Ai Attributes

33 attributes in this category. 33 deprecated

PII Visibility OTel

33 attributes

Deprecated Attributes

These attributes are deprecated and should not be used in new code. See each attribute for migration guidance.

`ai.citations` Deprecated

string[] PII: True Visibility: Public OTel: False

References or sources cited by the AI model in its response.

Example ["Citation 1","Citation 2"]

No replacement available at this time.

Changelog

v0.5.0 #264

v0.1.0 #55

Raw JSON

{
  "key": "ai.citations",
  "brief": "References or sources cited by the AI model in its response.",
  "type": "string[]",
  "pii": {
    "key": "true"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": [
    "Citation 1",
    "Citation 2"
  ],
  "deprecation": {
    "_status": null
  },
  "changelog": [
    {
      "version": "0.5.0",
      "prs": [
        264
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55
      ]
    }
  ]
}

`ai.completion_tokens.used` Deprecated

integer PII: Maybe Visibility: Public OTel: False

The number of tokens used to respond to the message.

Example 10

Aliases gen_ai.usage.output_tokensgen_ai.usage.completion_tokens

Use gen_ai.usage.output_tokens instead.

Status: backfill

Changelog

v0.4.0 #228

v0.1.0 #57 #61

v0.0.0

Raw JSON

{
  "key": "ai.completion_tokens.used",
  "brief": "The number of tokens used to respond to the message.",
  "type": "integer",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": 10,
  "deprecation": {
    "replacement": "gen_ai.usage.output_tokens",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.usage.output_tokens",
    "gen_ai.usage.completion_tokens"
  ],
  "changelog": [
    {
      "version": "0.4.0",
      "prs": [
        228
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        57,
        61
      ]
    },
    {
      "version": "0.0.0"
    }
  ]
}

`ai.documents` Deprecated

string[] PII: True Visibility: Public OTel: False

Documents or content chunks used as context for the AI model.

Example ["document1.txt","document2.pdf"]

No replacement available at this time.

Changelog

v0.5.0 #264

v0.1.0 #55

Raw JSON

{
  "key": "ai.documents",
  "brief": "Documents or content chunks used as context for the AI model.",
  "type": "string[]",
  "pii": {
    "key": "true"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": [
    "document1.txt",
    "document2.pdf"
  ],
  "deprecation": {
    "_status": null
  },
  "changelog": [
    {
      "version": "0.5.0",
      "prs": [
        264
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55
      ]
    }
  ]
}

`ai.finish_reason` Deprecated

string PII: Maybe Visibility: Public OTel: False

The reason why the model stopped generating.

Example COMPLETE

Aliases gen_ai.response.finish_reasons

Use gen_ai.response.finish_reasons instead.

Status: backfill

Changelog

v0.1.0 #55 #57 #61 #108 #127

Raw JSON

{
  "key": "ai.finish_reason",
  "brief": "The reason why the model stopped generating.",
  "type": "string",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": "COMPLETE",
  "deprecation": {
    "replacement": "gen_ai.response.finish_reasons",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.response.finish_reasons"
  ],
  "changelog": [
    {
      "version": "0.1.0",
      "prs": [
        55,
        57,
        61,
        108,
        127
      ]
    }
  ]
}

`ai.frequency_penalty` Deprecated

double PII: Maybe Visibility: Public OTel: False

Used to reduce repetitiveness of generated tokens. The higher the value, the stronger a penalty is applied to previously present tokens, proportional to how many times they have already appeared in the prompt or prior generation.

Example 0.5

Aliases gen_ai.request.frequency_penalty

Use gen_ai.request.frequency_penalty instead.

