Compile declarative DSPy programs into optimized LLM pipelines with teleprompters.
npx skills add https://github.com/MarbleSodas/Mavis --skill dspy-marblesodas
Please help me install this Agent Skill. Skill: dspy Source: https://github.com/MarbleSodas/Mavis/tree/main/skills/mlops/research/dspy Command: npx skills add https://github.com/MarbleSodas/Mavis --skill dspy-marblesodas
DSPy eliminates brittle, manually-tuned prompt engineering by compiling declarative LM programs into self-improving pipelines driven by data and evaluation metrics.
Configure a DSPy module for your task, then run an optimizer like BootstrapFewShot using a metric that scores the correctness of outputs on your labeled examples.
High-intent search queries and answers about installing and using this skill.
Automatic prompt optimization is achieved by defining declarative LM programs as signatures and running a teleprompter optimizer like BootstrapFewShot, which compiles your modules into reliable LLM pipelines using training data and evaluation metrics.
Building reliable RAG pipelines involves configuring declarative DSPy modules for multi-stage retrieval and reranking, then applying a teleprompter optimizer to improve generation quality against a held-out evaluation set.
To evaluate question answering accuracy, define a QA module using DSPy signatures, specify a custom evaluation metric to score correctness, and run an optimizer to produce a module that improves over time with your labeled examples.
Yes, declarative LM programs support wiring language model providers like OpenAI and Anthropic to execute tasks such as typed information extraction, multi-stage research agents, and code-based reasoning pipelines.
Prompt performance degrades because manually-tuned prompts are brittle; compiling declarative LM programs with a teleprompter optimizer automatically adjusts instructions and few-shot examples to fit the new model's behavior.
Yes, labeled examples are required to run automatic prompt optimization, as teleprompters like BootstrapFewShot and MIPRO rely on training sets and custom evaluation metrics to iteratively improve language model pipelines.
SriRamkunamsettyAutomate AI pipeline construction with declarative LM programming and prompt optimization.
VYRE-StudiosBuild declarative AI pipelines for language model tasks using Python and dspy.
carterwayneskhizeineBuild declarative language-model programs with structured signatures and optimizers.
liuerfireDesigns, optimizes and evaluates prompts for LLMs using techniques like chain-of-thought and few-shot learning.
