Skip to content

Latest commit

 

History

History
90 lines (64 loc) · 9.01 KB

azure-ai-inference.md

File metadata and controls

90 lines (64 loc) · 9.01 KB
Raw

Semantic Conventions for Azure AI Inference

Status: Experimental

The Semantic Conventions for Azure AI Inference extend and override the GenAI Semantic Conventions.

Azure AI Inference Spans

gen_ai.system MUST be set to "az.ai.inference" and SHOULD be provided at span creation time.

Attributes

Attribute Type Description Examples Requirement Level Stability
gen_ai.operation.name string The name of the operation being performed. [1] chat; text_completion; embeddings Required Experimental
error.type 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 Stable
gen_ai.request.model string The name of the GenAI model a request is being made to. [3] gpt-4 Conditionally Required If available. Experimental
server.port int GenAI server port. [4] 80; 8080; 443 Conditionally Required If not default (443). Stable
az.namespace string Azure Resource Provider Namespace as recognized by the client. [5] Microsoft.CognitiveServices Recommended Experimental
gen_ai.request.encoding_formats string[] The encoding formats requested in an embeddings operation, if specified. [6] ["base64"]; ["float", "binary"] Recommended Experimental
gen_ai.request.frequency_penalty double The frequency penalty setting for the GenAI request. 0.1 Recommended Experimental
gen_ai.request.max_tokens int The maximum number of tokens the model generates for a request. 100 Recommended Experimental
gen_ai.request.presence_penalty double The presence penalty setting for the GenAI request. 0.1 Recommended Experimental
gen_ai.request.stop_sequences string[] List of sequences that the model will use to stop generating further tokens. ["forest", "lived"] Recommended Experimental
gen_ai.request.temperature double The temperature setting for the GenAI request. 0.0 Recommended Experimental
gen_ai.request.top_p double The top_p sampling setting for the GenAI request. 1.0 Recommended Experimental
gen_ai.response.finish_reasons string[] Array of reasons the model stopped generating tokens, corresponding to each generation received. ["stop"]; ["stop", "length"] Recommended Experimental
gen_ai.response.id string The unique identifier for the completion. chatcmpl-123 Recommended Experimental
gen_ai.response.model string The name of the model that generated the response. [7] gpt-4-0613 Recommended Experimental
gen_ai.usage.input_tokens int The number of prompt tokens as reported in the usage prompt_tokens property of the response. 100 Recommended Experimental
gen_ai.usage.output_tokens int The number of completion tokens as reported in the usage completion_tokens property of the response. 180 Recommended Experimental
server.address string GenAI server address. [8] example.com; 10.1.2.80; /tmp/my.sock Recommended Stable

[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.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.

[4] 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.

[5] az.namespace: When az.namespace attribute is populated, it MUST be set to Microsoft.CognitiveServices for all operations performed by Azure AI Inference clients.

[6] 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.

[7] 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.

[8] 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.

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. Stable

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 Experimental
embeddings Embeddings operation such as OpenAI Create embeddings API Experimental
text_completion Text completions operation such as OpenAI Completions API (Legacy) Experimental

Azure AI Inference Metrics

Azure AI Inference metrics follow generic Generative AI metrics.