LlamaIndex Sessions: 12 RAG Pain Points and Solutions

Подписаться 21 тыс.

Просмотров 15 тыс.

50% 1

We’re excited to feature Wenqi Glantz for a personal walkthrough video of her popular “12 RAG Pain Points and Solutions” blog post, which is the most comprehensive cheatsheet we’ve seen of pain points that occur at every stage of the RAG pipeline: data ingestion, retrieval, reranking, synthesis, and more.
Source paper: towardsdatasci...

Опубликовано:

30 окт 2024

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист

Посмотреть позже

Комментарии : 14

@pim8268 21 день назад

What a lecture. Simply amazing.

@DonBranson1 7 месяцев назад

simply amazing. I liked your constructive response to a paper with a pessimistic title. Embrace your challenges and keep moving forward. Appreciate the mapping to LllamaIndex Notebooks.

@kenchang3456 5 месяцев назад

Excellent video, and very informative. Thank you very much.

@kevon217 8 месяцев назад

Excellent compilation. Super helpful.

@christyson4245 8 месяцев назад

This is brilliant! Thanks for sharing!

@duongkstn 8 месяцев назад

very informative, thanks !

@karanv293 8 месяцев назад

im genuinely confused. what is the most accurate strategy to date? Theres so many tutorials out there , which one should I use for my use case. If you could guide me on that and then I can follow along a tutorial of somekind would be great. For example, i saw your posted workshop of advanced RAG with gemini. Should i follow that as the guide?

@evermorecurious91 8 месяцев назад

Haha. You can read the SOTA of RAG paper. This stuff keeps evolving, so you better follow one good source or be that source.

@karanv293 8 месяцев назад

@@evermorecurious91 hahaha yeah I guess just stick with one and go with it.

@sysadmin9396 8 месяцев назад

I have a python flask chatbot working hosted on AWS. Issue is all users that query the bot are getting answers from other users, in other words, it’s just one huge chat session for many users. How can I separate the sessions?

@utsavdavda8419 12 дней назад

You can cache each users data separately by maintaining separate cache. In each session if the chatbot stores some data temporarily it should store it at the designated cache of the user.