Langchain vs LlamaIndex vs OpenAI GPTs: Which one should you use?

Are you using Large Language Models (LLMs) in your work and seeking the most effective way to leverage their power for your application? Then this video is for you. Let’s dive into LLM application development, comparing the paths of building your own framework from scratch with utilizing established platforms like LangChain, LlamaIndex, and OpenAI Assistants.
► Jump on our free RAG course from the Gen AI 360 Foundational Model Certification (Built in collaboration with Activeloop, Towards AI, and the Intel Disruptor Initiative): learn.activeloop.ai/courses/rag
►Twitter: / whats_ai
►My Newsletter (My AI updates and news clearly explained): louisbouchard.substack.com/
►Join Our AI Discord: / discord
Chapters:
0:00 Introduction
0:30 Coding everything yourself
1:30 Using OpenAI GPTs & assistants
2:54 When to use LangChain
5:05 When to use LlamaIndex
7:24 Recap and the best framework
#openai #llamaindex #langchain

[@footube3]

Excellent overview. Thanks so much for taking the time to create this!

[@mumpecydrone8788]

Thank you sooo much for this video. You have no idea how much time I saved with this

[@ladiflamez7415]

Hello Mauril! I'm hoping to learn how to create LLM apps from you, I have intermediate Python knowledge.
Best regards sensei !

[@Jonathan-rm6kt]

So after several weeks of diving into Langchain, I've personally found it to be cumbersome and overly complex for simple POC's I want to build. There are many integrations, but also a huge range of features, interface/method implementations, etc. The documentation page is great, *if* you are only mimicking the exact use case in the scenario. Try doing anything else, and found that the conceptual explanations are quite weak. I understand why they implemented LCEL, however that just adds yet another layer of abstraction to what would be a simple chain of function calls (and worse because you can't easily inspect what each component is doing. Has anyone else had this experience? Should i keep grinding, or spend more time hopping to even more platforms/integrations/etc. There are so many options!

[@luissantiagolopez3863]

I found the same result. However, I'm quite noob

[@ShantanuSingh-wc4ou]

This is a real gem. Keep working on these type of videos. Thank you.

[@augmentos]

Be cool to see agent swarm vs AutoGen 2 vs Lang graph

[@shoopieable]

Can i connect either of these to a MySQL database?

[@WhatsAI]

I believe you can yes! Llamaindex has libraries to deal with sql databases :)

[@shoopieable]

@@WhatsAI that's great, going to give it a try. So my use case seems plausible right. That I could be running natural language queries on my WordPress website (powered by MySQL) . Inclusive of customer purchases and orders which are stored in that database?

[@WhatsAI]

@shoopieable definitely sounds possible yes!

[@maxpaynestory]

OpenAI Assitant with Retrieval doesn't give good answers. LangChain + GPT3.5 + RAG give awesone answers.

[@WhatsAI]

Indeed!

[@s-guytech9160]

That's what I am currently using, you forgot to mention OAI A + R is slower and more expensive as well.