Status: backfill

Changelog

v0.4.0 #228

v0.1.0 #55 #57 #61 #108

Raw JSON

{
  "key": "ai.frequency_penalty",
  "brief": "Used to reduce repetitiveness of generated tokens. The higher the value, the stronger a penalty is applied to previously present tokens, proportional to how many times they have already appeared in the prompt or prior generation.",
  "type": "double",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": 0.5,
  "deprecation": {
    "replacement": "gen_ai.request.frequency_penalty",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.request.frequency_penalty"
  ],
  "changelog": [
    {
      "version": "0.4.0",
      "prs": [
        228
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55,
        57,
        61,
        108
      ]
    }
  ]
}

`ai.function_call` Deprecated

string PII: True Visibility: Public OTel: False

For an AI model call, the function that was called. This is deprecated for OpenAI, and replaced by tool_calls

Example function_name

Aliases gen_ai.tool.name

Use gen_ai.tool.name instead.

Status: backfill

Changelog

v0.1.0 #55 #57 #61 #108

Raw JSON

{
  "key": "ai.function_call",
  "brief": "For an AI model call, the function that was called. This is deprecated for OpenAI, and replaced by tool_calls",
  "type": "string",
  "pii": {
    "key": "true"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": "function_name",
  "deprecation": {
    "replacement": "gen_ai.tool.name",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.tool.name"
  ],
  "changelog": [
    {
      "version": "0.1.0",
      "prs": [
        55,
        57,
        61,
        108
      ]
    }
  ]
}

`ai.generation_id` Deprecated

string PII: Maybe Visibility: Public OTel: False

Unique identifier for the completion.

Example gen_123abc

Aliases gen_ai.response.id

Use gen_ai.response.id instead.

Status: backfill

Changelog

v0.1.0 #55 #57 #61 #108 #127

Raw JSON

{
  "key": "ai.generation_id",
  "brief": "Unique identifier for the completion.",
  "type": "string",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": "gen_123abc",
  "deprecation": {
    "replacement": "gen_ai.response.id",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.response.id"
  ],
  "changelog": [
    {
      "version": "0.1.0",
      "prs": [
        55,
        57,
        61,
        108,
        127
      ]
    }
  ]
}

`ai.input_messages` Deprecated

string PII: Maybe Visibility: Public OTel: False

The input messages sent to the model

Example [{"role": "user", "message": "hello"}]

Aliases gen_ai.request.messages

Use gen_ai.input.messages instead.

Status: backfill

Changelog

v0.1.0 #65 #119

v0.0.0

Raw JSON

{
  "key": "ai.input_messages",
  "brief": "The input messages sent to the model",
  "type": "string",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": "[{\"role\": \"user\", \"message\": \"hello\"}]",
  "deprecation": {
    "replacement": "gen_ai.input.messages",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.request.messages"
  ],
  "changelog": [
    {
      "version": "0.1.0",
      "prs": [
        65,
        119
      ]
    },
    {
      "version": "0.0.0"
    }
  ]
}

`ai.is_search_required` Deprecated

boolean PII: False Visibility: Public OTel: False

Boolean indicating if the model needs to perform a search.

Example false

No replacement available at this time.

Changelog

v0.5.0 #264

v0.1.0 #55

Raw JSON

{
  "key": "ai.is_search_required",
  "brief": "Boolean indicating if the model needs to perform a search.",
  "type": "boolean",
  "pii": {
    "key": "false"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": false,
  "deprecation": {
    "_status": null
  },
  "changelog": [
    {
      "version": "0.5.0",
      "prs": [
        264
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55
      ]
    }
  ]
}

`ai.metadata` Deprecated

string PII: Maybe Visibility: Public OTel: False

Extra metadata passed to an AI pipeline step.

Example {"user_id": 123, "session_id": "abc123"}

No replacement available at this time.

Changelog

v0.5.0 #264

v0.1.0 #55 #127

Raw JSON

{
  "key": "ai.metadata",
  "brief": "Extra metadata passed to an AI pipeline step.",
  "type": "string",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": "{\"user_id\": 123, \"session_id\": \"abc123\"}",
  "deprecation": {
    "_status": null
  },
  "changelog": [
    {
      "version": "0.5.0",
      "prs": [
        264
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55,
        127
      ]
    }
  ]
}

`ai.model_id` Deprecated

string PII: Maybe Visibility: Public OTel: False

The vendor-specific ID of the model used.

Example gpt-4

Aliases gen_ai.response.model

Use gen_ai.response.model instead.

