openai-python VS langchain

The ongoing model anchoring/grounding issue likely affects all GPT-4 checkpoints/variants, but is most prominent with the latest "gpt-4-turbo-2024-04-09" variant due to its most recent cutoff date, might imply deeper issues with the current model architecture, or at least how it's been updated:

https://github.com/openai/openai-python/issues/1310

See also the original thread on OpenAI's developer forums (linked on the GitHub issue) with confirmations from others.

A test code snippet is included in the GitHub issue to A/B test the problem yourself with your own questions if need be.

- Iterate on large codebases quickly: we use Rust for maximum performance

GritQL has already been used on thousands of repositories for complex migrations[1] but we're excited to collaborate more with the open source community.

[1] Ex. https://github.com/openai/openai-python/discussions/742

Explore OpenAI and learn how to easily integrate it into your existing application with the OpenAI Python module.

You tried to access openai.Completion, but this is no longer supported in openai>=1.0.0 - see the README at https://github.com/openai/openai-python for the API. You can run `openai migrate` to automatically upgrade your codebase to use the 1.0.0 interface. Alternatively, you can pin your installation to the old version, e.g. `pip install openai==0.28` A detailed migration guide is available here: https://github.com/openai/openai-python/discussions/742

Relatedly, I checked and OpenAI deleted all references to their ChatML spec from their GitHub repo.

This is what it said in an earlier commit: https://github.com/openai/openai-python/blob/2942bf4bb635b1e...

Make sure to install the OpenAI library first. Since I'm using Python, I need

Source: https://github.com/openai/openai-python/discussions/742

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