diff --git a/.chloggen/1655.yaml b/.chloggen/1655.yaml
new file mode 100644
index 0000000000..d15da0a393
--- /dev/null
+++ b/.chloggen/1655.yaml
@@ -0,0 +1,24 @@
+# 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: genai
+
+# A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: |
+ Adds OpenAI API compatible `gen_ai.system` attribute values: `az.ai.openai`, `deepseek`, `gemini`, `groq`,
+ `perplexity` and `xai`. Elaborates that `openai` can be ambiguous due to API emulation.
+
+# 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: [1655]
+
+# (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:
diff --git a/.chloggen/1715.yaml b/.chloggen/1715.yaml
new file mode 100644
index 0000000000..677bad9615
--- /dev/null
+++ b/.chloggen/1715.yaml
@@ -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: breaking
+
+# 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: Rename `gen_ai.openai.request.seed` to `gen_ai.request.seed` and use it on general GenAI conventions.
+
+# 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: [1715]
+
+# (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:
diff --git a/.github/workflows/checks.yml b/.github/workflows/checks.yml
index 024f8309b2..ec8ff06763 100644
--- a/.github/workflows/checks.yml
+++ b/.github/workflows/checks.yml
@@ -18,7 +18,7 @@ jobs:
run: make check-file-and-folder-names-in-docs
- name: run markdownlint
- run: npx gulp lint-md
+ run: make markdownlint
yamllint:
runs-on: ubuntu-latest
diff --git a/Makefile b/Makefile
index 813a09c639..644a633870 100644
--- a/Makefile
+++ b/Makefile
@@ -101,17 +101,8 @@ markdown-toc:
.PHONY: markdownlint
markdownlint:
- @if ! npm ls markdownlint; then npm install; fi
- @npx gulp lint-md
-
-.PHONY: markdownlint-old
-markdownlint-old:
- @if ! npm ls markdownlint; then npm install; fi
- @for f in $(ALL_DOCS); do \
- echo $$f; \
- npx --no -p markdownlint-cli markdownlint -c .markdownlint.yaml $$f \
- || exit 1; \
- done
+ @if ! npm ls markdownlint-cli; then npm install; fi
+ npx --no -- markdownlint-cli -c .markdownlint.yaml $(ALL_DOCS)
.PHONY: install-yamllint
install-yamllint:
diff --git a/dependencies.Dockerfile b/dependencies.Dockerfile
index 18b420c661..f48a728de0 100644
--- a/dependencies.Dockerfile
+++ b/dependencies.Dockerfile
@@ -6,7 +6,7 @@
FROM otel/weaver:v0.12.0 AS weaver
# OPA is used to test policies enforced by weaver.
-FROM openpolicyagent/opa:0.70.0 AS opa
+FROM openpolicyagent/opa:1.0.0 AS opa
# Semconv gen is used for backwards compatibility checks.
# TODO(jsuereth): Remove this when no longer used.
diff --git a/docs/attributes-registry/gen-ai.md b/docs/attributes-registry/gen-ai.md
index 5ada7b3cdb..61a0b08cce 100644
--- a/docs/attributes-registry/gen-ai.md
+++ b/docs/attributes-registry/gen-ai.md
@@ -44,8 +44,10 @@ This document defines the attributes used to describe telemetry in the context o
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.
+Multiple systems, including Azure OpenAI and Gemini, are accessible by OpenAI client
+libraries. In such cases, the `gen_ai.system` is set to `openai` based on the
+instrumentation's best knowledge, instead of the actual system. The `server.address`
+attribute may help identify the actual system in use for `openai`.
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`.
@@ -69,10 +71,16 @@ If none of these options apply, the `gen_ai.system` SHOULD be set to `_OTHER`.
