Delete a context cache

This guide shows you how to delete a context cache using the Vertex AI SDK for Python or the REST API.

Before you begin

You can delete a context cache using the Vertex AI SDK for Python or the REST API. The following table helps you choose the method that best suits your use case.

Method Description Use Case
Vertex AI SDK for Python Use the google-cloud-aiplatform library to interact with the API from your Python code. Recommended for developers building applications in Python, as it simplifies authentication and API interactions.
REST API Send a direct HTTP DELETE request to the Vertex AI API endpoint. Useful for scripting in various languages, for quick tests with tools like curl, or in environments where installing a client library isn't feasible.

To delete a context cache, you need the following information:

Delete a context cache

The following examples show you how to delete a context cache.

Python

Install

pip install --upgrade google-genai

To learn more, see the SDK reference documentation.

Set environment variables to use the Gen AI SDK with Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=us-central1
export GOOGLE_GENAI_USE_VERTEXAI=True
 

from google import genai

client = genai.Client()
# Delete content cache using name
# E.g cache_name = 'projects/111111111111/locations/us-central1/cachedContents/1111111111111111111'
client.caches.delete(name=cache_name)
print("Deleted Cache", cache_name)
# Example response
#   Deleted Cache projects/111111111111/locations/us-central1/cachedContents/1111111111111111111

Go

Learn how to install or update the Go.

To learn more, see the SDK reference documentation.

Set environment variables to use the Gen AI SDK with Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=us-central1
export GOOGLE_GENAI_USE_VERTEXAI=True
 

import (
	"context"
	"fmt"
	"io"

	genai "google.golang.org/genai"
)

// deleteContentCache shows how to delete content cache.
func deleteContentCache(w io.Writer, cacheName string) error {
	ctx := context.Background()

	client, err := genai.NewClient(ctx, &genai.ClientConfig{
		HTTPOptions: genai.HTTPOptions{APIVersion: "v1"},
	})
	if err != nil {
		return fmt.Errorf("failed to create genai client: %w", err)
	}

	_, err = client.Caches.Delete(ctx, cacheName, &genai.DeleteCachedContentConfig{})
	if err != nil {
		return fmt.Errorf("failed to delete content cache: %w", err)
	}

	fmt.Fprintf(w, "Deleted cache %q\n", cacheName)

	// Example response:
	// Deleted cache "projects/111111111111/locations/us-central1/cachedContents/1111111111111111111"

	return nil
}

REST

To delete a context cache, send a DELETE request to the Vertex AI API endpoint.

Before using any of the request data, make the following replacements:

  • PROJECT_ID: Your project ID.
  • LOCATION: The region where the request to create the context cache was processed and where the cached content is stored.
  • CACHE_ID: The ID of the context cache to delete. The context cache ID is returned when you create the context cache. You can also find context cache IDs by listing the context caches for a Google Cloud project using. For more information, see create a context cache and list context caches.

HTTP method and URL: 

DELETE https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/cachedContents/CACHE_ID

To send your request, choose one of these options:

curl

Execute the following command: 

curl -X DELETE \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/cachedContents/CACHE_ID"

PowerShell

Execute the following command: 

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method DELETE `
    -Headers $headers `
    -Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/cachedContents/CACHE_ID" | Select-Object -Expand Content

If the delete operation succeeds, the response is empty:

Example curl command

LOCATION="us-central1"
PROJECT_ID="PROJECT_ID"
CACHE_ID="CACHE_ID"

curl \
-X DELETE \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
https://${LOCATION}-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${LOCATION}/${CACHE_ID}

What's next