Grok 2 (beta) A hotel concierge holds an iPhone toward the camera. The phone screen displays the word “RAG”. Behind the desk is a large library full of books. A sign on the wall says “Retrieval”. Landscape aspect ratio.
“Huge turnout at the @Cohere x @AgentOpsAI Agent Build Day Lots of cool projects built with AgentOps 🖇️🖇️🖇️
“I am thrilled to share vectara-agentic, a new way to build Agentic RAG applications with @Vectara. Blog:
“How good do the latest long context LLMs (LLama-3.1-405b, GPT-4o-mini and Claude-3.5-sonnet) perform on RAG? We benchmarked 13 popular OSS and commercial models on context lengths from 2k to 125k, and the results are very interesting! Full post:
How Enterprises Can Start Building Agentic AI – https://cohere.com/blog/how-enterprises-can-start-building-agentic-ai
“📌 Golden-Retriever enhances Retrieval Augmented Generation (RAG) for industrial knowledge bases. Addresses challenges with domain-specific jargon and context interpretation. 📌 Results: Golden-Retriever improves total score of Meta-Llama-3-70B by 79.2% over vanilla LLM, 40.7%
Long Context RAG Performance of LLMs | Databricks Blog
“Processed 100 complinace documents using HybridRAG for an upcoming product launch. HybridRAG excels in faithfulness, answer relevancy, and context recall by combining naive cosine similarity search and KG retrieval. The pipeline uses the @vercel AI SDK’s generateObject to
“Building a Multimodal Recipe Recommender with @qdrant_engine, @llama_index, and Gemini 🧑🍳 This is an strikingly easy-to-follow tutorial by Benito Martin on building a multimodal RAG pipeline that can ingest a playlist of YouTube videos (including video descriptions and the video
“This is huge. You can now dump tons of data into the context window, with fast speeds and minimal cost. Examples: – show the LLM your entire codebase and ask for new features – instead of just RAGging in the top 5 docs, give the LLM the top 1000 – show hundreds of examples” / X
Leave a Reply