| `anthropic` | Anthropic |  |
| `aws.bedrock` | AWS Bedrock |  |
| `az.ai.inference` | Azure AI Inference |  |
+| `az.ai.openai` | Azure OpenAI |  |
| `cohere` | Cohere |  |
+| `deepseek` | DeepSeek |  |
+| `gemini` | Gemini |  |
+| `groq` | Groq |  |
| `ibm.watsonx.ai` | IBM Watsonx AI |  |
| `openai` | OpenAI |  |
+| `perplexity` | Perplexity |  |
| `vertex_ai` | Vertex AI |  |
+| `xai` | xAI |  |
---
diff --git a/docs/gen-ai/azure-ai-inference.md b/docs/gen-ai/azure-ai-inference.md
index ad9be5fb7a..5930182a4c 100644
--- a/docs/gen-ai/azure-ai-inference.md
+++ b/docs/gen-ai/azure-ai-inference.md
@@ -26,6 +26,7 @@ The Semantic Conventions for [Azure AI Inference](https://learn.microsoft.com/az
| [`gen_ai.operation.name`](/docs/attributes-registry/gen-ai.md) | string | The name of the operation being performed. [1] | `chat`; `text_completion`; `embeddings` | `Required` |  |
| [`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 |  |
| [`gen_ai.request.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the GenAI model a request is being made to. [3] | `gpt-4` | `Conditionally Required` If available. |  |
+| [`gen_ai.request.seed`](/docs/attributes-registry/gen-ai.md) | int | Requests with same seed value more likely to return same result. | `100` | `Conditionally Required` if appliable and if the request includes a seed |  |
| [`server.port`](/docs/attributes-registry/server.md) | int | GenAI server port. [4] | `80`; `8080`; `443` | `Conditionally Required` If not default (443). |  |
| [`az.namespace`](/docs/attributes-registry/azure.md) | string | [Azure Resource Provider Namespace](https://learn.microsoft.com/azure/azure-resource-manager/management/azure-services-resource-providers) as recognized by the client. [5] | `Microsoft.CognitiveServices` | `Recommended` |  |
| [`gen_ai.request.encoding_formats`](/docs/attributes-registry/gen-ai.md) | string[] | The encoding formats requested in an embeddings operation, if specified. [6] | `["base64"]`; `["float", "binary"]` | `Recommended` |  |
diff --git a/docs/gen-ai/gen-ai-events.md b/docs/gen-ai/gen-ai-events.md
index e7fa7c0beb..b43bb2578f 100644
--- a/docs/gen-ai/gen-ai-events.md
+++ b/docs/gen-ai/gen-ai-events.md
@@ -69,8 +69,10 @@ This event describes the system instructions passed to the GenAI model.
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.
+Multiple systems, including Azure OpenAI and Gemini, are accessible by OpenAI client
+libraries. In such cases, the `gen_ai.system` is set to `openai` based on the
+instrumentation's best knowledge, instead of the actual system. The `server.address`
+attribute may help identify the actual system in use for `openai`.
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`.
@@ -84,10 +86,16 @@ If none of these options apply, the `gen_ai.system` SHOULD be set to `_OTHER`.
| `anthropic` | Anthropic |  |
| `aws.bedrock` | AWS Bedrock |  |
| `az.ai.inference` | Azure AI Inference |  |
+| `az.ai.openai` | Azure OpenAI |  |
| `cohere` | Cohere |  |
+| `deepseek` | DeepSeek |  |
+| `gemini` | Gemini |  |
+| `groq` | Groq |  |
| `ibm.watsonx.ai` | IBM Watsonx AI |  |
| `openai` | OpenAI |  |
+| `perplexity` | Perplexity |  |
| `vertex_ai` | Vertex AI |  |
+| `xai` | xAI |  |
**Body fields:**
@@ -124,8 +132,10 @@ This event describes the user message passed to the GenAI model.
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.
+Multiple systems, including Azure OpenAI and Gemini, are accessible by OpenAI client
+libraries. In such cases, the `gen_ai.system` is set to `openai` based on the
+instrumentation's best knowledge, instead of the actual system. The `server.address`
+attribute may help identify the actual system in use for `openai`.
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`.
@@ -139,10 +149,16 @@ If none of these options apply, the `gen_ai.system` SHOULD be set to `_OTHER`.
| `anthropic` | Anthropic |  |
| `aws.bedrock` | AWS Bedrock |  |
| `az.ai.inference` | Azure AI Inference |  |
+| `az.ai.openai` | Azure OpenAI |  |
| `cohere` | Cohere |  |
+| `deepseek` | DeepSeek |  |
+| `gemini` | Gemini |  |
+| `groq` | Groq |  |
| `ibm.watsonx.ai` | IBM Watsonx AI |  |
| `openai` | OpenAI |  |
+| `perplexity` | Perplexity |  |
| `vertex_ai` | Vertex AI |  |
+| `xai` | xAI |  |
**Body fields:**
@@ -179,8 +195,10 @@ This event describes the assistant message passed to GenAI system.
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.
+Multiple systems, including Azure OpenAI and Gemini, are accessible by OpenAI client
+libraries. In such cases, the `gen_ai.system` is set to `openai` based on the
+instrumentation's best knowledge, instead of the actual system. The `server.address`
+attribute may help identify the actual system in use for `openai`.
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`.
@@ -194,10 +212,16 @@ If none of these options apply, the `gen_ai.system` SHOULD be set to `_OTHER`.
| `anthropic` | Anthropic |  |
| `aws.bedrock` | AWS Bedrock |  |
| `az.ai.inference` | Azure AI Inference |  |
+| `az.ai.openai` | Azure OpenAI |  |
| `cohere` | Cohere |  |
+| `deepseek` | DeepSeek |  |
+| `gemini` | Gemini |  |
+| `groq` | Groq |  |
| `ibm.watsonx.ai` | IBM Watsonx AI |  |
| `openai` | OpenAI |  |
+| `perplexity` | Perplexity |  |
| `vertex_ai` | Vertex AI |  |
+| `xai` | xAI |  |
**Body fields:**
@@ -249,8 +273,10 @@ This event describes the response from a tool or function call passed to the Gen
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.