Status: backfill

Changelog

v0.1.0 #57 #61 #127

v0.0.0

Raw JSON

{
  "key": "ai.model_id",
  "brief": "The vendor-specific ID of the model used.",
  "type": "string",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": "gpt-4",
  "deprecation": {
    "replacement": "gen_ai.response.model",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.response.model"
  ],
  "changelog": [
    {
      "version": "0.1.0",
      "prs": [
        57,
        61,
        127
      ]
    },
    {
      "version": "0.0.0"
    }
  ]
}

`ai.model.provider` Deprecated

string PII: Maybe Visibility: Public OTel: False

The provider of the model.

Example openai

Aliases gen_ai.provider.namegen_ai.system

Use gen_ai.provider.name instead.

Status: backfill

Changelog

v0.4.0 #253

v0.1.0 #57 #61 #108 #127

Raw JSON

{
  "key": "ai.model.provider",
  "brief": "The provider of the model.",
  "type": "string",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": "openai",
  "deprecation": {
    "replacement": "gen_ai.provider.name",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.provider.name",
    "gen_ai.system"
  ],
  "changelog": [
    {
      "version": "0.4.0",
      "prs": [
        253
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        57,
        61,
        108,
        127
      ]
    }
  ]
}

`ai.pipeline.name` Deprecated

string PII: Maybe Visibility: Public OTel: False

The name of the AI pipeline.

Example Autofix Pipeline

Aliases gen_ai.pipeline.name

Use gen_ai.pipeline.name instead.

Status: backfill

Changelog

v0.1.0 #53 #76 #108 #127

Raw JSON

{
  "key": "ai.pipeline.name",
  "brief": "The name of the AI pipeline.",
  "type": "string",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": "Autofix Pipeline",
  "deprecation": {
    "replacement": "gen_ai.pipeline.name",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.pipeline.name"
  ],
  "changelog": [
    {
      "version": "0.1.0",
      "prs": [
        53,
        76,
        108,
        127
      ]
    }
  ]
}

`ai.preamble` Deprecated

string PII: True Visibility: Public OTel: False

For an AI model call, the preamble parameter. Preambles are a part of the prompt used to adjust the model's overall behavior and conversation style.

Example You are now a clown.

Aliases gen_ai.system_instructions

Use gen_ai.system_instructions instead.

Status: backfill

Changelog

v0.5.0 #264

v0.1.0 #55

Raw JSON

{
  "key": "ai.preamble",
  "brief": "For an AI model call, the preamble parameter. Preambles are a part of the prompt used to adjust the model's overall behavior and conversation style.",
  "type": "string",
  "pii": {
    "key": "true"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": "You are now a clown.",
  "deprecation": {
    "replacement": "gen_ai.system_instructions",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.system_instructions"
  ],
  "changelog": [
    {
      "version": "0.5.0",
      "prs": [
        264
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55
      ]
    }
  ]
}

`ai.presence_penalty` Deprecated

double PII: Maybe Visibility: Public OTel: False

Used to reduce repetitiveness of generated tokens. Similar to frequency_penalty, except that this penalty is applied equally to all tokens that have already appeared, regardless of their exact frequencies.

Example 0.5

Aliases gen_ai.request.presence_penalty

Use gen_ai.request.presence_penalty instead.

Status: backfill

Changelog

v0.4.0 #228

v0.1.0 #55 #57 #61 #108

Raw JSON

{
  "key": "ai.presence_penalty",
  "brief": "Used to reduce repetitiveness of generated tokens. Similar to frequency_penalty, except that this penalty is applied equally to all tokens that have already appeared, regardless of their exact frequencies.",
  "type": "double",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": 0.5,
  "deprecation": {
    "replacement": "gen_ai.request.presence_penalty",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.request.presence_penalty"
  ],
  "changelog": [
    {
      "version": "0.4.0",
      "prs": [
        228
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55,
        57,
        61,
        108
      ]
    }
  ]
}

`ai.prompt_tokens.used` Deprecated

integer PII: Maybe Visibility: Public OTel: False

The number of tokens used to process just the prompt.

