AgentOoba VS dspy

Something similar was implemented here: https://github.com/flurb18/AgentOoba

Github

Take a look at https://github.com/flurb18/AgentOoba. It's still missing some pieces but it appears they're being worked on..

Right now, the agent functions as little more than a planner / "task splitter". However I have plans to implement a toolchain, which would be a set of tools that the agent could use to complete tasks. Considering native langchain, but have to look into it. Here's a screenshot and here's a complete sample output. The github link is https://github.com/flurb18/AgentOoba. Installation is very easy, just clone the repo inside the "extensions" folder in your main text-generation-webui folder and run the webui with --extensions AgentOoba. Then load a model and scroll down on the main page to see AgentOoba's input, output and parameters. Enjoy!

I’ve observed that Pydantic - which we’ve used for years in our API stack - has become very popular in LLM applications, for its type-adjacent features. It serves as a foundational technology for prompting libraries like [DSPy](https://github.com/stanfordnlp/dspy) which are abstracting “up the stack” of LLM apps. (some opinions there)

Operating AI apps reveals a big challenge, in that debugging probabilistic code paths requires more than the usual introspective abilities, and in an environment where function calls can have very real monetary impact we have to be able to see what’s happening in the runtime. See LangChain’s hosted solution (can’t recall the name) that allows an operator to see prompts and responses “on the wire”. (It just occurred to me that Langchain and Pydantic have a lot in common here, in approach.)

Having a coupling between Pydantic - which is *just about* the data layer itself - and an observability tool seems very interesting to me, and having this come from the folks who built it does not seem unreasonable. WRT open source and monetization, I would be lying if I said I wasn’t a little worried - given the recent few months - but I am choosing to see this in a positive light, given this team’s “believability weight” (to overuse Dalio) and history of delivering solid and really useful tooling.

DSPy is the best tool for optimizing prompts [0]: https://github.com/stanfordnlp/dspy

Think of it as a meta-prompt optimizer, it uses a LLM to optimize your prompts, to optimize your LLM.

Isn’t this just a very naive implementation of what DsPY does?

https://github.com/stanfordnlp/dspy

I don’t understand what is exceptional here.

Have you done any comparison with DSPy ? (https://github.com/stanfordnlp/dspy)

Feels very similiar to DSPy except you dont have optimizations yet. But I like your API and the programming model your are enforcing through this.

I'm interested in hearing if anyone has used DSPy (https://github.com/stanfordnlp/dspy) just for prompt optimization for GPT-3.5 or GPT-4. Was it worth the effort and much better than manual prompt iteration? Was the optimized prompt some weird incantation? Any other insights?

You should check out x.com/lateinteraction's DSPy — which is like an optimizer for prompts — https://github.com/stanfordnlp/dspy