feat(llm): extract BaseVertexAILLM around a model-construction hook

[matteomedioli]

Stack

Merge order: #565 → #567 → #566 → #571 → #572. Each PR builds on the previous one (this branch is stacked on matteo/base-gemini-llm). Until its base merges, GitHub may show parent commits in the diff — review only the commits unique to this branch.

Description

Same goal as the other base classes — subclass instead of fork — but VertexAI needs a different shape. There is no client object to construct: the SDK works through a global vertexai.init(...) call plus a fresh GenerativeModel created for every request.

So instead of "the subclass creates the clients", BaseVertexAILLM has one abstract method, _get_model(), which returns the model used for a call. That is the only thing a subclass implements — pointing at a different project, region, or endpoint is a few lines. Everything else (message building, config and schema handling, response parsing) is inherited.

• VertexAILLM implements _get_model() exactly as it did before the extraction — no behavior change.
• BaseVertexAILLM is exported from neo4j_graphrag.llm; the llm.rst extensibility page now has a Vertex AI section explaining why this hook differs from the Anthropic/OpenAI/Gemini client-injection shape (no http_client/base_url — endpoint config is global via vertexai.init), with a worked subclass example. api.rst cross-references it.
• The docs note that new projects should prefer GeminiLLM (google-genai SDK), positioning VertexAILLM as legacy support — resolving the maintainer question below in the docs.
• Tests cover the contract directly: the base class cannot be instantiated without _get_model, and a minimal subclass overriding only _get_model runs invoke() end to end with its custom model.

Question for maintainers: Google is retiring the vertexai.generative_models SDK in favor of google-genai — which GeminiLLM already uses, and which can also reach Vertex-hosted models. This PR still makes sense (it cleanly factors what exists); the docs now recommend GeminiLLM for new work. Shout if you'd rather drop that note or phrase it differently.

Type of Change

• New feature
• Bug fix
• Breaking change
• Documentation update
• Project configuration change

Complexity

Complexity: Low

How Has This Been Tested?

• Unit tests
• E2E tests
• Manual tests

Checklist

• Documentation has been updated
• Unit tests have been updated
• Examples have been updated
• CLA (https://neo4j.com/developer/cla/) has been signed
• CHANGELOG.md updated