[DOC] In gemini example, correct embedding function name

[scotbrew]

Description of changes

The gemini example uses invalid capitalization for the embedding function, resulting in an error. Correcting to use the current function name.

In examples/gemini/ for load_data.py and main.py:
Change
embedding_functions.GoogleGenerativeAIEmbeddingFunction
to
embedding_functions.GoogleGenerativeAiEmbeddingFunction

Fixes: #5977

Test plan

As described in README.md, execute the standard steps:

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

All should now execute properly.

Migration plan

N/A

Observability plan

N/A

Documentation Changes

None

[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]

Fix Gemini example embedding setup and batching logic

The PR updates examples/gemini/load_data.py and examples/gemini/main.py to use embedding_functions.GoogleGenerativeAiEmbeddingFunction, explicitly pass model_name='gemini-embedding-001', and switch the chat model to genai.GenerativeModel('gemini-2.5-flash'). It also reworks document ingestion to build an explicit ids list, load documents in small batches, and records the Gemini example storage folder in .gitignore.

Key Changes

• Replace embedding_functions.GoogleGenerativeAIEmbeddingFunction with embedding_functions.GoogleGenerativeAiEmbeddingFunction in both example scripts and wire in model_name='gemini-embedding-001'.
• Instantiate genai.GenerativeModel('gemini-2.5-flash') for querying in examples/gemini/main.py.
• Introduce an ids accumulator, smaller batch size, and revised batching loop around collection.add in examples/gemini/load_data.py.
• Ignore examples/gemini*/chroma_storage/ outputs via .gitignore.

Affected Areas

• examples/gemini/load_data.py
• examples/gemini/main.py
• .gitignore

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

[philipithomas]

Thank you for this fix!

[scotbrew]

The first iteration of this PR addresses a clear function name syntax error. Further changes needed though to address logic as well as Gemini model changes. Awaiting quota reset for further testing.

[scotbrew]

Revised collections.add() logic in load_data.py to work with non-empty collection.
Changed batch_size for loading documents.
Updated gemini model for embedding.
Changed gemini query model to a simpler model.

Loading documents now able to be properly tested. Awaiting quota reset for query testing.

[scotbrew]

After the latest modification to main.py to align the embedding model with the same one used now in load_data.py, the script now successfully executes and provides a query response as expected. It no longer errors out with You exceeded your current quota.

Full testing of example script execution now succeeds.

[scotbrew]

As the scope increased to address logic and the embedding model, should the title be revised?