deeplake VS langchain

I think Activeloop(YC) is too: https://github.com/activeloopai/deeplake/

This repository contains two Python scripts that demonstrate how to create a chatbot using Streamlit, OpenAI GPT-3.5-turbo, and Activeloop's Deep Lake. The chatbot searches a dataset stored in Deep Lake to find relevant information and generates responses based on the user's input.

Deep Lake GitHub

As the world is increasingly generating vast amounts of financial data, the need for advanced tools to analyze and make sense of it has never been greater. This is where LangChain and Deep Lake come in, offering a powerful combination of technology to help build a question-answering tool based on financial data. After participating in a LangChain hackathon last week, I created a way to use Deep Lake, the data lake for deep learning (a package my team and I are building) with LangChain. I decided to put together a guide of sorts on how you can approach building your own question-answering tools with LangChain and Deep Lake as the data store.

Re: HF - we know them and admire their work (primarily, until very recently, focused on NLP, while we focus mostly on CV). As mentioned in the post, a large part of Deep Lake, including the Python-based dataloader and dataset format, is open source as well - https://github.com/activeloopai/deeplake.

Likewise, we curate a list of large open source datasets here -> https://datasets.activeloop.ai/docs/ml/, but our main thing isn't aggregating datasets (focus for HF datasets), but rather providing people with a way to manage their data efficiently. That being said, all of the 125+ public datasets we have are available in seconds with one line of code. :)

We haven't benchmarked against HF datasets in a while, but Deep Lake's dataloader is much, much faster in third-party benchmarks (see this https://arxiv.org/pdf/2209.13705 and here for an older version, that was much slower than what we have now, see this: https://pasteboard.co/la3DmCUR2iFb.png). HF under the hood uses Git-LFS (to the best of my knowledge) and is not opinionated on formats, so LAION just dumps Parquet files on their storage.

While your setup would work for a few TBs, scaling to PB would be tricky including maintaining your own infrastructure. And yep, as you said NAS/NFS would neither be able to handle the scale (especially writes with 1k workers). I am also slightly curious about your use of mmap files with image/video compressed data (as zero-copy won’t happen) unless you decompress inside the GPU ;), but would love to learn more from you! Re: pricing thanks for the feedback, storage is one component and customly priced for PB-scale workloads.

Deep Lake is fresh off the "press", so we would really appreciate your feedback here or in our community, a star on GitHub. If you're interested to learn more, you can read the Deep Lake academic paper or the whitepaper (that talks more about our vision!).

Continue reading | heck out the paper and github

GIthub: https://github.com/activeloopai/deeplake

Langchain and the implementation of Custom Tools also is a great (and very efficient) way to setup a dedicated Q&A (for example for chat purpose) agent.

We're using it via langchain talking to Amazon Bedrock which is hosting Claude 1.x. It's comparable to GPT3.x, not bad. The integration doesn't seem to be fully there though, I think langchain is expecting "Human:" and "AI:", but Claude uses "Assistant:".

https://github.com/hwchase17/langchain/issues/2638

Depending on how much work you want to put into it, you can get started at HuggingFace with their models and datasets, but you'd need compute power, multiple MLOps, etc. I was introduced to the concept in this video, since Google has their Vertex AI tools on Google Cloud, and there's always LangChain but I'm not sure about anything recent.

a documentation chatbot proof of concept using GPT3.5 and LangChain

I encourage everyone to pay attention to the Langchain open-source project and leverage it to achieve tasks that ChatGPT cannot handle.

Yeah I never know where memory goes exactly in langchain, it's not exactly clear all the time. But sure, the main insight I remember is this, take a look at their MULTI_PROMPT_ROUTER_TEMPLATE: https://github.com/hwchase17/langchain/blob/560c4dfc98287da1...

It's a lot of instructions for an LLM, they seem to forget an LLM is an auto-completion machine, and which data it is trained on. Using <<>> for sections is not a normal thing, it's not markdown, which probably the thing read way more often on the internet, instead of open json comments, why not type signatures, instead of so many rules, why not give it examples? It is an autocomplete machine!

They are relying too much on the LLM being smart because they probably only test stuff in GPT-4 and 3.5, but with GPT4All models this prompt was not working at all, so I had to rewrite it, for simple routing, we don't even need json, carying the `next_inputs` here is weird if you don't need it.

So this is my version of it: https://gist.github.com/rogeriochaves/b67676977eebb1936b9b5c...

It's so basic it's dumb, yet it is more powerful, as it does not rely on GPT-4 level intelligence, it's just what I needed