open-telemetry
/
semantic-conventions
mirror of https://github.com/open-telemetry/semantic-conventions.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Add LLM model server metrics (#1103) 

Co-authored-by: Liudmila Molkova <limolkova@microsoft.com>
Co-authored-by: Drew Robbins <drew@drewby.com>
Co-authored-by: Joao Grassi <5938087+joaopgrassi@users.noreply.github.com>
This commit is contained in:
Ashok Chandrasekar 2024-06-27 11:05:12 +00:00 committed by GitHub
parent 5a2836bbea
commit a328d73b5b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
6 changed files with 298 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
.chloggen/1102.yaml Executable file
View File

@ -0,0 +1,22 @@
# Use this changelog template to create an entry for release notes.
#
# If your change doesn't affect end users you should instead start
# your pull request title with [chore] or use the "Skip Changelog" label.
# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
change_type: enhancement
# The name of the area of concern in the attributes-registry, (e.g. http, cloud, db)
component: gen-ai
# A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`).
note: Add GenAI model server metrics for measuring LLM serving latency
# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
# The values here must be integers.
issues: [1102]
# (Optional) One or more lines of additional information to render under the primary note.
# These lines will be padded with 2 spaces and then inserted directly into the document.
# Use pipe (|) for multiline entries.
subtext:

2
docs/attributes-registry/gen-ai.md
View File

@ -26,7 +26,7 @@ This document defines the attributes used to describe telemetry in the context o
| `gen_ai.response.finish_reasons` | string[] | Array of reasons the model stopped generating tokens, corresponding to each generation received. | `["stop"]` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | `gen_ai.response.finish_reasons` | string[] | Array of reasons the model stopped generating tokens, corresponding to each generation received. | `["stop"]` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| `gen_ai.response.id` | string | The unique identifier for the completion. | `chatcmpl-123` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | `gen_ai.response.id` | string | The unique identifier for the completion. | `chatcmpl-123` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| `gen_ai.response.model` | string | The name of the model that generated the response. | `gpt-4-0613` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | `gen_ai.response.model` | string | The name of the model that generated the response. | `gpt-4-0613` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| `gen_ai.system` | string | The Generative AI product as identified by the client instrumentation. [3] | `openai` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | `gen_ai.system` | string | The Generative AI product as identified by the client or server instrumentation. [3] | `openai` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| `gen_ai.token.type` | string | The type of token being counted. | `input`; `output` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | `gen_ai.token.type` | string | The type of token being counted. | `input`; `output` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| `gen_ai.usage.completion_tokens` | int | The number of tokens used in the GenAI response (completion). | `180` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | `gen_ai.usage.completion_tokens` | int | The number of tokens used in the GenAI response (completion). | `180` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| `gen_ai.usage.prompt_tokens` | int | The number of tokens used in the GenAI input or prompt. | `100` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | `gen_ai.usage.prompt_tokens` | int | The number of tokens used in the GenAI input or prompt. | `100` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |

