docs: Update RAG snippets to use latest RAG module from AgentPlatform SDK

[sararob]

Description

Fixes #

Checklist

Testing

• I have tested this change on a live environment and verified it works as intended.

Compliance & Style

• I have followed the Sample Guidelines..

---

Post-Approval Actions

• Please merge this PR for me once it is approved

[gemini-code-assist]

Code Review

This pull request migrates various Vertex AI RAG example scripts from the legacy vertexai SDK to the new agentplatform and google.genai SDKs. While the migration updates client initialization, corpus creation, and retrieval mechanisms, the review highlights several critical issues. Most notably, multiple files will raise NameErrors because types used in function return annotations (such as RagCorpus and GenerationResponse) are either not imported globally or need to be updated to their new namespaces (types.RagCorpus and genai_types.GenerateContentResponse). Additionally, there are bugs involving incorrect configuration nesting for Weaviate, passing uninstantiated classes as arguments, using the wrong client for content generation, and referencing undefined variables in return statements.

[gemini-code-assist]

Import agentplatform and types globally so they can be used in the function signature's return type annotation without raising a NameError at import time.

Suggested change

	from typing import Optional
	from typing import Optional
	import agentplatform
	from agentplatform import types

[gemini-code-assist]

Update the return type annotation to use types.RagCorpus instead of the undefined RagCorpus.

Suggested change

	) -> RagCorpus:
	) -> types.RagCorpus:

[gemini-code-assist]

Import agentplatform and types globally so they can be used in the function signature's return type annotation without raising a NameError at import time.

Suggested change

	from typing import Optional
	from typing import Optional
	import agentplatform
	from agentplatform import types

[gemini-code-assist]

Update the return type annotation to use types.RagCorpus instead of the undefined RagCorpus.

Suggested change

	) -> RagCorpus:
	) -> types.RagCorpus:

[gemini-code-assist]

Import agentplatform and types globally so they can be used in the function signature's return type annotation without raising a NameError at import time.

Suggested change

	from typing import Optional
	from typing import Optional
	import agentplatform
	from agentplatform import types

[gemini-code-assist]

Instantiate genai_types.VertexRagStoreRagResource with rag_corpus=corpus_name instead of passing the class itself.

                rag_resources=[
                    genai_types.VertexRagStoreRagResource(
                        rag_corpus=corpus_name,
                    )
                ],

[gemini-code-assist]

Remove the unused and undefined GenerativeModel instantiation, and use genai_client instead of client to call models.generate_content.

    response = genai_client.models.generate_content(
        model="gemini-2.5-pro",
        contents="Why is the sky blue?",
        config=genai_types.GenerateContentConfig(
            tools=[rag_retrieval_tool]
        )
    )

[gemini-code-assist]

The variable result returned on line 72 is undefined because result = await response.result() was removed. Please update line 72 to return response instead of result.

[gemini-code-assist]

The variable files returned on line 47 is undefined because files = rag.list_files(...) was replaced by files_response = client.rag.list_files(...). Please update line 47 to return files_response instead of files.

[gemini-code-assist]

Update the return type annotation to use types.RagCorpus and genai_types.GenerateContentResponse instead of the undefined rag.RagCorpus and GenerationResponse.

Suggested change

	) -> Tuple[rag.RagCorpus, GenerationResponse]:
	) -> Tuple[types.RagCorpus, genai_types.GenerateContentResponse]: