性能优化提示

# ❌ Problematic: Asking for exhaustive enumeration on a large document
problematic_schema = {
    "all_product_names": {
        "type": "array",
        "description": "Every single product mentioned anywhere in this document"
    }
}

# ✅ Better: Targeted, structured extraction
better_schema = {
    "primary_products": {
        "type": "array",
        "description": "The main 3-5 products featured in this section",
    },
    "product_category": {
        "type": "string",
        "description": "The category this section focuses on"
    }
}

# ✅ Process a large CSV in batches
def process_large_csv(csv_file, batch_size=50):
    results = []

    for i in range(0, len(csv_data), batch_size):
        batch = csv_data[i:i+batch_size]
        # Convert batch to document format
        result = agent.extract(batch)
        results.append(result)

    return combine_results(results)

# ❌ Problematic: Too much logic in the field description
problematic_field = {
    "calculated_score": {
        "type": "number",
        "description": "If revenue > 1M, multiply by 0.8, else if revenue < 500K multiply by 1.2, otherwise use the base score from table 3, but only if the date is after 2020 and the category is not 'exempt'"
    }
}

# ✅ Better: Simple extraction, handle logic separately
better_schema = {
    "revenue": {
        "type": "number",
        "description": "Total revenue in dollars"
    },
    "base_score": {
        "type": "number",
        "description": "Base score value from the scoring table"
    },
    "date": {
        "type": "string",
        "description": "Date in YYYY-MM-DD format"
    },
    "category": {
        "type": "string",
        "description": "Business category"
    }
}

# Then handle calculations in your application code:
def calculate_final_score(extracted_data):
    revenue = extracted_data["revenue"]
    if revenue > 1000000:
        return extracted_data["base_score"] * 0.8
    elif revenue < 500000:
        return extracted_data["base_score"] * 1.2
    else:
        return extracted_data["base_score"]