WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2024 • Nov 3, 2024 • Session details

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation

Carl Lapierre

Carl Lapierre proves basic vector search fails complex enterprise data. Discover how agentic RAG, hybrid algorithms, and DAGs create highly accurate, production-ready retrieval pipelines.

Pause
Mute Enter Fullscreen
#1 about 2 min

Speaker background and introduction to applied robotics work

How robotics and artificial intelligence applications solve industry challenges.

#2 about 2 min

Reviewing the basic retrieval-augmented generation pipeline

A walk-through of data preparation, chunking, embedding, vector storage, and retrieval.

#3 about 2 min

Real-world project examples and common pipeline requirements

Three case studies showing why explainability, accuracy, and complexity matter in search systems.

#4 about 1 min

Enhancing accuracy with hybrid search and reranking

Combining exact keyword matching with semantic search to improve retrieval relevance.

#5 about 1 min

Post-retrieval techniques using sibling and parent nodes

Expanding document context sizes prior to sending data to the language model.

#6 about 1 min

Data preparation improvements with abstractive processing

Using recursive abstractive processing to generate summary tree nodes for augmented context.

#7 about 2 min

Transitioning toward agentic retrieval-augmented generation frameworks

Adding reasoning steps through tool usage, memory, and orchestration components.

#8 about 2 min

Training models with reward functions and reinforcement learning

How large language models generate reinforcement learning reward functions for robots.

#9 about 3 min

Implementing self-critique and reflection in corrective systems

Evaluating retrieved node relevance to separate noise from useful knowledge snippets.

#10 about 2 min

Query translation and fusion for broadened search attempts

Rewriting user inputs across different perspectives to maximize relevant knowledge retrieval.

#11 about 1 min

Extending agent capabilities with customized function calling

Permitting the model to utilize external calculations, web lookups, and specialized algorithms.

#12 about 2 min

Managing complex query planning and reasoning loops

Comparing naive prompt routing to complex recursive reasoning patterns that isolate required tools.

#13 about 2 min

Parallel processing through directed acyclic graph frameworks

Modeling task dependencies to execute sub-queries simultaneously via advanced compiler architecture.

#14 about 2 min

Delegating workloads using multi-agent hierarchical collaboration

Separating concerns by creating atomic reasoning nodes equipped with specific capability scopes.

#15 about 3 min

Production considerations for advanced language model systems

Avoiding token cost overruns, unstable planning loops, and poisoned retrieval context.

Matching moments

1:32 min

Architectural patterns for developing robust generative AI applications

Julián Duque Julián Duque · World Congress 2025

2:05 min

Enhancing language models with retrieval-augmented generation

Mary Grygleski Mary Grygleski · LIVE

1:44 min

Understanding basic retrieval-augmented generation architectures in chatbots

Stan Girard Stan Girard · World Congress 2024

1:24 min

Expanding AI capabilities using retrieval-augmented generation

Cedric Clyburn Cedric Clyburn · World Congress 2024

2:00 min

Exploring retrieval augmented generation and advanced prompting techniques

Daniel Töws Daniel Töws · World Congress 2024

1:57 min

Understanding overarching retrieval and generation steps in RAG architectures

Csenge Szabo Csenge Szabo · Europe 2026 Virtual

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

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

Say goodbye to building boring APIs with Azure Data API Builder thumbnail
30:01
about 2 years ago

Say goodbye to building boring APIs with Azure Data API Builder

Sander ten Brinke

Related videos

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

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

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

When Should You Use an Agent? Architectural Trade-offs in Agentic Systems thumbnail
32:48
World Congress 2026 Europe • 3 months ago

When Should You Use an Agent? Architectural Trade-offs in Agentic Systems

Matheus Guimaraes

How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge thumbnail
42:26
Coffee With Developers • over 1 year ago

How to Avoid LLM Pitfalls - Mete Atamel and Guillaume Laforge

Meta Atamel, Guillaume Laforge

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

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.