Package io.opentelemetry.semconv.incubating

Class GenAiIncubatingAttributes

java.lang.Object
io.opentelemetry.semconv.incubating.GenAiIncubatingAttributes
public final class GenAiIncubatingAttributes extends Object

  • Field Details

    • GEN_AI_AGENT_DESCRIPTION

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_AGENT_DESCRIPTION
      Free-form description of the GenAI agent provided by the application.

    • GEN_AI_AGENT_ID

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_AGENT_ID
      The unique identifier of the GenAI agent.

    • GEN_AI_AGENT_NAME

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_AGENT_NAME
      Human-readable name of the GenAI agent provided by the application.

    • GEN_AI_AGENT_VERSION

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_AGENT_VERSION
      The version of the GenAI agent.

    • GEN_AI_COMPLETION

      @Deprecated public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_COMPLETION
      Deprecated.
      Removed, no replacement at this time.
      Deprecated, use Event API to report completions contents.

    • GEN_AI_CONVERSATION_ID

      public static final io.opentelemetry.api.common.AttributeKey<String> 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

      public static final io.opentelemetry.api.common.AttributeKey<String> 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.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.

    • GEN_AI_EMBEDDINGS_DIMENSION_COUNT

      public static final io.opentelemetry.api.common.AttributeKey<Long> GEN_AI_EMBEDDINGS_DIMENSION_COUNT
      The number of dimensions the resulting output embeddings should have.

    • GEN_AI_EVALUATION_EXPLANATION

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_EVALUATION_EXPLANATION
      A free-form explanation for the assigned score provided by the evaluator.

    • GEN_AI_EVALUATION_NAME

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_EVALUATION_NAME
      The name of the evaluation metric used for the GenAI response.

    • GEN_AI_EVALUATION_SCORE_LABEL

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_EVALUATION_SCORE_LABEL
      Human readable label for evaluation.

      Notes:

      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.

    • GEN_AI_EVALUATION_SCORE_VALUE

      public static final io.opentelemetry.api.common.AttributeKey<Double> GEN_AI_EVALUATION_SCORE_VALUE
      The evaluation score returned by the evaluator.

    • GEN_AI_OPENAI_REQUEST_RESPONSE_FORMAT

      @Deprecated public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_OPENAI_REQUEST_RESPONSE_FORMAT
      Deprecated.
      Replaced by gen_ai.output.type.
      Deprecated, use gen_ai.output.type.

    • GEN_AI_OPENAI_REQUEST_SEED

      @Deprecated public static final io.opentelemetry.api.common.AttributeKey<Long> GEN_AI_OPENAI_REQUEST_SEED
      Deprecated.
      Replaced by gen_ai.request.seed.
      Deprecated, use gen_ai.request.seed.

    • GEN_AI_OPENAI_REQUEST_SERVICE_TIER

      @Deprecated public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_OPENAI_REQUEST_SERVICE_TIER
      Deprecated.
      Replaced by openai.request.service_tier.
      Deprecated, use openai.request.service_tier.

    • GEN_AI_OPENAI_RESPONSE_SERVICE_TIER

      @Deprecated public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_OPENAI_RESPONSE_SERVICE_TIER
      Deprecated.
      Replaced by openai.response.service_tier.
      Deprecated, use openai.response.service_tier.

    • GEN_AI_OPENAI_RESPONSE_SYSTEM_FINGERPRINT

      @Deprecated public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_OPENAI_RESPONSE_SYSTEM_FINGERPRINT
      Deprecated.
      Replaced by openai.response.system_fingerprint.
      Deprecated, use openai.response.system_fingerprint.

    • GEN_AI_OPERATION_NAME

      public static final io.opentelemetry.api.common.AttributeKey<String> 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

      public static final io.opentelemetry.api.common.AttributeKey<String> 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 public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_PROMPT
      Deprecated.
      Removed, no replacement at this time.
      Deprecated, use Event API to report prompt contents.

    • GEN_AI_PROMPT_NAME

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_PROMPT_NAME
      The name of the prompt that uniquely identifies it.

    • GEN_AI_PROVIDER_NAME

      public static final io.opentelemetry.api.common.AttributeKey<String> 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, 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.

    • GEN_AI_REQUEST_CHOICE_COUNT

      public static final io.opentelemetry.api.common.AttributeKey<Long> 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_FORMATS
      The 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_PENALTY
      The frequency penalty setting for the GenAI request.

    • GEN_AI_REQUEST_MAX_TOKENS

      public static final io.opentelemetry.api.common.AttributeKey<Long> GEN_AI_REQUEST_MAX_TOKENS
      The maximum number of tokens the model generates for a request.

    • GEN_AI_REQUEST_MODEL

      public static final io.opentelemetry.api.common.AttributeKey<String> 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_PENALTY
      The presence penalty setting for the GenAI request.

    • GEN_AI_REQUEST_SEED

      public static final io.opentelemetry.api.common.AttributeKey<Long> 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_SEQUENCES
      List of sequences that the model will use to stop generating further tokens.

