langchain VS Prompt-Engineering-Guide

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

Prompt Engineering Guide is the holy grail of all guides, aiming to make it easier to stay up-to-date with prompt engineering guides, techniques, applications, and papers. If you are getting started, this is an excellent place to start.

Guides, papers, lecture, notebooks and resources for prompt engineering: https://github.com/dair-ai/Prompt-Engineering-Guide

this has been a great resource. approachable and great for practitioners. it's frequently updated with new papers and techniques https://www.promptingguide.ai/

The idea behind prompt engineering is to construct the queries given to the language models to optimise their performance. This helps to guide them to generate the desired output by fine-tuning their response. There is a plethora of research papers out there on different forms of prompt engineering. DAIR.AI published a guide on prompt engineering that you might find useful to get started.

Prompt Engineering Guide

Let's try to understand what is Prompt Engineering is all about. Here's the quote from Prompt Engineering Guide. DAIR-AI

I found this resource [0] handy for getting a grasp on all the different terms people use (zero/one-shot, tree of thoughts, RAG, etc). It's not super detailed, but was enough for me (a professional developer) to get started on some side projects with Mistral.

[0] https://www.promptingguide.ai/

There are better guides out there too

- https://www.promptingguide.ai/readings

- https://github.com/dair-ai/Prompt-Engineering-Guide/tree/mai...

- https://github.com/microsoft/promptbase (this one is less of a guide, but is likely the current SoTA)