Llama Index (aka GPT Index) Overview

Unlock the power of large language models like ChatGPT with llamaindex (formerly know as GPT Index)! In this video, we explore how this cutting-edge tool can help you efficiently interact with large bodies of data, from product catalogs to scientific research papers. Discover how llamaindex works, its benefits, and real-life examples of successful projects using it.

[@BeRohan5]

Hey! I would love to watch a detailed tutorial on how to setup the whole thing locally with opensource models.

[@ampef]

Thanks for writing Rohan and the suggestion. Yeah was thinking to do a deep dive into this, but the setup is a little too fragile right now with open source models. Waiting for FastChat to release an update allowing GPTQ 4bit support (github.com/lm-sys/FastChat/pull/487) as this would enable running the Vicuna 7B 1.1 with OpenAI formatted API calls and really streamline things.

[@storytimewithme2]

@@ampef update on this?

[@rahimnealyakoob5968]

great video, excited for the future of your channel !

[@johannesseikowsky8197]

Other people have already commented the same, but I'd also love to see that tutorial you mentioned at the end. Thanks a lot!

[@hilmiterzi3847]

Holy shit why haven't I see your channel before. This one is so good explained lol

[@ampef]

Thanks Ahmet, appreciate the feedback

[@mmacasual-]

Good Overview, no extra nonsense !! Keep on doing such videos, it's just a matter of time before people discover you. All the Best.

[@gcsk1982]

yeah agree. No extra nonsense. Love it.

[@byspec3239]

Would love to see what you described in the end of the video too, great video thanks!

[@BiranchiNarayanNayak]

Excellent tutorial on Llama Index.

[@jacobgoldenart]

great overview. I'd love to see more detailed deep-dives. Thanks

[@ampef]

Thanks Jacob. Was planning to do this shortly (see the comment to Rohan regarding the reason I've held back for now). In terms of the deep dive, anything specific you wanted me to focus on most?

[@mxolisibooi3706]

Thanks for this 🙏🏾

[@PerFeldvoss]

Key to using this would be that it can run on a local pc, not over the net. I know that would mean a lot of cost, but I guess that the data I will be using isn't huge!

[@ampef]

It's possible now without needing OpenAi calls. However, a GPU with 12GB ram is needed for best results. Will publish a tutorial once it becomes more straightforward with a lower memory GPU

[@Stubbelur]

Great video! I really hope you don't let the relatively low view counts discourage you. You have a great, if unrefined, talent for making content like this. Keep at it, and I'm sure you'll make your big break eventually :)

[@ampef]

Thank you for the feedback. Still planning to keep at it, just trying to tune my workflow a bit. Should have a new video on the channel shortly.

[@Stubbelur]

@@ampef Glad to hear. I'm just getting into LLMs hoping to make it part of my ETL pipeline, but not sure how it will turn out since it's not deterministic.

[@ampef]

@@Stubbelur Nice. Yeah, had an issue with this first hand. My work around was to provide the available options as context to the LLM, allow it to select the most appropriate option and then have a validator functioning double check if it really did select a viable answer (if not, re-run the LLM call).

[@anamtaamin6135]

how to perform summarization with llama index? Thanks

[@rahulvpoojari905]

Very helpful, how is this different from Langchain

[@mohammadtanvirhossain5576]

Great content buddy, would like a tutorial end to end from you.

[@enthuesd]

Hey great video. I'm looking to install llama index so this helps

[@adrianc1083]

What is the difference between this method and askPDF plugin?

[@nitinnp]

can i use llama index to summarize web url links

[@Niteshkumar-s5y8h]

How do we store those index to chat gpt so that every time return the result by reading my document files. I cannot send the entrire index content to gpt while asking some question?

[@mcfnord]

I think you first search your local vector database of embeddings, and pass embeddings that match along with your query to ChatGPT. But I dunno.

[@RUNFAST2010]

Nice work! I really enjoyed the tutorial. Any chance you could show how to do a localized .xls and LLAMA tie in?

[@ampef]

Any suggestion for the type of sheet you had in mind?

[@ampef]

Thanks for the kind comment ☺️

[@PaulJohnLeonard]

Thankyou, very good explination.

[@hilmiterzi3847]

What is your Linkedin?

[@ampef]

You can find me on LinkedIn here: www.linkedin.com/in/vassiliz/