Extract value with assisted analytics
summary
A live demo shows Gemini calling BigQuery via Function Calling with Gemini to turn plain-English questions into SQL, run queries, and format answers; the team builds a working prototype as a 270-line Python app that queries seven tables and reports metrics — one query returns 9.95% of orders are returned — and the system loops on generated functions until results match the data, enabling real‑time pulls, API calls, and workflow automation.
AI-written summary · about
chapters (6)
- 0:00Meet Manoj
- 0:14Chat with your data in BigQuery
- 0:49How does Gemini improves analytics
- 2:16Demo: SQL Talk with BigQuery
- 4:39Architecture overview
- 5:37Wrap up
related talks
18mIntroduction to Gemini APIs and AI Studio
37mIntroduction to the Gemini API for Web Apps
28mDinner for two with Gemini: takeaway or restaurant?
01h 45mAI Engineering with the Google Gemini 2.5 Model Family
22mMilliseconds to Magic: Real‑Time Workflows using the Gemini Live API and Pipecat
01h 01mBuilding Multimodal Apps with Gemini 2.0 and Gemini SDK
56mBuilding Multimodal Apps with Gemini 2 0 and Gemini SDK
28mFirebase analytics for BigQuery
