Gemini 명시적 캐싱(cachedContents)

from google import genai
from google.genai import types
 
client = genai.Client(
    api_key="<당신의 OFOXAI_API_KEY>",
    http_options={"api_version": "v1beta", "base_url": "https://api.ofox.ai/gemini"},
)
 
# 반복 사용되는 대용량 문서(최소 토큰 임계값을 충족해야 함)
LONG_DOCUMENT = open("knowledge_base.txt").read()
 
cache = client.caches.create(
    model="google/gemini-3.1-pro-preview",
    config=types.CreateCachedContentConfig(
        contents=[LONG_DOCUMENT],
        ttl="600s",  # 캐시 존속 10분
    ),
)
 
print(cache.name)  # cachedContents/xxxxxxxx —— 이후 참조에 사용할 핸들

import { GoogleGenAI } from '@google/genai'
import fs from 'node:fs'
 
const ai = new GoogleGenAI({
  apiKey: '<당신의 OFOXAI_API_KEY>',
  httpOptions: { apiVersion: 'v1beta', baseUrl: 'https://api.ofox.ai/gemini' },
})
 
const longDocument = fs.readFileSync('knowledge_base.txt', 'utf-8')
 
const cache = await ai.caches.create({
  model: 'google/gemini-3.1-pro-preview',
  config: {
    contents: [longDocument],
    ttl: '600s', // 캐시 존속 10분
  },
})
 
console.log(cache.name) // cachedContents/xxxxxxxx —— 이후 참조에 사용할 핸들

curl "https://api.ofox.ai/gemini/v1beta/cachedContents" \
  -H "x-goog-api-key: $OFOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.1-pro-preview",
    "contents": [
      { "role": "user", "parts": [{ "text": "<여기에 재사용할 대용량 컨텍스트를 넣으세요>" }] }
    ],
    "ttl": "600s"
  }'

response = client.models.generate_content(
    model="google/gemini-3.1-pro-preview",
    contents="根据上面的文档，总结三条要点",
    config=types.GenerateContentConfig(
        cached_content=cache.name,  # 캐시 참조
    ),
)
 
print(response.text)
# 캐시 적중: 캐싱된 부분은 더 낮은 「읽기」 가격으로 과금됨
print(response.usage_metadata.cached_content_token_count)

const response = await ai.models.generateContent({
  model: 'google/gemini-3.1-pro-preview',
  contents: '根据上面的文档，总结三条要点',
  config: {
    cachedContent: cache.name, // 캐시 참조
  },
})
 
console.log(response.text)
// 캐시 적중: 캐싱된 부분은 더 낮은 「읽기」 가격으로 과금됨
console.log(response.usageMetadata?.cachedContentTokenCount)

curl "https://api.ofox.ai/gemini/v1beta/models/google/gemini-3.1-pro-preview:generateContent" \
  -H "x-goog-api-key: $OFOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "cachedContent": "cachedContents/xxxxxxxx",
    "contents": [
      { "role": "user", "parts": [{ "text": "根据上面的文档，总结三条要点" }] }
    ]
  }'

# 조회
info = client.caches.get(name=cache.name)
print(info.expire_time)
 
# 삭제
client.caches.delete(name=cache.name)

// 조회
const info = await ai.caches.get({ name: cache.name })
console.log(info.expireTime)
 
// 삭제
await ai.caches.delete({ name: cache.name })

# 조회
curl "https://api.ofox.ai/gemini/v1beta/cachedContents/xxxxxxxx" \
  -H "x-goog-api-key: $OFOX_API_KEY"
 
# 삭제
curl -X DELETE "https://api.ofox.ai/gemini/v1beta/cachedContents/xxxxxxxx" \
  -H "x-goog-api-key: $OFOX_API_KEY"