feat: Gemini file search vectordb

[ishrath99]

Summary

This PR adds Gemini File Search as a new vector database integration for Agno, enabling semantic search using Google's managed File Search Store with native Gemini AI integration.

Key Changes:

• New GeminiFileSearch class implementing the VectorDb interface
• Three cookbook examples: basic usage, async operations, and metadata filtering
• Added google-genai dependency to pyproject.toml

Features:

• Document upload and management
• Semantic search with metadata filtering
• Async operation support
• Grounding metadata for citations
• Support for multiple Gemini models

Type of change

• Bug fix
• New feature
• Breaking change
• Improvement
• Model update
• Other:

---

Checklist

• Code complies with style guidelines
• Ran format/validation scripts (./scripts/format.sh and ./scripts/validate.sh)
• Self-review completed
• Documentation updated (comments, docstrings)
• Examples and guides: Relevant cookbook examples have been included or updated (if applicable)
• Tested in clean environment
• Tests added/updated (if applicable)

---

Additional Notes

Installation

pip install agno[gemini]