SAP / SAP/ai-sdk-python

SAP AI SDK pins langchain-google-genai to patch level 4.3.6

Open Beginner friendly
#152 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
4
Forks
1
Avg merge
2d 4h
Merged PRs (30d)
48

Description

Checklist
Describe the Problem

We discovered that version 7.3 and 7.4 are pinning the package langchain-google-genai hard coded to patch level 4.3.6:
Requires-Dist: langchain-google-genai<4.3.7,~=4.3.6; extra == "google"

Steps to reproduce:
-Install SAP AI SDK
-Try to upgrade langchain-google-genai to 4.4

Expected behavior:
Due to security requirements, we need to be able to ensure that related packages can at least be upgraded on patch level.
Additionally we need to use langchain-google-genai >4.4 in our next release.

Used Versions:
Python version via python3 --version: 3.12.10
SAP Cloud SDK for AI package version: 7.40 and 7.30
Region: EU10

Propose a Solution

upgrade langchain-google-genai to 4.4

Describe Alternatives

No response

Affected Development Phase

Development

Impact

Blocked

Timeline

No response

Additional Context

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the dependency metadata for the SDK's google extra and reproduce the installation with langchain-google-genai 4.4. Update the constraint so patch-level upgrades are allowed, then verify that the SDK can install with version 4.4 and that the existing dependency checks still pass.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai
Issue type
Bug
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
68/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.