+Multiple systems, including Azure OpenAI and Gemini, are accessible by OpenAI client
+libraries. In such cases, the `gen_ai.system` is set to `openai` based on the
+instrumentation's best knowledge, instead of the actual system. The `server.address`
+attribute may help identify the actual system in use for `openai`.
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`.
@@ -264,10 +290,16 @@ If none of these options apply, the `gen_ai.system` SHOULD be set to `_OTHER`.
| `anthropic` | Anthropic |  |
| `aws.bedrock` | AWS Bedrock |  |
| `az.ai.inference` | Azure AI Inference |  |
+| `az.ai.openai` | Azure OpenAI |  |
| `cohere` | Cohere |  |
+| `deepseek` | DeepSeek |  |
+| `gemini` | Gemini |  |
+| `groq` | Groq |  |
| `ibm.watsonx.ai` | IBM Watsonx AI |  |
| `openai` | OpenAI |  |
+| `perplexity` | Perplexity |  |
| `vertex_ai` | Vertex AI |  |
+| `xai` | xAI |  |
**Body fields:**
@@ -305,8 +337,10 @@ This event describes the Gen AI response message.
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.
+Multiple systems, including Azure OpenAI and Gemini, are accessible by OpenAI client
+libraries. In such cases, the `gen_ai.system` is set to `openai` based on the
+instrumentation's best knowledge, instead of the actual system. The `server.address`
+attribute may help identify the actual system in use for `openai`.
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`.
@@ -320,10 +354,16 @@ If none of these options apply, the `gen_ai.system` SHOULD be set to `_OTHER`.
| `anthropic` | Anthropic |  |
| `aws.bedrock` | AWS Bedrock |  |
| `az.ai.inference` | Azure AI Inference |  |
+| `az.ai.openai` | Azure OpenAI |  |
| `cohere` | Cohere |  |
+| `deepseek` | DeepSeek |  |
+| `gemini` | Gemini |  |
+| `groq` | Groq |  |
| `ibm.watsonx.ai` | IBM Watsonx AI |  |
| `openai` | OpenAI |  |
+| `perplexity` | Perplexity |  |
| `vertex_ai` | Vertex AI |  |
+| `xai` | xAI |  |
**Body fields:**
diff --git a/docs/gen-ai/gen-ai-metrics.md b/docs/gen-ai/gen-ai-metrics.md
index f47e0b2280..ac473e6c76 100644
--- a/docs/gen-ai/gen-ai-metrics.md
+++ b/docs/gen-ai/gen-ai-metrics.md
@@ -75,8 +75,10 @@ This metric SHOULD be specified with [ExplicitBucketBoundaries] of [1, 4, 16, 64
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.
+Multiple systems, including Azure OpenAI and Gemini, are accessible by OpenAI client
+libraries. In such cases, the `gen_ai.system` is set to `openai` based on the
+instrumentation's best knowledge, instead of the actual system. The `server.address`
+attribute may help identify the actual system in use for `openai`.
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`.
@@ -104,10 +106,16 @@ If none of these options apply, the `gen_ai.system` SHOULD be set to `_OTHER`.
| `anthropic` | Anthropic |  |
| `aws.bedrock` | AWS Bedrock |  |
| `az.ai.inference` | Azure AI Inference |  |
+| `az.ai.openai` | Azure OpenAI |  |
| `cohere` | Cohere |  |
+| `deepseek` | DeepSeek |  |
+| `gemini` | Gemini |  |
+| `groq` | Groq |  |
| `ibm.watsonx.ai` | IBM Watsonx AI |  |
| `openai` | OpenAI |  |
+| `perplexity` | Perplexity |  |
| `vertex_ai` | Vertex AI |  |
+| `xai` | xAI |  |
---
@@ -156,8 +164,10 @@ This metric SHOULD be specified with [ExplicitBucketBoundaries] of [0.01, 0.02,
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.
+Multiple systems, including Azure OpenAI and Gemini, are accessible by OpenAI client
+libraries. In such cases, the `gen_ai.system` is set to `openai` based on the
+instrumentation's best knowledge, instead of the actual system. The `server.address`
+attribute may help identify the actual system in use for `openai`.
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`.
@@ -197,10 +207,16 @@ Instrumentations SHOULD document the list of errors they report.
| `anthropic` | Anthropic |  |
| `aws.bedrock` | AWS Bedrock |  |
| `az.ai.inference` | Azure AI Inference |  |
+| `az.ai.openai` | Azure OpenAI |  |
| `cohere` | Cohere |  |
+| `deepseek` | DeepSeek |  |
+| `gemini` | Gemini |  |
+| `groq` | Groq |  |
| `ibm.watsonx.ai` | IBM Watsonx AI |  |
| `openai` | OpenAI |  |
+| `perplexity` | Perplexity |  |
| `vertex_ai` | Vertex AI |  |
+| `xai` | xAI |  |
@@ -247,8 +263,10 @@ This metric SHOULD be specified with [ExplicitBucketBoundaries] of
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.
