流式列表¶
本指南解释了如何使用 Instructor 流式处理结构化数据列表。流式处理列表允许您在集合项生成时即进行处理，从而提高了处理较大输出时的响应速度。
基本列表流式处理¶
以下是流式处理结构化对象列表的方法
from typing import List
import instructor
from openai import OpenAI
from pydantic import BaseModel, Field
# Initialize the client
client = instructor.from_openai(OpenAI())
class Book(BaseModel):
title: str = Field(..., description="Book title")
author: str = Field(..., description="Book author")
year: int = Field(..., description="Publication year")
# Stream a list of books
for book in client.chat.completions.create(
model="gpt-3.5-turbo",
messages=[
{"role": "user", "content": "List 5 classic science fiction books"}
],
response_model=List[Book], # Note: Using List directly
stream=True
):
print(f"Received: {book.title} by {book.author} ({book.year})")
此示例展示了如何： 1. 为每个列表项定义一个 Pydantic 模型 2. 使用 Python 的类型系统指定列表 3. 在流中处理每个到达的项
实际示例：任务生成¶
这是一个流式处理任务列表并跟踪进度的实际示例
from typing import List
import instructor
from openai import OpenAI
from pydantic import BaseModel, Field
import time
client = instructor.from_openai(OpenAI())
class Task(BaseModel):
title: str = Field(..., description="Task title")
description: str = Field(..., description="Detailed task description")
priority: str = Field(..., description="Task priority (High/Medium/Low)")
estimated_hours: float = Field(..., description="Estimated hours to complete")
print("Generating project tasks...")
start_time = time.time()
received_tasks = 0
for task in client.chat.completions.create(
model="gpt-3.5-turbo",
messages=[
{"role": "user", "content": "Generate a list of 5 tasks for building a personal website"}
],
response_model=List[Task],
stream=True
):
received_tasks += 1
print(f"\nTask {received_tasks}: {task.title} (Priority: {task.priority})")
print(f"Description: {task.description[:100]}...")
print(f"Estimated time: {task.estimated_hours} hours")
# Calculate progress percentage based on expected items
progress = (received_tasks / 5) * 100
print(f"Progress: {progress:.0f}%")
elapsed_time = time.time() - start_time
print(f"\nAll {received_tasks} tasks generated in {elapsed_time:.2f} seconds")