Spring/spring-ai
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Minor doc improvements to observability

Browse Source
This commit is contained in:
Mark Pollack
2024-10-08 14:46:25 +02:00
parent 2cd85a0781
commit cddb00a5f9
1 changed files with 13 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
spring-ai-docs/src/main/antora/modules/ROOT/pages/observabilty/index.adoc
View File

@@ -77,13 +77,13 @@ They measure the time spent in the advisor (including the time spend on the inne
== Chat Model
NOTE: Observability features are currently supported only for `ChatModel` implementations from the following AI model
providers: Anthropic, Azure OpenAI, Mistral AI, Ollama, and OpenAI.
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.
They measure the time spent on method completion and propagate the related tracing information.
The `gen_ai.client.token.usage` metrics measures number of input and output tokens used by a single model call.
IMPORTANT: The `gen_ai.client.token.usage` metrics measures number of input and output tokens used by a single model call.
.Low Cardinality Keys
@@ -116,6 +116,9 @@ The `gen_ai.client.token.usage` metrics measures number of input and output toke
|`gen_ai.completion` | The full response received from the model. Optional.
|===
NOTE: For measuring user tokens, the previous table lists the values present in an observation trace.
Use the metric name `gen_ai.client.token.usage` that is provided by the `ChatModel`.
.Events
[cols="a,a"]
|===
@@ -153,7 +156,7 @@ Additional AI model providers will be supported in a future release.
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.
The `gen_ai.client.token.usage` metrics measures number of input and output tokens used by a single model call.
IMPORTANT: The `gen_ai.client.token.usage` metrics measures number of input and output tokens used by a single model call.
.Low Cardinality Keys
[cols="a,a"]
@@ -174,6 +177,9 @@ The `gen_ai.client.token.usage` metrics measures number of input and output toke
|`gen_ai.usage.total_tokens` | The total number of tokens used in the model exchange.
|===
NOTE: For measuring user tokens, the previous table lists the values present in an observation trace.
Use the metric name `gen_ai.client.token.usage` that is provided by the `EmbeddingModel`.
== Image Model
NOTE: Observability features are currently supported only for `ImageModel` implementations from the following AI model
@@ -183,7 +189,7 @@ Additional AI model providers will be supported in a future release.
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.
The `gen_ai.client.token.usage` metrics measures number of input and output tokens used by a single model call.
IMPORTANT: The `gen_ai.client.token.usage` metrics measures number of input and output tokens used by a single model call.
.Low Cardinality Keys
@@ -209,6 +215,9 @@ The `gen_ai.client.token.usage` metrics measures number of input and output toke
|`gen_ai.prompt` | The full prompt sent to the model. Optional.
|===
NOTE: For measuring user tokens, the previous table lists the values present in an observation trace.
Use the metric name `gen_ai.client.token.usage` that is provided by the `ImageModel`.
.Events
[cols="a,a"]
|===