246
docs/gen-ai/gen-ai-metrics.md
View File

@ -2,16 +2,10 @@
linkTitle: Generative AI metrics linkTitle: Generative AI metrics
---> --->
# Semantic Conventions for Generative AI Client Metrics # Semantic Conventions for Generative AI Metrics
**Status**: [Experimental][DocumentStatus] **Status**: [Experimental][DocumentStatus]
The conventions described in this section are specific to Generative AI client
applications.
**Disclaimer:** These are initial Generative AI client metric instruments
and attributes but more may be added in the future.
<!-- Re-generate TOC with `markdown-toc --no-first-h1 -i` --> <!-- Re-generate TOC with `markdown-toc --no-first-h1 -i` -->
<!-- toc --> <!-- toc -->
@ -19,11 +13,21 @@ and attributes but more may be added in the future.
- [Generative AI Client Metrics](#generative-ai-client-metrics) - [Generative AI Client Metrics](#generative-ai-client-metrics)
- [Metric: `gen_ai.client.token.usage`](#metric-gen_aiclienttokenusage) - [Metric: `gen_ai.client.token.usage`](#metric-gen_aiclienttokenusage)
- [Metric: `gen_ai.client.operation.duration`](#metric-gen_aiclientoperationduration) - [Metric: `gen_ai.client.operation.duration`](#metric-gen_aiclientoperationduration)
- [Generative AI Model Server Metrics](#generative-ai-model-server-metrics)
- [Metric: `gen_ai.server.request.duration`](#metric-gen_aiserverrequestduration)
- [Metric: `gen_ai.server.time_per_output_token`](#metric-gen_aiservertime_per_output_token)
- [Metric: `gen_ai.server.time_to_first_token`](#metric-gen_aiservertime_to_first_token)
<!-- tocstop --> <!-- tocstop -->
## Generative AI Client Metrics ## Generative AI Client Metrics
The conventions described in this section are specific to Generative AI client
applications.
**Disclaimer:** These are initial Generative AI client metric instruments
and attributes but more may be added in the future.
The following metric instruments describe Generative AI operations. An The following metric instruments describe Generative AI operations. An
operation may be a request to an LLM, a function call, or some other operation may be a request to an LLM, a function call, or some other
distinct action within a larger Generative AI workflow. distinct action within a larger Generative AI workflow.
@ -69,7 +73,7 @@ This metric SHOULD be specified with [ExplicitBucketBoundaries] of [1, 4, 16, 64
|---|---|---|---|---|---| |---|---|---|---|---|---|
| [`gen_ai.operation.name`](/docs/attributes-registry/gen-ai.md) | string | The name of the operation being performed. | `chat`; `completion` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | [`gen_ai.operation.name`](/docs/attributes-registry/gen-ai.md) | string | The name of the operation being performed. | `chat`; `completion` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`gen_ai.request.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the GenAI model a request is being made to. | `gpt-4` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | [`gen_ai.request.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the GenAI model a request is being made to. | `gpt-4` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`gen_ai.system`](/docs/attributes-registry/gen-ai.md) | string | The Generative AI product as identified by the client instrumentation. [1] | `openai` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | [`gen_ai.system`](/docs/attributes-registry/gen-ai.md) | string | The Generative AI product as identified by the client or server instrumentation. [1] | `openai` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`gen_ai.token.type`](/docs/attributes-registry/gen-ai.md) | string | The type of token being counted. | `input`; `output` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | [`gen_ai.token.type`](/docs/attributes-registry/gen-ai.md) | string | The type of token being counted. | `input`; `output` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`server.port`](/docs/attributes-registry/server.md) | int | Server port number. [2] | `80`; `8080`; `443` | `Conditionally Required` If `sever.address` is set. | ![Stable](https://img.shields.io/badge/-stable-lightgreen) | | [`server.port`](/docs/attributes-registry/server.md) | int | Server port number. [2] | `80`; `8080`; `443` | `Conditionally Required` If `sever.address` is set. | ![Stable](https://img.shields.io/badge/-stable-lightgreen) |
| [`gen_ai.response.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the model that generated the response. | `gpt-4-0613` | `Recommended` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | [`gen_ai.response.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the model that generated the response. | `gpt-4-0613` | `Recommended` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
@ -142,7 +146,7 @@ This metric SHOULD be specified with [ExplicitBucketBoundaries] of [ 0.01, 0.02,
