DSPy: The framework for programming with foundation models DSPy: Programming—not prompting—Foundation Models DSPy is the framework for solving advanced tasks with language models (LMs) and retrieval models (RMs). DSPy unifies techniques for prompting and fine-tuning LMs as well as improving them with reasoning and tool/retrieval augmentation, all expressed through a minimalistic set of Pythonic modules that compose and learn. To make this possible: DSPy provides composable and declarati…
A guidance language for controlling large language models. Where there is no guidance, a model fails, but in an abundance of instructions there is safety. - GPT 11:14 Guidance enables you to control modern language models more effectively and efficiently than traditional prompting or chaining. Guidance programs allow you to interleave generation, prompting, and logical control into a single continuous flow matching how the language model actually processes the text. Simple output st…
🖌 Webstudio Visual Builder Webstudio is an Open Source Visual Development Platform for developers, designers, and cross-functional teams. You own the data, components, and infrastructure. You can use the hosted version or roll out your own. Learning ressources Blog Community documentation Brand and product design Social Media Twitter Youtube Discord Contributing Contributing guide Github Discussions Wishlist Builder Issues tracker Roadmap Design Assets and docs
A Survey on LLM-based Autonomous Agents Autonomous artificial intelligence (AI) agents are designed to accomplish specific objectives by self-guided instructions, automatic memorization, planning, and action. With the advent and prospering of large language models (LLMs), there is an expanding frontier in using LLMs as core controllers for these autonomous entities. However, a unified view that ties together the diverse studies in this field has been lacking. This repository houses a comprehens…
Open source observability and analytics for LLM applications 🪢 Langfuse Open source observability & analytics for LLM-based applications Observability: Explore and debug complex logs & traces in a visual UI Analytics: Measure & improve costs, latency and response quality Join the Langfuse Discord » langfuse.com · Docs · Report Bu…
Open Source Creator DocumentationRoblox Creator Documentation This repository holds source code for the creator documentation at create.roblox.com/docs. Note: Currently, the repository has guides, tutorials, and educational content. Engine API reference files and code samples are coming soon. If you're unfamiliar with the GitHub contribution process, see About pull requests and the following video. contributing-to-creator-docs-on-github.mp4 Reporting Iss…
MagicEdit: High-Fidelity Temporally Coherent Video Editing MagicEdit: High-Fidelity and Temporally Coherent Video Editing Jun Hao Liew* · Hanshu Yan* · Jianfeng Zhang · Zhongcong Xu · Jiashi Feng ByteDance Inc. MagicEdit explicitly disentangles the learning of appearance and motion to achieve high-fidelity and temporally coherent video editing. It supports various edit…
Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals Scalene: a Python CPU+GPU+memory profiler with AI-powered optimization proposals by Emery Berger, Sam Stern, and Juan Altmayer Pizzorno. Scalene community Slack (tweet from Ian Ozsvald, author of High Performance Python) About Scalene Scalene is a high-performance CPU, GPU and memory profiler for Python that does a number of things that other Python profilers do not …
Implementation of Nougat Neural Optical Understanding for Academic Documents Nougat: Neural Optical Understanding for Academic Documents This is the official repository for Nougat, the academic document PDF parser that understands LaTeX math and tables. Project page: https://facebookresearch.github.io/nougat/ Install From pip: pip install nougat-ocr From repository: pip install git+https://github.com/facebookresearch/nougat There are extra dependencies if you want to call the model from…