Re:Show HN: Agentflow – Run Complex LLM Workflows from Simpl...
by gremlinsinc on Tuesday August 08, 2023 @06:35PM
(#37056403)
If ever there was a place where a standard would be nice, it's with LLM API's.
Re:Show HN: Agentflow – Run Complex LLM Workflows from Simpl...
by simonmesmith on Tuesday August 08, 2023 @08:28PM
(#37057296)
Agreed. Right now it seems like everyone’s trying to differentiate, e.g. with function calling (OpenAI) and longer context windows (Anthropic). So a universal API wouldn’t work.
Re:Show HN: Agentflow – Run Complex LLM Workflows from Simpl...
by pablo1107 on Tuesday August 08, 2023 @08:03PM
(#37057118)
There is probably use for go-skynet/LocalAI[0] or lm-sys/FastChat[1] which can emulate an OpenAI API using local models.
0: https://github.com/go-skynet/LocalAI 1: https://github.com/lm-sys/FastChat/
Edit: idk if any of this support function calling tho
Re:Show HN: Agentflow – Run Complex LLM Workflows from Simpl...
by simonmesmith on Tuesday August 08, 2023 @08:26PM
(#37057285)
I don’t know of any other models that support function calling like OpenAI’s, unfortunately.
The main issue right now is that I’m relying on the OpenAI API’s function-calling capabilities to enable the use of functions in workflows.
If we switch to other LLMs, we’ll need to create some additional wrapping around them to allow such function calling. (As far as I know. If any open source LLMs already have function calling built in, let me know.)
LangChain (which I’m not using due to personally finding it overcomplicated and too obfuscating) does have function calling, but it uses approaches like REACT (if I remember correctly) that aren’t as reliable as OpenAI’s approach.