filmov
tv
Pinecone Workshop: LLM Size Doesn't Matter — Context Does
Показать описание
This discussion is critical for every AI, Engineering, Analytics, and Product leader interested in deploying AI solutions. Pinecone and Prolego share the surprising insights from their independent research studies on optimizing LLM RAG applications.
Although state-of-the-art LLMs like GPT-4 perform best on general benchmarks, small and open-source LLMs perform just as well when given the right context. These results are critical for: (1) overcoming policy constraints preventing you from sending data to model providers, (2) reducing the costs and increasing the ROI of your RAG, and (3) giving you more control over your models and infrastructure.
Although state-of-the-art LLMs like GPT-4 perform best on general benchmarks, small and open-source LLMs perform just as well when given the right context. These results are critical for: (1) overcoming policy constraints preventing you from sending data to model providers, (2) reducing the costs and increasing the ROI of your RAG, and (3) giving you more control over your models and infrastructure.
0:58:33
Pinecone Workshop: LLM Size Doesn't Matter — Context Does
0:42:15
Don't naive RAG do hybrid search instead (Pinecone Weaviate or pgvector + full text search &...
0:59:12
Building the Future with LLMs, LangChain, & Pinecone
0:18:35
Building Production-Ready RAG Applications: Jerry Liu
1:01:26
Build enterprise-grade Q&A at scale with Open LLMs on AWS
0:32:30
Hugging Face LLMs with SageMaker + RAG with Pinecone
0:48:57
LlamaIndex Webinar: Build/Break/Test LLM Apps Showcase (co-hosted with TrueEra, Pinecone)
0:59:53
Building Production-Grade LLM Apps
0:50:50
Optimizing query performance with Pinecone's Rerank API and Fleak
0:29:32
The ULTIMATE Local AI Setup: LLMs, Qdrant, n8n (NO CODE!!)
1:29:45
RAG Workshop with Langchain and LlamaIndex
0:34:22
How to build Multimodal Retrieval-Augmented Generation (RAG) with Gemini
1:02:29
The Future of Multi-Modal Search
0:58:52
Harnessing RAG with Open-Source LLMs — @matthew_berman, @jamesbriggs
0:59:30
Boosting Your Chatbot's Intelligence with Retrieval
0:16:28
PGVector vs Pinecone vs Redis - how should you choose a vector database?
1:02:40
Troubleshooting Search and Retrieval: Enhance Performance with Powerful AI Solutions
0:06:32
Generative AI | Jobs with GPT 3, GPT 4, ChatGPT Knowledge and Skills | Career Talk With Anand
0:44:30
Vector Database Workshop - Scaling LLMs by Yujian Tang
0:53:14
LlamaIndex: Building RAG Applications with Multiple Data Sources
0:41:52
ClippyGPT - How I Built Supabase’s OpenAI Doc Search (Embeddings)
2:12:00
The missing pieces to your AI app (pgvector + RAG in prod)
0:47:55
Dan Gibson - An Introduction to Retrieval Augmented Generation - PyData London 2024
0:52:48
LlamaIndex Webinar: Document Metadata and Local Models for Better, Faster Retrieval
Комментарии