Use a context cache

fromgoogleimport genai
fromgoogle.genai.typesimport GenerateContentConfig, HttpOptions
client = genai.Client(http_options=HttpOptions(api_version="v1"))
# Use content cache to generate text response
# E.g cache_name = 'projects/.../locations/.../cachedContents/1111111111111111111'
response = client.models.generate_content(
 model="gemini-2.5-flash",
 contents="Summarize the pdfs",
 config=GenerateContentConfig(
 cached_content=cache_name,
 ),
)
print(response.text)
# Example response
# The Gemini family of multimodal models from Google DeepMind demonstrates remarkable capabilities across various
# modalities, including image, audio, video, and text....

import(
	"context"
	"fmt"
	"io"
	genai "google.golang.org/genai"
)
// useContentCacheWithTxt shows how to use content cache to generate text content.
func useContentCacheWithTxt(w io.Writer, cacheName string) error {
	ctx := context.Background()
	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}
	resp, err := client.Models.GenerateContent(ctx,
		"gemini-2.5-flash",
		genai.Text("Summarize the pdfs"),
		&genai.GenerateContentConfig{
			CachedContent: cacheName,
		},
	)
	if err != nil {
		return fmt.Errorf("failed to use content cache to generate content: %w", err)
	}
	respText := resp.Text()
	fmt.Fprintln(w, respText)
	// Example response:
	// The provided research paper introduces Gemini 1.5 Pro, a multimodal model capable of recalling
	// and reasoning over information fromvery long contexts (up to 10 million tokens). Key findings include:
	//
	// * **Long Context Performance:**
	// ...
	return nil
}

importcom.google.genai.Client;
importcom.google.genai.types.GenerateContentConfig;
importcom.google.genai.types.GenerateContentResponse;
importcom.google.genai.types.HttpOptions;
public classContentCacheUseWithText {
 public static void main(String[] args) {
 // TODO(developer): Replace these variables before running the sample.
 String modelId = "gemini-2.5-flash";
 // E.g cacheName = "projects/111111111111/locations/global/cachedContents/1111111111111111111"
 String cacheName = "your-cache-name";
 contentCacheUseWithText(modelId, cacheName);
 }
 // Shows how to generate text using cached content
 public static String contentCacheUseWithText(String modelId, String cacheName) {
 // 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,
 "Summarize the pdfs",
 GenerateContentConfig.builder().cachedContent(cacheName).build());
 System.out.println(response.text());
 // Example response
 // The Gemini family of multimodal models fromGoogle DeepMind demonstrates remarkable
 // capabilities across various
 // modalities, including image, audio, video, and text....
 return response.text();
 }
 }
}

const{GoogleGenAI}=require('@google/genai');
constGOOGLE_CLOUD_PROJECT=process.env.GOOGLE_CLOUD_PROJECT;
constGOOGLE_CLOUD_LOCATION=process.env.GOOGLE_CLOUD_LOCATION||'global';
asyncfunctionuseContentCache(
projectId=GOOGLE_CLOUD_PROJECT,
location=GOOGLE_CLOUD_LOCATION,
cacheName='example-cache'
){
constclient=newGoogleGenAI({
vertexai:true,
project:projectId,
location:location,
httpOptions:{
apiVersion:'v1',
},
});
constresponse=awaitclient.models.generateContent({
model:'gemini-2.5-flash',
contents:'Summarize the pdfs',
config:{
cachedContent:cacheName,
},
});
console.log(response.text);
returnresponse.text;
}
//Exampleresponse
//TheGeminifamilyofmultimodalmodelsfromGoogleDeepMinddemonstratesremarkablecapabilitiesacrossvarious
//modalities,includingimage,audio,video,andtext....