+Multiple systems, including Azure OpenAI and Gemini, are accessible by OpenAI client
+libraries. In such cases, the `gen_ai.system` is set to `openai` based on the
+instrumentation's best knowledge, instead of the actual system. The `server.address`
+attribute may help identify the actual system in use for `openai`.
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`.
@@ -288,10 +306,16 @@ Instrumentations SHOULD document the list of errors they report.
| `anthropic` | Anthropic |  |
| `aws.bedrock` | AWS Bedrock |  |
| `az.ai.inference` | Azure AI Inference |  |
+| `az.ai.openai` | Azure OpenAI |  |
| `cohere` | Cohere |  |
+| `deepseek` | DeepSeek |  |
+| `gemini` | Gemini |  |
+| `groq` | Groq |  |
| `ibm.watsonx.ai` | IBM Watsonx AI |  |
| `openai` | OpenAI |  |
+| `perplexity` | Perplexity |  |
| `vertex_ai` | Vertex AI |  |
+| `xai` | xAI |  |
@@ -337,8 +361,10 @@ This metric SHOULD be specified with [ExplicitBucketBoundaries] of
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.
+Multiple systems, including Azure OpenAI and Gemini, are accessible by OpenAI client
+libraries. In such cases, the `gen_ai.system` is set to `openai` based on the
+instrumentation's best knowledge, instead of the actual system. The `server.address`
+attribute may help identify the actual system in use for `openai`.
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`.
@@ -366,10 +392,16 @@ If none of these options apply, the `gen_ai.system` SHOULD be set to `_OTHER`.
| `anthropic` | Anthropic |  |
| `aws.bedrock` | AWS Bedrock |  |
| `az.ai.inference` | Azure AI Inference |  |
+| `az.ai.openai` | Azure OpenAI |  |
| `cohere` | Cohere |  |
+| `deepseek` | DeepSeek |  |
+| `gemini` | Gemini |  |
+| `groq` | Groq |  |
| `ibm.watsonx.ai` | IBM Watsonx AI |  |
| `openai` | OpenAI |  |
+| `perplexity` | Perplexity |  |
| `vertex_ai` | Vertex AI |  |
+| `xai` | xAI |  |
@@ -414,8 +446,10 @@ This metric SHOULD be specified with [ExplicitBucketBoundaries] of
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.
+Multiple systems, including Azure OpenAI and Gemini, are accessible by OpenAI client
+libraries. In such cases, the `gen_ai.system` is set to `openai` based on the
+instrumentation's best knowledge, instead of the actual system. The `server.address`
+attribute may help identify the actual system in use for `openai`.
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`.
@@ -443,10 +477,16 @@ If none of these options apply, the `gen_ai.system` SHOULD be set to `_OTHER`.
| `anthropic` | Anthropic |  |
| `aws.bedrock` | AWS Bedrock |  |
| `az.ai.inference` | Azure AI Inference |  |
+| `az.ai.openai` | Azure OpenAI |  |
| `cohere` | Cohere |  |
+| `deepseek` | DeepSeek |  |
+| `gemini` | Gemini |  |
+| `groq` | Groq |  |
| `ibm.watsonx.ai` | IBM Watsonx AI |  |
| `openai` | OpenAI |  |
+| `perplexity` | Perplexity |  |
| `vertex_ai` | Vertex AI |  |
+| `xai` | xAI |  |
diff --git a/docs/gen-ai/gen-ai-spans.md b/docs/gen-ai/gen-ai-spans.md
index 70c8d3d5bf..24a70cade6 100644
--- a/docs/gen-ai/gen-ai-spans.md
+++ b/docs/gen-ai/gen-ai-spans.md
@@ -48,6 +48,7 @@ Many of these attributes only apply to specific GenAI operations. For example, G
| [`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` |  |
| [`error.type`](/docs/attributes-registry/error.md) | string | Describes a class of error the operation ended with. [3] | `timeout`; `java.net.UnknownHostException`; `server_certificate_invalid`; `500` | `Conditionally Required` if the operation ended in an error |  |
| [`gen_ai.request.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the GenAI model a request is being made to. [4] | `gpt-4` | `Conditionally Required` If available. |  |
+| [`gen_ai.request.seed`](/docs/attributes-registry/gen-ai.md) | int | Requests with same seed value more likely to return same result. | `100` | `Conditionally Required` if appliable and if the request includes a seed |  |
| [`server.port`](/docs/attributes-registry/server.md) | int | GenAI server port. [5] | `80`; `8080`; `443` | `Conditionally Required` If `server.address` is set. |  |
| [`gen_ai.request.encoding_formats`](/docs/attributes-registry/gen-ai.md) | string[] | The encoding formats requested in an embeddings operation, if specified. [6] | `["base64"]`; `["float", "binary"]` | `Recommended` |  |
| [`gen_ai.request.frequency_penalty`](/docs/attributes-registry/gen-ai.md) | double | The frequency penalty setting for the GenAI request. | `0.1` | `Recommended` |  |
@@ -70,8 +71,10 @@ Many of these attributes only apply to specific GenAI operations. For example, G
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.
