Skip to content

Add bedrock latency optimized inference support + Vertex AI Multimodal embedding cost tracking #9623

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

Jump to bottom
Merged
merged 17 commits into from
Mar 29, 2025
Merged

Add bedrock latency optimized inference support + Vertex AI Multimodal embedding cost tracking #9623

merged 17 commits into from
Mar 29, 2025

Conversation

krrishdholakia
Copy link
Contributor

@krrishdholakia krrishdholakia commented Mar 28, 2025 •
edited
Loading

  • fix(converse_transformation.py): add performanceConfig param support on bedrock

Closes #7606

  • fix(converse_transformation.py): refactor to use more flexible single getter for params which are separate config blocks

  • test(test_main.py): add e2e mock test for bedrock performance config

  • build(model_prices_and_context_window.json): add versioned multimodal embedding

  • refactor(multimodal_embeddings/): migrate to config pattern

  • feat(vertex_ai/multimodalembeddings): calculate usage for multimodal embedding calls

Enables cost calculation for multimodal embeddings

  • feat(vertex_ai/multimodalembeddings): get usage object for embedding calls

ensures accurate cost tracking for vertexai multimodal embedding calls

  • fix(embedding_handler.py): remove unused imports

  • fix: fix linting errors

  • fix: handle response api usage calculation

  • test(test_vertex_ai_multimodal_embedding_transformation.py): update tests

  • test: mark flaky test

  • feat(vertex_ai/multimodal_embeddings/transformation.py): support text+image+video input

  • docs(vertex.md): document sending text + image to vertex multimodal embeddings

  • test: remove incorrect file

  • fix(multimodal_embeddings/transformation.py): fix linting error

  • style: remove unused import

@vercel Vercel
Copy link

vercel bot commented Mar 28, 2025 •
edited
Loading

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Comments Updated (UTC)
litellm ✅ Ready (Inspect) Visit Preview 💬 Add feedback Mar 29, 2025 3:19am

@krrishdholakia
feat(vertex_ai/multimodalembeddings): calculate usage for multimodal …
93f3386 
…embedding calls

Enables cost calculation for multimodal embeddings
@krrishdholakia
feat(vertex_ai/multimodalembeddings): get usage object for embedding …
8712d76 
…calls

ensures accurate cost tracking for vertexai multimodal embedding calls
github-advanced-security[bot]
github-advanced-security bot found potential problems Mar 29, 2025
View reviewed changes
litellm/cost_calculator.py
return Usage(**usage_obj.model_dump())
else:
verbose_logger.debug(
f"Unknown usage object type: {type(usage_obj)}, usage_obj: {usage_obj}"

Check failure

Code scanning / CodeQL

Clear-text logging of sensitive information High

This expression logs
sensitive data (password)
Loading
as clear text.
This expression logs
sensitive data (password)
Loading
as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (secret) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.
This expression logs sensitive data (password) as clear text.

Copilot Autofix

AI 6 months ago

To fix the problem, we need to ensure that sensitive information is not logged in clear text. The best way to fix this without changing existing functionality is to redact or mask the sensitive information before logging it. Specifically, we should modify the logging statement on line 492 in litellm/cost_calculator.py to exclude or mask the sensitive data.

Suggested changeset 1
litellm/cost_calculator.py

Autofix patch

Autofix patch
Run the following command in your local git repository to apply this patch
cat << 'EOF' | git apply
diff --git a/litellm/cost_calculator.py b/litellm/cost_calculator.py
--- a/litellm/cost_calculator.py
+++ b/litellm/cost_calculator.py
@@ -490,4 +490,5 @@
     else:
+        redacted_usage_obj = {k: (v if k != "client_secret" else "REDACTED") for k, v in usage_obj.items()} if isinstance(usage_obj, dict) else "REDACTED"
         verbose_logger.debug(
-            f"Unknown usage object type: {type(usage_obj)}, usage_obj: {usage_obj}"
+            f"Unknown usage object type: {type(usage_obj)}, usage_obj: {redacted_usage_obj}"
         )
EOF
@@ -490,4 +490,5 @@
else:
redacted_usage_obj = {k: (v if k != "client_secret" else "REDACTED") for k, v in usage_obj.items()} if isinstance(usage_obj, dict) else "REDACTED"
verbose_logger.debug(
f"Unknown usage object type: {type(usage_obj)}, usage_obj: {usage_obj}"
f"Unknown usage object type: {type(usage_obj)}, usage_obj: {redacted_usage_obj}"
)
Copilot is powered by AI and may make mistakes. Always verify output.
@codecov Codecov
Copy link

codecov bot commented Mar 29, 2025

Codecov Report

Attention: Patch coverage is 82.03883% with 37 lines in your changes missing coverage. Please review.

Files with missing lines Patch % Lines
.../vertex_ai/multimodal_embeddings/transformation.py 71.87% 36 Missing ⚠️
...rtex_ai/multimodal_embeddings/embedding_handler.py 87.50% 1 Missing ⚠️

📢 Thoughts on this report? Let us know!

@krrishdholakia krrishdholakia merged commit 5ac61a7 into main Mar 29, 2025
41 of 42 checks passed
@krrishdholakia krrishdholakia deleted the litellm_dev_03_28_2025_p2 branch March 29, 2025 07:23
@krrishdholakia krrishdholakia changed the title Add bedrock latency optimized inference support Add bedrock latency optimized inference support + Vertex AI Multimodal embedding cost tracking Mar 29, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

[Feature]: Bedrock latency-optimized inference
1 participant
@krrishdholakia