|---|---|---|---|---|---| |---|---|---|---|---|---|
| [`gen_ai.operation.name`](/docs/attributes-registry/gen-ai.md) | string | The name of the operation being performed. | `chat`; `completion` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | [`gen_ai.operation.name`](/docs/attributes-registry/gen-ai.md) | string | The name of the operation being performed. | `chat`; `completion` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`gen_ai.request.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the GenAI model a request is being made to. | `gpt-4` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | [`gen_ai.request.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the GenAI model a request is being made to. | `gpt-4` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`gen_ai.system`](/docs/attributes-registry/gen-ai.md) | string | The Generative AI product as identified by the client instrumentation. [1] | `openai` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | [`gen_ai.system`](/docs/attributes-registry/gen-ai.md) | string | The Generative AI product as identified by the client or server instrumentation. [1] | `openai` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`error.type`](/docs/attributes-registry/error.md) | 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](https://img.shields.io/badge/-stable-lightgreen) | | [`error.type`](/docs/attributes-registry/error.md) | 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](https://img.shields.io/badge/-stable-lightgreen) |
| [`server.port`](/docs/attributes-registry/server.md) | int | Server port number. [3] | `80`; `8080`; `443` | `Conditionally Required` If `sever.address` is set. | ![Stable](https://img.shields.io/badge/-stable-lightgreen) | | [`server.port`](/docs/attributes-registry/server.md) | int | Server port number. [3] | `80`; `8080`; `443` | `Conditionally Required` If `sever.address` is set. | ![Stable](https://img.shields.io/badge/-stable-lightgreen) |
| [`gen_ai.response.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the model that generated the response. | `gpt-4-0613` | `Recommended` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | [`gen_ai.response.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the model that generated the response. | `gpt-4-0613` | `Recommended` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
@ -179,6 +183,230 @@ Instrumentations SHOULD document the list of errors they report.
<!-- markdownlint-restore -->
<!-- prettier-ignore-end -->
<!-- END AUTOGENERATED TEXT -->
<!-- endsemconv -->
## Generative AI Model Server Metrics
The following metric instruments describe Generative AI model servers'
operational metrics. It includes both functional and performance metrics.
### Metric: `gen_ai.server.request.duration`
This metric is [recommended][MetricRecommended] to report the model server
latency in terms of time spent per request.
This metric SHOULD be specified with [ExplicitBucketBoundaries] of
[0.01, 0.02, 0.04, 0.08, 0.16, 0.32, 0.64, 1.28, 2.56, 5.12,10.24, 20.48, 40.96, 81.92].
<!-- semconv metric.gen_ai.server.request.duration(metric_table) -->
<!-- NOTE: THIS TEXT IS AUTOGENERATED. DO NOT EDIT BY HAND. -->
<!-- see templates/registry/markdown/snippet.md.j2 -->
<!-- prettier-ignore-start -->
<!-- markdownlint-capture -->
<!-- markdownlint-disable -->
| Name | Instrument Type | Unit (UCUM) | Description | Stability |
| -------- | --------------- | ----------- | -------------- | --------- |
| `gen_ai.server.request.duration` | Histogram | `s` | Generative AI server request duration such as time-to-last byte or last output token | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
<!-- markdownlint-restore -->
<!-- prettier-ignore-end -->
<!-- END AUTOGENERATED TEXT -->
<!-- endsemconv -->
<!-- semconv metric.gen_ai.server.request.duration(full) -->
<!-- NOTE: THIS TEXT IS AUTOGENERATED. DO NOT EDIT BY HAND. -->
<!-- see templates/registry/markdown/snippet.md.j2 -->
<!-- prettier-ignore-start -->
<!-- markdownlint-capture -->
<!-- markdownlint-disable -->
| Attribute | Type | Description | Examples | [Requirement Level](https://opentelemetry.io/docs/specs/semconv/general/attribute-requirement-level/) | Stability |
|---|---|---|---|---|---|
| [`gen_ai.operation.name`](/docs/attributes-registry/gen-ai.md) | string | The name of the operation being performed. | `chat`; `completion` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`gen_ai.request.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the GenAI model a request is being made to. | `gpt-4` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`gen_ai.system`](/docs/attributes-registry/gen-ai.md) | string | The Generative AI product as identified by the client or server instrumentation. [1] | `openai` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`error.type`](/docs/attributes-registry/error.md) | 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](https://img.shields.io/badge/-stable-lightgreen) |
