Semantic conventions for Generative AI events
Status: Development
[!Warning]
Existing GenAI instrumentations that are using v1.36.0 of this document (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_INas 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.
Note: Events are in-development and not yet available in some languages. Check spec-compliance matrix 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.
Attributes:
| Key | Stability | Requirement Level | Value Type | Description | Example Values |
|---|---|---|---|---|---|
gen_ai.operation.name |  | Required | string | The name of the operation being performed. [1] | chat; generate_content; text_completion |
error.type |  | Conditionally Required if the operation ended in an error | string | Describes a class of error the operation ended with. [2] | timeout; java.net.UnknownHostException; server_certificate_invalid; 500 |
gen_ai.conversation.id | | Conditionally Required when available | string | The unique identifier for a conversation (session, thread), used to store and correlate messages within this conversation. [3] | conv_5j66UpCpwteGg4YSxUnt7lPY |
gen_ai.output.type | | Conditionally Required [4] | string | Represents the content type requested by the client. [5] | text; json; image |
gen_ai.request.choice.count | | Conditionally Required if available, in the request, and !=1 | int | The target number of candidate completions to return. | 3 |
gen_ai.request.model | | Conditionally Required If available. | string | The name of the GenAI model a request is being made to. [6] | gpt-4 |
gen_ai.request.seed | | Conditionally Required if applicable and if the request includes a seed | int | Requests with same seed value more likely to return same result. | 100 |
server.port | | Conditionally Required If server.address is set. | int | GenAI server port. [7] | 80; 8080; 443 |
gen_ai.request.frequency_penalty | | Recommended | double | The frequency penalty setting for the GenAI request. | 0.1 |
gen_ai.request.max_tokens | | Recommended | int | The maximum number of tokens the model generates for a request. | 100 |
gen_ai.request.presence_penalty | | Recommended | double | The presence penalty setting for the GenAI request. | 0.1 |
gen_ai.request.stop_sequences | | Recommended | string[] | List of sequences that the model will use to stop generating further tokens. | ["forest", "lived"] |
gen_ai.request.temperature | | Recommended | double | The temperature setting for the GenAI request. | 0.0 |
gen_ai.request.top_p | | Recommended | double | The top_p sampling setting for the GenAI request. | 1.0 |
gen_ai.response.finish_reasons | | Recommended | string[] | Array of reasons the model stopped generating tokens, corresponding to each generation received. | ["stop"]; ["stop", "length"] |
gen_ai.response.id | | Recommended | string | The unique identifier for the completion. | chatcmpl-123 |
gen_ai.response.model | | Recommended | string | The name of the model that generated the response. [8] | gpt-4-0613 |
gen_ai.usage.input_tokens | | Recommended | int | The number of tokens used in the GenAI input (prompt). | 100 |
gen_ai.usage.output_tokens | | Recommended | int | The number of tokens used in the GenAI response (completion). | 180 |
server.address | | Recommended | string | GenAI server address. [9] | example.com; 10.1.2.80; /tmp/my.sock |
gen_ai.input.messages | | Opt-In | 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” } ] } ] |
gen_ai.output.messages | | Opt-In | 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” } ] |
gen_ai.system_instructions | | Opt-In | 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." } ] |
gen_ai.tool.definitions | | Opt-In | 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” ] } } ] |
[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)
when instrumenting GenAI client libraries that maintain conversation on the backend side (see AWS Bedrock agent sessions, OpenAI Assistant 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: when applicable and if the request includes an output format.
[5] 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.
[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.
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.
[11] 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.
[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.
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.
[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 | |
create_agent | Create GenAI agent | |
embeddings | Embeddings operation such as OpenAI Create embeddings API | |
execute_tool | Execute a tool | |
generate_content | Multimodal content generation operation such as Gemini Generate Content | |
invoke_agent | Invoke GenAI agent | |
text_completion | Text completions operation such as OpenAI Completions API (Legacy) | |
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.
Attributes:
| Key | Stability | Requirement Level | Value Type | Description | Example Values |
|---|---|---|---|---|---|
gen_ai.evaluation.name | | Required | string | The name of the evaluation metric used for the GenAI response. | Relevance; IntentResolution |
error.type | | Conditionally Required if the operation ended in an error | string | Describes a class of error the operation ended with. [1] | timeout; java.net.UnknownHostException; server_certificate_invalid; 500 |
gen_ai.evaluation.score.label | | Conditionally Required if applicable | string | Human readable label for evaluation. [2] | relevant; not_relevant; correct; incorrect; pass; fail |
gen_ai.evaluation.score.value | | Conditionally Required if applicable | double | The evaluation score returned by the evaluator. | 4.0 |
gen_ai.evaluation.explanation | | Recommended | 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. |
gen_ai.response.id | | Recommended when available | string | The unique identifier for the completion. [3] | chatcmpl-123 |
[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. | |
Feedback
Was this page helpful?
Thank you. Your feedback is appreciated!
Please let us know how we can improve this page. Your feedback is appreciated!