Advanced RAG with ColBERT in LangChain and LlamaIndex

preview_player
Показать описание
ColBERT is a fast and accurate retrieval model, enabling scalable BERT-based search over large text collections in tens of milliseconds. This can be used as a potential alternative to Dense Embeddings in Retrieval Augmented Generation. In this video we explore using ColBERTv2 with RAGatouille and compare it with OpenAI Embedding models.

Signup for Advanced RAG:

LINKS:

TIMESTAMPS:
[00:00] Introduction
[00:29] Use ColBERT in LangChain
[08:46] Use ColBERT in LlamaIndex

All Interesting Videos:

  1. Prompt Engineering
  2. prompt engineering
  3. Prompt Engineer
  4. LLMs
  5. AI
  6. artificial Intelligence
Рекомендации по теме
Advanced RAG with 0:13:35

Advanced RAG with ColBERT in LangChain and LlamaIndex

Supercharge Your RAG 0:17:45

Supercharge Your RAG with Contextualized Late Interactions

Advanced RAG Concept: 0:12:33

Advanced RAG Concept: Improving RAG with Multi-stage Document Reranking

RAG But Better: 0:23:43

RAG But Better: Rerankers with Cohere AI

Learn RAG From 2:33:11

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

Stanford CS25: V3 1:19:27

Stanford CS25: V3 I Retrieval Augmented Language Models

RAG From Scratch: 0:07:13

RAG From Scratch: Part 14 (ColBERT)

Build a Streamlit 0:00:30

Build a Streamlit Chatbot using Langchain, ColBERT, Ragatouille, and ChromaDB

DSPy: MOST Advanced 0:18:55

DSPy: MOST Advanced AI RAG Framework with Auto Reasoning and Prompting

Neural Notes: ColBERT 0:31:09

Neural Notes: ColBERT & ColBERTv2

Lady Gaga’s best 0:00:26

Lady Gaga’s best response ever

He Didn't Even 0:00:26

He Didn't Even Hesitate 😳 #shorts #comedy

Developing and Serving 0:29:11

Developing and Serving RAG-Based LLM Applications in Production

Simple ideas to 0:39:31

Simple ideas to improve your RAG (Stanford, Google)

Sting watching his 0:00:16

Sting watching his song get murdered… 🔪 #sting #thepolice #80smusic #80s #rock #everybreathyoutake...

Learn RAG from 0:11:21

Learn RAG from Scratch in Python without using frameworks (langchain or llamaIndex)

Meryl Streep Meets 0:05:37

Meryl Streep Meets Anna Wintour at Vogue

DSPy explained: No 0:53:22

DSPy explained: No more LangChain PROMPT Templates

Howard and Melissa 0:19:42

Howard and Melissa Rauch doing voice of Howard's Mom |Jim mocking comic con 201l

Ep. 8 — 0:57:23

Ep. 8 — ColBERT + ColBERTv2: late interaction at a reasonable inference cost

Homework: Few-shot OpenQA 0:17:07

Homework: Few-shot OpenQA with ColBERT retrieval | Stanford CS224U Natural Language Understanding

RAG Basics to 1:57:37

RAG Basics to Intermediate | Query Transformation, Construction, Routing, Advanced Retrievers

LangChain Retrieval Webinar 1:05:32

LangChain Retrieval Webinar

Neil deGrasse Tyson 0:21:07

Neil deGrasse Tyson Panicking Over Declassified Photos From Venus By The Soviet Union!

Комментарии
Автор

can you make a video on how to evaluate a RAG? And compare different RAG approaches.

pawan
Автор

Very interesting video indeed!! Could you please create a video on how to use colBERTv2 for embedding with pg_vector for persistent storage?

mjaym
Автор

I’d like to do RAG over a medical textbook. What strategies would you recommend for chunking. I’m thinking a hierarchical graph structure makes intuitive sense. What are your thoughts on this?

hamslammula
Автор

@engineerprompt, can we use a persistant vector db like chroma, qdrant and others with Ragatouille? So that I can just embed the documents once and re-use them for inferences later.

nbbhaskar
Автор

Is the Plaid DB persistent? As in, if I do this, how do I connect to that particular DB again?

jayethompson
Автор

Cant find the google collab notebook? Would love to copy this across to my own account and havd a play. Not sure if I'm overlooking it? I just see the github link?

iaincampbell
Автор

How can we use approaches like ColBERT with other languages, as portuguese? Thanks!

almirbolduan
Автор

I am working on a machine that is running Ubuntu and connected to 4 80GB A100 GPU's. The issue i face is RAG.index cell is running forever on this machine. Whereas same code running on Google Colab free version runs within seconds. Any insights on how this can be resolved will be helpful. Thanks :)

shameekm
Автор

Navigating the landscape of storytelling and video experimentation, VideoGPT silently empowers my creative journey, adding a layer of sophistication to my content.

hales
Автор

of course the last result is more accurate. you gave it almost 50% (5 instead of 3 chunks) more context. when using multiple ways to achieve the same goal, please use the same amount of data. otherwise it is hard to compare the output.

on the topic of chunks given to RAG - why define that? what if one does not know about how many parts may contain relevant information?

iham
Автор

How can I monetize whatever is being said as a beginner..?

linuswatiti