coreason-optimizer 0.3.0

coreason-optimizer

coreason-optimizer

Automated Prompt Engineering / LLM Compilation / DSPy Integration for CoReason-AI

coreason-optimizer is the "Compiler" for the CoReason Agentic Platform. It automates prompt engineering by treating prompts as trainable weights, optimizing them against ground-truth datasets to maximize performance metrics.

---

Installation

pip install coreason-optimizer

Features

• Automated Optimization: Rewrites instructions and selects examples to maximize a score, not human intuition.
• Optimization-as-a-Service: Run as a microservice API to compile prompts on-demand.
• Model-Specific Compilation: Generates optimized prompts specifically tuned for target models (e.g., GPT-4, Claude 3.5).
• Continuous Learning: Re-runs optimization on recent logs to patch prompts against data drift.
• Mutate-Evaluate Loop: Systematic cycle of drafting, evaluating, diagnosing, mutating, and selecting prompts.
• Strategies: Includes BootstrapFewShot (mining successful traces) and MIPRO (Multi-prompt Instruction PRoposal Optimizer).
• Integration: Works seamlessly with coreason-construct, coreason-archive, and coreason-assay.

For full product requirements, see docs/product_requirements.md.

Usage

You can use coreason-optimizer as a Python library, a CLI tool, or a Microservice.

1. Python Library

from coreason_optimizer import OptimizerConfig, PromptOptimizer
from coreason_optimizer.core.interfaces import Construct
from coreason_optimizer.data import Dataset

# Define Agent
class MockAgent(Construct):
    inputs = ["question"]
    outputs = ["answer"]
    system_prompt = "You are a helpful assistant."
agent = MockAgent()

# Compile
dataset = Dataset.from_csv("data/gold_set.csv")
train_set, val_set = dataset.split(train_ratio=0.8)

optimizer = PromptOptimizer(config=OptimizerConfig(target_model="gpt-4o"))
manifest = optimizer.compile(agent, train_set, val_set)

print(f"Optimized Score: {manifest.performance_metric}")

2. Server Mode (Microservice)

Run the optimizer as a standalone service using Docker:

docker run -p 8000:8000 -e OPENAI_API_KEY=$OPENAI_API_KEY coreason-optimizer:latest

Then call the API:

curl -X POST http://localhost:8000/optimize -d @request.json

For detailed instructions, see docs/usage.md.