Build and optimize declarative language model pipelines with DSPy.
npx skills add https://github.com/eddielueng/hermes-agent-zh --skill dspy-eddielueng
Please help me install this Agent Skill. Skill: dspy Source: https://github.com/eddielueng/hermes-agent-zh/tree/main/skills/mlops/research/dspy Command: npx skills add https://github.com/eddielueng/hermes-agent-zh --skill dspy-eddielueng
DSPy eliminates fragile, manual prompt engineering by letting you build language model systems with declarative components and then optimize them using data and objective metrics.
Ask the AI assistant to build a simple DSPy RAG pipeline, then compile it using a small training set and a correctness metric you define.
High-intent search queries and answers about installing and using this skill.
Automatic prompt optimization compiles declarative LM pipelines using optimizers that search for better instructions and few-shot examples from a defined correctness metric. This eliminates fragile manual engineering by relying on objective data.
Yes, you can build a modular RAG pipeline declaratively with DSPy by defining input-output signatures and configuring an LM provider like OpenAI or Anthropic. The system retrieves passages, generates answers, and compiles for reliability.
Declarative LM programming works by defining signatures for inputs and outputs, then composing modules for tasks like extraction and reasoning. These modular components create maintainable agent workflows and multi-stage pipelines.
You evaluate reliability by defining a specific evaluation metric and compiling modules with optimizers against a held-out training set. The optimizer searches for improved instructions and examples to maximize extraction and classification accuracy.
The best way to structure agent workflows is defining declarative signatures and composing modular components for tool usage. Compiling these modules with appropriate optimizers and evaluation metrics eliminates the need for fragile manual prompts.
Yes, you need to provide a training set and define a correctness metric to compile and optimize the extraction pipelines. The optimizer uses these examples to automatically search for and generate better instructions and few-shot prompts.
cabeznoDefine declarative LM programs and optimize prompts with DSPy.
LauraFlorentinMonitors agent performance and generates metrics for CI/CD pipelines and audits.
ricableBuild declarative language-model pipelines and optimize them with teleprompters.
richardnguyen0715Build declarative AI pipelines with automatic prompt optimization and retrieval-augmented generation.
