LogprobsResult

All Implemented Interfaces:
```
public abstract class LogprobsResult
extends JsonSerializable
                    
```
The log probabilities of the tokens generated by the model. This is useful for understanding the model's confidence in its predictions and for debugging. For example, you can use log probabilities to identify when the model is making a less confident prediction or to explore alternative responses that the model considered. A low log probability can also indicate that the model is "hallucinating" or generating factually incorrect information.

Nested Class Summary

Nested Classes
Modifier and Type	Class	Description
`public abstract class`	`LogprobsResult.Builder`	Builder for LogprobsResult.

Field Summary

Fields
Modifier and Type	Field	Description
`public final static String`	`MAX_READ_LENGTH_PROPERTY`

Constructor Summary

Constructors
Constructor	Description
`LogprobsResult()`

Enum Constant Summary

Enum Constants
Enum Constant	Description

Method Summary

Modifier and Type	Method	Description
`abstract Optional<List<LogprobsResultCandidate>>`	`chosenCandidates()`	A list of the chosen candidate tokens at each decoding step.
`abstract Optional<List<LogprobsResultTopCandidates>>`	`topCandidates()`	A list of the top candidate tokens at each decoding step.
`abstract Optional<Float>`	`logProbabilitySum()`	Sum of log probabilities for all tokens.
`static LogprobsResult.Builder`	`builder()`	Instantiates a builder for LogprobsResult.
`abstract LogprobsResult.Builder`	`toBuilder()`	Creates a builder with the same values as this instance.
`static LogprobsResult`	`fromJson(String jsonString)`	Deserializes a JSON string to a LogprobsResult object.

Methods inherited from class com.google.genai.JsonSerializable
fromJsonNode, fromJsonString, objectMapper, setMaxReadLength, stringToJsonNode, toJson, toJsonNode, toJsonString
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Constructor Detail
  - LogprobsResult
```
LogprobsResult()
```
- Method Detail
  - chosenCandidates
```
 abstract Optional<List<LogprobsResultCandidate>> chosenCandidates()
```
    A list of the chosen candidate tokens at each decoding step. The length of this list is equal to the total number of decoding steps. Note that the chosen candidate might not be in `top_candidates`.
  - topCandidates
```
 abstract Optional<List<LogprobsResultTopCandidates>> topCandidates()
```
    A list of the top candidate tokens at each decoding step. The length of this list is equal to the total number of decoding steps.
  - logProbabilitySum
```
 abstract Optional<Float> logProbabilitySum()
```
    Sum of log probabilities for all tokens. This field is not supported in Vertex AI.
  - builder
```
 static LogprobsResult.Builder builder()
```
    Instantiates a builder for LogprobsResult.
  - toBuilder
```
 abstract LogprobsResult.Builder toBuilder()
```
    Creates a builder with the same values as this instance.
  - fromJson
```
 static LogprobsResult fromJson(String jsonString)
```
    Deserializes a JSON string to a LogprobsResult object.