Tag
GEPA-optimized LLM judges from dspy are used for data filtering in Microsoft's MAI-Thinking-1 model pre-training pipeline.
The author compares Structural Equation Modeling, Neural ODEs, and AI Programs like DSPy as declarative frameworks for defining and optimizing computational graphs, arguing that structured flows are essential for trustworthy AI agents.
Ax is an open-source TypeScript library that implements DSPy-style typed signatures and agent frameworks for building reliable AI applications with minimal prompting. It supports multiple LLM providers and includes features like agents, flows, RAG, and self-improving pipelines.
DSPy has a new front page and documentation for easier onboarding, and is approaching a major DSPy 4.0 release with radical new ideas.
Ported the PEEK method to DSPy, allowing any DSPy agent to benefit from improved performance and cost reduction as demonstrated in the linked paper.
PEEK feature is coming to ax-agent, a TypeScript library for automatic prompt generation and AI agents, supporting multiple providers.
Manning Books announces a new early access book 'Building LLM Applications with DSPy', teaching how to use the DSPy framework to optimize LLM prompts with Python. The book is 50% off through June 3rd.
kg-gen is an open-source Python package that uses language models (via LiteLLM and DSPy) to extract knowledge graphs from plain text or conversation messages, featuring chunking, clustering, and flexible provider routing.
MaximeRivest explains DSPy's five core components—Optimizers, Signatures, LMs, Modules, and Adapters—and argues that effective AI engineering requires mastering these elements, highlighting the often-overlooked role of rendering structured outputs.
ROMA is a recursive multi-agent framework built on DSPy, designed to solve complex reasoning tasks through a hierarchical recursive structure. It supports task decomposition, parallel processing, and multiple LLM providers.
Maxime Rivest argues that compound AI systems for images are undervalued and suggests leveraging optimization frameworks like DSPy and GEPA to automate pipeline creation involving SAM and classifiers.
Tutorial shows how to quickly set up DSPy with GEPA and RLM using Claude and Codex, providing copy-paste ready code.
DSPy 3.2.0 improves dspy.RLM parsing, tool execution, and failure recovery, plus ongoing work to decouple from LiteLLM.
A social media post highlighting a writeup on applying RLM and DSPy to multi-modal data.
A post reflecting on the DSPy framework's architecture built around signatures, modules, and optimizers, and noting its continued growth since 2022.