Example 20

Aliases gen_ai.usage.prompt_tokensgen_ai.usage.input_tokens

Use gen_ai.usage.input_tokens instead.

Status: backfill

Changelog

v0.4.0 #228

v0.1.0 #57 #61

v0.0.0

Raw JSON

{
  "key": "ai.prompt_tokens.used",
  "brief": "The number of tokens used to process just the prompt.",
  "type": "integer",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": 20,
  "deprecation": {
    "replacement": "gen_ai.usage.input_tokens",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.usage.prompt_tokens",
    "gen_ai.usage.input_tokens"
  ],
  "changelog": [
    {
      "version": "0.4.0",
      "prs": [
        228
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        57,
        61
      ]
    },
    {
      "version": "0.0.0"
    }
  ]
}

`ai.raw_prompting` Deprecated

boolean PII: False Visibility: Public OTel: False

When enabled, the user’s prompt will be sent to the model without any pre-processing.

Example true

No replacement available at this time.

Changelog

v0.5.0 #264

v0.1.0 #55

Raw JSON

{
  "key": "ai.raw_prompting",
  "brief": "When enabled, the user’s prompt will be sent to the model without any pre-processing.",
  "type": "boolean",
  "pii": {
    "key": "false"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": true,
  "deprecation": {
    "_status": null
  },
  "changelog": [
    {
      "version": "0.5.0",
      "prs": [
        264
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55
      ]
    }
  ]
}

`ai.response_format` Deprecated

string PII: Maybe Visibility: Public OTel: False

For an AI model call, the format of the response

Example json_object

No replacement available at this time.

Changelog

v0.5.0 #264

v0.1.0 #55 #127

Raw JSON

{
  "key": "ai.response_format",
  "brief": "For an AI model call, the format of the response",
  "type": "string",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": "json_object",
  "deprecation": {
    "_status": null
  },
  "changelog": [
    {
      "version": "0.5.0",
      "prs": [
        264
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55,
        127
      ]
    }
  ]
}

`ai.responses` Deprecated

string[] PII: Maybe Visibility: Public OTel: False

The response messages sent back by the AI model.

Example ["hello","world"]

Use gen_ai.output.messages instead.

Status: backfill

Changelog

v0.1.0 #65 #127

v0.0.0

Raw JSON

{
  "key": "ai.responses",
  "brief": "The response messages sent back by the AI model.",
  "type": "string[]",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": [
    "hello",
    "world"
  ],
  "deprecation": {
    "replacement": "gen_ai.output.messages",
    "_status": "backfill"
  },
  "changelog": [
    {
      "version": "0.1.0",
      "prs": [
        65,
        127
      ]
    },
    {
      "version": "0.0.0"
    }
  ]
}

`ai.search_queries` Deprecated

string[] PII: True Visibility: Public OTel: False

Queries used to search for relevant context or documents.

Example ["climate change effects","renewable energy"]

No replacement available at this time.

Changelog

v0.5.0 #264

v0.1.0 #55

Raw JSON

{
  "key": "ai.search_queries",
  "brief": "Queries used to search for relevant context or documents.",
  "type": "string[]",
  "pii": {
    "key": "true"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": [
    "climate change effects",
    "renewable energy"
  ],
  "deprecation": {
    "_status": null
  },
  "changelog": [
    {
      "version": "0.5.0",
      "prs": [
        264
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55
      ]
    }
  ]
}

`ai.search_results` Deprecated

string[] PII: True Visibility: Public OTel: False

Results returned from search queries for context.

Example ["search_result_1, search_result_2"]

No replacement available at this time.

Changelog

v0.5.0 #264

v0.1.0 #55

Raw JSON

{
  "key": "ai.search_results",
  "brief": "Results returned from search queries for context.",
  "type": "string[]",
  "pii": {
    "key": "true"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": [
    "search_result_1, search_result_2"
  ],
  "deprecation": {
    "_status": null
  },
  "changelog": [
    {
      "version": "0.5.0",
      "prs": [
        264
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55
      ]
    }
  ]
}

`ai.seed` Deprecated

string PII: Maybe Visibility: Public OTel: False

The seed, ideally models given the same seed and same other parameters will produce the exact same output.

