[DOC] Add examples/gemini-genai script example

[scotbrew]

Description of changes

Create new Gemini google.genai example (examples/gemini-genai)
This is a new example script that uses the newer google.genai API, based on the existing examples/gemini example that uses the older google.generativeai API. Full change history of the modifications retained.

• Improvements & Bug fixes
  • Update from google.generativeai to google.genai
  • Use env variable GOOGLE_API_KEY for the api_key
  • Fix document loading logic issues, if interrupted.
  • Add single and batch document loading methods
  • Make document loading batch processing more flexible and robust
  • Separate out the embed model from the query model
  • Reduce the batch size so it will better work with Google Free Tier.
  • Revise output to more explicitly separate the collection closest documents from the LLM query.

Fixes: #5998

Test plan

Example scripts tested locally.

pip install -r requirements.txt
python load_data.py
python main.py

Migration plan

N/A

Observability plan

N/A

Documentation Changes

No

[github-actions]

Reviewer Checklist

Please leverage this checklist to ensure your code review is thorough before approving

Testing, Bugs, Errors, Logs, Documentation

• Can you think of any use case in which the code does not behave as intended? Have they been tested?
• Can you think of any inputs or external events that could break the code? Is user input validated and safe? Have they been tested?
• If appropriate, are there adequate property based tests?
• If appropriate, are there adequate unit tests?
• Should any logging, debugging, tracing information be added or removed?
• Are error messages user-friendly?
• Have all documentation changes needed been made?
• Have all non-obvious changes been commented?

System Compatibility

• Are there any potential impacts on other parts of the system or backward compatibility?
• Does this change intersect with any items on our roadmap, and if so, is there a plan for fitting them together?

Quality

• Is this code of a unexpectedly high quality (Readability, Modularity, Intuitiveness)

[propel-code-bot]

Add google.genai-based Gemini example with robust data loader

Adds a new examples/gemini-genai sample that mirrors the existing Gemini demo but targets the google.genai client. The scripts load the bundled 2022/2023 U.S. State of the Union texts into Chroma, then run conversational retrieval with separate embedding and generative models, updated batching/resume logic, and clearer console output. Supporting updates include a dedicated requirements file, README walkthrough, and a .gitignore rule for persisted collections.

Key Changes

• Introduce examples/gemini-genai with updated main.py that queries google.genai, separates embed/query models, and improves console diagnostics.
• Rewrite load_data.py to batch inserts, resume interrupted loads safely, and prompt for GOOGLE_API_KEY when absent.
• Document usage in examples/gemini-genai/README.md, add Python dependencies in examples/gemini-genai/requirements.txt, and ignore generated chroma_storage/ directories.

Affected Areas

• examples/gemini-genai/main.py
• examples/gemini-genai/load_data.py
• examples/gemini-genai/README.md
• examples/gemini-genai/requirements.txt
• .gitignore

This summary was automatically generated by @propel-code-bot