GenerativeModelFutures
public abstract class GenerativeModelFutures
A Java-friendly wrapper for the GenerativeModel class, providing ListenableFuture for asynchronous operations.
Summary
Public methods |
|
|---|---|
abstract @NonNull ListenableFuture<@FeatureStatus @NonNull Integer> |
Checks the current availability status of the content generation feature. |
abstract @NonNull ListenableFuture<@NonNull Void> |
Clears all caches created by prefix caching. |
abstract @NonNull ListenableFuture<@NonNull CountTokensResponse> |
countTokens(@NonNull GenerateContentRequest request)Counts the number of tokens in the request. |
abstract @NonNull ListenableFuture<@NonNull Void> |
download(@NonNull DownloadCallback callback)Downloads the required model assets for the content generation feature if they are not already available. |
static final @NonNull GenerativeModelFutures |
from(@NonNull GenerativeModel generativeModel) |
abstract @NonNull ListenableFuture<@NonNull GenerateContentResponse> |
generateContent(@NonNull String prompt)Runs a non-streaming inference call to the model for the provided prompt. |
abstract @NonNull ListenableFuture<@NonNull GenerateContentResponse> |
generateContent(@NonNull GenerateContentRequest request)Runs a non-streaming inference call to the model for the provided |
abstract @NonNull ListenableFuture<@NonNull GenerateContentResponse> |
generateContent(Runs a streaming inference call to the model for the provided prompt. |
abstract @NonNull ListenableFuture<@NonNull GenerateContentResponse> |
generateContent(Runs a streaming inference call to the model for the provided |
abstract @NonNull ListenableFuture<@NonNull String> |
Returns the name of the base model used by this generator instance. |
abstract @NonNull GenerativeModel |
Returns the underlying |
abstract @NonNull ListenableFuture<@NonNull Integer> |
Returns total token limit for the API including both input and output tokens. |
abstract @NonNull ListenableFuture<@NonNull Void> |
warmup()Warms up the inference engine for use by loading necessary models. |
Public methods
checkStatus
public abstract @NonNull ListenableFuture<@FeatureStatus @NonNull Integer> checkStatus()
Checks the current availability status of the content generation feature.
clearCaches
public abstract @NonNull ListenableFuture<@NonNull Void> clearCaches()
Clears all caches created by prefix caching.
This experimental method clears all caches created by prefix caching. When promptPrefix is provided in GenerateContentRequest, the system caches its processing to reduce inference time for subsequent requests sharing the same prefix. This method clears all such created caches.
countTokens
public abstract @NonNull ListenableFuture<@NonNull CountTokensResponse> countTokens(@NonNull GenerateContentRequest request)
Counts the number of tokens in the request.
The number of tokens counted includes input and output tokens. The result can be compared with getTokenLimit to check if the request is within the token limit.
| Parameters | |
|---|---|
@NonNull GenerateContentRequest request |
a non-null |
| Returns | |
|---|---|
@NonNull ListenableFuture<@NonNull CountTokensResponse> |
a |
download
public abstract @NonNull ListenableFuture<@NonNull Void> download(@NonNull DownloadCallback callback)
Downloads the required model assets for the content generation feature if they are not already available.
from
public static final @NonNull GenerativeModelFutures from(@NonNull GenerativeModel generativeModel)
| Parameters | |
|---|---|
@NonNull GenerativeModel generativeModel |
the |
| Returns | |
|---|---|
@NonNull GenerativeModelFutures |
a |
generateContent
public abstract @NonNull ListenableFuture<@NonNull GenerateContentResponse> generateContent(@NonNull String prompt)
Runs a non-streaming inference call to the model for the provided prompt.
generateContent
public abstract @NonNull ListenableFuture<@NonNull GenerateContentResponse> generateContent(@NonNull GenerateContentRequest request)
Runs a non-streaming inference call to the model for the provided GenerateContentRequest.
generateContent
public abstract @NonNull ListenableFuture<@NonNull GenerateContentResponse> generateContent(
@NonNull String prompt,
@NonNull StreamingCallback callback
)
Runs a streaming inference call to the model for the provided prompt.
| Parameters | |
|---|---|
@NonNull String prompt |
the input prompt text. |
@NonNull StreamingCallback callback |
the callback to receive streaming results. |
| Returns | |
|---|---|
@NonNull ListenableFuture<@NonNull GenerateContentResponse> |
a |
generateContent
public abstract @NonNull ListenableFuture<@NonNull GenerateContentResponse> generateContent(
@NonNull GenerateContentRequest request,
@NonNull StreamingCallback callback
)
Runs a streaming inference call to the model for the provided GenerateContentRequest.
| Parameters | |
|---|---|
@NonNull GenerateContentRequest request |
the request containing the prompt of text and images. |
@NonNull StreamingCallback callback |
the callback to receive streaming results. |
| Returns | |
|---|---|
@NonNull ListenableFuture<@NonNull GenerateContentResponse> |
A |
getBaseModelName
public abstract @NonNull ListenableFuture<@NonNull String> getBaseModelName()
Returns the name of the base model used by this generator instance.
getGenerativeModel
public abstract @NonNull GenerativeModel getGenerativeModel()
Returns the underlying GenerativeModel instance that was used to create this object.
getTokenLimit
public abstract @NonNull ListenableFuture<@NonNull Integer> getTokenLimit()
Returns total token limit for the API including both input and output tokens.
This limit can be used with countTokens to check if a request is within limits before running inference. The input size returned by countTokens plusing the output size specified by GenerateContentRequest.maxOutputTokens should be no larger than the limit returned by this method.
| Returns | |
|---|---|
@NonNull ListenableFuture<@NonNull Integer> |
a |
warmup
public abstract @NonNull ListenableFuture<@NonNull Void> warmup()
Warms up the inference engine for use by loading necessary models.