+Multiple systems, including Azure OpenAI and Gemini, are accessible by OpenAI client
+libraries. In such cases, the `gen_ai.system` is set to `openai` based on the
+instrumentation's best knowledge, instead of the actual system. The `server.address`
+attribute may help identify the actual system in use for `openai`.
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`.
@@ -117,10 +120,16 @@ Instrumentations SHOULD document the list of errors they report.
| `anthropic` | Anthropic |  |
| `aws.bedrock` | AWS Bedrock |  |
| `az.ai.inference` | Azure AI Inference |  |
+| `az.ai.openai` | Azure OpenAI |  |
| `cohere` | Cohere |  |
+| `deepseek` | DeepSeek |  |
+| `gemini` | Gemini |  |
+| `groq` | Groq |  |
| `ibm.watsonx.ai` | IBM Watsonx AI |  |
| `openai` | OpenAI |  |
+| `perplexity` | Perplexity |  |
| `vertex_ai` | Vertex AI |  |
+| `xai` | xAI |  |
diff --git a/docs/gen-ai/openai.md b/docs/gen-ai/openai.md
index 35b274b17a..6496fd5663 100644
--- a/docs/gen-ai/openai.md
+++ b/docs/gen-ai/openai.md
@@ -40,9 +40,9 @@ attributes and ones specific the OpenAI.
| [`gen_ai.request.model`](/docs/attributes-registry/gen-ai.md) | string | The name of the GenAI model a request is being made to. [2] | `gpt-4` | `Required` |  |
| [`error.type`](/docs/attributes-registry/error.md) | string | Describes a class of error the operation ended with. [3] | `timeout`; `java.net.UnknownHostException`; `server_certificate_invalid`; `500` | `Conditionally Required` if the operation ended in an error |  |
| [`gen_ai.openai.request.response_format`](/docs/attributes-registry/gen-ai.md) | string | The response format that is requested. | `json` | `Conditionally Required` if the request includes a response_format |  |
-| [`gen_ai.openai.request.seed`](/docs/attributes-registry/gen-ai.md) | int | Deprecated, use `gen_ai.request.seed`. | `100` | `Conditionally Required` if the request includes a seed | 
Replaced by `gen_ai.request.seed` attribute. |
| [`gen_ai.openai.request.service_tier`](/docs/attributes-registry/gen-ai.md) | string | The service tier requested. May be a specific tier, default, or auto. | `auto`; `default` | `Conditionally Required` [4] |  |
| [`gen_ai.openai.response.service_tier`](/docs/attributes-registry/gen-ai.md) | string | The service tier used for the response. | `scale`; `default` | `Conditionally Required` [5] |  |
+| [`gen_ai.request.seed`](/docs/attributes-registry/gen-ai.md) | int | Requests with same seed value more likely to return same result. | `100` | `Conditionally Required` if appliable and if the request includes a seed |  |
| [`server.port`](/docs/attributes-registry/server.md) | int | GenAI server port. [6] | `80`; `8080`; `443` | `Conditionally Required` If `server.address` is set. |  |
| [`gen_ai.openai.response.system_fingerprint`](/docs/attributes-registry/gen-ai.md) | string | A fingerprint to track any eventual change in the Generative AI environment. | `fp_44709d6fcb` | `Recommended` |  |
| [`gen_ai.request.encoding_formats`](/docs/attributes-registry/gen-ai.md) | string[] | The encoding formats requested in an embeddings operation, if specified. [7] | `["base64"]`; `["float", "binary"]` | `Recommended` |  |
diff --git a/gulpfile.js b/gulpfile.js
deleted file mode 100644
index b01927ecc0..0000000000
--- a/gulpfile.js
+++ /dev/null
@@ -1,64 +0,0 @@
-const gulp = require("gulp");
-const through2 = require("through2");
-const markdownlint = require("markdownlint");
-const yaml = require("js-yaml");
-const fs = require("fs");
-
-let numFilesProcessed = 0,
- numFilesWithIssues = 0;
-
-function markdownLintFile(file, encoding, callback) {
- const config = yaml.load(fs.readFileSync("./.markdownlint.yaml", "utf8"));
- const options = {
- files: [file.path],
- config: config,
- };
-
- markdownlint(options, function (err, result) {
- if (err) {
- console.error("ERROR occurred while running markdownlint: ", err);
- return callback(err);
- }
-
- const _resultString = (result || "").toString();
- // Result is a string with lines of the form:
- //
- // :\s*:
- //
- // Strip out any whitespace between the filepath and line number
- // so that tools can jump directly to the line.