| [`server.port`](/docs/attributes-registry/server.md) | int | Server port number. [3] | `80`; `8080`; `443` | `Conditionally Required` If `sever.address` is set. | ![Stable](https://img.shields.io/badge/-stable-lightgreen) |
| [`gen_ai.response.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the model that generated the response. | `gpt-4-0613` | `Recommended` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`server.address`](/docs/attributes-registry/server.md) | string | Server domain name if available without reverse DNS lookup; otherwise, IP address or Unix domain socket name. [4] | `example.com`; `10.1.2.80`; `/tmp/my.sock` | `Recommended` | ![Stable](https://img.shields.io/badge/-stable-lightgreen) |
**[1]:** 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`.
**[2]:** The `error.type` SHOULD match the error code returned by the Generative AI service,
the canonical name of exception that occurred, or another low-cardinality error identifier.
Instrumentations SHOULD document the list of errors they report.
**[3]:** 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.
**[4]:** 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](https://img.shields.io/badge/-stable-lightgreen) |
`gen_ai.system` 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 |
|---|---|---|
| `anthropic` | Anthropic | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| `cohere` | Cohere | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| `openai` | OpenAI | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| `vertex_ai` | Vertex AI | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
<!-- markdownlint-restore -->
<!-- prettier-ignore-end -->
<!-- END AUTOGENERATED TEXT -->
<!-- endsemconv -->
### Metric: `gen_ai.server.time_per_output_token`
This metric is [recommended][MetricRecommended] to report the model server
latency in terms of time per token generated after the first token for any model
servers which support serving LLMs. It is measured by subtracting the time taken
to generate the first output token from the request duration and dividing the
rest of the duration by the number of output tokens generated after the first
token. This is important in measuring the performance of the decode phase of LLM
inference.
This metric SHOULD be specified with [ExplicitBucketBoundaries] of
[0.01, 0.025, 0.05, 0.075, 0.1, 0.15, 0.2, 0.3, 0.4, 0.5, 0.75, 1.0, 2.5].
<!-- semconv metric.gen_ai.server.time_per_output_token(metric_table) -->
<!-- NOTE: THIS TEXT IS AUTOGENERATED. DO NOT EDIT BY HAND. -->
<!-- see templates/registry/markdown/snippet.md.j2 -->
<!-- prettier-ignore-start -->
<!-- markdownlint-capture -->
<!-- markdownlint-disable -->
| Name | Instrument Type | Unit (UCUM) | Description | Stability |
| -------- | --------------- | ----------- | -------------- | --------- |
| `gen_ai.server.time_per_output_token` | Histogram | `s` | Time per output token generated after the first token for successful responses | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
<!-- markdownlint-restore -->
<!-- prettier-ignore-end -->
<!-- END AUTOGENERATED TEXT -->
<!-- endsemconv -->
<!-- semconv metric.gen_ai.server.time_per_output_token(full) -->
<!-- NOTE: THIS TEXT IS AUTOGENERATED. DO NOT EDIT BY HAND. -->
<!-- see templates/registry/markdown/snippet.md.j2 -->
<!-- prettier-ignore-start -->
<!-- markdownlint-capture -->
<!-- markdownlint-disable -->
| Attribute | Type | Description | Examples | [Requirement Level](https://opentelemetry.io/docs/specs/semconv/general/attribute-requirement-level/) | Stability |
|---|---|---|---|---|---|
| [`gen_ai.operation.name`](/docs/attributes-registry/gen-ai.md) | string | The name of the operation being performed. | `chat`; `completion` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`gen_ai.request.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the GenAI model a request is being made to. | `gpt-4` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`gen_ai.system`](/docs/attributes-registry/gen-ai.md) | string | The Generative AI product as identified by the client or server instrumentation. [1] | `openai` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`server.port`](/docs/attributes-registry/server.md) | int | Server port number. [2] | `80`; `8080`; `443` | `Conditionally Required` If `sever.address` is set. | ![Stable](https://img.shields.io/badge/-stable-lightgreen) |