Example 1234567890

Aliases gen_ai.request.seed

Use gen_ai.request.seed instead.

Status: backfill

Changelog

v0.1.0 #55 #57 #61 #108 #127

Raw JSON

{
  "key": "ai.seed",
  "brief": "The seed, ideally models given the same seed and same other parameters will produce the exact same output.",
  "type": "string",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": "1234567890",
  "deprecation": {
    "replacement": "gen_ai.request.seed",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.request.seed"
  ],
  "changelog": [
    {
      "version": "0.1.0",
      "prs": [
        55,
        57,
        61,
        108,
        127
      ]
    }
  ]
}

`ai.streaming` Deprecated

boolean PII: Maybe Visibility: Public OTel: False

Whether the request was streamed back.

Example true

Aliases gen_ai.response.streaming

Use gen_ai.response.streaming instead.

Status: backfill

Changelog

v0.1.0 #76 #108

v0.0.0

Raw JSON

{
  "key": "ai.streaming",
  "brief": "Whether the request was streamed back.",
  "type": "boolean",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": true,
  "deprecation": {
    "replacement": "gen_ai.response.streaming",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.response.streaming"
  ],
  "changelog": [
    {
      "version": "0.1.0",
      "prs": [
        76,
        108
      ]
    },
    {
      "version": "0.0.0"
    }
  ]
}

`ai.tags` Deprecated

string PII: Maybe Visibility: Public OTel: False

Tags that describe an AI pipeline step.

Example {"executed_function": "add_integers"}

No replacement available at this time.

Changelog

v0.5.0 #264

v0.1.0 #55 #127

Raw JSON

{
  "key": "ai.tags",
  "brief": "Tags that describe an AI pipeline step.",
  "type": "string",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": "{\"executed_function\": \"add_integers\"}",
  "deprecation": {
    "_status": null
  },
  "changelog": [
    {
      "version": "0.5.0",
      "prs": [
        264
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55,
        127
      ]
    }
  ]
}

`ai.temperature` Deprecated

double PII: Maybe Visibility: Public OTel: False

For an AI model call, the temperature parameter. Temperature essentially means how random the output will be.

Example 0.1

Aliases gen_ai.request.temperature

Use gen_ai.request.temperature instead.

Status: backfill

Changelog

v0.4.0 #228

v0.1.0 #55 #57 #61 #108

Raw JSON

{
  "key": "ai.temperature",
  "brief": "For an AI model call, the temperature parameter. Temperature essentially means how random the output will be.",
  "type": "double",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": 0.1,
  "deprecation": {
    "replacement": "gen_ai.request.temperature",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.request.temperature"
  ],
  "changelog": [
    {
      "version": "0.4.0",
      "prs": [
        228
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55,
        57,
        61,
        108
      ]
    }
  ]
}

`ai.texts` Deprecated

string[] PII: True Visibility: Public OTel: False

Raw text inputs provided to the model.

Example ["Hello, how are you?","What is the capital of France?"]

Aliases gen_ai.input.messages

Use gen_ai.input.messages instead.

Status: backfill

Changelog

v0.5.0 #264

v0.1.0 #55

Raw JSON

{
  "key": "ai.texts",
  "brief": "Raw text inputs provided to the model.",
  "type": "string[]",
  "pii": {
    "key": "true"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": [
    "Hello, how are you?",
    "What is the capital of France?"
  ],
  "deprecation": {
    "replacement": "gen_ai.input.messages",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.input.messages"
  ],
  "changelog": [
    {
      "version": "0.5.0",
      "prs": [
        264
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55
      ]
    }
  ]
}

`ai.tool_calls` Deprecated

string[] PII: True Visibility: Public OTel: False

For an AI model call, the tool calls that were made.

Example ["tool_call_1","tool_call_2"]

Use gen_ai.output.messages instead.