- const resultString = _resultString
- .split("\n")
- .map((line) => line.replace(/^([^:]+):\s*(\d+):(.*)/, "$1:$2:$3"))
- .join("\n");
- if (resultString) {
- console.log(resultString);
- numFilesWithIssues++;
- // Don't report an error yet so that other files can be checked:
- // callback(new Error('...'));
- }
- numFilesProcessed++;
- callback(null, file);
- });
-}
-
-function lintMarkdown() {
- const markdownFiles = ["**/*.md", "!**/node_modules/**", "!**/.github/**"];
-
- return gulp
- .src(markdownFiles)
- .pipe(through2.obj(markdownLintFile))
- .on("end", () => {
- const fileOrFiles = "file" + (numFilesProcessed == 1 ? "" : "s");
- const msg = `Processed ${numFilesProcessed} ${fileOrFiles}, ${numFilesWithIssues} had issues.`;
- if (numFilesWithIssues > 0) {
- throw new Error(msg);
- } else {
- console.log(msg);
- }
- });
-}
-
-lintMarkdown.description = `Run markdownlint on all '*.md' files.`;
-
-gulp.task("lint-md", lintMarkdown);
diff --git a/model/gen-ai/registry.yaml b/model/gen-ai/registry.yaml
index ddf79f91ed..09c36698e4 100644
--- a/model/gen-ai/registry.yaml
+++ b/model/gen-ai/registry.yaml
@@ -17,6 +17,10 @@ groups:
stability: experimental
value: "vertex_ai"
brief: 'Vertex AI'
+ - id: gemini
+ stability: experimental
+ value: "gemini"
+ brief: 'Gemini'
- id: anthropic
stability: experimental
value: "anthropic"
@@ -29,6 +33,10 @@ groups:
stability: experimental
value: "az.ai.inference"
brief: 'Azure AI Inference'
+ - id: az.ai.openai
+ stability: experimental
+ value: "az.ai.openai"
+ brief: 'Azure OpenAI'
- id: ibm.watsonx.ai
stability: experimental
value: "ibm.watsonx.ai"
@@ -37,14 +45,33 @@ groups:
stability: experimental
value: "aws.bedrock"
brief: 'AWS Bedrock'
+ - id: perplexity
+ stability: experimental
+ value: "perplexity"
+ brief: 'Perplexity'
+ - id: xai
+ stability: experimental
+ value: "xai"
+ brief: 'xAI'
+ - id: deepseek
+ stability: experimental
+ value: "deepseek"
+ brief: 'DeepSeek'
+ - id: groq
+ stability: experimental
+ value: "groq"
+ brief: 'Groq'
+
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.
+ Multiple systems, including Azure OpenAI and Gemini, are accessible by OpenAI client
+ libraries. In such cases, the `gen_ai.system` is set to `openai` based on the
+ instrumentation's best knowledge, instead of the actual system. The `server.address`
+ attribute may help identify the actual system in use for `openai`.
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`.
diff --git a/model/gen-ai/spans.yaml b/model/gen-ai/spans.yaml
index e6a3c743be..1d1311d9a1 100644
--- a/model/gen-ai/spans.yaml
+++ b/model/gen-ai/spans.yaml
@@ -26,6 +26,9 @@ groups:
requirement_level: recommended
- ref: gen_ai.request.presence_penalty
requirement_level: recommended
+ - ref: gen_ai.request.seed
+ requirement_level:
+ conditionally_required: if appliable and if the request includes a seed
- ref: gen_ai.request.encoding_formats
requirement_level: recommended
- ref: gen_ai.response.id
@@ -82,9 +85,6 @@ groups:
attributes:
- ref: gen_ai.request.model
requirement_level: required
- - ref: gen_ai.openai.request.seed
- requirement_level:
- conditionally_required: if the request includes a seed
- ref: gen_ai.openai.request.response_format
requirement_level:
conditionally_required: if the request includes a response_format
diff --git a/package.json b/package.json
index ef069a000a..6e32c045d4 100644
--- a/package.json
+++ b/package.json
@@ -9,14 +9,10 @@
"test": "npm run check"
},
"devDependencies": {
- "gulp": "^5.0.0",
- "js-yaml": "^4.1.0",
"markdown-link-check": "3.11.2",
"markdown-toc": "^1.2.0",
- "markdownlint": "0.36.1",
"markdownlint-cli": "0.43.0",
- "prettier": "^3.0.0",
- "through2": "^4.0.2"
+ "prettier": "^3.0.0"
},
"prettier": {
"proseWrap": "preserve"
diff --git a/policies/group_stability.rego b/policies/group_stability.rego
index 17d7f3dd91..62eb061bb9 100644
--- a/policies/group_stability.rego
+++ b/policies/group_stability.rego
@@ -1,7 +1,7 @@
package after_resolution
-
+import rego.v1
# checks that stable group does not have experimental attributes with requirement levels other than opt_in
-deny[group_stability_violation(description, group.id, name)] {
+deny contains group_stability_violation(description, group.id, name) if {
group := input.groups[_]
# ignore attribute_groups
group.type != "attribute_group"
@@ -27,7 +27,7 @@ deny[group_stability_violation(description, group.id, name)] {
description := sprintf("Stable group '%s' references experimental attribute with requirement level '%s', only 'opt_in' level is allowed", [group.id, name])
