Retrieval Augmented Generation in the Wild: Anton Troynikov

Показать описание

In the last few months, we've seen an explosion of the use of retrieval in the context of AI. Document question answering, autonomous agents, and more use embeddings-based retrieval systems in a variety of ways. This talk will cover what we've learned building for these applications, the challenges developers face, and the future of retrieval in the context of AI.

About Anton Troynikov
Anton is the co-founder of Chroma. He does not believe AI will kill us all. Chroma build an open-source embeddings store, specifically built for AI-native applications.

AI Engineer

Рекомендации по теме

Комментарии

FYI there is a failure of direct retrieval with GPT-4 using the new OpenAI Assistant API. GPT tokenizes text and creates its own vector embeddings based on its specific training data. The new terms and sequences may not connect well to the pretrained knowledge in GPT's weight tensors.
There was no semantic similarity between the new API terms and GPT's existing vector space. This is a fundamental issue with retrieval augmentation systems like Rag - external knowledge is not truly integrated into the model's learned weights. Adding more vector stores cannot solve this core problem.
The solution is to have multiple learned "knowledge planes" with trained weight tensors for specific tasks that can be switched in. This is better than just retrieving separate vector representations.

Pure_Science_and_Technology

Excellent presentation. I have found vanilla embeddings insufficient to do “level2” tasks, which require multiple pieces of context that may vary from ultra specific, to rolled up across the entire document. If anyone can link research on how to embed temporal meaning within chronological text, would love to take a look!

Jaybearno

Retrieval Augmented Generation in the Wild: Anton Troynikov

What is Retrieval-Augmented Generation (RAG)?

Back to Basics: Understanding Retrieval Augmented Generation (RAG)

A Helping Hand for LLMs (Retrieval Augmented Generation) - Computerphile

What is RAG? (Retrieval Augmented Generation)

How to use Retrieval Augmented Generation (RAG)

Was ist Retrieval Augmented Generation?

Intro to RAG for AI (Retrieval Augmented Generation)

Retrieval Augmented Generation (RAG) Explained: Embedding, Sentence BERT, Vector Database (HNSW)

Beyond Chatbots: How Large Language Models Are Evolving with Retrieval-Augmented Generation (RAG)

What is Retrieval-Augmented Generation (RAG)?

Retrieval Augmented Generation'a Giriş

Retrieval Augmented Generation (RAG) Explained in 8 Minutes!

Setting up Retrieval Augmented Generation (RAG) in 3 Steps

Build a Retrieval-Augmented Generation Chatbot in 5 Minutes

How RAG Turns AI Chatbots Into Something Practical

What is Retrieval Augmented Generation (RAG) - Augmenting LLMs with a memory

How to set up RAG - Retrieval Augmented Generation (demo)

Learn RAG From Scratch – Python AI Tutorial from a LangChain Engineer

What is Retrieval Augmented Generation?

Stanford CS25: V3 I Retrieval Augmented Language Models

Build a Large Language Model AI Chatbot using Retrieval Augmented Generation

Retrieval Augmented Generation (RAG) | Embedding Model, Vector Database, LangChain, LLM

AI Explained - AI LLM Retrieval-Augmented Generation (RAG)

When Do You Use Fine-Tuning Vs. Retrieval Augmented Generation (RAG)? (Guest: Harpreet Sahota)