filmov
tv
Taking RAG Pipelines in Haystack to the Next Level With Document Ranking, Tuana Celik, Deepset
Показать описание
Taking RAG Pipelines in Haystack to the Next Level With Document Ranking, Tuana Celik, Lead Developer Advocate, Deepset
Retrieval Augmented Generation is one of the most promising techniques to make use of LLMs, while avoiding hallucinations. In this 10 minute lightning talk, we will discuss new ranking techniques for the retrieval step: Diversity Ranking, Recentness Ranking and “Lost in the Middle” Ranking. Each technique helps us improve different use cases of RAG pipelines. For example, we will see how diversity ranking can help achieve better results for long-form question answering, while “Lost in the Middle” aims to minimize valuable context being overlooked.
Video Recorded at The AI Conference. Copyright, The AI Conference, All Rights Reserved
Retrieval Augmented Generation is one of the most promising techniques to make use of LLMs, while avoiding hallucinations. In this 10 minute lightning talk, we will discuss new ranking techniques for the retrieval step: Diversity Ranking, Recentness Ranking and “Lost in the Middle” Ranking. Each technique helps us improve different use cases of RAG pipelines. For example, we will see how diversity ranking can help achieve better results for long-form question answering, while “Lost in the Middle” aims to minimize valuable context being overlooked.
Video Recorded at The AI Conference. Copyright, The AI Conference, All Rights Reserved
0:09:02
Intro to Haystack Pipelines: Build and customize AI applications
0:08:34
Taking RAG Pipelines in Haystack to the Next Level With Document Ranking, Tuana Celik, Deepset
0:46:03
Haystack by Deepset - Framework to Build LLM Apps | RAG Pipeline Using Haystack and OpenAI
0:06:55
Haystack AI: Production-ready RAG with Custom Data made easy!
0:12:05
Create Complete RAG Pipeline Locally and Free with FastRAG and HayStack
0:43:47
Deepset's Haystack 2.0: End-to-End LLM Pipelines for RAG Applications
0:38:43
Ramp Up Your RAG with Haystack 2.0
0:07:10
Evaluating Retrieval Augmented Generation for a PubMed QA App
0:34:02
Talks - Tuana Celik: Everything is a graph, including LLM Applications (and that’s handy)
1:06:24
Steps to Production: Evaluating RAG Pipelines
0:51:57
RAG Implementation using Mistral 7B, Haystack, Weaviate, and FastAPI
1:03:40
Tracing for Agentic AI Pipelines with Arize Phoenix & Haystack
0:53:15
Designing Retrieval Augmentation for Generative Pipelines with Haystack
0:22:35
Neo4j & Haystack Part 1: Knowledge Graphs for RAG
0:18:35
Building Production-Ready RAG Applications: Jerry Liu
0:06:36
What is Retrieval-Augmented Generation (RAG)?
0:11:14
RAG Pipeline with Haystack and NVIDIA NIM
0:26:26
How to Build a Question Answering Application with Haystack in 30 MinutesJulian NLP Summit
0:30:26
Ranking and Retrieval Techniques for Retrieval Augmented Generation with Haystack
0:14:25
Easy Way to Build Local RAG Pipeline with Ollama and Haystack
1:06:56
Python RAG - Haystack and MongoDB Atlas
0:02:53
Build a Large Language Model AI Chatbot using Retrieval Augmented Generation
1:05:38
Building Performant AI Applications with NVIDIA NIMs and Haystack
0:32:25
Neo4j & Haystack Part 2: How the Integration Works
Комментарии