Pinned
Hey everyone! I am super excited to share that our new research report is live on ArXiv! 🎉
IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answering!
Thread with more details! 🧵(1/11)
Connor Shorten
19.2K posts
Connor Shorten
@CShorten30
AI and Databases @weaviate_io
- Hey everyone! I am super excited to share our new research report is live on ArXiv! 🎉 Querying Databases with Function Calling! Thread with more details! 🧵(1/8)
- DSPy is a SUPER exciting advancement for AI and building applications with LLMs!🧩🤯 Pioneered by frameworks such as LangChain and LlamaIndex, we can build much more powerful systems by chaining together LLM calls! This means that the output of one call to an LLM is the input to
- Unfortunately, Large Language Models will not consistently follow the instructions that you give them. This is a massive problem when you are building AI systems that require a particular type of output from the previous step to feed into the next one! For example, imagine you
- Anthropic's new Prompt Engineering podcast describes how most of the focus on effective prompting is around clearly describing the task. If a human cannot perform the task based on the description, you shouldn't expect the LLM to do it. 🎯 In addition to clearly describing aEffective prompting is the key to building with language models. How are you engineering your prompts? 🤨
- ChatGPT is amazing for regular expression writing in Python! 🤯🚀
- Llama 3!! 🦙🎉 I put together a quick video going through the release notes, how performance is reported and the plans for a 400B+ model, and then diving into a demo showing how to build a RAG system with Llama 3 and DSPy, and then most excitingly 🥁, Using DSPy's MIPRO
- I am making a new series of videos explaining the Introduction to Reinforcement Learning book by Richard Sutton and Andrew Barto chapter by chapter! Please check out chapter 1!! youtu.be/4SLGEq_HZxk #100DaysOfMLCode
- DSPy lets you prototype LLM Programs like AlphaCodium in 2 minutes! 🧩🔥
AlphaCodium - super interesting work that shows just how much alpha (no pun intended) is there from building complex prompt flows in this case for code generation. It achieves better results than DeepMind's AlphaCode with 4 orders of magnitude fewer LLM calls! This is a direct - Hello world, DSPy! I am SUPER excited to share a new video walking through the end-to-end of how to use DSPy to optimize the CIFAR-10 for LLM programs, RAG with FAQs! 🛠️ This tutorial contains *4 major parts*: (1) library installation, settings, and creating a dataset with
- Gartner has just published one of their famous Hype Cycle curves for 2023, specialized to Generative AI! The curve is encouragingly optimistic on Vector Databases, predicting we still have 5-10 years to hit the infamous Peak of Inflated Expectations! Here are 5 reasons why I
- GEPA is a SUPER exciting advancement for @DSPyOSS and a new generation of optimization algorithms re-imagined with LLMs! 🧩🚀 Starting with the title of the paper, the authors find that Reflective Prompt Evolution can outperform Reinforcement Learning!! 🤯 Using LLMs to write
