Context caching

import os
import pathlib
import requests
import time

from google import genai
from google.genai import types

client = genai.Client()

# Download a test video file and save it locally
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():
    path_to_video_file.write_bytes(requests.get(url).content)

# 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':
    time.sleep(2.5)
    video_file = client.files.get(name=video_file.name)

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

model='models/gemini-3-flash-preview'

# Create a cache with a 5 minute TTL (300 seconds)
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",
    )
)

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)

print(response.text)

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

client = genai.Client()

long_context_pdf_path = "https://sma.nasa.gov/SignificantIncidents/assets/a11_missionreport.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-3-flash-preview"
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],
    )
)

print(f'{cache=}')

response = client.models.generate_content(
  model=model_name,
  contents="Please summarize this transcript",
  config=types.GenerateContentConfig(
    cached_content=cache.name
  ))

print(f'{response.usage_metadata=}')

print('\n\n', response.text)

wget https://storage.googleapis.com/generativeai-downloads/data/a11.txt
echo '{
  "model": "models/gemini-3-flash-preview",
  "contents":[
    {
      "parts":[
        {
          "inline_data": {
            "mime_type":"text/plain",
            "data": "'$(base64 $B64FLAGS a11.txt)'"
          }
        }
      ],
    "role": "user"
    }
  ],
  "systemInstruction": {
    "parts": [
      {
        "text": "You are an expert at analyzing transcripts."
      }
    ]
  },
  "ttl": "300s"
}' > request.json

curl -X POST "https://generativelanguage.googleapis.com/v1beta/cachedContents?key=$GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d @request.json \
> cache.json

CACHE_NAME=$(cat cache.json | grep '"name":' | cut -d '"' -f 4 | head -n 1)

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-3-flash-preview:generateContent?key=$GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
      "contents": [
        {
          "parts":[{
            "text": "Please summarize this transcript"
          }],
          "role": "user"
        },
      ],
      "cachedContent": "'$CACHE_NAME'"
    }'

DOC_URL="https://sma.nasa.gov/SignificantIncidents/assets/a11_missionreport.pdf"
DISPLAY_NAME="A11_Mission_Report"
SYSTEM_INSTRUCTION="You are an expert at analyzing transcripts."
PROMPT="Please summarize this transcript"
MODEL="models/gemini-3-flash-preview"
TTL="300s"

# Download the PDF
wget -O "${DISPLAY_NAME}.pdf" "${DOC_URL}"

MIME_TYPE=$(file -b --mime-type "${DISPLAY_NAME}.pdf")
NUM_BYTES=$(wc -c < "${DISPLAY_NAME}.pdf")

echo "MIME_TYPE: ${MIME_TYPE}"
echo "NUM_BYTES: ${NUM_BYTES}"

tmp_header_file=upload-header.tmp

# Initial resumable request defining metadata.
# The upload url is in the response headers dump them to a file.
curl "${BASE_URL}/upload/v1beta/files?key=${GOOGLE_API_KEY}" \
  -D upload-header.tmp \
  -H "X-Goog-Upload-Protocol: resumable" \
  -H "X-Goog-Upload-Command: start" \
  -H "X-Goog-Upload-Header-Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Header-Content-Type: ${MIME_TYPE}" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null

upload_url=$(grep -i "x-goog-upload-url: " "${tmp_header_file}" | cut -d" " -f2 | tr -d "\r")
rm "${tmp_header_file}"

# Upload the actual bytes.
curl "${upload_url}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${DISPLAY_NAME}.pdf" 2> /dev/null > file_info.json

file_uri=$(jq ".file.uri" file_info.json)
echo "file_uri: ${file_uri}"

# Clean up the downloaded PDF
rm "${DISPLAY_NAME}.pdf"

# Create the cached content request
echo '{
  "model": "'$MODEL'",
  "contents":[
    {
      "parts":[
        {"file_data": {"mime_type": "'$MIME_TYPE'", "file_uri": '$file_uri'}}
      ],
    "role": "user"
    }
  ],
  "system_instruction": {
    "parts": [
      {
        "text": "'$SYSTEM_INSTRUCTION'"
      }
    ],
    "role": "system"
  },
  "ttl": "'$TTL'"
}' > request.json

# Send the cached content request
curl -X POST "${BASE_URL}/v1beta/cachedContents?key=$GOOGLE_API_KEY" \
-H 'Content-Type: application/json' \
-d @request.json \
> cache.json

CACHE_NAME=$(cat cache.json | grep '"name":' | cut -d '"' -f 4 | head -n 1)
echo "CACHE_NAME: ${CACHE_NAME}"
# Send the generateContent request using the cached content
curl -X POST "${BASE_URL}/${MODEL}:generateContent?key=$GOOGLE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
      "contents": [
        {
          "parts":[{
            "text": "'$PROMPT'"
          }],
          "role": "user"
        }
      ],
      "cachedContent": "'$CACHE_NAME'"
    }' > response.json

cat response.json

echo jq ".candidates[].content.parts[].text" response.json