# Semantic conventions for Generative AI events **Status**: [Development][DocumentStatus] - [Event: `event.gen_ai.client.inference.operation.details`](#event-eventgen_aiclientinferenceoperationdetails) - [Event: `event.gen_ai.evaluation.result`](#event-eventgen_aievaluationresult) > [!Warning] > > Existing GenAI instrumentations that are using > [v1.36.0 of this document](https://github.com/open-telemetry/semantic-conventions/blob/v1.36.0/docs/gen-ai/README.md) > (or prior): > > * SHOULD NOT change the version of the GenAI conventions that they emit by default. > Conventions include, but are not limited to, attributes, metric, span and event names, > span kind and unit of measure. > * SHOULD introduce an environment variable `OTEL_SEMCONV_STABILITY_OPT_IN` > as a comma-separated list of category-specific values. The list of values > includes: > * `gen_ai_latest_experimental` - emit the latest experimental version of > GenAI conventions (supported by the instrumentation) and do not emit the > old one (v1.36.0 or prior). > * The default behavior is to continue emitting whatever version of the GenAI > conventions the instrumentation was emitting (1.36.0 or prior). > > This transition plan will be updated to include stable version before the > GenAI conventions are marked as stable. GenAI instrumentations MAY capture user inputs sent to the model and responses received from it as [events](https://github.com/open-telemetry/opentelemetry-specification/tree/v1.49.0/specification/logs/data-model.md#events). > Note: > Events are in-development and not yet available in some languages. Check [spec-compliance matrix](https://github.com/open-telemetry/opentelemetry-specification/tree/v1.49.0/spec-compliance-matrix.md#logs) to see the implementation status in corresponding language. ## Event: `event.gen_ai.client.inference.operation.details` **Status:**  The event name MUST be `gen_ai.client.inference.operation.details`. Describes the details of a GenAI completion request including chat history and parameters. This event is opt-in and could be used to store input and output details independently from traces. | Attribute | Type | Description | Examples | [Requirement Level](https://opentelemetry.io/docs/specs/semconv/general/attribute-requirement-level/) | Stability | |---|---|---|---|---|---| | [`gen_ai.operation.name`](/docs/registry/attributes/gen-ai.md) | string | The name of the operation being performed. [1] | `chat`; `generate_content`; `text_completion` | `Required` |  | | [`error.type`](/docs/registry/attributes/error.md) | string | Describes a class of error the operation ended with. [2] | `timeout`; `java.net.UnknownHostException`; `server_certificate_invalid`; `500` | `Conditionally Required` if the operation ended in an error |  | | [`gen_ai.conversation.id`](/docs/registry/attributes/gen-ai.md) | string | The unique identifier for a conversation (session, thread), used to store and correlate messages within this conversation. [3] | `conv_5j66UpCpwteGg4YSxUnt7lPY` | `Conditionally Required` when available |  | | [`gen_ai.output.type`](/docs/registry/attributes/gen-ai.md) | string | Represents the content type requested by the client. [4] | `text`; `json`; `image` | `Conditionally Required` [5] |  | | [`gen_ai.request.choice.count`](/docs/registry/attributes/gen-ai.md) | int | The target number of candidate completions to return. | `3` | `Conditionally Required` if available, in the request, and !=1 |  | | [`gen_ai.request.model`](/docs/registry/attributes/gen-ai.md) | string | The name of the GenAI model a request is being made to. [6] | `gpt-4` | `Conditionally Required` If available. |  | | [`gen_ai.request.seed`](/docs/registry/attributes/gen-ai.md) | int | Requests with same seed value more likely to return same result. | `100` | `Conditionally Required` if applicable and if the request includes a seed |  | | [`server.port`](/docs/registry/attributes/server.md) | int | GenAI server port. [7] | `80`; `8080`; `443` | `Conditionally Required` If `server.address` is set. |  | | [`gen_ai.request.frequency_penalty`](/docs/registry/attributes/gen-ai.md) | double | The frequency penalty setting for the GenAI request. | `0.1` | `Recommended` |  | | [`gen_ai.request.max_tokens`](/docs/registry/attributes/gen-ai.md) | int | The maximum number of tokens the model generates for a request. | `100` | `Recommended` |  | | [`gen_ai.request.presence_penalty`](/docs/registry/attributes/gen-ai.md) | double | The presence penalty setting for the GenAI request. | `0.1` | `Recommended` |  | | [`gen_ai.request.stop_sequences`](/docs/registry/attributes/gen-ai.md) | string[] | List of sequences that the model will use to stop generating further tokens. | `["forest", "lived"]` | `Recommended` |  | | [`gen_ai.request.temperature`](/docs/registry/attributes/gen-ai.md) | double | The temperature setting for the GenAI request. | `0.0` | `Recommended` |  | | [`gen_ai.request.top_p`](/docs/registry/attributes/gen-ai.md) | double | The top_p sampling setting for the GenAI request. | `1.0` | `Recommended` |  | | [`gen_ai.response.finish_reasons`](/docs/registry/attributes/gen-ai.md) | string[] | Array of reasons the model stopped generating tokens, corresponding to each generation received. | `["stop"]`; `["stop", "length"]` | `Recommended` |  | | [`gen_ai.response.id`](/docs/registry/attributes/gen-ai.md) | string | The unique identifier for the completion. | `chatcmpl-123` | `Recommended` |  | | [`gen_ai.response.model`](/docs/registry/attributes/gen-ai.md) | string | The name of the model that generated the response. [8] | `gpt-4-0613` | `Recommended` |  | | [`gen_ai.usage.input_tokens`](/docs/registry/attributes/gen-ai.md) | int | The number of tokens used in the GenAI input (prompt). | `100` | `Recommended` |  | | [`gen_ai.usage.output_tokens`](/docs/registry/attributes/gen-ai.md) | int | The number of tokens used in the GenAI response (completion). | `180` | `Recommended` |  | | [`server.address`](/docs/registry/attributes/server.md) | string | GenAI server address. [9] | `example.com`; `10.1.2.80`; `/tmp/my.sock` | `Recommended` |  | | [`gen_ai.input.messages`](/docs/registry/attributes/gen-ai.md) | any | The chat history provided to the model as an input. [10] | [
  {
    "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"
      }
    ]
  }
] | `Opt-In` |  | | [`gen_ai.output.messages`](/docs/registry/attributes/gen-ai.md) | any | Messages returned by the model where each message represents a specific model response (choice, candidate). [11] | [
  {
    "role": "assistant",
    "parts": [
      {
        "type": "text",
        "content": "The weather in Paris is currently rainy with a temperature of 57°F."
      }
    ],
    "finish_reason": "stop"
  }
] | `Opt-In` |  | | [`gen_ai.system_instructions`](/docs/registry/attributes/gen-ai.md) | any | The system message or instructions provided to the GenAI model separately from the chat history. [12] | [
  {
    "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."
  }
] | `Opt-In` |  | | [`gen_ai.tool.definitions`](/docs/registry/attributes/gen-ai.md) | any | The list of source system tool definitions available to the GenAI agent or model. [13] | [
  {
    "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"
      ]
    }
  }
] | `Opt-In` |  | **[1] `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. **[2] `error.type`:** The `error.type` SHOULD match the error code returned by the Generative AI provider or the client library, the canonical name of exception that occurred, or another low-cardinality error identifier. Instrumentations SHOULD document the list of errors they report. **[3] `gen_ai.conversation.id`:** Instrumentations SHOULD populate conversation id when they have it readily available for a given operation, for example: - when client framework being instrumented manages conversation history (see [LlamaIndex chat store](https://docs.llamaindex.ai/en/stable/module_guides/storing/chat_stores/)) - when instrumenting GenAI client libraries that maintain conversation on the backend side (see [AWS Bedrock agent sessions](https://docs.aws.amazon.com/bedrock/latest/userguide/agents-session-state.html), [OpenAI Assistant threads](https://platform.openai.com/docs/api-reference/threads)) Application developers that manage conversation history MAY add conversation id to GenAI and other spans or logs using custom span or log record processors or hooks provided by instrumentation libraries. **[4] `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. **[5] `gen_ai.output.type`:** when applicable and if the request includes an output format. **[6] `gen_ai.request.model`:** The name of the GenAI model a request is being made to. If the model is supplied by a vendor, then the value must be the exact name of the model requested. If the model is a fine-tuned custom model, the value should have a more specific name than the base model that's been fine-tuned. **[7] `server.port`:** When observed from the client side, and when communicating through an intermediary, `server.port` SHOULD represent the server port behind any intermediaries, for example proxies, if it's available. **[8] `gen_ai.response.model`:** If available. The name of the GenAI model that provided the response. If the model is supplied by a vendor, then the value must be the exact name of the model actually used. If the model is a fine-tuned custom model, the value should have a more specific name than the base model that's been fine-tuned. **[9] `server.address`:** When observed from the client side, and when communicating through an intermediary, `server.address` SHOULD represent the server address behind any intermediaries, for example proxies, if it's available. **[10] `gen_ai.input.messages`:** Instrumentations MUST follow [Input messages JSON schema](/docs/gen-ai/gen-ai-input-messages.json). 