paper-qa VS langchain

Why does this post link to a renamed fork of Paper-QA (https://github.com/whitead/paper-qa) which has made zero changes and is 19 commits behind the original?

To be honest, I'm not too sure about this part, and think that it is probably not the best approach to have the model itself generate references. I prefer the approach used in e.g. paperqa, but wanted to explore both options.

I’ve come across Paper QA (github page) and as a graduate student I loved the idea that when I do literature review and find tons of papers I can just ask the AI to find the info I’m looking for in the paper. However, this service requires OpenAI API key, which I’ve acquired but turns out it’s a paid service. Free key doesn’t get me anything. Is there a service/software like this that is free? Or something that I can host on my PC instead of using people’s servers so it’s cheaper/free?

I tried it [1] a lot, but I must say it confuses me most of the time and I need to read the original text to check if it makes sense. Lots of times it doesn't.

[1] https://github.com/whitead/paper-qa

Have a look at this: https://github.com/whitead/paper-qa

1: We are finding out. Someone else mentioned: https://github.com/whitead/paper-qa We're hoping to keep our service be accessible and easy to use, and add features. Such as from your other questions...

2: We are thinking of the website integration. Do you think OpenAI may release this too? Questions received by email is a new idea that sounds interesting!

3: Thanks for the suggestion – we will look into it.

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