So, it feels like this should exist. But I couldn't find it. So I tried to build it.Agentflow lets you run complex LLM workflows from a simple JSON file. This can be as little as a list of tasks. Tasks can include variables, so you can reuse workflows for different outputs by providing different variable values. They can also include custom functions, so you can go beyond text generation to do anything you want to write a function for.Someone might say: "Why not just use ChatGPT?" Among other reasons, I'd say that you can't template a workflow with ChatGPT, trigger it with different variable values, easily add in custom functions, or force the use of custom functions for steps in the workflow.Someone might also say: "Then why not use Auto-GPT or BabyAGI?" Among other reasons, I'd say you can't if you want consistency because these tools operate autonomously, creating and executing their own tasks. Agentflow, on the other and, lets you define a step-by-step workflow to give you more control.I'd like to do more with this, including adding more custom functions, and more examples, and more ways to trigger workflows (such as in response to events). But first, I want to make sure I'm not wasting my time! For starters, if something like this already exists, please tell me.
Users suggest collaborations with Magic Loop and API discussion, and recommend using cached AI results for consistency. There's interest in workflow automation tools like api2ai and FlowFlow.AI, as well as open-source alternatives to Step Functions. The tool receives praise for its functionality, with requests for workflow configuration details, examples, and comparisons to LangChain. Curiosity about function calls and image generation is noted. Users express interest in trying the tool, and there are inquiries about support for local LLMs and potential use of LocalAI or FastChat for OpenAI API emulation. The need for a standard LLM API and appreciation for lightweight alternatives to LangChain are also mentioned.
Users criticized the product for lacking AI for user input, requiring Python, needing more examples and a LangChain comparison, unclear statements about 'no code with LangChain', no support for local LLMs, uncertainty about function calling support, lack of a standard for LLM APIs, and the JSON basis being moot without a provided library.