GraphAcademy Live: Neo4j & LLM Fundamentals

Подписаться 50 тыс.

Просмотров 2,5 тыс.

50% 1

Discover the power of integrating Neo4j with Generative AI models through Langchain.
Learn how to use graph databases to enhance the accuracy and reliability of Large Language Models (LLMs) by grounding them with factual information, effectively preventing misinformation or 'hallucinations.' We go hands-on using Langchain and Python to seamlessly connect an LLM with Neo4j, using Cypher and Vector Indexes for robust AI applications. Although we focus on OpenAI models, Langchain's versatility allows for exploring various LLMs.
Presenter: Martin O'Hanlon
Full Course: bit.ly/3zvclqo
0:00 Intro
3:40 GraphAcademy and Course Overview
5:55 Neo4j & GenAI
15:55 Avoid Hallucination
24:40 Grounding
28:30 Vectors & Semantic Search
34:35 Vector Indexes
47:38 Introductio to Langchain
54:30 Overview of Rest of Course
56:10 Q&A
58:44 Wrap-Up
#neo4j #graphdatabase #llm #langchain #genai #python #genai

Развлечения

Опубликовано:

25 июл 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 7

@j.hanleysmith8333 2 месяца назад

That's why I came here, hoping for this topic exactly.

@thanartchamnanyantarakij9950 3 месяца назад

still waiting for Constructing a Knowledge Graph with LLMs

@neo4j 2 месяца назад

we are working on it - hopefully we can talk about this one in more details soon!

@maged_helmy 6 дней назад

@@neo4j any updates?

@philippyoutube-account8625 2 месяца назад

How would you handle if the schema is too big for the LLM Context. Do I always need an embedding model to find the starting point. Or do you have other ideas on how to create a subgraph(subschema)?

@noghte 2 месяца назад

Some LLMs accepts a large quantity of tokens. If it still doesn't fit, you can create a chain. The first chain can be executing this prompt: 'given this schema, which nodes and relationships are related to this query? {user_query} answer in JSON and consider the relationship direction.' you can also provide an example of the JSON you'd like to receive as the sub-schema.