上下文缓存

import os
import pathlib
import requests
import time

from google import genai
from google.genai import types

# Get your API key from https://aistudio.google.com/app/apikey
# Put it in a "GOOGLE_API_KEY" environment variable.
# For more details, see
# https://github.com/google-gemini/cookbook/blob/main/quickstarts/Authentication.ipynb
client = genai.Client()

# Download video file
url = 'https://storage.googleapis.com/generativeai-downloads/data/Sherlock_Jr_FullMovie.mp4'
path_to_video_file = pathlib.Path('Sherlock_Jr_FullMovie.mp4')
if not path_to_video_file.exists():
  with path_to_video_file.open('wb') as wf:
    response = requests.get(url, stream=True)
    for chunk in response.iter_content(chunk_size=32768):
      wf.write(chunk)

# Upload the video using the Files API
video_file = client.files.upload(file=path_to_video_file)

# Wait for the file to finish processing
while video_file.state.name == 'PROCESSING':
  print('Waiting for video to be processed.')
  time.sleep(2)
  video_file = client.files.get(name=video_file.name)

print(f'Video processing complete: {video_file.uri}')

# You must use an explicit version suffix. "-flash-001", not just "-flash".
model='models/gemini-1.5-flash-001'

# Create a cache with a 5 minute TTL
cache = client.caches.create(
    model=model,
    config=types.CreateCachedContentConfig(
      display_name='sherlock jr movie', # used to identify the cache
      system_instruction=(
          'You are an expert video analyzer, and your job is to answer '
          'the user\'s query based on the video file you have access to.'
      ),
      contents=[video_file],
      ttl="300s",
  )
)

# Construct a GenerativeModel which uses the created cache.
response = client.models.generate_content(
  model = model,
  contents= (
    'Introduce different characters in the movie by describing '
    'their personality, looks, and names. Also list the timestamps '
    'they were introduced for the first time.'),
  config=types.GenerateContentConfig(cached_content=cache.name)
)

print(response.usage_metadata)

# The output should look something like this:
#
# prompt_token_count: 696219
# cached_content_token_count: 696190
# candidates_token_count: 214
# total_token_count: 696433

print(response.text)

for cache in client.caches.list():
  print(cache)

client.caches.get(name=name)

from google import genai
from google.genai import types

client.caches.update(
  name = cache.name,
  config  = types.UpdateCachedContentConfig(
      ttl='300s'
  )
)

from google import genai
from google.genai import types
import datetime

# You must use a time zone-aware time.
in10min = datetime.datetime.now(datetime.timezone.utc) + datetime.timedelta(minutes=10)

client.caches.update(
  name = cache.name,
  config  = types.UpdateCachedContentConfig(
      expire_time=in10min
  )
)

client.caches.delete(cache.name)