    • GEN_AI_REQUEST_STREAM

      public static final io.opentelemetry.api.common.AttributeKey<Boolean> GEN_AI_REQUEST_STREAM
      Indicates whether the GenAI request was made in streaming mode.

    • GEN_AI_REQUEST_TEMPERATURE

      public static final io.opentelemetry.api.common.AttributeKey<Double> GEN_AI_REQUEST_TEMPERATURE
      The temperature setting for the GenAI request.

    • GEN_AI_REQUEST_TOP_K

      public static final io.opentelemetry.api.common.AttributeKey<Double> GEN_AI_REQUEST_TOP_K
      The top_k sampling setting for the GenAI request.

    • GEN_AI_REQUEST_TOP_P

      public static final io.opentelemetry.api.common.AttributeKey<Double> 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_REASONS
      Array of reasons the model stopped generating tokens, corresponding to each generation received.

    • GEN_AI_RESPONSE_ID

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_RESPONSE_ID
      The unique identifier for the completion.

    • GEN_AI_RESPONSE_MODEL

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_RESPONSE_MODEL
      The name of the model that generated the response.

    • GEN_AI_RESPONSE_TIME_TO_FIRST_CHUNK

      public static final io.opentelemetry.api.common.AttributeKey<Double> GEN_AI_RESPONSE_TIME_TO_FIRST_CHUNK
      Time to first chunk in a streaming response, measured from request issuance, in seconds. The value is measured from when the client issues the generation request to when the first chunk is received in the response stream.

    • GEN_AI_RETRIEVAL_QUERY_TEXT

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_RETRIEVAL_QUERY_TEXT
      The query text used for retrieval.

      Notes:

      [!Warning] This attribute may contain sensitive information.

    • GEN_AI_SYSTEM

      @Deprecated public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_SYSTEM
      Deprecated.
      Replaced by gen_ai.provider.name.
      Deprecated, use gen_ai.provider.name instead.

    • GEN_AI_TOKEN_TYPE

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_TOKEN_TYPE
      The type of token being counted.

    • GEN_AI_TOOL_CALL_ID

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_TOOL_CALL_ID
      The tool call identifier.

    • GEN_AI_TOOL_DESCRIPTION

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_TOOL_DESCRIPTION
      The tool description.

    • GEN_AI_TOOL_NAME

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_TOOL_NAME
      Name of the tool utilized by the agent.

    • GEN_AI_TOOL_TYPE

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_TOOL_TYPE
      Type of the tool utilized by the agent

      Notes:

      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_CACHE_CREATION_INPUT_TOKENS

      public static final io.opentelemetry.api.common.AttributeKey<Long> GEN_AI_USAGE_CACHE_CREATION_INPUT_TOKENS
      The number of input tokens written to a provider-managed cache.

      Notes:

      The value SHOULD be included in gen_ai.usage.input_tokens.

    • GEN_AI_USAGE_CACHE_READ_INPUT_TOKENS

      public static final io.opentelemetry.api.common.AttributeKey<Long> GEN_AI_USAGE_CACHE_READ_INPUT_TOKENS
      The number of input tokens served from a provider-managed cache.

      Notes:

      The value SHOULD be included in gen_ai.usage.input_tokens.

    • GEN_AI_USAGE_COMPLETION_TOKENS

      @Deprecated public static final io.opentelemetry.api.common.AttributeKey<Long> GEN_AI_USAGE_COMPLETION_TOKENS
      Deprecated.
      Replaced by gen_ai.usage.output_tokens.
      Deprecated, use gen_ai.usage.output_tokens instead.

    • GEN_AI_USAGE_INPUT_TOKENS

      public static final io.opentelemetry.api.common.AttributeKey<Long> GEN_AI_USAGE_INPUT_TOKENS
      The number of tokens used in the GenAI input (prompt).

      Notes:

      This value SHOULD include all types of input tokens, including cached tokens. Instrumentations SHOULD make a best effort to populate this value, using a total provided by the provider when available or, depending on the provider API, by summing different token types parsed from the provider output.

    • GEN_AI_USAGE_OUTPUT_TOKENS

      public static final io.opentelemetry.api.common.AttributeKey<Long> 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_TOKENS
      Deprecated.
      Replaced by gen_ai.usage.input_tokens.
      Deprecated, use gen_ai.usage.input_tokens instead.

    • GEN_AI_USAGE_REASONING_OUTPUT_TOKENS

      public static final io.opentelemetry.api.common.AttributeKey<Long> GEN_AI_USAGE_REASONING_OUTPUT_TOKENS
      The number of output tokens used for reasoning (e.g. chain-of-thought, extended thinking).

      Notes:

      The value SHOULD be included in gen_ai.usage.output_tokens.

    • GEN_AI_WORKFLOW_NAME

      public static final io.opentelemetry.api.common.AttributeKey<String> GEN_AI_WORKFLOW_NAME
      Human-readable name of the GenAI workflow provided by the application.

      Notes:

      This attribute can be populated in different frameworks eg: name of the first chain in LangChain OR name of the crew in CrewAI.