| [`gen_ai.response.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the model that generated the response. | `gpt-4-0613` | `Recommended` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`server.address`](/docs/attributes-registry/server.md) | string | Server domain name if available without reverse DNS lookup; otherwise, IP address or Unix domain socket name. [3] | `example.com`; `10.1.2.80`; `/tmp/my.sock` | `Recommended` | ![Stable](https://img.shields.io/badge/-stable-lightgreen) |
**[1]:** 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`.
**[2]:** 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.
**[3]:** 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.
`gen_ai.system` 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 |
|---|---|---|
| `anthropic` | Anthropic | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| `cohere` | Cohere | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| `openai` | OpenAI | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| `vertex_ai` | Vertex AI | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
<!-- markdownlint-restore -->
<!-- prettier-ignore-end -->
<!-- END AUTOGENERATED TEXT -->
<!-- endsemconv -->
### Metric: `gen_ai.server.time_to_first_token`
This metric is [recommended][MetricRecommended] to report the model server
latency in terms of time spent to generate the first token of the response for
any model servers which support serving LLMs. It helps measure the time spent in
the queue and the prefill phase. It is important especially for streaming
requests. It is calculated at a request level and is reported as a histogram
using the buckets mentioned below.
This metric SHOULD be specified with [ExplicitBucketBoundaries] of
[0.001, 0.005, 0.01, 0.02, 0.04, 0.06, 0.08, 0.1, 0.25, 0.5, 0.75, 1.0, 2.5, 5.0, 7.5, 10.0].
<!-- semconv metric.gen_ai.server.time_to_first_token(metric_table) -->
<!-- NOTE: THIS TEXT IS AUTOGENERATED. DO NOT EDIT BY HAND. -->
<!-- see templates/registry/markdown/snippet.md.j2 -->
<!-- prettier-ignore-start -->
<!-- markdownlint-capture -->
<!-- markdownlint-disable -->
| Name | Instrument Type | Unit (UCUM) | Description | Stability |
| -------- | --------------- | ----------- | -------------- | --------- |
| `gen_ai.server.time_to_first_token` | Histogram | `s` | Time to generate first token for successful responses | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
<!-- markdownlint-restore -->
<!-- prettier-ignore-end -->
<!-- END AUTOGENERATED TEXT -->
<!-- endsemconv -->
<!-- semconv metric.gen_ai.server.time_to_first_token(full) -->
<!-- NOTE: THIS TEXT IS AUTOGENERATED. DO NOT EDIT BY HAND. -->
<!-- see templates/registry/markdown/snippet.md.j2 -->
<!-- prettier-ignore-start -->
<!-- markdownlint-capture -->
<!-- markdownlint-disable -->
| Attribute | Type | Description | Examples | [Requirement Level](https://opentelemetry.io/docs/specs/semconv/general/attribute-requirement-level/) | Stability |
|---|---|---|---|---|---|
| [`gen_ai.operation.name`](/docs/attributes-registry/gen-ai.md) | string | The name of the operation being performed. | `chat`; `completion` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`gen_ai.request.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the GenAI model a request is being made to. | `gpt-4` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`gen_ai.system`](/docs/attributes-registry/gen-ai.md) | string | The Generative AI product as identified by the client or server instrumentation. [1] | `openai` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`server.port`](/docs/attributes-registry/server.md) | int | Server port number. [2] | `80`; `8080`; `443` | `Conditionally Required` If `sever.address` is set. | ![Stable](https://img.shields.io/badge/-stable-lightgreen) |
| [`gen_ai.response.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the model that generated the response. | `gpt-4-0613` | `Recommended` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`server.address`](/docs/attributes-registry/server.md) | string | Server domain name if available without reverse DNS lookup; otherwise, IP address or Unix domain socket name. [3] | `example.com`; `10.1.2.80`; `/tmp/my.sock` | `Recommended` | ![Stable](https://img.shields.io/badge/-stable-lightgreen) |
**[1]:** 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`.
**[2]:** 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.
**[3]:** 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.
`gen_ai.system` 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 |
|---|---|---|
| `anthropic` | Anthropic | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| `cohere` | Cohere | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| `openai` | OpenAI | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| `vertex_ai` | Vertex AI | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
<!-- markdownlint-restore --> <!-- markdownlint-restore -->
<!-- prettier-ignore-end --> <!-- prettier-ignore-end -->
<!-- END AUTOGENERATED TEXT --> <!-- END AUTOGENERATED TEXT -->

