This version is still in development and is not considered stable yet. For the latest snapshot version, please use Spring AI 1.0.0-SNAPSHOT!spring-doc.cn
Low cardinality keys will be added to metrics and traces, while high cardinality keys will only be added to traces.
Table 1. Low cardinality Keys

Namespring-doc.cn

Descriptionspring-doc.cn

gen_ai.operation.namespring-doc.cn

frameworkspring-doc.cn

gen_ai.systemspring-doc.cn

spring_aispring-doc.cn

spring.ai.kindspring-doc.cn

Spring AI kind - chat_clientspring-doc.cn

spring.ai.chat.client.streamspring-doc.cn

Is the chat model response a stream - true or falsespring-doc.cn
Table 2. High cardinality Keys

Namespring-doc.cn

Descriptionspring-doc.cn

spring.ai.chat.client.advisor.paramsspring-doc.cn

Map of advisor parameters.spring-doc.cn

spring.ai.chat.client.advisorsspring-doc.cn

List of configured chat client advisors.spring-doc.cn

spring.ai.chat.client.streamspring-doc.cn

Is the chat model response a stream.spring-doc.cn

spring.ai.chat.client.system.paramsspring-doc.cn

Chat client system parameters.spring-doc.cn

spring.ai.chat.client.system.textspring-doc.cn

Chat client system text.spring-doc.cn

spring.ai.chat.client.tool.function.namesspring-doc.cn

Enabled tool function names.spring-doc.cn

spring.ai.chat.client.tool.functioncallbacksspring-doc.cn

List of configured chat client function callbacks.spring-doc.cn

spring.ai.chat.client.user.paramsspring-doc.cn

Chat client user parameters.spring-doc.cn

spring.ai.chat.client.user.textspring-doc.cn

Chat client user text.spring-doc.cn

Propertyspring-doc.cn

Descriptionspring-doc.cn

Defaultspring-doc.cn

spring.ai.chat.client.observations.include-inputspring-doc.cn

Enables the inclusion of the input content in the observations. This brings the risk of exposing sensitive or private information. Please, be careful!spring-doc.cn

falsespring-doc.cn
Table 3. Low Cardinality Keys

Namespring-doc.cn

Descriptionspring-doc.cn

spring.ai.kindspring-doc.cn

Spring AI kind - chat_client_advisorspring-doc.cn

spring.ai.chat.client.advisor.typespring-doc.cn

Where the advisor applies it’s logic in the request processing, one of BEFORE, AFTER, or AROUND.spring-doc.cn
Table 4. High Cardinality Keys

Namespring-doc.cn

Descriptionspring-doc.cn

spring.ai.chat.client.advisor.namespring-doc.cn

Name of the advisorspring-doc.cn
Observability features are currently supported only for ChatModel and EmbeddingModel implementations from the following AI model providers: OpenAI, Ollama, Anthropic, and Mistral. Additional AI model providers will be supported in a future release.
Table 5. Low Cardinality Keys

Namespring-doc.cn

Descriptionspring-doc.cn

gen_ai.operation.namespring-doc.cn

The name of the operation being performed.spring-doc.cn

gen_ai.systemspring-doc.cn

The model provider as identified by the client instrumentation.spring-doc.cn

gen_ai.request.modelspring-doc.cn

The name of the model a request is being made to.spring-doc.cn

gen_ai.response.modelspring-doc.cn

The name of the model that generated the response.spring-doc.cn
Table 6. High Cardinality Keys

Namespring-doc.cn

Descriptionspring-doc.cn

gen_ai.request.frequency_penaltyspring-doc.cn

The frequency penalty setting for the model request.spring-doc.cn

gen_ai.request.max_tokensspring-doc.cn

The maximum number of tokens the model generates for a request.spring-doc.cn

gen_ai.request.presence_penaltyspring-doc.cn

The presence penalty setting for the model request.spring-doc.cn

gen_ai.request.stop_sequencesspring-doc.cn

List of sequences that the model will use to stop generating further tokens.spring-doc.cn

gen_ai.request.temperaturespring-doc.cn

The temperature setting for the model request.spring-doc.cn

gen_ai.request.top_kspring-doc.cn

The top_k sampling setting for the model request.spring-doc.cn

gen_ai.request.top_pspring-doc.cn

The top_p sampling setting for the model request.spring-doc.cn

gen_ai.response.finish_reasonsspring-doc.cn

Reasons the model stopped generating tokens, corresponding to each generation received.spring-doc.cn

gen_ai.response.idspring-doc.cn

The unique identifier for the AI response.spring-doc.cn

gen_ai.usage.input_tokensspring-doc.cn

The number of tokens used in the model input (prompt).spring-doc.cn

gen_ai.usage.output_tokensspring-doc.cn

The number of tokens used in the model output (completion).spring-doc.cn

gen_ai.usage.total_tokensspring-doc.cn

The total number of tokens used in the model exchange.spring-doc.cn

gen_ai.promptspring-doc.cn

The full prompt sent to the model.spring-doc.cn

gen_ai.completionspring-doc.cn

The full response received from the model.spring-doc.cn

Propertyspring-doc.cn

Descriptionspring-doc.cn

Defaultspring-doc.cn

spring.ai.chat.observations.include-promptspring-doc.cn

true or falsespring-doc.cn

falsespring-doc.cn

spring.ai.chat.observations.include-completionspring-doc.cn

true or falsespring-doc.cn

falsespring-doc.cn
Observability features are currently supported only for ChatModel and EmbeddingModel implementations from the following AI model providers: OpenAI, Ollama, Anthropic, and Mistral. Additional AI model providers will be supported in a future release.
Table 7. Low Cardinality Keys

