Package org.springframework.ai.chat.observation

Enum Class ChatModelObservationDocumentation.HighCardinalityKeyNames

java.lang.Object

java.lang.Enum<ChatModelObservationDocumentation.HighCardinalityKeyNames>

org.springframework.ai.chat.observation.ChatModelObservationDocumentation.HighCardinalityKeyNames

All Implemented Interfaces:

io.micrometer.common.docs.KeyName, Serializable, Comparable<ChatModelObservationDocumentation.HighCardinalityKeyNames>, Constable

Enclosing class:

ChatModelObservationDocumentation

public static enum ChatModelObservationDocumentation.HighCardinalityKeyNames
extends Enum<ChatModelObservationDocumentation.HighCardinalityKeyNames>
implements io.micrometer.common.docs.KeyName

High-cardinality observation key names for chat model operations.

Nested Class Summary

Nested classes/interfaces inherited from class java.lang.Enum

Enum.EnumDesc<E extends Enum<E>>

Enum Constant Summary

Enum Constants

Enum Constant	Description
COMPLETION	The full response received from the model.
PROMPT	The full prompt sent to the model.
REQUEST_FREQUENCY_PENALTY	The frequency penalty setting for the model request.
REQUEST_MAX_TOKENS	The maximum number of tokens the model generates for a request.
REQUEST_PRESENCE_PENALTY	The presence penalty setting for the model request.
REQUEST_STOP_SEQUENCES	List of sequences that the model will use to stop generating further tokens.
REQUEST_TEMPERATURE	The temperature setting for the model request.
REQUEST_TOP_K	The top_k sampling setting for the model request.
REQUEST_TOP_P	The top_p sampling setting for the model request.
RESPONSE_FINISH_REASONS	Reasons the model stopped generating tokens, corresponding to each generation received.
RESPONSE_ID	The unique identifier for the AI response.
USAGE_INPUT_TOKENS	The number of tokens used in the model input (prompt).
USAGE_OUTPUT_TOKENS	The number of tokens used in the model output (completion).
USAGE_TOTAL_TOKENS	The total number of tokens used in the model exchange.

Method Summary

Modifier and Type	Method	Description
static ChatModelObservationDocumentation.HighCardinalityKeyNames	valueOf(String name)	Returns the enum constant of this class with the specified name.
static ChatModelObservationDocumentation.HighCardinalityKeyNames[]	values()	Returns an array containing the constants of this enum class, in the order they are declared.

Methods inherited from class java.lang.Enum

clone, compareTo, describeConstable, equals, finalize, getDeclaringClass, hashCode, name, ordinal, toString, valueOf

Methods inherited from class java.lang.Object

getClass, notify, notifyAll, wait, wait, wait

Methods inherited from interface io.micrometer.common.docs.KeyName

asString, isRequired, withValue, withValue

Enum Constant Details

REQUEST_FREQUENCY_PENALTY

public static final ChatModelObservationDocumentation.HighCardinalityKeyNames REQUEST_FREQUENCY_PENALTY

The frequency penalty setting for the model request.

REQUEST_MAX_TOKENS

public static final ChatModelObservationDocumentation.HighCardinalityKeyNames REQUEST_MAX_TOKENS

The maximum number of tokens the model generates for a request.

REQUEST_PRESENCE_PENALTY

public static final ChatModelObservationDocumentation.HighCardinalityKeyNames REQUEST_PRESENCE_PENALTY

The presence penalty setting for the model request.

REQUEST_STOP_SEQUENCES

public static final ChatModelObservationDocumentation.HighCardinalityKeyNames REQUEST_STOP_SEQUENCES

List of sequences that the model will use to stop generating further tokens.

REQUEST_TEMPERATURE

public static final ChatModelObservationDocumentation.HighCardinalityKeyNames REQUEST_TEMPERATURE

The temperature setting for the model request.

REQUEST_TOP_K

public static final ChatModelObservationDocumentation.HighCardinalityKeyNames REQUEST_TOP_K

The top_k sampling setting for the model request.

REQUEST_TOP_P

public static final ChatModelObservationDocumentation.HighCardinalityKeyNames REQUEST_TOP_P

The top_p sampling setting for the model request.

RESPONSE_FINISH_REASONS

public static final ChatModelObservationDocumentation.HighCardinalityKeyNames RESPONSE_FINISH_REASONS

Reasons the model stopped generating tokens, corresponding to each generation received.

RESPONSE_ID

public static final ChatModelObservationDocumentation.HighCardinalityKeyNames RESPONSE_ID

The unique identifier for the AI response.

USAGE_INPUT_TOKENS

public static final ChatModelObservationDocumentation.HighCardinalityKeyNames USAGE_INPUT_TOKENS

The number of tokens used in the model input (prompt).

USAGE_OUTPUT_TOKENS

public static final ChatModelObservationDocumentation.HighCardinalityKeyNames USAGE_OUTPUT_TOKENS

The number of tokens used in the model output (completion).

USAGE_TOTAL_TOKENS

public static final ChatModelObservationDocumentation.HighCardinalityKeyNames USAGE_TOTAL_TOKENS

The total number of tokens used in the model exchange.

PROMPT

public static final ChatModelObservationDocumentation.HighCardinalityKeyNames PROMPT

The full prompt sent to the model.

COMPLETION

public static final ChatModelObservationDocumentation.HighCardinalityKeyNames COMPLETION

The full response received from the model.

Method Details

values

public static ChatModelObservationDocumentation.HighCardinalityKeyNames[] values()

Returns an array containing the constants of this enum class, in the order they are declared.

Returns:

an array containing the constants of this enum class, in the order they are declared

valueOf

public static ChatModelObservationDocumentation.HighCardinalityKeyNames valueOf(String name)

Returns the enum constant of this class with the specified name. The string must match exactly an identifier used to declare an enum constant in this class. (Extraneous whitespace characters are not permitted.)

Parameters:

name - the name of the enum constant to be returned.

Returns:

the enum constant with the specified name

Throws:

IllegalArgumentException - if this enum class has no constant with the specified name

NullPointerException - if the argument is null