}
-group_stability_violation(description, group, attr) = violation {
+group_stability_violation(description, group, attr) = violation if {
violation := {
"id": description,
"type": "semconv_attribute",
diff --git a/policies/registry.rego b/policies/registry.rego
index fccafd9b79..3e145c1afa 100644
--- a/policies/registry.rego
+++ b/policies/registry.rego
@@ -1,11 +1,12 @@
package before_resolution
+import rego.v1
# This file enforces policies requiring all attributes to be defined within
# a semantic convention "registry". This is a naming/structure convention
# used by semantic conventions.
# Helper to create attribute registry violations.
-attr_registry_violation(description, group_id, attr_id) = violation {
+attr_registry_violation(description, group_id, attr_id) = violation if {
violation := {
"id": description,
"type": "semconv_attribute",
@@ -16,7 +17,7 @@ attr_registry_violation(description, group_id, attr_id) = violation {
}
# We only allow attribute groups in the attribute registry.
-deny[attr_registry_violation(description, group.id, "")] {
+deny contains attr_registry_violation(description, group.id, "") if {
group := input.groups[_]
startswith(group.id, "registry.")
group.type != "attribute_group"
@@ -28,7 +29,7 @@ deny[attr_registry_violation(description, group.id, "")] {
# Any group that is NOT in the attribute registry that has an attribute id is
# in violation of not using the attribute registry.
-deny[attr_registry_violation(description, group.id, attr.id)] {
+deny contains attr_registry_violation(description, group.id, attr.id) if {
group := input.groups[_]
not startswith(group.id, "registry.")
attr := group.attributes[_]
@@ -43,7 +44,7 @@ deny[attr_registry_violation(description, group.id, attr.id)] {
# A registry `attribute_group` containing at least one `ref` attribute is
# considered invalid if it's not in the registry group.
-deny[attr_registry_violation(description, group.id, attr.ref)] {
+deny contains attr_registry_violation(description, group.id, attr.ref) if {
# TODO - this will need to be updated to support `embed` in the future.
group := input.groups[_]
startswith(group.id, "registry.")
@@ -56,7 +57,7 @@ deny[attr_registry_violation(description, group.id, attr.ref)] {
}
# We don't allow attribute definitions to have requirement_level
-deny[attr_registry_violation(description, group.id, attr.id)] {
+deny contains attr_registry_violation(description, group.id, attr.id) if {
group := input.groups[_]
startswith(group.id, "registry.")
@@ -69,8 +70,8 @@ deny[attr_registry_violation(description, group.id, attr.id)] {
description := sprintf("Attribute definition '%s' has requirement_level set to %s. Only attribute references can set requirement_level.", [attr.id, attr.requirement_level])
}
-get_attribute_name(attr, group) = name {
- full_name = concat(".", [group.prefix, attr.id])
+get_attribute_name(attr, group) := name if {
+ full_name := concat(".", [group.prefix, attr.id])
# if there was no prefix, we have a leading dot
name := trim(full_name, ".")
diff --git a/policies/yaml_schema.rego b/policies/yaml_schema.rego
index d8d60471f0..a2575930bc 100644
--- a/policies/yaml_schema.rego
+++ b/policies/yaml_schema.rego
@@ -1,7 +1,8 @@
package before_resolution
+import rego.v1
# checks attribute name format
-deny[yaml_schema_violation(description, group.id, name)] {
+deny contains yaml_schema_violation(description, group.id, name) if {
group := input.groups[_]
attr := group.attributes[_]
name := attr.id
@@ -12,7 +13,7 @@ deny[yaml_schema_violation(description, group.id, name)] {
}
# checks attribute name has a namespace
-deny[yaml_schema_violation(description, group.id, name)] {
+deny contains yaml_schema_violation(description, group.id, name) if {
group := input.groups[_]
attr := group.attributes[_]
name := attr.id
@@ -24,9 +25,8 @@ deny[yaml_schema_violation(description, group.id, name)] {
description := sprintf("Attribute name '%s' should have a namespace. Attribute name %s", [name, invalid_name_helper])
}
-
# checks metric name format
-deny[yaml_schema_violation(description, group.id, name)] {
+deny contains yaml_schema_violation(description, group.id, name) if {
group := input.groups[_]
name := group.metric_name
@@ -37,7 +37,7 @@ deny[yaml_schema_violation(description, group.id, name)] {
}
# checks that metric id matches metric.{metric_name}
-deny[yaml_schema_violation(description, group.id, name)] {
+deny contains yaml_schema_violation(description, group.id, name) if {
group := input.groups[_]
name := group.metric_name
name != null
@@ -49,7 +49,7 @@ deny[yaml_schema_violation(description, group.id, name)] {
}
# checks event name format
-deny[yaml_schema_violation(description, group.id, name)] {
+deny contains yaml_schema_violation(description, group.id, name) if {
