filmov
tv
Fixing LLM Hallucinations with Retrieval Augmentation in LangChain #6
Показать описание
Large Language Models (LLMs) have a data freshness problem. Even some of the most powerful models, like ChatGPT's gpt-3.5-turbo and GPT-4, have no idea about recent events.
The world, according to LLMs, is frozen in time. They only know the world as it appeared through their training data.
So, how do we handle this problem? We can use retrieval augmentation. This technique allows us to retrieve relevant information from an external knowledge base and give that information to our LLM.
The external knowledge base is our "window" into the world beyond the LLM's training data. In this video, we will learn all about implementing retrieval augmentation for LLMs using LangChain and the Pinecone vector database.
🌲 Pinecone article:
📌 Code notebook:
👋🏼 NLP + LLM Consulting:
👾 Discord:
🎙️ Support me on Patreon:
🤖 70% Discount on the NLP With Transformers in Python course:
🎉 Subscribe for Article and Video Updates!
00:00 Hallucination in LLMs
01:32 Types of LLM Knowledge
03:08 Data Preprocessing with LangChain
09:54 Creating Embeddings with OpenAI's Ada 002
13:14 Creating the Pinecone Vector Database
16:57 Indexing Data into Our Database
20:27 Querying with LangChain
23:07 Generative Question-Answering with LangChain
25:27 Adding Citations to Generated Answers
28:42 Summary of Retrieval Augmentation in LangChain
#artificialintelligence #langchain #nlp #openai #deeplearning #chatgpt
The world, according to LLMs, is frozen in time. They only know the world as it appeared through their training data.
So, how do we handle this problem? We can use retrieval augmentation. This technique allows us to retrieve relevant information from an external knowledge base and give that information to our LLM.
The external knowledge base is our "window" into the world beyond the LLM's training data. In this video, we will learn all about implementing retrieval augmentation for LLMs using LangChain and the Pinecone vector database.
🌲 Pinecone article:
📌 Code notebook:
👋🏼 NLP + LLM Consulting:
👾 Discord:
🎙️ Support me on Patreon:
🤖 70% Discount on the NLP With Transformers in Python course:
🎉 Subscribe for Article and Video Updates!
00:00 Hallucination in LLMs
01:32 Types of LLM Knowledge
03:08 Data Preprocessing with LangChain
09:54 Creating Embeddings with OpenAI's Ada 002
13:14 Creating the Pinecone Vector Database
16:57 Indexing Data into Our Database
20:27 Querying with LangChain
23:07 Generative Question-Answering with LangChain
25:27 Adding Citations to Generated Answers
28:42 Summary of Retrieval Augmentation in LangChain
#artificialintelligence #langchain #nlp #openai #deeplearning #chatgpt
0:31:00
Fixing LLM Hallucinations with Retrieval Augmentation in LangChain #6
0:08:40
Reducing Hallucinations in LLMs | Retrieval QA w/ LangChain + Ray + Weights & Biases
0:09:38
Why Large Language Models Hallucinate
1:02:56
LLM Hallucinations in RAG QA - Thomas Stadelmann, deepset.ai
0:08:51
LLM Limitations and Hallucinations
0:10:46
How to Reduce Hallucinations in LLMs
0:07:23
Ep 6. Conquer LLM Hallucinations with an Evaluation Framework
0:00:16
Hallucination in Large Language Models (LLMs)
0:17:29
Chunking in RAG (Retrieval Augmented Generation) with hands-on in LangChain and LlamaIndex
0:55:40
Webinar: Fix Hallucinations in RAG Systems with Pinecone and Galileo
0:01:25
Grounding AI Explained: How to stop AI hallucinations
0:14:06
MoME Reduces LLM Hallucinations by 10X!
0:09:26
My 7 Tricks to Reduce Hallucinations with ChatGPT (works with all LLMs) !
0:00:49
Beating OpenAI Hallucinations — OP stack event
0:45:32
A Survey of Techniques for Maximizing LLM Performance
1:00:40
Mitigating LLM Hallucinations with a Metrics-First Evaluation Framework
0:02:04
Ai hallucinations explained
0:03:23
LLM hallucinations explained | Marc Andreessen and Lex Fridman
0:16:11
Agentic RAG: How to Take Your Retrieval to the NEXT Level
0:34:31
Lessons Learned on LLM RAG Solutions
1:19:27
Stanford CS25: V3 I Retrieval Augmented Language Models
0:09:36
How to Improve your LLM? Find the Best & Cheapest Solution
0:43:43
Combining LLMs with Knowledge Bases to Prevent Hallucinations // Scott Mackie // LLMs in Prod Con 2
0:35:53
Chatbots with RAG: LangChain Full Walkthrough
Комментарии