It's open-source and everything is running locally on your computer, so you can even use it offline :)
646 karma · joined November 12, 2013
The example just calls a single LLM what about that is agentic?
It sounds like this app for windows does that.
That's wy I built the simple LLM agents repo which you can understand in 5 minutes:
To be fair to langchain, though: I like it a lot and it offers a lot more than my repo, but yeah definitely not the best place to understand how it all plays together.
Some kind of ensemble agent which is more robust, might play with that idea.
So even though there was a thought, I didn't print it
To make them more accessible I rewrote them in ~200 lines of code, so you can easily understand how it works.
They have access to a python console, Google search and hacker news search:
Should be fine, though, as it iterates over it, it creates embeddings and then stores them in the FAISS store (https://github.com/facebookresearch/faiss) which was created to handle a large amount of embeddings.
For the actual queries, it filters it down by the most relevant documents which are closest in the embedding space, so this should work.
Let me know how it goes!
It cost around 0.05$ to create the embeddings for my ~50 blog entries.
Asking a question in the way I've described it also costs around 0.05$ via the API.