使用上下文缓存

from google import genai
from google.genai.types import GenerateContentConfig, HttpOptions

client = genai.Client(http_options=HttpOptions(api_version="v1"))
# Use content cache to generate text response
# E.g cache_name = 'projects/111111111111/locations/us-central1/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 from very long contexts (up to 10 million tokens).  Key findings include:
	//
	// * **Long Context Performance:**
	// ...

	return nil
}