Chapter 31

batch processing

NotebookPython 3 (ipykernel)45 cells

Batch processing with the Batch API

The new Batch API allows to create async batch jobs for a lower price and with higher rate limits.

Batches will be completed within 24h, but may be processed sooner depending on global usage.

Ideal use cases for the Batch API include:

Tagging, captioning, or enriching content on a marketplace or blog
Categorizing and suggesting answers for support tickets
Performing sentiment analysis on large datasets of customer feedback
Generating summaries or translations for collections of documents or articles

and much more!

This cookbook will walk you through how to use the Batch API with a couple of practical examples.

We will start with an example to categorize movies using gpt-4o-mini, and then cover how we can use the vision capabilities of this model to caption images.

Please note that multiple models are available through the Batch API, and that you can use the same parameters in your Batch API calls as with the Chat Completions endpoint.

Setup

In [ ]python · cell 3

python

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

In [1]python · cell 4

python

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

In [2]python · cell 5

python

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

First example: Categorizing movies

In this example, we will use gpt-4o-mini to extract movie categories from a description of the movie. We will also extract a 1-sentence summary from this description.

We will use JSON mode to extract categories as an array of strings and the 1-sentence summary in a structured format.

For each movie, we want to get a result that looks like this:

code

{
    categories: ['category1', 'category2', 'category3'],
    summary: '1-sentence summary'
}

Loading data

We will use the IMDB top 1000 movies dataset for this example.

In [3]python · cell 8

python

dataset_path = "data/imdb_top_1000.csv"

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

Output

                                         Poster_Link  \
0  https://m.media-amazon.com/images/M/MV5BMDFkYT...   
1  https://m.media-amazon.com/images/M/MV5BM2MyNj...   
2  https://m.media-amazon.com/images/M/MV5BMTMxNT...   
3  https://m.media-amazon.com/images/M/MV5BMWMwMG...   
4  https://m.media-amazon.com/images/M/MV5BMWU4N2...   

               Series_Title Released_Year Certificate  Runtime  \
0  The Shawshank Redemption          1994           A  142 min   
1             The Godfather          1972           A  175 min   
2           The Dark Knight          2008          UA  152 min   
3    The Godfather: Part II          1974           A  202 min   
4              12 Angry Men          1957           U   96 min   

                  Genre  IMDB_Rating  \
0                 Drama          9.3   
1          Crime, Drama          9.2   
2  Action, Crime, Drama          9.0   
3          Crime, Drama          9.0   
4          Crime, Drama          9.0   

                                            Overview  Meta_score  \
0  Two imprisoned men bond over a number of years...        80.0   
1  An organized crime dynasty's aging patriarch t...       100.0   
2  When the menace known as the Joker wreaks havo...        84.0   
3  The early life and career of Vito Corleone in ...        90.0   
4  A jury holdout attempts to prevent a miscarria...        96.0   

               Director           Star1           Star2          Star3  \
0        Frank Darabont     Tim Robbins  Morgan Freeman     Bob Gunton   
1  Francis Ford Coppola   Marlon Brando       Al Pacino     James Caan   
2     Christopher Nolan  Christian Bale    Heath Ledger  Aaron Eckhart   
3  Francis Ford Coppola       Al Pacino  Robert De Niro  Robert Duvall   
4          Sidney Lumet     Henry Fonda     Lee J. Cobb  Martin Balsam   

            Star4  No_of_Votes        Gross  
0  William Sadler      2343110   28,341,469  
1    Diane Keaton      1620367  134,966,411  
2   Michael Caine      2303232  534,858,444  
3    Diane Keaton      1129952   57,300,000  
4    John Fiedler       689845    4,360,000

.dataframe tbody tr th:only-of-type { vertical-align: middle; } .dataframe tbody tr th { vertical-align: top; } .dataframe thead th { text-align: right; }

