not supported and SHOULD be recorded in structured form otherwise.

[12] gen_ai.tool.definitions: The value of this attribute matches source system tool definition format.

It's expected to be an array of objects where each object represents a tool definition. In case a serialized string is available to the instrumentation, the instrumentation SHOULD do the best effort to deserialize it to an array. When recorded on spans, it MAY be recorded as a JSON string if structured format is not supported and SHOULD be recorded in structured form otherwise.

Since this attribute could be large, it's NOT RECOMMENDED to populate it by default. Instrumentations MAY provide a way to enable populating this attribute.

[13] gen_ai.tool.type: Extension: A tool executed on the agent-side to directly call external APIs, bridging the gap between the agent and real-world systems. Agent-side operations involve actions that are performed by the agent on the server or within the agent's controlled environment. Function: A tool executed on the client-side, where the agent generates parameters for a predefined function, and the client executes the logic. Client-side operations are actions taken on the user's end or within the client application. Datastore: A tool used by the agent to access and query structured or unstructured external data for retrieval-augmented tasks or knowledge updates.

gen_ai.operation.name 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
chat Chat completion operation such as OpenAI Chat API Development
create_agent Create GenAI agent Development
embeddings Embeddings operation such as OpenAI Create embeddings API Development
execute_tool Execute a tool Development
generate_content Multimodal content generation operation such as Gemini Generate Content Development
invoke_agent Invoke GenAI agent Development
text_completion Text completions operation such as OpenAI Completions API (Legacy) Development

gen_ai.output.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
image Image Development
json JSON object with known or unknown schema Development
speech Speech Development
text Plain text Development

gen_ai.provider.name 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 Development
aws.bedrock AWS Bedrock Development
azure.ai.inference Azure AI Inference Development
azure.ai.openai Azure OpenAI Development
cohere Cohere Development
deepseek DeepSeek Development
gcp.gemini Gemini [14] Development
gcp.gen_ai Any Google generative AI endpoint [15] Development
gcp.vertex_ai Vertex AI [16] Development
groq Groq Development
ibm.watsonx.ai IBM Watsonx AI Development
mistral_ai Mistral AI Development
openai OpenAI Development
perplexity Perplexity Development
x_ai xAI Development

[14]: Used when accessing the 'generativelanguage.googleapis.com' endpoint. Also known as the AI Studio API.

[15]: May be used when specific backend is unknown.

[16]: Used when accessing the 'aiplatform.googleapis.com' endpoint.

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.) Development
output Output tokens (completion, response, etc.) Development

Deprecated GenAI Attributes

Describes deprecated gen_ai attributes.

Attribute Type Description Examples Stability
gen_ai.completion string Deprecated, use Event API to report completions contents. [{'role': 'assistant', 'content': 'The capital of France is Paris.'}] Deprecated
Removed, no replacement at this time.
gen_ai.prompt string Deprecated, use Event API to report prompt contents. [{'role': 'user', 'content': 'What is the capital of France?'}] Deprecated
Removed, no replacement at this time.
gen_ai.system string Deprecated, use gen_ai.provider.name instead. openai; gcp.gen_ai; gcp.vertex_ai Deprecated
Replaced by gen_ai.provider.name.
gen_ai.usage.completion_tokens int Deprecated, use gen_ai.usage.output_tokens instead. 42 Deprecated
Replaced by gen_ai.usage.output_tokens.
gen_ai.usage.prompt_tokens int Deprecated, use gen_ai.usage.input_tokens instead. 42 Deprecated
Replaced by gen_ai.usage.input_tokens.

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 Development
aws.bedrock AWS Bedrock Development
azure.ai.inference Azure AI Inference Development
azure.ai.openai Azure OpenAI Development
cohere Cohere Development
deepseek DeepSeek Development
gcp.gemini Gemini [17] Development
gcp.gen_ai Any Google generative AI endpoint [18] Development
gcp.vertex_ai Vertex AI [19] Development
groq Groq Development
ibm.watsonx.ai IBM Watsonx AI Development
mistral_ai Mistral AI Development
openai OpenAI Development
perplexity Perplexity Development
xai xAI Development

[17]: This refers to the 'generativelanguage.googleapis.com' endpoint. Also known as the AI Studio API. May use common attributes prefixed with 'gcp.gen_ai.'.

[18]: May be used when specific backend is unknown. May use common attributes prefixed with 'gcp.gen_ai.'.

[19]: This refers to the 'aiplatform.googleapis.com' endpoint. May use common attributes prefixed with 'gcp.gen_ai.'.

Deprecated OpenAI GenAI Attributes

Describes deprecated gen_ai.openai attributes.

Attribute Type Description Examples Stability
gen_ai.openai.request.response_format string Deprecated, use gen_ai.output.type. text; json_object; json_schema Deprecated
Replaced by gen_ai.output.type.
gen_ai.openai.request.seed int Deprecated, use gen_ai.request.seed. 100 Deprecated
Replaced by gen_ai.request.seed.
gen_ai.openai.request.service_tier string Deprecated, use openai.request.service_tier. auto; default Deprecated
Replaced by openai.request.service_tier.
gen_ai.openai.response.service_tier string Deprecated, use openai.response.service_tier. scale; default Deprecated
Replaced by openai.response.service_tier.
gen_ai.openai.response.system_fingerprint string Deprecated, use openai.response.system_fingerprint. fp_44709d6fcb Deprecated
Replaced by openai.response.system_fingerprint.

gen_ai.openai.request.response_format 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
json_object JSON object response format Development
json_schema JSON schema response format Development
text Text response format Development

gen_ai.openai.request.service_tier 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
auto The system will utilize scale tier credits until they are exhausted. Development
default The system will utilize the default scale tier. Development