Status: backfill

Changelog

v0.1.0 #55 #65

Raw JSON

{
  "key": "ai.tool_calls",
  "brief": "For an AI model call, the tool calls that were made.",
  "type": "string[]",
  "pii": {
    "key": "true"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": [
    "tool_call_1",
    "tool_call_2"
  ],
  "deprecation": {
    "replacement": "gen_ai.output.messages",
    "_status": "backfill"
  },
  "changelog": [
    {
      "version": "0.1.0",
      "prs": [
        55,
        65
      ]
    }
  ]
}

`ai.tools` Deprecated

string[] PII: Maybe Visibility: Public OTel: False

For an AI model call, the functions that are available

Example ["function_1","function_2"]

Use gen_ai.tool.definitions instead.

Status: backfill

Changelog

v0.1.0 #55 #65 #127

Raw JSON

{
  "key": "ai.tools",
  "brief": "For an AI model call, the functions that are available",
  "type": "string[]",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": [
    "function_1",
    "function_2"
  ],
  "deprecation": {
    "replacement": "gen_ai.tool.definitions",
    "_status": "backfill"
  },
  "changelog": [
    {
      "version": "0.1.0",
      "prs": [
        55,
        65,
        127
      ]
    }
  ]
}

`ai.top_k` Deprecated

integer PII: Maybe Visibility: Public OTel: False

Limits the model to only consider the K most likely next tokens, where K is an integer (e.g., top_k=20 means only the 20 highest probability tokens are considered).

Example 35

Aliases gen_ai.request.top_k

Use gen_ai.request.top_k instead.

Status: backfill

Changelog

v0.4.0 #228

v0.1.0 #55 #57 #61 #108

Raw JSON

{
  "key": "ai.top_k",
  "brief": "Limits the model to only consider the K most likely next tokens, where K is an integer (e.g., top_k=20 means only the 20 highest probability tokens are considered).",
  "type": "integer",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": 35,
  "deprecation": {
    "replacement": "gen_ai.request.top_k",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.request.top_k"
  ],
  "changelog": [
    {
      "version": "0.4.0",
      "prs": [
        228
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55,
        57,
        61,
        108
      ]
    }
  ]
}

`ai.top_p` Deprecated

double PII: Maybe Visibility: Public OTel: False

Limits the model to only consider tokens whose cumulative probability mass adds up to p, where p is a float between 0 and 1 (e.g., top_p=0.7 means only tokens that sum up to 70% of the probability mass are considered).

Example 0.7

Aliases gen_ai.request.top_p

Use gen_ai.request.top_p instead.

Status: backfill

Changelog

v0.4.0 #228

v0.1.0 #55 #57 #61 #108

Raw JSON

{
  "key": "ai.top_p",
  "brief": "Limits the model to only consider tokens whose cumulative probability mass adds up to p, where p is a float between 0 and 1 (e.g., top_p=0.7 means only tokens that sum up to 70% of the probability mass are considered).",
  "type": "double",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": 0.7,
  "deprecation": {
    "replacement": "gen_ai.request.top_p",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.request.top_p"
  ],
  "changelog": [
    {
      "version": "0.4.0",
      "prs": [
        228
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55,
        57,
        61,
        108
      ]
    }
  ]
}

`ai.total_cost` Deprecated

double PII: Maybe Visibility: Public OTel: False

The total cost for the tokens used.

Example 12.34

Aliases gen_ai.cost.total_tokens

Use gen_ai.cost.total_tokens instead.

Status: backfill

Changelog

v0.5.0 #264

v0.4.0 #228

v0.1.0 #53

Raw JSON

{
  "key": "ai.total_cost",
  "brief": "The total cost for the tokens used.",
  "type": "double",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": 12.34,
  "deprecation": {
    "replacement": "gen_ai.cost.total_tokens",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.cost.total_tokens"
  ],
  "changelog": [
    {
      "version": "0.5.0",
      "prs": [
        264
      ]
    },
    {
      "version": "0.4.0",
      "prs": [
        228
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        53
      ]
    }
  ]
}

`ai.total_tokens.used` Deprecated

integer PII: Maybe Visibility: Public OTel: False

The total number of tokens used to process the prompt.

