uv add "alquimia-fair-forge"
uv add langchain-groq  # or your preferred LLM provider

import json
from fair_forge import Retriever
from fair_forge.schemas import Dataset
from fair_forge.prompt_optimizer.mipro import MIPROv2Optimizer
from langchain_groq import ChatGroq

class IncidentsRetriever(Retriever):
    def load_dataset(self) -> list[Dataset]:
        with open("dataset.json", encoding="utf-8") as f:
            return [Dataset.model_validate(item) for item in json.load(f)]

model = ChatGroq(model="llama-3.3-70b-versatile")

result = MIPROv2Optimizer.run(
    retriever=IncidentsRetriever,
    model=model,
    seed_prompt="Eres un agente de soporte técnico.",
    objective=(
        "Responder incidencias técnicas con un diagnóstico estructurado en 4 secciones: "
        "Diagnóstico, Causa probable, Solución inmediata (pasos numerados), y Seguimiento. "
        "Usar únicamente la información del contexto proporcionado."
    ),
)

print(f"Score: {result.initial_score:.2f} → {result.final_score:.2f}  ({result.n_examples} examples)")
print(result.optimized_prompt)

result.optimized_prompt        # str         — instruction + examples, ready to use as system prompt
result.optimized_instruction   # str         — instruction part only (without examples)
result.initial_score           # float       — seed prompt score (0.0–1.0)
result.final_score             # float       — best score found (0.0–1.0)
result.trials_run              # int         — number of trials executed
result.n_examples              # int         — total examples in the dataset
result.demos                   # list[Demo]  — selected few-shot examples
result.trials                  # list[TrialResult]

# Trial history — see how the search progressed
best_so_far = 0.0
for t in result.trials:
    is_best = t.score > best_so_far
    if is_best:
        best_so_far = t.score
    marker = " ★ new best" if is_best else ""
    print(f"  Trial {t.trial + 1:2d} — instruction #{t.instruction_idx + 1}, "
          f"demo set #{t.demo_set_idx + 1} — score: {t.score:.2f}{marker}")

# Final result — instruction and examples separately
print("=== Optimized instruction ===")
print(result.optimized_instruction)

print("=== Selected examples ===")
for demo in result.demos:
    print(f"User: {demo.query}")
    print(f"Assistant: {demo.response}")
    print()

def my_executor(prompt: str, query: str, context: str) -> str:
    return my_agent.call(system=prompt, user=query, context=context)

result = MIPROv2Optimizer.run(
    retriever=MyRetriever,
    model=model,
    seed_prompt="...",
    objective="...",
    executor=my_executor,
)