Advanced RAG with ColBERT in LangChain and LlamaIndex

[@engineerprompt]

If you are interested in learning more about how to build robust RAG applications, check out this course: prompt-s-site.thinkific.com/courses/rag

[@pawan3133]

can you make a video on how to evaluate a RAG? And compare different RAG approaches.

[@joxxen]

I would also be interested in this :) specially with open source llm's and embeddings. Tried alot and cant figure out which is the best one

[@KOTAGIRISIVAKUMAR]

@@joxxen I`m to waiting for that if you found any resource let me know.

[@mjaym30]

Very interesting video indeed!! Could you please create a video on how to use colBERTv2 for embedding with pg_vector for persistent storage?

[@nbbhaskar3294]

@engineerprompt, can we use a persistant vector db like chroma, qdrant and others with Ragatouille? So that I can just embed the documents once and re-use them for inferences later.

[@engineerprompt]

It supports only FAISS at the moment for persisting it to disk

[@hamslammula6182]

I’d like to do RAG over a medical textbook. What strategies would you recommend for chunking. I’m thinking a hierarchical graph structure makes intuitive sense. What are your thoughts on this?

[@iaincampbell4422]

Cant find the google collab notebook? Would love to copy this across to my own account and havd a play. Not sure if I'm overlooking it? I just see the github link?

[@valentind.5398]

Thanks for sharing

[@jayethompson3414]

Is the Plaid DB persistent? As in, if I do this, how do I connect to that particular DB again?

[@almirbolduan]

How can we use approaches like ColBERT with other languages, as portuguese? Thanks!

[@engineerprompt]

I think you will have to finetune the model for the language first

[@shameekm2146]

I am working on a machine that is running Ubuntu and connected to 4 80GB A100 GPU's. The issue i face is RAG.index cell is running forever on this machine. Whereas same code running on Google Colab free version runs within seconds. Any insights on how this can be resolved will be helpful. Thanks :)

[@engineerprompt]

Is your env able to see the GPUs? Check that the torch is actually using the gpu

[@shameekm2146]

@@engineerprompt yes i run LLM's on same notebook, it is able to load that to gpu. I checked via nvidia-smi command

[@StarWarsNexusGalaxy]

Navigating the landscape of storytelling and video experimentation, VideoGPT silently empowers my creative journey, adding a layer of sophistication to my content.

[@iham1313]

of course the last result is more accurate. you gave it almost 50% (5 instead of 3 chunks) more context. when using multiple ways to achieve the same goal, please use the same amount of data. otherwise it is hard to compare the output. on the topic of chunks given to RAG - why define that? what if one does not know about how many parts may contain relevant information?

[@engineerprompt]

If you are interested in leanring more about Advanced RAG Course, signup here: tally.so/r/3y9bb0

[@linuswatiti8078]

How can I monetize whatever is being said as a beginner..?