81–90 of 108 posts
Inefficiency (in other words, higher expense)is sometimes even easier to perceive for decision-makers
I wrote a book on LangChain and LlamaIndex about 14 months ago, and at the time I thought that RAG style applications were great, but now I am viewing them as being more like material for demos. I am also less enthusiastic about LangChain and LlamaIndex; they are still useful, but the libraries are a moving target and often it seems best to just code up what I need by hand. The moving target issue is huge for me, upd…
It’s strange: most answers here assume the next gen models won’t be able to perform RAG on its own. IMO, it would be wise to assume the opposite - anything humans currently do to make models smarter will be built in.
What I Observe: Simple RAG is Fading, but Complex RAG Will Persist and Evolve - Involving Query Rewriting, Data Cleaning, Reflection, Vector Search, Graph Search, Rerankers, and More Intelligent Chunking. Large Models Should Not Just Be Knowledge Providers, But Tool Users and Process Drivers"
Earlier quoted context omitted.
tl;dr we only need a vector database if we want to do semantic vector-embedding search AND our dataset is too large for memory long answer: RAG is just a pattern of working with LLMs, independent of particular database technologies. Basically it means you inject some context data or domain specific data into the prompt to achieve the following: 1. Nudging the model into the right direction so it will use the "correct…
Thank you for your insights. AS someone who is absolutely new to this, could you clarify the role of embedding in RAG? Do I need to use OpenAI's OpenAI embedding model (text-embedding-ada-002) always to use for embeddings ? Supposing I do use text-embedding-ada-002 model and store the index in a vector database, will I be able use these for RAG with other LLMs such as Claude Haiku etc. ? Or does each LLM have its own…
You need to use the same embedding for indexing and retrieval. Beyond that, you want to select an appropriate embedding; optimized for indexing the kind of content you have.
I wrote a book on LangChain and LlamaIndex about 14 months ago, and at the time I thought that RAG style applications were great, but now I am viewing them as being more like material for demos. I am also less enthusiastic about LangChain and LlamaIndex; they are still useful, but the libraries are a moving target and often it seems best to just code up what I need by hand. The moving target issue is huge for me, upd…
Do you have a problem with LangChain and LlamaIndex due to their changing codebases/APIs/etc., or do you think there's a fundamental issue with RAG itself?
I think both projects were super useful, grateful for them. There is a lot of utility tucked away in both projects.
A year ago,I started using LLM APIs in non-Python languages and realized that sometimes building from scratch is better.
Earlier quoted context omitted.
Do you have a problem with LangChain and LlamaIndex due to their changing codebases/APIs/etc., or do you think there's a fundamental issue with RAG itself?
Maybe a mixture of both? I think both projects were super useful, grateful for them. There is a lot of utility tucked away in both projects. A year ago,I started using LLM APIs in non-Python languages and realized that sometimes building from scratch is better.
That being said, I do use RAG a lot (though generally code most of the implementations myself).
We think that RAG is fundamentally limited: https://www.aryn.ai/post/rag-is-a-band-aid-we-need-llm-power... We do see a world where LLMs are used to answer questions (Luna), but it’s a more complex compound AI system that references a corpus (knowledge source), and uses LLMs to process that data. The discussion around context sizes is a red herring. They can’t grow as fast the demand for data.
Earlier quoted context omitted.
Based on what assumptions can one validly claim this is the ‘best’ solution? (In response to “The best solution to reducing the problem of Hallucinations is first someone telling us what their Error rates in production are.”) If I were to make an educated guess, one response would be akin to “one cannot correct errors without measuring the errors at prediction time”. This is incorrect; measuring prediction errors is…
The issue at hand right now, is that the discussion on Hallucinations is missing information on interaction with clients and users.
[1] "Expecting Short Inferential Distances" by E. Yudkowsky 2007
Transformer Memory as a Differentiable Search Index: