Skip to content

feat: add new GenAI SDK count tokens samples #10145

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -0,0 +1,77 @@
/*
* Copyright 2025 Google LLC
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/

package genai.counttokens;

// [START googlegenaisdk_counttoken_compute_with_txt]

import com.google.genai.Client;
import com.google.genai.types.ComputeTokensResponse;
import com.google.genai.types.HttpOptions;
import com.google.genai.types.TokensInfo;
import java.nio.charset.StandardCharsets;
import java.util.List;
import java.util.Optional;

public class CountTokensComputeWithText {

public static void main(String[] args) {
// TODO(developer): Replace these variables before running the sample.
String modelId = "gemini-2.5-flash";
computeTokens(modelId);
}

// Computes tokens with text input
public static Optional<List<TokensInfo>> computeTokens(String modelId) {
// Initialize client that will be used to send requests. This client only needs to be created
// once, and can be reused for multiple requests.
try (Client client =
Client.builder()
.location("global")
.vertexAI(true)
.httpOptions(HttpOptions.builder().apiVersion("v1").build())
.build()) {

ComputeTokensResponse response = client.models.computeTokens(
modelId, "What's the longest word in the English language?", null);

// Print TokensInfo
response.tokensInfo().ifPresent(tokensInfoList -> {
for (TokensInfo info : tokensInfoList) {
info.role().ifPresent(role -> System.out.println("role: " + role));
info.tokenIds().ifPresent(tokenIds -> System.out.println("tokenIds: " + tokenIds));
// print tokens input as strings since they are in a form of byte array
System.out.println("tokens: ");
info.tokens().ifPresent(tokens ->
tokens.forEach(token ->
System.out.println(new String(token, StandardCharsets.UTF_8))
)
);
}
});
// Example response.tokensInfo()
// role: user
// tokenIds: [1841, 235303, 235256, 573, 32514, 2204, 575, 573, 4645, 5255, 235336]
// tokens:
// What
// '
// s
// the
return response.tokensInfo();
}
}
}
// [END googlegenaisdk_counttoken_compute_with_txt]
Original file line number Diff line number Diff line change
@@ -0,0 +1,63 @@
/*
* Copyright 2025 Google LLC
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/

package genai.counttokens;

// [START googlegenaisdk_counttoken_resp_with_txt]

import com.google.genai.Client;
import com.google.genai.types.GenerateContentResponse;
import com.google.genai.types.GenerateContentResponseUsageMetadata;
import com.google.genai.types.HttpOptions;
import java.util.Optional;

public class CountTokensResponseWithText {

public static void main(String[] args) {
// TODO(developer): Replace these variables before running the sample.
String modelId = "gemini-2.5-flash";
countTokens(modelId);
}

// Generates content response usage metadata that contains prompt and response token counts
public static Optional<GenerateContentResponseUsageMetadata> countTokens(String modelId) {
// Initialize client that will be used to send requests. This client only needs to be created
// once, and can be reused for multiple requests.
try (Client client =
Client.builder()
.location("global")
.vertexAI(true)
.httpOptions(HttpOptions.builder().apiVersion("v1").build())
.build()) {

GenerateContentResponse response =
client.models.generateContent(modelId, "Why is the sky blue?", null);

response.usageMetadata().ifPresent(System.out::println);
// Example response:
// GenerateContentResponseUsageMetadata{cacheTokensDetails=Optional.empty,
// cachedContentTokenCount=Optional.empty, candidatesTokenCount=Optional[569],
// candidatesTokensDetails=Optional[[ModalityTokenCount{modality=Optional[TEXT],
// tokenCount=Optional[569]}]], promptTokenCount=Optional[6],
// promptTokensDetails=Optional[[ModalityTokenCount{modality=Optional[TEXT],
// tokenCount=Optional[6]}]], thoughtsTokenCount=Optional[1132],
// toolUsePromptTokenCount=Optional.empty, toolUsePromptTokensDetails=Optional.empty,
// totalTokenCount=Optional[1707], trafficType=Optional[ON_DEMAND]}
return response.usageMetadata();
}
}
}
// [END googlegenaisdk_counttoken_resp_with_txt]
Original file line number Diff line number Diff line change
Expand Up @@ -19,11 +19,8 @@
// [START googlegenaisdk_counttoken_with_txt]

import com.google.genai.Client;
import com.google.genai.types.Content;
import com.google.genai.types.CountTokensResponse;
import com.google.genai.types.HttpOptions;
import com.google.genai.types.Part;
import java.util.List;
import java.util.Optional;

public class CountTokensWithText {
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,5 @@ public void testControlledGenerationWithEnumSchema() {
String prompt = "What type of instrument is an oboe?";
String response = ControlledGenerationWithEnumSchema.generateContent(GEMINI_FLASH, prompt);
assertThat(response).isNotEmpty();
assertThat(response).isEqualTo("Woodwind");
}
}
Original file line number Diff line number Diff line change
Expand Up @@ -19,8 +19,12 @@
import static com.google.common.truth.Truth.assertThat;
import static com.google.common.truth.Truth.assertWithMessage;

import com.google.genai.types.GenerateContentResponseUsageMetadata;
import com.google.genai.types.TokensInfo;
import java.io.ByteArrayOutputStream;
import java.io.PrintStream;
import java.util.ArrayList;
import java.util.List;
import java.util.Optional;
import org.junit.After;
import org.junit.Before;
Expand All @@ -32,7 +36,6 @@
@RunWith(JUnit4.class)
public class CountTokensIT {


private static final String GEMINI_FLASH = "gemini-2.5-flash";
private ByteArrayOutputStream bout;
private PrintStream out;
Expand Down Expand Up @@ -74,4 +77,37 @@ public void testCountTokensWithTextAndVideo() {
assertThat(response).isPresent();
assertThat(response.get()).isGreaterThan(6);
}

@Test
public void testCountTokensComputeWithText() {

List<TokensInfo> response =
CountTokensComputeWithText.computeTokens(GEMINI_FLASH).orElse(new ArrayList<>());

assertThat(response).isNotEmpty();
TokensInfo tokensInfo = response.get(0);

assertThat(tokensInfo.role()).isPresent();

assertThat(tokensInfo.tokenIds()).isPresent();
assertThat(tokensInfo.tokenIds().get()).isNotEmpty();

assertThat(tokensInfo.tokens()).isPresent();
assertThat(tokensInfo.tokens().get()).isNotEmpty();

}

@Test
public void testCountTokensResponseWithText() {

Optional<GenerateContentResponseUsageMetadata> response =
CountTokensResponseWithText.countTokens(GEMINI_FLASH);

assertThat(response).isPresent();
assertThat(response.get().totalTokenCount()).isPresent();
assertThat(response.get().totalTokenCount().get()).isGreaterThan(0);
assertThat(response.get().promptTokenCount()).isPresent();
assertThat(response.get().promptTokenCount().get()).isGreaterThan(0);

}
}