Compile declarative language model calls into self-improving pipelines.
npx skills add https://github.com/Rheasilvia/hermes-desktop --skill dspy-rheasilvia
Please help me install this Agent Skill. Skill: dspy Source: https://github.com/Rheasilvia/hermes-desktop/tree/main/optional-skills/mlops/research/dspy Command: npx skills add https://github.com/Rheasilvia/hermes-desktop --skill dspy-rheasilvia
This Skill solves the fragility and manual labor of traditional prompt engineering by providing a framework to program language models declaratively and optimize them automatically.
Use the dspy skill to optimize a question-answering module by compiling it against a provided training dataset of question-answer pairs.
High-intent search queries and answers about installing and using this skill.
Automate prompt engineering by compiling declarative language model programs into self-improving pipelines. This framework abstracts prompts into modular signatures and uses data-driven optimizers to systematically improve instructions.
Build portable RAG systems by defining modular pipelines declaratively rather than using brittle prompt templates. This approach allows complex retrieval workflows to be compiled and optimized independently of the underlying language model.
Optimize few-shot examples by compiling declarative modules against a training dataset of input-output pairs. The framework uses automatic optimizers to synthesize effective demonstrations and improve multi-stage classification accuracy.
Training data is required to execute automatic prompt optimization. You must provide a dataset of input-output examples so the compiler can systematically improve prompt instructions and synthesize few-shot demonstrations.
This declarative programming approach works with OpenAI and Anthropic models. It requires integration with language model providers to execute the automatic prompt optimization and compile the modular pipelines.
Manually engineered prompts break due to their inherent fragility across different language models. Declarative programming solves this by abstracting tasks into signatures, allowing modular pipelines to remain portable and automatically optimized.
cas-bigdatalabAutomate calibration of question-answer pairs against reference text using data_juicer.
heysuhasCompile declarative language model programs into self-improving pipelines with automated prompt optimization.
icyzhCompile declarative language model calls into self-improving pipelines with automated optimization.
iani-kuliCompile declarative language model calls into self-improving pipelines.