2
docs/gen-ai/gen-ai-spans.md
View File

@ -46,7 +46,7 @@ These attributes track input data and metadata for a request to an GenAI model.
| Attribute | Type | Description | Examples | [Requirement Level](https://opentelemetry.io/docs/specs/semconv/general/attribute-requirement-level/) | Stability | | Attribute | Type | Description | Examples | [Requirement Level](https://opentelemetry.io/docs/specs/semconv/general/attribute-requirement-level/) | Stability |
|---|---|---|---|---|---| |---|---|---|---|---|---|
| [`gen_ai.request.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the GenAI model a request is being made to. [1] | `gpt-4` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | [`gen_ai.request.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the GenAI model a request is being made to. [1] | `gpt-4` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`gen_ai.system`](/docs/attributes-registry/gen-ai.md) | string | The Generative AI product as identified by the client instrumentation. [2] | `openai` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | [`gen_ai.system`](/docs/attributes-registry/gen-ai.md) | string | The Generative AI product as identified by the client or server instrumentation. [2] | `openai` | `Required` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`gen_ai.request.frequency_penalty`](/docs/attributes-registry/gen-ai.md) | double | The frequency penalty setting for the GenAI request. | `0.1` | `Recommended` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | [`gen_ai.request.frequency_penalty`](/docs/attributes-registry/gen-ai.md) | double | The frequency penalty setting for the GenAI request. | `0.1` | `Recommended` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`gen_ai.request.max_tokens`](/docs/attributes-registry/gen-ai.md) | int | The maximum number of tokens the model generates for a request. | `100` | `Recommended` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | [`gen_ai.request.max_tokens`](/docs/attributes-registry/gen-ai.md) | int | The maximum number of tokens the model generates for a request. | `100` | `Recommended` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
| [`gen_ai.request.presence_penalty`](/docs/attributes-registry/gen-ai.md) | double | The presence penalty setting for the GenAI request. | `0.1` | `Recommended` | ![Experimental](https://img.shields.io/badge/-experimental-blue) | | [`gen_ai.request.presence_penalty`](/docs/attributes-registry/gen-ai.md) | double | The presence penalty setting for the GenAI request. | `0.1` | `Recommended` | ![Experimental](https://img.shields.io/badge/-experimental-blue) |

36
model/metrics/gen-ai.yaml
View File

@ -16,6 +16,18 @@ groups:
requirement_level: required requirement_level: required
- ref: gen_ai.operation.name - ref: gen_ai.operation.name
requirement_level: required requirement_level: required
- id: metric_attributes.gen_ai.server
type: attribute_group
brief: 'This group describes GenAI server metrics attributes'
extends: metric_attributes.gen_ai
attributes:
- ref: error.type
requirement_level:
conditionally_required: "if the operation ended in an error"
note: |
The `error.type` SHOULD match the error code returned by the Generative AI service,
the canonical name of exception that occurred, or another low-cardinality error identifier.
Instrumentations SHOULD document the list of errors they report.
- id: metric.gen_ai.client.token.usage - id: metric.gen_ai.client.token.usage
type: metric type: metric
metric_name: gen_ai.client.token.usage metric_name: gen_ai.client.token.usage
@ -43,3 +55,27 @@ groups:
The `error.type` SHOULD match the error code returned by the Generative AI provider or the client library, 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. the canonical name of exception that occurred, or another low-cardinality error identifier.
Instrumentations SHOULD document the list of errors they report. Instrumentations SHOULD document the list of errors they report.
- id: metric.gen_ai.server.request.duration
type: metric
metric_name: gen_ai.server.request.duration
brief: 'Generative AI server request duration such as time-to-last byte or last output token'
instrument: histogram
unit: "s"
stability: experimental
extends: metric_attributes.gen_ai.server
- id: metric.gen_ai.server.time_per_output_token
type: metric
metric_name: gen_ai.server.time_per_output_token
brief: 'Time per output token generated after the first token for successful responses'
instrument: histogram
unit: "s"
stability: experimental
extends: metric_attributes.gen_ai
- id: metric.gen_ai.server.time_to_first_token
type: metric
metric_name: gen_ai.server.time_to_first_token
brief: 'Time to generate first token for successful responses'
instrument: histogram
unit: "s"
stability: experimental
extends: metric_attributes.gen_ai

2
model/registry/gen-ai.yaml
View File

@ -25,7 +25,7 @@ groups:
stability: experimental stability: experimental
value: "cohere" value: "cohere"
brief: 'Cohere' brief: 'Cohere'
brief: The Generative AI product as identified by the client instrumentation. brief: The Generative AI product as identified by the client or server instrumentation.
note: > note: >
The actual GenAI product may differ from the one identified by the client. 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` For example, when using OpenAI client libraries to communicate with Mistral, the `gen_ai.system`