Example 30

Aliases gen_ai.usage.total_tokens

Use gen_ai.usage.total_tokens instead.

Status: backfill

Changelog

v0.4.0 #228

v0.1.0 #57 #61 #108

v0.0.0

Raw JSON

{
  "key": "ai.total_tokens.used",
  "brief": "The total number of tokens used to process the prompt.",
  "type": "integer",
  "pii": {
    "key": "maybe"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": 30,
  "deprecation": {
    "replacement": "gen_ai.usage.total_tokens",
    "_status": "backfill"
  },
  "alias": [
    "gen_ai.usage.total_tokens"
  ],
  "changelog": [
    {
      "version": "0.4.0",
      "prs": [
        228
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        57,
        61,
        108
      ]
    },
    {
      "version": "0.0.0"
    }
  ]
}

`ai.warnings` Deprecated

string[] PII: True Visibility: Public OTel: False

Warning messages generated during model execution.

Example ["Token limit exceeded"]

No replacement available at this time.

Changelog

v0.5.0 #264

v0.1.0 #55

Raw JSON

{
  "key": "ai.warnings",
  "brief": "Warning messages generated during model execution.",
  "type": "string[]",
  "pii": {
    "key": "true"
  },
  "is_in_otel": false,
  "visibility": "public",
  "example": [
    "Token limit exceeded"
  ],
  "deprecation": {
    "_status": null
  },
  "changelog": [
    {
      "version": "0.5.0",
      "prs": [
        264
      ]
    },
    {
      "version": "0.1.0",
      "prs": [
        55
      ]
    }
  ]
}

Ai Attributes

Deprecated Attributes

ai.citations Deprecated

ai.completion_tokens.used Deprecated

ai.documents Deprecated

ai.finish_reason Deprecated

ai.frequency_penalty Deprecated

ai.function_call Deprecated

ai.generation_id Deprecated

ai.input_messages Deprecated

ai.is_search_required Deprecated

ai.metadata Deprecated

ai.model_id Deprecated

ai.model.provider Deprecated

ai.pipeline.name Deprecated

ai.preamble Deprecated

ai.presence_penalty Deprecated

ai.prompt_tokens.used Deprecated

ai.raw_prompting Deprecated

ai.response_format Deprecated

ai.responses Deprecated

ai.search_queries Deprecated

ai.search_results Deprecated

ai.seed Deprecated

ai.streaming Deprecated

ai.tags Deprecated

ai.temperature Deprecated

ai.texts Deprecated

ai.tool_calls Deprecated

ai.tools Deprecated

ai.top_k Deprecated

ai.top_p Deprecated

ai.total_cost Deprecated

ai.total_tokens.used Deprecated

ai.warnings Deprecated

`ai.citations` Deprecated

`ai.completion_tokens.used` Deprecated

`ai.documents` Deprecated

`ai.finish_reason` Deprecated

`ai.frequency_penalty` Deprecated

`ai.function_call` Deprecated

`ai.generation_id` Deprecated

`ai.input_messages` Deprecated

`ai.is_search_required` Deprecated

`ai.metadata` Deprecated

`ai.model_id` Deprecated

`ai.model.provider` Deprecated

`ai.pipeline.name` Deprecated

`ai.preamble` Deprecated

`ai.presence_penalty` Deprecated

`ai.prompt_tokens.used` Deprecated

`ai.raw_prompting` Deprecated

`ai.response_format` Deprecated

`ai.responses` Deprecated

`ai.search_queries` Deprecated

`ai.search_results` Deprecated

`ai.seed` Deprecated

`ai.streaming` Deprecated

`ai.tags` Deprecated

`ai.temperature` Deprecated

`ai.texts` Deprecated

`ai.tool_calls` Deprecated

`ai.tools` Deprecated

`ai.top_k` Deprecated

`ai.top_p` Deprecated

`ai.total_cost` Deprecated

`ai.total_tokens.used` Deprecated

`ai.warnings` Deprecated