Gemini, Google's Large Language Model
summary
Introduction to Google/DeepMind’s Gemini family of LLMs (Nano to Ultra and the open Gemma variant) and how to use Gemini via the Google Cloud API in Java apps, specifically with the LangChain4j library. Covers Gemini’s multimodal capabilities (text, images, video), practical uses: extracting unstructured data, text classification, Retrieval-Augmented Generation (RAG) to extend knowledge, and using function-calling to invoke external services during generation.
AI-written summary · about
chapters (22)
- 0:00Gemini introduction
- 3:50Gemini interface demo
- 5:15Gemini versions
- 7:222M token context demo
- 11:39Google AI Studio demos
- 14:34Gemini vs Gemma
- 17:44Gemini API Java
- 21:16LangChain4j API calls
- 23:43Streaming responses
- 24:47Chat memory
- 27:40Dynamic prompts
- 29:24Image analysis
- 30:48Text classification
- 33:56Structured data extraction
- 36:03RAG explained
- 38:53RAG demo car manual
- 42:28Function calling
- 44:34Weather demo
- 45:57Local Gemma setup
- 47:23Advanced agents
- 49:31RAG agent Berlin
- 50:12Summary
related talks
51mGemini, Google's Large Language Model
54mGemini, Google's Large Language Model
16mOpen models in the Gemini era
37mIntroduction to the Gemini API for Web Apps
19mGemini 2.0: Beyond the Basics
01h 45mAI Engineering with the Google Gemini 2.5 Model Family
56mBuilding Multimodal Apps with Gemini 2 0 and Gemini SDK
01h 01mBuilding Multimodal Apps with Gemini 2.0 and Gemini SDK