RAPTOR: Dynamic Tree-Structured Summaries with LangChain - Advanced RAG

preview_player
Показать описание


Timestamps
0:00 What is RAPTOR?
1:02 Code Walkthrough
10:08 Dynamic Code in Action
  1. Coding Crash Courses
  2. langchain
  3. raptor
  4. rag
  5. retrieval augmented generation
Рекомендации по теме
RAPTOR: Dynamic Tree-Structured 0:12:30

RAPTOR: Dynamic Tree-Structured Summaries with LangChain - Advanced RAG

Coding for 1 0:00:24

Coding for 1 Month Versus 1 Year #shorts #coding

RAPTOR: New Retrieval 0:16:01

RAPTOR: New Retrieval Method for RAG | Chat with your Data using GPT

Growing up Pentecostal... 0:00:15

Growing up Pentecostal... #short

Do you want 0:00:16

Do you want to better your life? #philippines #angelescity #expat #pampanga #travelvlog

Burkina Faso's Young 0:00:38

Burkina Faso's Young Military President Ibrahim Traore Scares Putin At Russia-Africa Summit, Ni...

Simple ideas to 0:39:31

Simple ideas to improve your RAG (Stanford, Google)

RaptorJIT: a fast, 0:17:43

RaptorJIT: a fast, dynamic systems programming language Forking LuaJIT to target heavy-duty server …...

How To Create 0:02:37

How To Create A Flowchart With ChatGPT

Building Production-Ready RAG 0:18:35

Building Production-Ready RAG Applications: Jerry Liu

Birds gliding through 0:02:17

Birds gliding through bubbles reveal aerodynamic trick

Play Around with 1:44:00

Play Around with Raptor Write!

Black fortuner accident 0:00:14

Black fortuner accident #carkslover #short #viral

The Full Story 1:58:04

The Full Story of ARK - Before You Play ASCENDED

What Happens If 0:11:17

What Happens If You Shoot Down a Drone?

Bubble sort in 0:02:10

Bubble sort in 2 minutes

Insertion sort in 0:02:19

Insertion sort in 2 minutes

Live #31: Inspecting 0:34:40

Live #31: Inspecting RaptorJIT IR with Studio

Live #16: RaptorJIT 1:33:20

Live #16: RaptorJIT bootstrapping, asm-vs-C VM, 96-bit heap, sealed tables invariant

A Cookbook for 1:00:09

A Cookbook for Web-Based Data Visualisations with R + Highcharter by Tom Bishop

Biotech Connector: Structural 1:15:48

Biotech Connector: Structural Biology as a Tool

Selection sort in 0:02:43

Selection sort in 3 minutes

Mallow Boardwalk 1:07:54

Mallow Boardwalk

It’s Time To 0:14:24

It’s Time To Put A 3D Scanner In Your Toolbox

Комментарии
Автор

Another great video from my birthplace. Thank you!
Why are you using a overlap at the chunks, when you have to join the chunks for clustering? Or does this have no effect?

ki-werkstatt
Автор

Thanks for this! I’ve been extending this to find values for n_neighbors, dims, etc that maximize the quality of the clusters. I’m applying this to 10-k filings which are pretty similar in overall “semantic” content and organization, so I’m hoping that as I process more 10-Ks, I’ll gradually find a set of parameters that generalizes well across most 10-ks. Kind of surprising that I haven’t seen anyone talk about this as far as RAPTOR

RiskSeeking-gimi
Автор

Hi, is line 157 in the code meant to come before the iteration summaries loop or after in line 165? i.e. are we updating the all_summaries field with the previous cluster texts or does it not matter? Otherwise we would be updating "iteration summaries["texts"]" with the same value as "iteration summaries["summaries"]"

patriciachirwa
Автор

Awesome. If I might suggest: how about a tutorial on CodeGen-specific advanced RAG, i.e. repository-wide code "understanding" and generation? :) Cheers!

robertputneydrake
Автор

Is this subject to loss in the middle problem?

lesptitsoiseaux
Автор

Thanks, why not using open source LLM and embeddings?

henkhbit
Автор

Ho it look like my idea in the previous video no ?
So you don’t need anymore the code ?

loicbaconnier