dspy

Use a teleprompter such as BootstrapFewShot with a metric function and a training set of dspy.Example objects. Call optimizer.compile(module, trainset=trainset) to generate few-shot demonstrations that improve your module's accuracy without manual prompt editing.

Predict makes a direct LM call for simple tasks, while ChainOfThought generates reasoning steps before the answer. ChainOfThought is roughly twice as slow but significantly more accurate on math and logical reasoning tasks.

DSPy optimizes prompts automatically from data and offers typed signatures with high modularity, while LangChain relies on manual prompt engineering with prebuilt chains. Choose DSPy when you have training data and need systematic improvement; choose LangChain for quick prototypes with existing integrations.

Yes, DSPy supports local models through dspy.OllamaLocal by pointing to a base URL such as http://localhost:11434. It also supports OpenAI, Anthropic Claude, and multiple models configured for different pipeline stages.

BootstrapFewShot works with 10-50 examples, while MIPRO benefits from 50-200 examples plus a separate validation set. BootstrapFinetune for weight fine-tuning recommends 100 or more examples to avoid overfitting.

Avoid DSPy for quick one-off prototypes where manual prompting is faster, or when you lack any training data or metrics to optimize against. It also adds a medium-high learning curve compared to direct API calls.