Prompt language model

As explained in Building LLM Applications with DSPy

A language model assigned to generate candidate instructions during prompt optimization.

lm_5 = dspy.LM(model='gpt-5', temperature=1.0, max_tokens=30000)
copro = dspy.COPRO(prompt_model=lm_5, init_temperature=1.0,
                   metric=validate_answer, 
                   breadth=2, depth=2, track_stats=True)
prog_copro_2 = copro.compile(intent_classifier, trainset=val_set,
                             eval_kwargs={"num_threads": 3,
                             'display_progress': True})

How Building LLM Applications with DSPy covers it

How deep it goes

Defines its optimization-only role and gives call-frequency and configuration guidance, without detailing model internals.

Examples

Uses GPT-5 as the COPRO prompt model and gpt-4o-mini as the task model.

What you can do after

Apply it by assigning a separate model to propose instructions during COPRO compilation while retaining the task model for evaluation and production.

How it connects

Links instruction generation to prompt optimization, task language models, COPRO, MIPROv2, and BootstrapFewShot.

liveBookmanning.com

Read Building LLM Applications with DSPy on liveBook Get the book at manning.com

Related concepts

• language modelkind of · A language model is a computational model that represents patterns in linguistic tokens to assign probabilities to, predict, or generate sequences of language.
• groundingused by · Grounding is the practice of anchoring or constraining an AI system’s outputs with relevant information, context, or evidence.

This explainer was generated by Manning's knowledge graph from the text of Building LLM Applications with DSPy. The section links point to the parts of the book it draws on.