WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2024 • Aug 20, 2024 • Session details

Build RAG from Scratch

philnash

Phil Nash proves you can build a vector search engine from scratch using just Node.js. Ditch traditional keyword matching and master the math behind Retrieval-Augmented Generation.

Pause
Mute Enter Fullscreen
#1 about 2 min

Overcoming large language model knowledge gaps

Large language models lack access to private organizational data and suffer from strict knowledge cutoff dates.

#2 about 2 min

Understanding the architecture of retrieval augmented generation

Augmenting user prompts with natively retrieved data context gives models accurate information to generate informed responses.

#3 about 2 min

Searching by semantic meaning with vector embeddings

Converting text into structured lists of numbers allows systems to mathematically represent and search for semantic meaning.

#4 about 7 min

Creating a sparse bag-of-words vector from plain text

Extracting a unique glossary enables generating a sparse array representation of text frequency using basic scripts.

#5 about 6 min

Measuring dimensional vector angle with cosine similarity

Calculating multidimensional vector direction through dot product and magnitude equations determines the structural similarity of records.

#6 about 2 min

Returning relevant matches with local similarity sorting

Mapping cosine similarity scores against incoming search vectors provides a functional foundation for local context retrieval.

#7 about 2 min

Understanding the performance and semantic limits of bag-of-words

A raw vocabulary approach suffers from exact-word dependency, calculation overhead, and ignores inherent linguistic context.

#8 about 2 min

Switching from sparse representations to dense embedding models

Purpose-built LLM embedding protocols automatically compress complex phrasing and negative inference into densely packed numerical dimensions.

#9 about 4 min

Scaling vector similarity search using dedicated databases

Vector databases handle high-volume embedding storage and native nearest-neighbor indexing far more efficiently than iterated local arrays.

#10 about 2 min

Advancing semantic boundaries with colbert and knowledge graphs

Incorporating token-level evaluation logic, knowledge graphs, and dedicated related-content engines significantly deepens modern system retrieval capabilities.

Matching moments

1:44 min

Understanding basic retrieval-augmented generation architectures in chatbots

Stan Girard Stan Girard · World Congress 2024

3:50 min

Building local RAG architectures using the Anything LLM tool

Cedric Clyburn Cedric Clyburn +1 · World Congress 2025

1:57 min

Understanding overarching retrieval and generation steps in RAG architectures

Csenge Szabo Csenge Szabo · Europe 2026 Virtual

1:24 min

Expanding AI capabilities using retrieval-augmented generation

Cedric Clyburn Cedric Clyburn · World Congress 2024

1:28 min

Reviewing the basic retrieval-augmented generation pipeline

Carl Lapierre Carl Lapierre · World Congress 2024

2:05 min

Enhancing language models with retrieval-augmented generation

Mary Grygleski Mary Grygleski · LIVE

More from World Congress 2024

Beyond the Hype: Real-World AI Strategies Panel thumbnail
24:07
12 months ago

Beyond the Hype: Real-World AI Strategies Panel

Mike Butcher, Jürgen Müller, Katrin Lehmann, Tobias Regenfuss

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation thumbnail
21:17
almost 2 years ago

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation

Carl Lapierre

Coding an Immersive Copilot using Unity / .NET and Azure OpenAI! thumbnail
31:50
about 2 years ago

Coding an Immersive Copilot using Unity / .NET and Azure OpenAI!

Zaid Zaim

Building a diverse tech company: The power of Diversity, Equity, Inclusion, and Belonging thumbnail
29:43
about 2 years ago

Building a diverse tech company: The power of Diversity, Equity, Inclusion, and Belonging

Sue Quackenbush

Dapr in Practice thumbnail
24:08
about 2 years ago

Dapr in Practice

marcklefter

Minimising the Carbon Footprint of Workloads thumbnail
27:46
about 2 years ago

Minimising the Carbon Footprint of Workloads

Michael Mueller

Related videos

Develop AI-powered Applications with OpenAI Embeddings and Azure Search thumbnail
57:52
LIVE • almost 3 years ago

Develop AI-powered Applications with OpenAI Embeddings and Azure Search

Rainer Stropek

The R in RAG: Why retrieval is often the weakest link (and how to fix it) thumbnail
28:22
World Congress 2026 Europe • 3 months ago

The R in RAG: Why retrieval is often the weakest link (and how to fix it)

Tomek Porożyński

Accelerating GenAI Development: Harnessing Astra DB Vector Store and Langflow for LLM-Powered Apps thumbnail
28:57
World Congress 2024 • about 2 years ago

Accelerating GenAI Development: Harnessing Astra DB Vector Store and Langflow for LLM-Powered Apps

David Leconte, Michel de Ru

How to Decipher User Uncertainty with GenAI and Vector Search thumbnail
24:47
World Congress 2025 • about 1 year ago

How to Decipher User Uncertainty with GenAI and Vector Search

Ben Greenberg

Scaling GraphRAG: Efficient Knowledge Retrieval for AI thumbnail
24:04
World Congress 2026 Europe • 3 months ago

Scaling GraphRAG: Efficient Knowledge Retrieval for AI

Gal Shubeli

Building Blocks of RAG: From Understanding to Implementation thumbnail
26:25
LIVE • almost 2 years ago

Building Blocks of RAG: From Understanding to Implementation

Ashish Sharma

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.