#is a context cache created with gemini 1

1 messages · Page 1 of 1 (latest)

silver wyvern
#

I didn't get any errors when passing in the cache but was curious if it was actually doing anything or if it was just being ignored

edgy pasture
#

can you share the code? i assume the later model name is just being ignored

silver wyvern
#

It was something like this

cache = client.caches.create(
    model="gemini-flash-1.5-001",
    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 = "gemini-flash-2.0-001",
  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)
)