Namespring-doc.cn

Descriptionspring-doc.cn

gen_ai.operation.namespring-doc.cn

The name of the operation being performed.spring-doc.cn

gen_ai.systemspring-doc.cn

The model provider as identified by the client instrumentation.spring-doc.cn

gen_ai.request.modelspring-doc.cn

The name of the model a request is being made to.spring-doc.cn

gen_ai.response.modelspring-doc.cn

The name of the model that generated the response.spring-doc.cn
Table 8. High Cardinality Keys

Namespring-doc.cn

Descriptionspring-doc.cn

gen_ai.request.embedding.dimensionsspring-doc.cn

The number of dimensions the resulting output embeddings have.spring-doc.cn

gen_ai.usage.input_tokensspring-doc.cn

The number of tokens used in the model input.spring-doc.cn

gen_ai.usage.total_tokensspring-doc.cn

The total number of tokens used in the model exchange.spring-doc.cn
Table 9. Low Cardinality Keys

Namespring-doc.cn

Descriptionspring-doc.cn

gen_ai.operation.namespring-doc.cn

The name of the operation being performed.spring-doc.cn

gen_ai.systemspring-doc.cn

The model provider as identified by the client instrumentation.spring-doc.cn

gen_ai.request.modelspring-doc.cn

The name of the model a request is being made to.spring-doc.cn
Table 10. High Cardinality Keys

Namespring-doc.cn

Descriptionspring-doc.cn

gen_ai.request.image.response_formatspring-doc.cn

The format in which the generated image is returned.spring-doc.cn

gen_ai.request.image.sizespring-doc.cn

The size of the image to generate.spring-doc.cn

gen_ai.request.image.stylespring-doc.cn

The style of the image to generate.spring-doc.cn

gen_ai.response.idspring-doc.cn

The unique identifier for the AI response.spring-doc.cn

gen_ai.response.modelspring-doc.cn

The name of the model that generated the response.spring-doc.cn

gen_ai.usage.input_tokensspring-doc.cn

The number of tokens used in the model input (prompt).spring-doc.cn

gen_ai.usage.output_tokensspring-doc.cn

The number of tokens used in the model output (generation).spring-doc.cn

gen_ai.usage.total_tokensspring-doc.cn

The total number of tokens used in the model exchange.spring-doc.cn

gen_ai.promptspring-doc.cn

The full prompt sent to the model.spring-doc.cn

Propertyspring-doc.cn

Descriptionspring-doc.cn

Defaultspring-doc.cn

spring.ai.image.observations.include-promptspring-doc.cn

true or falsespring-doc.cn

falsespring-doc.cn
Table 11. Low Cardinality Keys

Namespring-doc.cn

Descriptionspring-doc.cn

spring.ai.kindspring-doc.cn

Spring AI kind - vector_storespring-doc.cn

db.systemspring-doc.cn

The database management system (DBMS) product as identified by the client instrumentation. One of pg_vector, azure, cassandra, chroma, elasticsearch, milvus, neo4j, opensearch, qdrant, redis, typesense, weaviate, pinecone, oracle, mongodb, gemfire, hana, simplespring-doc.cn

db.operation.namespring-doc.cn

The name of the operation or command being executed. One of add, delete, or query.spring-doc.cn
Table 12. High Cardinality Keys

Namespring-doc.cn

Descriptionspring-doc.cn

db.collection.namespring-doc.cn

The name of a collection (table, container) within the database.spring-doc.cn

db.vector.dimension_countspring-doc.cn

The dimension of the vector.spring-doc.cn

db.vector.field_namespring-doc.cn

The name field as of the vector (e.g. a field name).spring-doc.cn

db.vector.query.filterspring-doc.cn

The metadata filters used in the search query.spring-doc.cn

db.namespacespring-doc.cn

The namespace of the database.spring-doc.cn

db.vector.query.contentspring-doc.cn

The content of the search query being executed.spring-doc.cn

db.vector.query.response.documentsspring-doc.cn

Returned documents from a similarity search query. Needs to be enabled with auto-configuration and use of OpenTelemetry events.spring-doc.cn

db.vector.similarity_metricspring-doc.cn

The metric used in similarity search.spring-doc.cn

db.vector.query.similarity_thresholdspring-doc.cn

Similarity threshold that accepts all search scores. A threshold value of 0.0 means any similarity is accepted or disable the similarity threshold filtering. A threshold value of 1.0 means an exact match is required.spring-doc.cn

db.vector.query.top_kspring-doc.cn

The top-k most similar vectors returned by a query.spring-doc.cn

Propertyspring-doc.cn

Descriptionspring-doc.cn

Defaultspring-doc.cn

spring.ai.vectorstore.observations.include-query-responsespring-doc.cn

true or falsespring-doc.cn

falsespring-doc.cn