Skip to content

fix: Anthropic prompt caching on GCP Vertex AI #9605

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Mar 30, 2025
Merged

fix: Anthropic prompt caching on GCP Vertex AI #9605

Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2a6d6df
fix: Anthropic prompt caching on GCP Vertex AI
sammcj Mar 27, 2025
0cea7ef
Merge branch 'main' into gcp_prompt_caching
sammcj Mar 28, 2025
688c4f8
test(vertex): anthropic prompt caching
sammcj Mar 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions litellm/llms/anthropic/chat/transformation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,9 +143,15 @@ def get_anthropic_headers(
if user_anthropic_beta_headers is not None:
betas.update(user_anthropic_beta_headers)

# Don't send any beta headers to Vertex, Vertex has failed requests when they are sent
# Handle beta headers for Vertex AI
# We allow prompt caching beta header for Vertex, but exclude other beta headers that might cause issues
if is_vertex_request is True:
pass
vertex_safe_betas = set()
# Allow prompt caching beta header for Vertex
if "prompt-caching-2024-07-31" in betas:
vertex_safe_betas.add("prompt-caching-2024-07-31")
if len(vertex_safe_betas) > 0:
headers["anthropic-beta"] = ",".join(vertex_safe_betas)
elif len(betas) > 0:
headers["anthropic-beta"] = ",".join(betas)

Expand Down
Loading