上下文缓存

import os
import pathlib
import requests
import time

from google import genai
from google.genai import types

client = genai.Client()

# Download video file
url = 'https://storage.googleapis.com/generativeai-downloads/data/SherlockJr._10min.mp4'
path_to_video_file = pathlib.Path('SherlockJr._10min.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-2.0-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)

from google import genai
from google.genai import types
import io
import httpx

client = genai.Client()

long_context_pdf_path = "https://www.nasa.gov/wp-content/uploads/static/history/alsj/a17/A17_FlightPlan.pdf"

# Retrieve and upload the PDF using the File API
doc_io = io.BytesIO(httpx.get(long_context_pdf_path).content)

document = client.files.upload(
  file=doc_io,
  config=dict(mime_type='application/pdf')
)

model_name = "gemini-2.0-flash-001"
system_instruction = "You are an expert analyzing transcripts."

# Create a cached content object
cache = client.caches.create(
    model=model_name,
    config=types.CreateCachedContentConfig(
      system_instruction=system_instruction,
      contents=[document],
    )
)

# Display the cache details
print(f'{cache=}')

# Generate content using the cached prompt and document
response = client.models.generate_content(
  model=model_name,
  contents="Please summarize this transcript",
  config=types.GenerateContentConfig(
    cached_content=cache.name
  ))

# (Optional) Print usage metadata for insights into the API call
print(f'{response.usage_metadata=}')

# Print the generated text
print('\n\n', response.text)