优化提示教程

本教程示例使用 MLflow 提示优化，通过 GEPA 和 GPT-OSS 20B 优化简单 查询分类 提示以完成分类任务。

安装依赖项

%pip install --upgrade mlflow databricks-sdk dspy openai
dbutils.library.restartPython()

确保你有权访问 Databricks Foundation 模型 API 以成功运行此 API。

import mlflow
import openai
from mlflow.genai.optimize import GepaPromptOptimizer
from mlflow.genai.scorers import Correctness
from databricks.sdk import WorkspaceClient

w = WorkspaceClient()

# Change the catalog and schema to your catalog and schema
catalog = ""
schema = ""
prompt_registry_name = "qa"
prompt_location = f"{catalog}.{schema}.{prompt_registry_name}"

openai_client = w.serving_endpoints.get_open_ai_client()

# Register initial prompt
prompt = mlflow.genai.register_prompt(
    name=prompt_location,
    template="classify this: {{query}}",
)

# Define your prediction function
def predict_fn(query: str) -> str:
    prompt = mlflow.genai.load_prompt(f"prompts:/{prompt_location}/1")
    completion = openai_client.chat.completions.create(
        model="databricks-gpt-oss-20b",
        # load prompt template using PromptVersion.format()
        messages=[{"role": "user", "content": prompt.format(question=query)}],
    )
    return completion.choices[0].message.content

测试你的函数

观察模型在仅用基础提示时对输入进行分类的准确性。虽然准确，但它与要查找的任何任务或用例不一致。

from IPython.display import Markdown

output = predict_fn("The emergence of HIV as a chronic condition means that people living with HIV are required to take more responsibility for the self-management of their condition , including making physical , emotional and social adjustments.")

Markdown(output[1]['text'])

针对数据进行优化

提供预期的反馈和事实，以帮助优化模型的行为和结果，以适合你的用例的方式。

在这种情况下，你希望模型从五个单词的选择中输出一个单词。它只应输出该单词而不作任何进一步解释。

# Training data with inputs and expected outputs
dataset = [
    {
        "inputs": {"query": "The emergence of HIV as a chronic condition means that people living with HIV are required to take more responsibility for the self-management of their condition , including making physical , emotional and social adjustments."},
        "outputs": {"response": "BACKGROUND"},
        "expectations": {"expected_facts": ["Classification label must be 'CONCLUSIONS', 'RESULTS', 'METHODS', 'OBJECTIVE', 'BACKGROUND'"]}
    },
    {
        "inputs": {"query": "This paper describes the design and evaluation of Positive Outlook , an online program aiming to enhance the self-management skills of men living with HIV ."},
        "outputs": {"response": "BACKGROUND"},
        "expectations": {"expected_facts": ["Classification label must be 'CONCLUSIONS', 'RESULTS', 'METHODS', 'OBJECTIVE', 'BACKGROUND'"]}
    },
    {
        "inputs": {"query": "This study is designed as a randomised controlled trial in which men living with HIV in Australia will be assigned to either an intervention group or usual care control group ."},
        "outputs": {"response": "METHODS"},
        "expectations": {"expected_facts": ["Classification label must be 'CONCLUSIONS', 'RESULTS', 'METHODS', 'OBJECTIVE', 'BACKGROUND'"]}
    },
    {
        "inputs": {"query": "The intervention group will participate in the online group program ` Positive Outlook ' ."},
        "outputs": {"response": "METHODS"},
        "expectations": {"expected_facts": ["Classification label must be 'CONCLUSIONS', 'RESULTS', 'METHODS', 'OBJECTIVE', 'BACKGROUND'"]}
    },
    {
        "inputs": {"query": "The program is based on self-efficacy theory and uses a self-management approach to enhance skills , confidence and abilities to manage the psychosocial issues associated with HIV in daily life ."},
        "outputs": {"response": "METHODS"},
        "expectations": {"expected_facts": ["Classification label must be 'CONCLUSIONS', 'RESULTS', 'METHODS', 'OBJECTIVE', 'BACKGROUND'"]}
    },
    {
        "inputs": {"query": "Participants will access the program for a minimum of 90 minutes per week over seven weeks ."},
        "outputs": {"response": "METHODS"},
        "expectations": {"expected_facts": ["Classification label must be 'CONCLUSIONS', 'RESULTS', 'METHODS', 'OBJECTIVE', 'BACKGROUND'"]}
    }
]

# Optimize the prompt
result = mlflow.genai.optimize_prompts(
    predict_fn=predict_fn,
    train_data=dataset,
    prompt_uris=[prompt.uri],
    optimizer=GepaPromptOptimizer(reflection_model="databricks:/databricks-claude-sonnet-4-5"),
    scorers=[Correctness(model="databricks:/databricks-gpt-5")],
)

# Use the optimized prompt
optimized_prompt = result.optimized_prompts[0]
print(f"Optimized template: {optimized_prompt.template}")

查看提示

打开 MLflow 试验的链接，并完成以下步骤，让试验中出现提示：

确保试验类型设置为 GenAI 应用和代理
导航到提示选项卡
单击右上角的 选择架构，并输入上面设置的相同架构以查看提示

加载新提示并再次测试

查看提示的外观，并将其加载到预测函数中，以查看模型的性能如何不同。

from IPython.display import Markdown
prompt = mlflow.genai.load_prompt(f"prompts:/{prompt_location}/34")

Markdown(prompt.template)

from IPython.display import Markdown

def predict_fn(query: str) -> str:
    prompt = mlflow.genai.load_prompt(f"prompts:/{prompt_location}/34")
    completion = openai_client.chat.completions.create(
        model="databricks-gpt-oss-20b",
        # load prompt template using PromptVersion.format()
        messages=[{"role": "user", "content": prompt.format(query=query)}],
    )
    return completion.choices[0].message.content

output = predict_fn("The emergence of HIV as a chronic condition means that people living with HIV are required to take more responsibility for the self-management of their condition , including making physical , emotional and social adjustments.")

Markdown(output[1]['text'])

示例笔记本

下面是一个可运行的笔记本，它使用 MLflow GenAI 的 GEPA 提示优化功能来优化提示，并演示了 GPT-OSS 20B 的分类任务。

使用 GEPA 和 GPT-OSS 20B 提示优化

获取笔记本

Last updated on 2026-01-26

通过