semantic-conventions/model/gen-ai/registry.yaml

218 lines
8.6 KiB
YAML

groups:
- id: registry.gen_ai
type: attribute_group
display_name: GenAI Attributes
brief: >
This document defines the attributes used to describe telemetry in the context of Generative Artificial Intelligence (GenAI) Models requests and responses.
attributes:
- id: gen_ai.system
stability: experimental
type:
members:
- id: openai
stability: experimental
value: "openai"
brief: 'OpenAI'
- id: vertex_ai
stability: experimental
value: "vertex_ai"
brief: 'Vertex AI'
- id: anthropic
stability: experimental
value: "anthropic"
brief: 'Anthropic'
- id: cohere
stability: experimental
value: "cohere"
brief: 'Cohere'
- id: az.ai.inference
stability: experimental
value: "az.ai.inference"
brief: 'Azure AI Inference'
- id: ibm.watsonx.ai
stability: experimental
value: "ibm.watsonx.ai"
brief: 'IBM Watsonx AI'
- id: aws.bedrock
stability: experimental
value: "aws.bedrock"
brief: 'AWS Bedrock'
brief: The Generative AI product as identified by the client or server instrumentation.
note: |
The `gen_ai.system` describes a family of GenAI models with specific model identified
by `gen_ai.request.model` and `gen_ai.response.model` attributes.
The actual GenAI product may differ from the one identified by the client.
For example, when using OpenAI client libraries to communicate with Mistral, the `gen_ai.system`
is set to `openai` based on the instrumentation's best knowledge.
For custom model, a custom friendly name SHOULD be used.
If none of these options apply, the `gen_ai.system` SHOULD be set to `_OTHER`.
examples: 'openai'
- id: gen_ai.request.model
stability: experimental
type: string
brief: The name of the GenAI model a request is being made to.
examples: 'gpt-4'
- id: gen_ai.request.max_tokens
stability: experimental
type: int
brief: The maximum number of tokens the model generates for a request.
examples: [100]
- id: gen_ai.request.temperature
stability: experimental
type: double
brief: The temperature setting for the GenAI request.
examples: [0.0]
- id: gen_ai.request.top_p
stability: experimental
type: double
brief: The top_p sampling setting for the GenAI request.
examples: [1.0]
- id: gen_ai.request.top_k
stability: experimental
type: double
brief: The top_k sampling setting for the GenAI request.
examples: [1.0]
- id: gen_ai.request.stop_sequences
stability: experimental
type: string[]
brief: List of sequences that the model will use to stop generating further tokens.
examples:
- [forest, lived]
- id: gen_ai.request.frequency_penalty
stability: experimental
type: double
brief: The frequency penalty setting for the GenAI request.
examples: [0.1]
- id: gen_ai.request.presence_penalty
stability: experimental
type: double
brief: The presence penalty setting for the GenAI request.
examples: [0.1]
- id: gen_ai.request.encoding_formats
stability: experimental
type: string[]
brief: The encoding formats requested in an embeddings operation, if specified.
examples:
- ['base64']
- ['float', 'binary']
note: >
In some GenAI systems the encoding formats are called embedding types.
Also, some GenAI systems only accept a single format per request.
- id: gen_ai.request.seed
stability: experimental
type: int
brief: Requests with same seed value more likely to return same result.
examples: [100]
- id: gen_ai.response.id
stability: experimental
type: string
brief: The unique identifier for the completion.
examples: ['chatcmpl-123']
- id: gen_ai.response.model
stability: experimental
type: string
brief: The name of the model that generated the response.
examples: ['gpt-4-0613']
- id: gen_ai.response.finish_reasons
stability: experimental
type: string[]
brief: Array of reasons the model stopped generating tokens, corresponding to each generation received.
examples:
- [stop]
- [stop, length]
- id: gen_ai.usage.input_tokens
stability: experimental
type: int
brief: The number of tokens used in the GenAI input (prompt).
examples: [100]
- id: gen_ai.usage.output_tokens
stability: experimental
type: int
brief: The number of tokens used in the GenAI response (completion).
examples: [180]
- id: gen_ai.token.type
stability: experimental
type:
members:
- id: input
stability: experimental
value: "input"
brief: 'Input tokens (prompt, input, etc.)'
- id: completion
stability: experimental
value: "output"
brief: 'Output tokens (completion, response, etc.)'
brief: The type of token being counted.
examples: ['input', 'output']
- id: gen_ai.operation.name
stability: experimental
type:
members:
- id: chat
value: "chat"
brief: 'Chat completion operation such as [OpenAI Chat API](https://platform.openai.com/docs/api-reference/chat)'
stability: experimental
- id: text_completion
value: "text_completion"
brief: 'Text completions operation such as [OpenAI Completions API (Legacy)](https://platform.openai.com/docs/api-reference/completions)'
stability: experimental
- id: embeddings
value: "embeddings"
brief: 'Embeddings operation such as [OpenAI Create embeddings API](https://platform.openai.com/docs/api-reference/embeddings/create)'
stability: experimental
brief: The name of the operation being performed.
note: >
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.
- id: registry.gen_ai.openai
type: attribute_group
display_name: OpenAI Attributes
brief: >
Thie group defines attributes for OpenAI.
attributes:
- id: gen_ai.openai.request.response_format
stability: experimental
type:
members:
- id: text
value: "text"
brief: 'Text response format'
stability: experimental
- id: json_object
value: "json_object"
brief: 'JSON object response format'
stability: experimental
- id: json_schema
value: "json_schema"
brief: 'JSON schema response format'
stability: experimental
brief: The response format that is requested.
examples: ['json']
- id: gen_ai.openai.request.service_tier
stability: experimental
type:
members:
- id: auto
value: "auto"
brief: The system will utilize scale tier credits until they are exhausted.
stability: experimental
- id: default
value: "default"
brief: The system will utilize the default scale tier.
stability: experimental
brief: The service tier requested. May be a specific tier, default, or auto.
examples: ['auto', 'default']
- id: gen_ai.openai.response.service_tier
stability: experimental
type: string
brief: The service tier used for the response.
examples: ['scale', 'default']
- id: gen_ai.openai.response.system_fingerprint
stability: experimental
type: string
brief: A fingerprint to track any eventual change in the Generative AI environment.
examples: ["fp_44709d6fcb"]