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](/docs/gen-ai/gen-ai-spans.md#recording-content-on-attributes) section for more details. **[11] `gen_ai.output.messages`:** Instrumentations MUST follow [Output messages JSON schema](/docs/gen-ai/gen-ai-output-messages.json) 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](/docs/gen-ai/gen-ai-spans.md#recording-content-on-attributes) section for more details. **[12] `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](/docs/gen-ai/gen-ai-system-instructions.json). 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](/docs/gen-ai/gen-ai-spans.md#recording-content-on-attributes) section for more details. **[13] `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. --- `error.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 | |---|---|---| | `_OTHER` | A fallback error value to be used when the instrumentation doesn't define a custom value. |  | --- `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](https://platform.openai.com/docs/api-reference/chat) |  | | `create_agent` | Create GenAI agent |  | | `embeddings` | Embeddings operation such as [OpenAI Create embeddings API](https://platform.openai.com/docs/api-reference/embeddings/create) |  | | `execute_tool` | Execute a tool |  | | `generate_content` | Multimodal content generation operation such as [Gemini Generate Content](https://ai.google.dev/api/generate-content) |  | | `invoke_agent` | Invoke GenAI agent |  | | `text_completion` | Text completions operation such as [OpenAI Completions API (Legacy)](https://platform.openai.com/docs/api-reference/completions) |  | --- `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 |  | | `json` | JSON object with known or unknown schema |  | | `speech` | Speech |  | | `text` | Plain text |  | ## Event: `event.gen_ai.evaluation.result` **Status:**  The event name MUST be `gen_ai.evaluation.result`. This event captures the result of evaluating GenAI output for quality, accuracy, or other characteristics. This event SHOULD be parented to GenAI operation span being evaluated when possible or set `gen_ai.response.id` when span id is not available. | Attribute | Type | Description | Examples | [Requirement Level](https://opentelemetry.io/docs/specs/semconv/general/attribute-requirement-level/) | Stability | |---|---|---|---|---|---| | [`gen_ai.evaluation.name`](/docs/registry/attributes/gen-ai.md) | string | The name of the evaluation metric used for the GenAI response. | `Relevance`; `IntentResolution` | `Required` |  | | [`error.type`](/docs/registry/attributes/error.md) | string | Describes a class of error the operation ended with. [1] | `timeout`; `java.net.UnknownHostException`; `server_certificate_invalid`; `500` | `Conditionally Required` if the operation ended in an error |  | | [`gen_ai.evaluation.score.label`](/docs/registry/attributes/gen-ai.md) | string | Human readable label for evaluation. [2] | `relevant`; `not_relevant`; `correct`; `incorrect`; `pass`; `fail` | `Conditionally Required` if applicable |  | | [`gen_ai.evaluation.score.value`](/docs/registry/attributes/gen-ai.md) | double | The evaluation score returned by the evaluator. | `4.0` | `Conditionally Required` if applicable |  | | [`gen_ai.evaluation.explanation`](/docs/registry/attributes/gen-ai.md) | 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.` | `Recommended` |  | | [`gen_ai.response.id`](/docs/registry/attributes/gen-ai.md) | string | The unique identifier for the completion. [3] | `chatcmpl-123` | `Recommended` when available |  | **[1] `error.type`:** The `error.type` SHOULD match the error code returned by the Generative AI Evaluation provider or the client library, the canonical name of exception that occurred, or another low-cardinality error identifier. Instrumentations SHOULD document the list of errors they report. **[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.response.id`:** The unique identifier assigned to the specific completion being evaluated. This attribute helps correlate the evaluation event with the corresponding operation when span id is not available. --- `error.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 | |---|---|---| | `_OTHER` | A fallback error value to be used when the instrumentation doesn't define a custom value. |  | [DocumentStatus]: https://opentelemetry.io/docs/specs/otel/document-status