Agentic RAG: Make Chatting with Docs Smarter

Рет қаралды 18,644

Prompt Engineering

Күн бұрын

Пікірлер: 31

@engineerprompt 4 ай бұрын

Checkout the Advanced RAG course here: prompt-s-site.thinkific.com/courses/rag

@criticalnodecapital 4 ай бұрын

thanks.. Can you become the ISHOWSPEED of AI. also are you based in USA or Subcontinent?

@engineerprompt 4 ай бұрын

@@criticalnodecapital haha, that would be a good achievement :D I am based in the USA.

@camerongolinsky Ай бұрын

Cool idea! When a course comes out focused on csv or databases, then I'll be there!

@unclecode 4 ай бұрын

So clear and simple compared to other libraries for building genetic pipelines. Intuitive and feels like it should've been in Hugging Face libraries from the start. Makes other libraries seem overly complex and unnecessary. Easy to create an LLM engine with just a callable class. You can build any structure, with complexity only from yourself, not the library. Not surprising from Hugging Face, just like how fine-tuning models with HF library is intuitive and easy. Love a simple, powerful library that doesn't over-abstract. This is the way. Thanks for sharing.

@engineerprompt 4 ай бұрын

Yeah, really like their implementation. Clean and straightforward.

@rocio6454 2 ай бұрын

Thanks for the video! it would be interesting to see a multiagent and routing approach with 2 sources like a vector store for rag and a sql db, each one with their agents

@olympiasaha7165 4 ай бұрын

It would have been interesting to see if you would have used GPT-4o as the LLM engine in the traditional RAG method to compare it with the agentic RAG response.

@legendchdou9578 4 ай бұрын

Great video can we use GROQ API for the LLM?

@Parthi97 3 ай бұрын

It depends upon the prompt message you give.. Yes we can utilize GROQ models for simpler agentic RAG process

@Jonzybeatz Ай бұрын

thanks for the video. I would like to analyze PDF studies of several hundred pages and make summaries to extract insights. The problem is that I can't copy/paste the pdf into GPT because it goes beyond the context window. Can I use RAG to do this use case? The RAG seems to be designed more for answering specific questions from a knowledge base than for synthesizing documents.

@Fact_is_Real 27 күн бұрын

YES OFCOURSE!

@anubisai 4 ай бұрын

Agentic RAG + Knowledge Graph would be bad ass. Someone steal my idea, please. 😂 🙏

@severian42 3 ай бұрын

working on it!!!!

@dulinak6251 3 ай бұрын

@@severian42 any updates?

@johnathanbell6992 3 ай бұрын

Any updates?

@proudestberozgaar 2 ай бұрын

@@severian42 Any updates?

@BamiCake 4 ай бұрын

In your video the agentic rag takes about 4 times longer (15 sec). Is there a way to speed up agentic rag?

@engineerprompt 4 ай бұрын

Unfortunately, using agents in the loop with take longer than standard RAG since it has to make additional calls to the LLM and do retrieval again. Over time you can cache queries and responses for faster retrieval.

@paragshah2943 4 ай бұрын

OP, Under what circumstances might you have duplicate chunks? Is it becuase two files that are same with differnt names?

@engineerprompt 4 ай бұрын

Yes, that happens a lot. In big datasets, there can be duplicates.

@nobody84980 3 ай бұрын

Why do I need an agent when I can add the agent description as a system prompt

@engineerprompt 3 ай бұрын

Agent has the ability to do multiple passes of retrieval if it's not able to find the info in the first pass. If you add this to the system prompt, I will just run once and can't repeat the process with reasoning and Planning.

@sauxybanana2332 4 ай бұрын

how does this compare to graph rag?

@iukeay 3 ай бұрын

It really depends on your use case. GraphRDF is currently ten to twenty times more expensive. Also, depending on the type of data and the type of query, it could be useful for you or not. It also increases lag by a very substantial margin. I have not found any startups or ideas implementing graph-lag effectively and usable yet. If you do, please keep me in the loop.