Bump langchain, disable llama_index, and fix Vector Store materializer

[strickvl]

Addresses #2012 by:

• bumping our langchain dependency to >=0.0.325 (which handles the critical severity vulnerability
• disable llama_index integration until sqlmodel allows sqlalchemy>=2.0 (see 🚀 Roadmap fastapi/sqlmodel#654 for their roadmap)
• fixing the import for the vector store materializer
• add (missing) test for vector store materializer
• (fix broken test for openAI embedding materializer)

Given the new base langchain dependency version, I tagged this as a breaking change, but not sure whether we consider this a breaking change per our semantic versioning.

Pre-requisites

Please ensure you have done the following:

• I have read the CONTRIBUTING.md document.
• If my change requires a change to docs, I have updated the documentation accordingly.
• If I have added an integration, I have updated the integrations table and the corresponding website section.
• I have added tests to cover my changes.
• I have based my new branch on develop and the open PR is targeting develop. If your branch wasn't based on develop read Contribution guide on rebasing branch to develop.

Types of changes

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Other (add details above)

[strickvl]

@avishniakov am merging this because it's just the MCP test that's failing. Let's fix that in a separate PR off develop.