[iennae]

Summary

Updates samples across generative_ai/chat_completions, generative_ai/rag, and generative_ai/model_garden to use current model versions, valid SDK methods/configs, and an unrestricted RAG Engine region:

• generative_ai/chat_completions (9 files):

  • Updates OpenAI-compatible Vertex AI samples from retired Gemini 1.5 models to google/gemini-3.8-flash on the global endpoint.
  • Fixes the two-turn function calling conversation history in chat_completions_function_calling_basic.py and chat_completions_function_calling_config.py so the assistant's tool_calls message is included prior to the tool response message.
  • Updates chat_completions_test.py assertions for non-empty responses and tool call outputs.

• generative_ai/model_garden (4 files):

  • Updates Anthropic Claude samples (claude_3_streaming_example.py, claude_3_tool_example.py, claude_3_unary_example.py) from retired claude-3-5-sonnet-v2@20241022 to claude-sonnet-4-6.
  • Updates anthropic[vertex] in requirements.txt to 2.2.0.

• generative_ai/rag (20 files):

  • Unifies all RAG Engine samples on the unrestricted GA region us-east5 (see RAG Engine supported regions). Note: an alternative when using restricted regions such as us-central1 is switching RagEngineConfig to Serverless mode.
  • Updates embedding model references from text-embedding-004 to text-embedding-005 and generation model references in generate_content_example.py and quickstart_example.py to gemini-3.8-flash (via the global genai.Client).
  • Fixes agentplatform RAG SDK method calls (client.rag.delete_corpus, client.rag.get_corpus, client.rag.delete_file, client.rag.get_file, client.rag.list_files, client.rag.upload_file) and google.genai.types imports.
  • Updates import_files_example.py and import_files_async_example.py to configure gcs_source in ImportRagFilesConfig (which enforces a mutually exclusive oneof across data sources) and clarifies the function docstrings.
  • Wires api_auth into RagVectorDbConfig in create_corpus_pinecone_example.py and create_corpus_weaviate_example.py, and moves rag_embedding_model_config inside RagVectorDbConfig in create_corpus_weaviate_example.py.
  • Updates generative_ai/rag/requirements.txt to google-cloud-aiplatform==2.6.0 and google-genai==2.29.0.

[gemini-code-assist]

Code Review

This pull request updates various generative AI examples across chat completions, model garden, and RAG modules to use new locations (such as "global" and "us-east5"), updates model references, and bumps dependency versions in requirements files. The review feedback highlights critical issues where several of the newly specified model names (such as "google/gemini-3.8-flash" and "claude-sonnet-4-6") and package dependency versions (such as "anthropic[vertex]==2.2.0", "google-cloud-aiplatform==2.6.0", and "google-genai==2.29.0") do not actually exist. It is recommended to use valid, existing model names and package versions to prevent runtime and installation failures.