Create modular AI pipelines with declarative programming and language models.
npx skills add https://github.com/aivos-xie/hermes-skills --skill dspy-aivos-xie
Please help me install this Agent Skill. Skill: dspy Source: https://github.com/aivos-xie/hermes-skills/tree/main/mlops/research/dspy Command: npx skills add https://github.com/aivos-xie/hermes-skills --skill dspy-aivos-xie
This Skill allows you to build complex AI systems using declarative programming with Language Models (LMs), focusing on optimizing prompts and building modular pipelines.
Use the dspy skill to create a simple QA system with the following command: dspy create qa --prompt "Question: {input} | Answer: {output}".
High-intent search queries and answers about installing and using this skill.
Automatic prompt optimization for large language models is handled by using DSPy to programmatically adjust and refine prompts, shifting from manual tuning to declarative optimization for improved model performance.
Building a multi-step RAG system is achieved by creating modular AI pipelines with DSPy, which integrates retrieval, reasoning, and generation steps into a single declarative program.
Specific API providers are required to use declarative LM programs, as the system depends on the dspy, openai, and anthropic libraries to interface with your chosen language model provider.
Declarative programming can be used to build AI agents and classifiers, allowing you to define modular pipelines where language models handle the reasoning and decision-making tasks.
Creating a simple QA pipeline with DSPy involves running a create command with a specified prompt template, immediately setting up a modular reasoning system for answering questions.
thisismynewfmail-uiBuild AI systems with declarative DSPy signatures and automatic prompt optimization.
8b-isBuild type-safe DSPy.rb workflows with signatures, modules, and provider configurations.
ThiNepoCreates Retrieval-Augmented Generation pipelines with Chroma, FAISS, and Pinecone vector stores.
icyzhCompile declarative language model calls into self-improving pipelines with automated optimization.
