Sascha HeyerinGoogle Cloud - CommunityGoogle Cloud RAG API30 lines of code is all you need for RAG. The easiest way to get started with RAG.3d ago23d ago2
Sascha HeyerinGoogle Cloud - CommunityMultimodal Document ProcessingHow to process 10251 documents for just 1$. Built within 15 minutes.Sep 6Sep 6
Sascha HeyerinGoogle Cloud - CommunityVertex AI Function CallingLLMs are turning into reasoning engines using capabilities like web search and calling external APIs.Aug 31Aug 31
Sascha HeyerinGoogle Cloud - CommunityRerankingA Reranker is a language model that computes a relevance score using a document and a query.Aug 23Aug 23
Sascha HeyerinGoogle Cloud - CommunityGemini Code Assist“There are no programmers in 5 years”. Emad Mostaque, the CEO of Stability AI, made this prediction.Aug 2Aug 2
Sascha HeyerinGoogle Cloud - CommunityOrchestrate Generative AI Applicationswith Cloud WorkflowsJul 201Jul 201
Sascha HeyerinGoogle Cloud - CommunityEnhancing Vector Search with Gemini as Multimodal Re-RankerWhy Vertex AI Vector Search and Gemini’s Multimodal Capabilities are a Perfect MatchJul 11Jul 11
Sascha HeyerinGoogle Cloud - CommunityVertex AI Context Caching with GeminiUse caching to make your Gemini input up to 4 times cheaper.Jul 24Jul 24
Sascha HeyerinGoogle Cloud - CommunityVertex AI Controlled Generation with GeminiRespond reliably with JSON and other formatsJun 26Jun 26
Sascha HeyerVertex AI Grounding Large Language ModelsGrounding allows Google’s large Language models to use your specific data to produce more accurate and relevant responses.Dec 7, 20233Dec 7, 20233