使用 Batch API 进行批处理 ​

# Make sure you have the latest version of the SDK available to use the Batch API
%pip install openai --upgrade

import json
from openai import OpenAI
import pandas as pd
from IPython.display import Image, display

# Initializing OpenAI client - see https://platform.openai.com/docs/quickstart?context=python
client = OpenAI()

dataset_path = "data/imdb_top_1000.csv"

df = pd.read_csv(dataset_path)
df.head()

categorize_system_prompt = '''
Your goal is to extract movie categories from movie descriptions, as well as a 1-sentence summary for these movies.
You will be provided with a movie description, and you will output a json object containing the following information:

{
    categories: string[] // Array of categories based on the movie description,
    summary: string // 1-sentence summary of the movie based on the movie description
}

Categories refer to the genre or type of the movie, like "action", "romance", "comedy", etc. Keep category names simple and use only lower case letters.
Movies can have several categories, but try to keep it under 3-4. Only mention the categories that are the most obvious based on the description.
'''

def get_categories(description):
    response = client.chat.completions.create(
    model="gpt-4o-mini",
    temperature=0.1,
    # This is to enable JSON mode, making sure responses are valid json objects
    response_format={ 
        "type": "json_object"
    },
    messages=[
        {
            "role": "system",
            "content": categorize_system_prompt
        },
        {
            "role": "user",
            "content": description
        }
    ],
    )

    return response.choices[0].message.content

# Testing on a few examples
for _, row in df[:5].iterrows():
    description = row['Overview']
    title = row['Series_Title']
    result = get_categories(description)
    print(f"TITLE: {title}\nOVERVIEW: {description}\n\nRESULT: {result}")
    print("\n\n----------------------------\n\n")

# Creating an array of json tasks

tasks = []

for index, row in df.iterrows():
    
    description = row['Overview']
    
    task = {
        "custom_id": f"task-{index}",
        "method": "POST",
        "url": "/v1/chat/completions",
        "body": {
            # This is what you would have in your Chat Completions API call
            "model": "gpt-4o-mini",
            "temperature": 0.1,
            "response_format": { 
                "type": "json_object"
            },
            "messages": [
                {
                    "role": "system",
                    "content": categorize_system_prompt
                },
                {
                    "role": "user",
                    "content": description
                }
            ],
        }
    }
    
    tasks.append(task)

# Creating the file

file_name = "data/batch_tasks_movies.jsonl"

with open(file_name, 'w') as file:
    for obj in tasks:
        file.write(json.dumps(obj) + '\n')

batch_file = client.files.create(
  file=open(file_name, "rb"),
  purpose="batch"
)

print(batch_file)

batch_job = client.batches.create(
  input_file_id=batch_file.id,
  endpoint="/v1/chat/completions",
  completion_window="24h"
)

batch_job = client.batches.retrieve(batch_job.id)
print(batch_job)

result_file_id = batch_job.output_file_id
result = client.files.content(result_file_id).content

result_file_name = "data/batch_job_results_movies.jsonl"

with open(result_file_name, 'wb') as file:
    file.write(result)

# Loading data from saved file
results = []
with open(result_file_name, 'r') as file:
    for line in file:
        # Parsing the JSON string into a dict and appending to the list of results
        json_object = json.loads(line.strip())
        results.append(json_object)

# Reading only the first results
for res in results[:5]:
    task_id = res['custom_id']
    # Getting index from task id
    index = task_id.split('-')[-1]
    result = res['response']['body']['choices'][0]['message']['content']
    movie = df.iloc[int(index)]
    description = movie['Overview']
    title = movie['Series_Title']
    print(f"TITLE: {title}\nOVERVIEW: {description}\n\nRESULT: {result}")
    print("\n\n----------------------------\n\n")

dataset_path = "data/amazon_furniture_dataset.csv"
df = pd.read_csv(dataset_path)
df.head()

caption_system_prompt = '''
Your goal is to generate short, descriptive captions for images of items.
You will be provided with an item image and the name of that item and you will output a caption that captures the most important information about the item.
If there are multiple items depicted, refer to the name provided to understand which item you should describe.
Your generated caption should be short (1 sentence), and include only the most important information about the item.
The most important information could be: the type of item, the style (if mentioned), the material or color if especially relevant and/or any distinctive features.
Keep it short and to the point.
'''

def get_caption(img_url, title):
    response = client.chat.completions.create(
    model="gpt-4o-mini",
    temperature=0.2,
    max_tokens=300,
    messages=[
        {
            "role": "system",
            "content": caption_system_prompt
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": title
                },
                # The content type should be "image_url" to use gpt-4-turbo's vision capabilities
                {
                    "type": "image_url",
                    "image_url": {
                        "url": img_url
                    }
                },
            ],
        }
    ]
    )

    return response.choices[0].message.content

# Testing on a few images
for _, row in df[:5].iterrows():
    img_url = row['primary_image']
    caption = get_caption(img_url, row['title'])
    img = Image(url=img_url)
    display(img)
    print(f"CAPTION: {caption}\n\n")

# Creating an array of json tasks

tasks = []

for index, row in df.iterrows():
    
    title = row['title']
    img_url = row['primary_image']
    
    task = {
        "custom_id": f"task-{index}",
        "method": "POST",
        "url": "/v1/chat/completions",
        "body": {
            # This is what you would have in your Chat Completions API call
            "model": "gpt-4o-mini",
            "temperature": 0.2,
            "max_tokens": 300,
            "messages": [
                {
                    "role": "system",
                    "content": caption_system_prompt
                },
                {
                    "role": "user",
                    "content": [
                        {
                            "type": "text",
                            "text": title
                        },
                        {
                            "type": "image_url",
                            "image_url": {
                                "url": img_url
                            }
                        },
                    ],
                }
            ]            
        }
    }
    
    tasks.append(task)

# Creating the file

file_name = "data/batch_tasks_furniture.jsonl"

with open(file_name, 'w') as file:
    for obj in tasks:
        file.write(json.dumps(obj) + '\n')

# Uploading the file 

batch_file = client.files.create(
  file=open(file_name, "rb"),
  purpose="batch"
)

# Creating the job

batch_job = client.batches.create(
  input_file_id=batch_file.id,
  endpoint="/v1/chat/completions",
  completion_window="24h"
)

batch_job = client.batches.retrieve(batch_job.id)
print(batch_job)

# Retrieving result file

result_file_id = batch_job.output_file_id
result = client.files.content(result_file_id).content

result_file_name = "data/batch_job_results_furniture.jsonl"

with open(result_file_name, 'wb') as file:
    file.write(result)

# Loading data from saved file

results = []
with open(result_file_name, 'r') as file:
    for line in file:
        # Parsing the JSON string into a dict and appending to the list of results
        json_object = json.loads(line.strip())
        results.append(json_object)

# Reading only the first results
for res in results[:5]:
    task_id = res['custom_id']
    # Getting index from task id
    index = task_id.split('-')[-1]
    result = res['response']['body']['choices'][0]['message']['content']
    item = df.iloc[int(index)]
    img_url = item['primary_image']
    img = Image(url=img_url)
    display(img)
    print(f"CAPTION: {result}\n\n")