LlamaIndex Workshop: Building RAG with Knowledge Graphs

Показать описание

We host a comprehensive workshop with Wey Gu (NebulaGraph) on how to use LLMs with Knowledge Graphs. Come learn everything from the basic concepts to hands-on sections going through automated KG construction and querying, to simple demo examples.

We cover the key concepts:
- How to construct a knowledge graph automatically
- How to query a knowledge graph with different approaches (Graph RAG, Text-to-Cypher)

LlamaIndex

Рекомендации по теме

Комментарии

Very impressive and can't wait to try these methods out✨

lion

So nice to see this video. Bravo Nebula.

saraili

Thank you for showing how to persist index to disk and reload on separate machine 👍

jonathansims

thank you very much for this informative explanation. looking forward to getting this up and running for a project I'm working on.

EmilioGagliardi

Any clue if we already have property graph how to make Rag on top of it. I have created nodes and relationships and properties already and stored in Neo4j

killerdrama

Hi.. I see triplets getting stored in nebula graph(local or on cloud). So why we need persistent storage? can't we directly access the nebula server to get the relations?

jaysadhwani

Can you tell us which python version you were using and have you used an new virtual environment or not?

mohamedhazem

I want a system where I upload PDFs and it makes a knowledge graph and I have a viable product.

generativeresearch

I can't understand the speaker very well.

milindbebarta

great content... but a bit too long, would have loved a more to the point and concise explanation

VibhaVikramRao

I don't like the speaker, he can barely explain things clearly. What is language module...I guess he was trying to say language model...And it is in-context learning, rather than in-content learning... Also, the code will be opaqued when he moved his mouse, I can hardly see anything...

chloetete

It’s so stressful to follow the speaker, may be this video is not for a beginner. Speaker starts directly explaining without explaining what is he focusing to solve.

diwakardayalan

please postprocess these recordings to remove "umm"s, those filler words that make it quite unpleasant to watch. There must be automatized tools you can use in a click. All the quality content but poor presentation unfortunately. Thank you

burada

new_index =
documents,
max_triplets_per_chunk=2,
service_context=service_context,
include_embeddings=True,
)
In the above case, how are the embeddings getting created?

techstrolls_with_vibha

LlamaIndex Workshop: Building RAG with Knowledge Graphs

LlamaIndex Workshop: Building RAG with Knowledge Graphs

Building RAG with Knowledge Graphs | Workshop with LlamaIndex

New course: Building Agentic RAG with LlamaIndex

Building Production-Ready RAG Applications: Jerry Liu

Building a multi-strategy RAG workflow with reflection in LlamaIndex

Building Production RAG Over Complex Documents

Building and deploying multi-agent RAG systems in 2024 with LlamaIndex

LlamaIndex Workshop: Multimodal + Advanced RAG Workhop with Gemini

Practical Tips for Building Production-Grade RAG Applications with LlamaIndex

RAG Workshop with Langchain and LlamaIndex

Build Agents from Scratch (Building Advanced RAG, Part 3)

@LlamaIndex CEO Jerry Liu talks about what is Retrieval Augmented Generation #shorts

LlamaIndex Webinar: Using RAG with LlamaIndex for Large-Scale Generative Coding

LlamaIndex Webinar: Improving RAG with Advanced Parsing + Metadata Extraction

😲 Building Advanced RAG systems #ai

Learn RAG From Scratch – Python AI Tutorial from a LangChain Engineer

LlamaIndex Webinar: Make RAG Production-Ready

LlamaIndex Workshop: Evaluation-Driven Development (EDD)

High-performance RAG with LlamaIndex

Agents in LlamaIndex : 02 : How to add Agents to your RAG application ?

Agentic RAG with LlamaIndex Workflows

LlamaIndex: Building RAG Applications with Multiple Data Sources

LlamaIndex Webinar: Building LLM Apps for Production, Part 1 (co-hosted with Anyscale)

How to build Multimodal Retrieval-Augmented Generation (RAG) with Gemini