Explored the Gen AI SDK and learned about using Gemini models with multimodal prompts, fine-tuning model parameters, and applying filters for better output control.
Worked with Gemini Flash model for image and audio understanding, generating video descriptions, reasoning over code bases, making recommendations from images, and interpreting technical diagrams.
Function Calling with Gemini enabled structured querying for Google Store, geocoding addresses with Maps API, and extracting entities from unstructured data.
Equipped with technical tools and new ideas for integrating generative AI in real-world solutions, looking forward to applying the skills in future projects.