rivet VS dspy

But now coming to today's tool, let's talk about a topic that comes and goes, but it's always fun to play around with. I'm referring to AI; as you know, I'm not an AI-addicted person, but I like to have my share of fun with it! And a few days ago I came across the program that I am presenting to you today which aims to be very interesting and fun! Rivet, this is the name of the tool of this week, is a visual development environment for AI agents. But in what sense? Well, once you download the software, you will have a drag and drop interface to create a flow of information that can interact with various LLMs, whether it's GPT, Google models, or even Open models like Ollama running locally. It can handle all the classic control flows (if, loop etc.) and can integrate JS functions directly into it or import them from the project where we decide to incorporate it.

https://rivet.ironcladapp.com

Legal practitioners often need to find specific cases and clauses across thousands of dense documents. While traditional keyword-based search techniques are useful, they fail to fully capture semantic content of queries and case files. Vector search engines and large language models provide an intriguing alternative. In this talk, I will show you how to build a legal search application using the DSPy framework and the Milvus vector search engine.

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