A deep dive into Retrieval-Augmented Generation with Llamaindex

In this talk we cover:
* What LlamaIndex is
* What LlamaHub and create-llama are
* The stages of Retrieval-Augmented Generation (RAG)
* LlamaIndex's ingestion pipeline with caching
* The set of vector stores, LLMs and embedding models available in LlamaIndex
* Inspecting and customizing your prompts
* And then seven advanced querying strategies, including
* SubQuestionQueryEngine for complex questions
* Small-to-big retrieval for improved precision
* Metadata filtering, also for improved precision
* Hybrid search including traditional search engine techniques
* Recursive Retrieval for complex documents
* Text to SQL
* Multi-document agents that can combine all of these techniques

[@yashshukla7025]

have gone through 100s of videos for llama index - and this is the best one

[@jasonliu6213]

I think we’re the lucky few who discovered this.

[@bruinaly]

Best overview I've seen. Thank you!

[@cgintrallying]

Thanks for the clear introduction into the possibilities of llama-index

[@johanteekens4456]

thanks for this very clear overview and explanation!

[@HazemAzim]

Best High level coverage on LLamaIndex .. Thank you .. Good job

[@schepa1234]

Thank your for your excellent video!

[@98f5]

Just found your repo today and have been doing this with some custom code to convert sdk docs and code into a graphdb. This looks like it'll be extremely helpful. Thank you

[@cgintrallying]

Interesting - what is your use case if i may ask ?
I am about to test such a scenario in the near future as well.
The most interesting part for me is to achieve this with open models and completely local datastores in the end.
For sure also comparing to enterprise models like GPT-4 and Gemini to see what is possible and where the huge models are helpful and where smaller models reach a comparable output.

[@gustavstressemann7817]

This is nice stuff.

[@hydtechietalks3607]

your reading text killled the mojo of learning...as if old news reader.... But Hats off to the efforts!

[@randradefonseca]

I would like to see a complete script in which you show all these functionalities, I hope you publish it soon. Thank you.

[@explorer945]

Performance makes key differentiator apart from novel techniques. I heard some criticism on langchain. Hoping you guys do better in both performance and most reliable RAG with intuitive implementation

[@_XY_]

Cool 👏

[@ragsAI]

Hi! Is Langchain integratable/compatible with redshift/databricks? (especially the text-to-sql framework)? Thank you.

[@nguyenne21]

could you share the slide please, I would be appreciated

[@WilliamReyor]

Laurie Voss is awesome.

[@98f5]

Even better its in ts!

[@UdaySatapathy]

So many ads!