Llama-2-Onnx VS dify

System: Here's some docs, answer concisely in a sentence.

YMMV on cost still, depends on cloud vendor, and my intuition & viewpoint agrees with yours, GPT-3.5 is priced low enough that there isn't a case where it makes sense to use another model.

It strikes me now that _very_ likely and not just our intuition: OpenAI's $/GPU hour is likely <= any other vendor's.

The next big step will come from formalizing the stuff rolling around the local LLM community, for months now it's either been one-off $X.c stunts that run on desktop, and the vast majority of the _actual_ usage and progress is coming from porn-y stuff, like all nascent tech.

Microsoft has LLaMa-2 ONNX available on GitHub[1]. There's budding but very small projects in different languages to wrap ONNX. Once there's a genuine cross-platform[2] ONNX wrapper that makes running LLaMa-2 easy, there will be a step change. It'll be "free"[3] to run your fine-tuned model that does as well as GPT-4 .

It's not clear to me exactly when this will occur. It's "difficult" now, but only because the _actual usage_ in the local LLM community doesn't have a reason to invest in ONNX, and it's extremely intimidating to figure out how exactly to get LLaMa-2 running in ONNX. Microsoft kinda threw it up on GitHub and moved on, the sample code even still needs a PyTorch model. I see at least one very small company on HuggingFace that _may_ have figured out full ONNX.

[1] https://github.com/microsoft/Llama-2-Onnx

Perhaps this would be of use? https://github.com/langgenius/dify/ I use it for quick workflows and it's pretty intuitive.

This visual IDE for LLM pipelines was posted recently: https://github.com/langgenius/dify

See if it helps.

> https://github.com/langgenius/dify/blob/main/LICENSE

everyone is apparently a license pioneer

Xorbits Inference (Xinference) is an open-source platform to streamline the operation and integration of a wide array of AI models. With Xinference, you’re empowered to run inference using any open-source LLMs, embedding models, and multimodal models either in the cloud or on your own premises, and create robust AI-driven applications. It provides a RESTful API compatible with OpenAI API, Python SDK, CLI, and WebUI. Furthermore, it integrates third-party developer tools like LangChain, LlamaIndex, and Dify, facilitating model integration and development.

If you are looking to develop QnA or chat based apps then check out https://dify.ai. Do a quick check and see if it fit your requirements. You can integrate it with your app using the apis it provides

As an AI newbie, I used to find coding apps from scratch an absolute nightmare! The learning curve was steep as a ski slope, debugging took endless hours, and developing even a simple AI app nearly drove me insane! But since discovering Dify, it has totally revolutionized my life by enabling app development without any coding skills!