group := input.groups[_]
group.type == "event"
name := group.name
@@ -61,7 +61,7 @@ deny[yaml_schema_violation(description, group.id, name)] {
}
# checks that event id matches event.{name}
-deny[yaml_schema_violation(description, group.id, name)] {
+deny contains yaml_schema_violation(description, group.id, name) if {
group := input.groups[_]
group.type == "event"
name := group.name
@@ -73,7 +73,7 @@ deny[yaml_schema_violation(description, group.id, name)] {
}
# checks event.name is not referenced in event attributes
-deny[yaml_schema_violation(description, group.id, name)] {
+deny contains yaml_schema_violation(description, group.id, name) if {
group := input.groups[_]
group.type == "event"
name := group.name
@@ -85,7 +85,7 @@ deny[yaml_schema_violation(description, group.id, name)] {
}
# require resources have names
-deny[yaml_schema_violation(description, group.id, "")] {
+deny contains yaml_schema_violation(description, group.id, "") if {
group := input.groups[_]
group.type == "resource"
group.name == null
@@ -93,7 +93,7 @@ deny[yaml_schema_violation(description, group.id, "")] {
}
# checks resource name format
-deny[yaml_schema_violation(description, group.id, name)] {
+deny contains yaml_schema_violation(description, group.id, name) if {
group := input.groups[_]
group.type == "resource"
name := group.name
@@ -105,7 +105,7 @@ deny[yaml_schema_violation(description, group.id, name)] {
}
# checks that resource group id matches resource.{name}
-deny[yaml_schema_violation(description, group.id, name)] {
+deny contains yaml_schema_violation(description, group.id, name) if {
group := input.groups[_]
group.type == "resource"
@@ -122,7 +122,7 @@ deny[yaml_schema_violation(description, group.id, name)] {
}
# checks attribute member id format
-deny[yaml_schema_violation(description, group.id, attr_name)] {
+deny contains yaml_schema_violation(description, group.id, attr_name) if {
group := input.groups[_]
attr := group.attributes[_]
attr_name := attr.id
@@ -134,7 +134,7 @@ deny[yaml_schema_violation(description, group.id, attr_name)] {
}
# check that attribute is fully qualified with their id, prefix is no longer supported
-deny[yaml_schema_violation(description, group.id, "")] {
+deny contains yaml_schema_violation(description, group.id, "") if {
group := input.groups[_]
group.prefix != null
@@ -146,7 +146,7 @@ deny[yaml_schema_violation(description, group.id, "")] {
# TODO: remove after span_kind is required https://github.com/open-telemetry/semantic-conventions/issues/1513
# checks that span id matches span.*. pattern if span_kind is not provided
-deny[yaml_schema_violation(description, group.id, "")] {
+deny contains yaml_schema_violation(description, group.id, "") if {
group := input.groups[_]
group.type == "span"
kind := group.span_kind
@@ -157,7 +157,7 @@ deny[yaml_schema_violation(description, group.id, "")] {
}
# checks that span id matches span.*.{kind} pattern if span_kind is not provided
-deny[yaml_schema_violation(description, group.id, "")] {
+deny contains yaml_schema_violation(description, group.id, "") if {
group := input.groups[_]
group.type == "span"
kind := group.span_kind
@@ -168,7 +168,7 @@ deny[yaml_schema_violation(description, group.id, "")] {
description := sprintf("Group id '%s' is invalid. Span group 'id' must follow 'span.*.%s' pattern", [group.id, kind])
}
-yaml_schema_violation(description, group, attr) = violation {
+yaml_schema_violation(description, group, attr) = violation if {
violation := {
"id": description,
"type": "semconv_attribute",
diff --git a/policies_test/yaml_schema_test.rego b/policies_test/yaml_schema_test.rego
index 6c5cb4cc89..81dd0f2d55 100644
--- a/policies_test/yaml_schema_test.rego
+++ b/policies_test/yaml_schema_test.rego
@@ -100,21 +100,21 @@ test_fails_on_invalid_resource_id if {
}
}
-create_attribute_group(attr) = json {
+create_attribute_group(attr) = json if {
json := [{"id": "yaml_schema.test", "attributes": [{"id": attr}]}]
}
-create_metric(name) = json {
+create_metric(name) = json if {
id := sprintf("metric.%s", [name])
json := [{"id": id, "type": "metric", "metric_name": name}]
}
-create_event(name) = json {
+create_event(name) = json if {
id := sprintf("event.%s", [name])
json := [{"id": id, "type": "event", "name": name}]
}
-create_resource(name) = json {
+create_resource(name) = json if {
id := sprintf("resource.%s", [name])
json := [{"id": id, "type": "resource", "name": name}]
}
diff --git a/schema-next.yaml b/schema-next.yaml
index 1a429b3724..49ec864f23 100644
--- a/schema-next.yaml
+++ b/schema-next.yaml
@@ -7,6 +7,7 @@ versions:
# https://github.com/open-telemetry/semantic-conventions/pull/1632
- rename_attributes:
attribute_map:
+ gen_ai.openai.request.seed: gen_ai.request.seed
system.network.state: network.connection.state
1.29.0:
all: