如何优化多个提示¶

基于对话日志和反馈优化系统中的多个提示。该算法旨在实现三个目标：

根据轨迹（和可选反馈）推断“梯度”或系统输出的建议更改
将系统性能归因于每个提示步骤
推荐对最需要调整的提示进行更新更改

from langmem import create_multi_prompt_optimizer

# Example team: researcher finds information, writer creates reports
conversations = [
    (
        [
            {"role": "user", "content": "Research quantum computing advances"},
            {
                "role": "assistant",
                "content": "Found several papers on quantum supremacy...",
            },
            {
                "role": "assistant",
                "content": "Recent quantum computing developments show...",
            },
            {"role": "user", "content": "The report is missing implementation details"},
        ],
        # No explicit feedback provided but the optimizer can infer from the conversation
        None,
    ),
    (
        [
            {"role": "user", "content": "Analyze new ML models"},
            {"role": "assistant", "content": "Key findings on architecture: ..."},
            {"role": "assistant", "content": "Based on the research, these models..."},
            {"role": "user", "content": "Great report, very thorough"},
        ],
        # Numeric score for the team as a whole
        {"score": 0.95},
    ),
]

# Define prompts for each role
prompts = [
    {
        "name": "researcher",
        "prompt": "You analyze technical papers and extract key findings",
    },
    {"name": "writer", "prompt": "You write clear reports based on research findings"},
]

# Create optimizer
optimizer = create_multi_prompt_optimizer(
    "anthropic:claude-3-5-sonnet-latest",
    kind="gradient",  # Best for team dynamics
    config={"max_reflection_steps": 3},
)

# Update all prompts based on team performance
updated = optimizer.invoke({"trajectories": conversations, "prompts": prompts})
print(updated)

输出提示

[
    {
        'name': 'researcher',
        'prompt': '''You analyze technical papers and extract key findings. For each analysis, include:
1. High-level overview of the main contributions
2. Technical implementation details and methodologies
3. Architectural components and design choices
4. Experimental results and performance metrics
5. Practical implications and limitations

Ensure your analysis maintains technical depth while remaining accessible. When discussing implementation details, include specific technical parameters, algorithms, and methodologies used. Structure your response to clearly separate these components.'''
    },
    {
        'name': 'writer',
        'prompt': 'You write clear reports based on research findings'
    }
]

参阅单个提示优化，了解如何优化单个代理以及有关不同优化策略的更多信息。

如何优化多个提示¶

评论