Skip to content

Remove advisor low-cardinality keys that aren't actually exposed. #1660

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

Remove advisor low-cardinality keys that aren't actually exposed. #1660

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 6 additions & 8 deletions spring-ai-docs/src/main/antora/modules/ROOT/pages/observability/index.adoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ NOTE: Low cardinality keys will be added to metrics and traces, while high cardi

== Chat Client

The `spring.ai.chat.client` observations are recorded when a ChatClient `call()` or `stream()` operations are invoked.
The `spring.ai.chat.client` observations are recorded when a ChatClient `call()` or `stream()` operations are invoked.
They measure the time spent performing the invocation and propagate the related tracing information.

.Low Cardinality Keys
Expand Down Expand Up @@ -56,16 +56,14 @@ WARNING: If you enable the inclusion of the input content in the observations, t

=== Chat Client Advisors

The `spring.ai.advisor` observations are recorded when a call or stream around advisors is performed.
The `spring.ai.advisor` observations are recorded when a call or stream around advisors is performed.
They measure the time spent in the advisor (including the time spend on the inner advisors) and propagate the related tracing information.

.Low Cardinality Keys
[cols="a,a", stripes=even]
|===
|Name | Description

|`gen_ai.operation.name` | Always `framework`.
|`gen_ai.system` | Always `spring_ai`.
|`spring.ai.advisor.type` | Where the advisor applies it's logic in the request processing, one of `BEFORE`, `AFTER`, or `AROUND`.
|`spring.ai.kind` | The kind of framework API in Spring AI: `advisor`.
|===
Expand All @@ -85,7 +83,7 @@ NOTE: Observability features are currently supported only for `ChatModel` implem
providers: Anthropic, Azure OpenAI, Mistral AI, Ollama, OpenAI, Vertex AI, MiniMax, Moonshot, QianFan, Zhiu AI.
Additional AI model providers will be supported in a future release.

The `gen_ai.client.operation` observations are recorded when calling the ChatModel `call` or `stream` methods.
The `gen_ai.client.operation` observations are recorded when calling the ChatModel `call` or `stream` methods.
They measure the time spent on method completion and propagate the related tracing information.

IMPORTANT: The `gen_ai.client.token.usage` metrics measures number of input and output tokens used by a single model call.
Expand Down Expand Up @@ -162,7 +160,7 @@ NOTE: Observability features are currently supported only for `EmbeddingModel` i
AI model providers: Azure OpenAI, Mistral AI, Ollama, and OpenAI.
Additional AI model providers will be supported in a future release.

The `gen_ai.client.operation` observations are recorded on embedding model method calls.
The `gen_ai.client.operation` observations are recorded on embedding model method calls.
They measure the time spent on method completion and propagate the related tracing information.

IMPORTANT: The `gen_ai.client.token.usage` metrics measures number of input and output tokens used by a single model call.
Expand Down Expand Up @@ -197,7 +195,7 @@ NOTE: Observability features are currently supported only for `ImageModel` imple
providers: OpenAI.
Additional AI model providers will be supported in a future release.

The `gen_ai.client.operation` observations are recorded on image model method calls.
The `gen_ai.client.operation` observations are recorded on image model method calls.
They measure the time spent on method completion and propagate the related tracing information.

IMPORTANT: The `gen_ai.client.token.usage` metrics measures number of input and output tokens used by a single model call.
Expand Down Expand Up @@ -260,7 +258,7 @@ WARNING: If you enable the inclusion of the image prompt data in the observation

All vector store implementations in Spring AI are instrumented to provide metrics and distributed tracing data through Micrometer.

The `db.vector.client.operation` observations are recorded when interacting with the Vector Store.
The `db.vector.client.operation` observations are recorded when interacting with the Vector Store.
They measure the time spent on the `query`, `add` and `remove` operations and propagate the related tracing information.

.Low Cardinality Keys
Expand Down