Automate declarative development and optimization of language model workflows.
npx skills add https://github.com/ZardLi1115/zedclaw --skill dspy-zardli1115
Please help me install this Agent Skill. Skill: dspy Source: https://github.com/ZardLi1115/zedclaw/tree/main/skills/mlops/research/dspy Command: npx skills add https://github.com/ZardLi1115/zedclaw --skill dspy-zardli1115
DSPy helps you avoid brittle, manually-crafted prompt pipelines by letting you describe model behavior declaratively and then automatically optimize it using data and evaluation metrics.
Example use case: You have a dataset of user questions with expected answers and you want a RAG agent that retrieves relevant passages, generates answers, and improves accuracy via an optimizer-driven evaluation loop.
Configure DSPy with your chosen LLM and create a signature-based QA predictor, then run it on a question to get an answer.
High-intent search queries and answers about installing and using this skill.
Declarative LM programming lets you define task inputs and outputs as signatures, then use optimizers and evaluation metrics to automatically compile better prompting strategies from your examples.
Yes, RAG pipelines support multi-hop retrieval and reranking approaches. You define the retrieval modules declaratively, then compile the workflow using optimizers to improve generation accuracy.
Configure your chosen LM backend like OpenAI or Anthropic, define declarative signatures for structured extraction or QA, then execute the pipeline to generate reliable outputs without manual prompt engineering.
Declarative LM programming replaces brittle manual prompts by defining agent behavior modularly using reasoning modules like ReAct, then automatically optimizing the behavior with data and evaluation metrics.
Yes, building and compiling pipelines requires defining DSPy Signatures and Modules in code, then optionally compiling them with teleprompters using custom evaluation metrics to optimize performance.
Inconsistent results often stem from unoptimized manual prompts. Using teleprompters to compile your declarative pipeline with evaluation metrics standardizes behavior across LM backends like OpenAI and Anthropic.
SriRamkunamsettyAutomate AI pipeline construction with declarative LM programming and prompt optimization.
granietCompile task signatures into optimized language model pipelines with DSPy.
tankpkgDesign production RAG pipelines with chunking, retrieval, reranking, and context assembly.
rickyanandaBuild and optimize declarative language model programs with structured signatures.
