Class GenAiIncubatingAttributes
-
Nested Class Summary
Nested ClassesModifier and TypeClassDescriptionstatic final classDeprecated.static final classDeprecated.Replaced byopenai.request.service_tier.static final classValues forGEN_AI_OPERATION_NAME.static final classValues forGEN_AI_OUTPUT_TYPE.static final classValues forGEN_AI_PROVIDER_NAME.static final classDeprecated.Replaced bygen_ai.provider.name.static final classValues forGEN_AI_TOKEN_TYPE. -
Field Summary
FieldsModifier and TypeFieldDescriptionstatic final io.opentelemetry.api.common.AttributeKey<String>Free-form description of the GenAI agent provided by the application.static final io.opentelemetry.api.common.AttributeKey<String>The unique identifier of the GenAI agent.static final io.opentelemetry.api.common.AttributeKey<String>Human-readable name of the GenAI agent provided by the application.static final io.opentelemetry.api.common.AttributeKey<String>Deprecated.Removed, no replacement at this time.static final io.opentelemetry.api.common.AttributeKey<String>The unique identifier for a conversation (session, thread), used to store and correlate messages within this conversation.static final io.opentelemetry.api.common.AttributeKey<String>The data source identifier.static final io.opentelemetry.api.common.AttributeKey<String>Deprecated.Replaced bygen_ai.output.type.static final io.opentelemetry.api.common.AttributeKey<Long>Deprecated.Replaced bygen_ai.request.seed.static final io.opentelemetry.api.common.AttributeKey<String>Deprecated.Replaced byopenai.request.service_tier.static final io.opentelemetry.api.common.AttributeKey<String>Deprecated.Replaced byopenai.response.service_tier.static final io.opentelemetry.api.common.AttributeKey<String>Deprecated.Replaced byopenai.response.system_fingerprint.static final io.opentelemetry.api.common.AttributeKey<String>The name of the operation being performed.static final io.opentelemetry.api.common.AttributeKey<String>Represents the content type requested by the client.static final io.opentelemetry.api.common.AttributeKey<String>Deprecated.Removed, no replacement at this time.static final io.opentelemetry.api.common.AttributeKey<String>The Generative AI provider as identified by the client or server instrumentation.static final io.opentelemetry.api.common.AttributeKey<Long>The target number of candidate completions to return.The encoding formats requested in an embeddings operation, if specified.static final io.opentelemetry.api.common.AttributeKey<Double>The frequency penalty setting for the GenAI request.static final io.opentelemetry.api.common.AttributeKey<Long>The maximum number of tokens the model generates for a request.static final io.opentelemetry.api.common.AttributeKey<String>The name of the GenAI model a request is being made to.static final io.opentelemetry.api.common.AttributeKey<Double>The presence penalty setting for the GenAI request.static final io.opentelemetry.api.common.AttributeKey<Long>Requests with same seed value more likely to return same result.List of sequences that the model will use to stop generating further tokens.static final io.opentelemetry.api.common.AttributeKey<Double>The temperature setting for the GenAI request.static final io.opentelemetry.api.common.AttributeKey<Double>The top_k sampling setting for the GenAI request.static final io.opentelemetry.api.common.AttributeKey<Double>The top_p sampling setting for the GenAI request.Array of reasons the model stopped generating tokens, corresponding to each generation received.static final io.opentelemetry.api.common.AttributeKey<String>The unique identifier for the completion.static final io.opentelemetry.api.common.AttributeKey<String>The name of the model that generated the response.static final io.opentelemetry.api.common.AttributeKey<String>Deprecated.Replaced bygen_ai.provider.name.static final io.opentelemetry.api.common.AttributeKey<String>The type of token being counted.static final io.opentelemetry.api.common.AttributeKey<String>The tool call identifier.static final io.opentelemetry.api.common.AttributeKey<String>The tool description.static final io.opentelemetry.api.common.AttributeKey<String>Name of the tool utilized by the agent.static final io.opentelemetry.api.common.AttributeKey<String>Type of the tool utilized by the agentstatic final io.opentelemetry.api.common.AttributeKey<Long>Deprecated.Replaced bygen_ai.usage.output_tokens.static final io.opentelemetry.api.common.AttributeKey<Long>The number of tokens used in the GenAI input (prompt).static final io.opentelemetry.api.common.AttributeKey<Long>The number of tokens used in the GenAI response (completion).static final io.opentelemetry.api.common.AttributeKey<Long>Deprecated.Replaced bygen_ai.usage.input_tokens. -
Method Summary
-
Field Details
-
GEN_AI_AGENT_DESCRIPTION
Free-form description of the GenAI agent provided by the application. -
GEN_AI_AGENT_ID
The unique identifier of the GenAI agent. -
GEN_AI_AGENT_NAME
Human-readable name of the GenAI agent provided by the application. -
GEN_AI_COMPLETION
Deprecated.Removed, no replacement at this time.Deprecated, use Event API to report completions contents. -
GEN_AI_CONVERSATION_ID
The unique identifier for a conversation (session, thread), used to store and correlate messages within this conversation. -
GEN_AI_DATA_SOURCE_ID
The data source identifier.Notes:
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.idSHOULD 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 referencinggen_ai.data_source.idMAY also leverage additional attributes, such asdb.*, to further identify and describe the data source. -
GEN_AI_OPENAI_REQUEST_RESPONSE_FORMAT
@Deprecated public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_OPENAI_REQUEST_RESPONSE_FORMATDeprecated.Replaced bygen_ai.output.type.Deprecated, usegen_ai.output.type. -
GEN_AI_OPENAI_REQUEST_SEED
@Deprecated public static final io.opentelemetry.api.common.AttributeKey<Long> GEN_AI_OPENAI_REQUEST_SEEDDeprecated.Replaced bygen_ai.request.seed.Deprecated, usegen_ai.request.seed. -
GEN_AI_OPENAI_REQUEST_SERVICE_TIER
@Deprecated public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_OPENAI_REQUEST_SERVICE_TIERDeprecated.Replaced byopenai.request.service_tier.Deprecated, useopenai.request.service_tier. -
GEN_AI_OPENAI_RESPONSE_SERVICE_TIER
@Deprecated public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_OPENAI_RESPONSE_SERVICE_TIERDeprecated.Replaced byopenai.response.service_tier.Deprecated, useopenai.response.service_tier. -
GEN_AI_OPENAI_RESPONSE_SYSTEM_FINGERPRINT
@Deprecated public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_OPENAI_RESPONSE_SYSTEM_FINGERPRINTDeprecated.Replaced byopenai.response.system_fingerprint.Deprecated, useopenai.response.system_fingerprint. -
GEN_AI_OPERATION_NAME
The name of the operation being performed.Notes:
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.
-
GEN_AI_OUTPUT_TYPE
Represents the content type requested by the client.Notes:
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. -
GEN_AI_PROMPT
Deprecated.Removed, no replacement at this time.Deprecated, use Event API to report prompt contents. -
GEN_AI_PROVIDER_NAME
The Generative AI provider as identified by the client or server instrumentation.Notes:
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, andserver.addressattributes may help identify the actual system in use.The
gen_ai.provider.nameattribute 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 thegen_ai.provider.nameset toaws.bedrockand include applicableaws.bedrock.*attributes and are not expected to includeopenai.*attributes. -
GEN_AI_REQUEST_CHOICE_COUNT
The target number of candidate completions to return. -
GEN_AI_REQUEST_ENCODING_FORMATS
public static final io.opentelemetry.api.common.AttributeKey<List<String>> GEN_AI_REQUEST_ENCODING_FORMATSThe encoding formats requested in an embeddings operation, if specified.Notes:
In some GenAI systems the encoding formats are called embedding types. Also, some GenAI systems only accept a single format per request.
-
GEN_AI_REQUEST_FREQUENCY_PENALTY
public static final io.opentelemetry.api.common.AttributeKey<Double> GEN_AI_REQUEST_FREQUENCY_PENALTYThe frequency penalty setting for the GenAI request. -
GEN_AI_REQUEST_MAX_TOKENS
The maximum number of tokens the model generates for a request. -
GEN_AI_REQUEST_MODEL
The name of the GenAI model a request is being made to. -
GEN_AI_REQUEST_PRESENCE_PENALTY
public static final io.opentelemetry.api.common.AttributeKey<Double> GEN_AI_REQUEST_PRESENCE_PENALTYThe presence penalty setting for the GenAI request. -
GEN_AI_REQUEST_SEED
Requests with same seed value more likely to return same result. -
GEN_AI_REQUEST_STOP_SEQUENCES
public static final io.opentelemetry.api.common.AttributeKey<List<String>> GEN_AI_REQUEST_STOP_SEQUENCESList of sequences that the model will use to stop generating further tokens. -
GEN_AI_REQUEST_TEMPERATURE
The temperature setting for the GenAI request. -
GEN_AI_REQUEST_TOP_K
The top_k sampling setting for the GenAI request. -
GEN_AI_REQUEST_TOP_P
The top_p sampling setting for the GenAI request. -
GEN_AI_RESPONSE_FINISH_REASONS
public static final io.opentelemetry.api.common.AttributeKey<List<String>> GEN_AI_RESPONSE_FINISH_REASONSArray of reasons the model stopped generating tokens, corresponding to each generation received. -
GEN_AI_RESPONSE_ID
The unique identifier for the completion. -
GEN_AI_RESPONSE_MODEL
The name of the model that generated the response. -
GEN_AI_SYSTEM
Deprecated.Replaced bygen_ai.provider.name.Deprecated, usegen_ai.provider.nameinstead. -
GEN_AI_TOKEN_TYPE
The type of token being counted. -
GEN_AI_TOOL_CALL_ID
The tool call identifier. -
GEN_AI_TOOL_DESCRIPTION
The tool description. -
GEN_AI_TOOL_NAME
Name of the tool utilized by the agent. -
GEN_AI_TOOL_TYPE
Type of the tool utilized by the agentNotes:
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_USAGE_COMPLETION_TOKENS
@Deprecated public static final io.opentelemetry.api.common.AttributeKey<Long> GEN_AI_USAGE_COMPLETION_TOKENSDeprecated.Replaced bygen_ai.usage.output_tokens.Deprecated, usegen_ai.usage.output_tokensinstead. -
GEN_AI_USAGE_INPUT_TOKENS
The number of tokens used in the GenAI input (prompt). -
GEN_AI_USAGE_OUTPUT_TOKENS
The number of tokens used in the GenAI response (completion). -
GEN_AI_USAGE_PROMPT_TOKENS
@Deprecated public static final io.opentelemetry.api.common.AttributeKey<Long> GEN_AI_USAGE_PROMPT_TOKENSDeprecated.Replaced bygen_ai.usage.input_tokens.Deprecated, usegen_ai.usage.input_tokensinstead.
-
gen_ai.output.type.