	Poster_Link	Series_Title	Released_Year	Certificate	Runtime	Genre	IMDB_Rating	Overview	Meta_score	Director	Star1	Star2	Star3	Star4	No_of_Votes	Gross
0	https://m.media-amazon.com/images/M/MV5BMDFkYT...	The Shawshank Redemption	1994	A	142 min	Drama	9.3	Two imprisoned men bond over a number of years...	80.0	Frank Darabont	Tim Robbins	Morgan Freeman	Bob Gunton	William Sadler	2343110	28,341,469
1	https://m.media-amazon.com/images/M/MV5BM2MyNj...	The Godfather	1972	A	175 min	Crime, Drama	9.2	An organized crime dynasty's aging patriarch t...	100.0	Francis Ford Coppola	Marlon Brando	Al Pacino	James Caan	Diane Keaton	1620367	134,966,411
2	https://m.media-amazon.com/images/M/MV5BMTMxNT...	The Dark Knight	2008	UA	152 min	Action, Crime, Drama	9.0	When the menace known as the Joker wreaks havo...	84.0	Christopher Nolan	Christian Bale	Heath Ledger	Aaron Eckhart	Michael Caine	2303232	534,858,444
3	https://m.media-amazon.com/images/M/MV5BMWMwMG...	The Godfather: Part II	1974	A	202 min	Crime, Drama	9.0	The early life and career of Vito Corleone in ...	90.0	Francis Ford Coppola	Al Pacino	Robert De Niro	Robert Duvall	Diane Keaton	1129952	57,300,000
4	https://m.media-amazon.com/images/M/MV5BMWU4N2...	12 Angry Men	1957	U	96 min	Crime, Drama	9.0	A jury holdout attempts to prevent a miscarria...	96.0	Sidney Lumet	Henry Fonda	Lee J. Cobb	Martin Balsam	John Fiedler	689845	4,360,000

Processing step

Here, we will prepare our requests by first trying them out with the Chat Completions endpoint.

Once we're happy with the results, we can move on to creating the batch file.

In [4]python · cell 10

python

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

In [5]python · cell 11

python

# 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")

Output

TITLE: The Shawshank Redemption
OVERVIEW: Two imprisoned men bond over a number of years, finding solace and eventual redemption through acts of common decency.

RESULT: {
    "categories": ["drama"],
    "summary": "Two imprisoned men develop a deep bond over the years, ultimately finding redemption through their shared acts of kindness."
}


----------------------------


TITLE: The Godfather
OVERVIEW: An organized crime dynasty's aging patriarch transfers control of his clandestine empire to his reluctant son.

RESULT: {
    "categories": ["crime", "drama"],
    "summary": "An aging crime lord hands over his empire to his hesitant son."
}


----------------------------


TITLE: The Dark Knight
OVERVIEW: When the menace known as the Joker wreaks havoc and chaos on the people of Gotham, Batman must accept one of the greatest psychological and physical tests of his ability to fight injustice.

RESULT: {
    "categories": ["action", "thriller", "superhero"],
    "summary": "Batman faces a formidable challenge as the Joker unleashes chaos on Gotham City."
}


----------------------------


TITLE: The Godfather: Part II
OVERVIEW: The early life and career of Vito Corleone in 1920s New York City is portrayed, while his son, Michael, expands and tightens his grip on the family crime syndicate.

RESULT: {
    "categories": ["crime", "drama"],
    "summary": "The film depicts the early life of Vito Corleone and the rise of his son Michael within the family crime syndicate in 1920s New York City."
}


----------------------------


TITLE: 12 Angry Men
OVERVIEW: A jury holdout attempts to prevent a miscarriage of justice by forcing his colleagues to reconsider the evidence.

RESULT: {
    "categories": ["drama", "thriller"],
    "summary": "A jury holdout fights to ensure justice is served by challenging his fellow jurors to reevaluate the evidence."
}


----------------------------

Creating the batch file

The batch file, in the jsonl format, should contain one line (json object) per request. Each request is defined as such:

code

{
    "custom_id": <REQUEST_ID>,
    "method": "POST",
    "url": "/v1/chat/completions",
    "body": {
        "model": <MODEL>,
        "messages": <MESSAGES>,
        // other parameters
    }
}

Note: the request ID should be unique per batch. This is what you can use to match results to the initial input files, as requests will not be returned in the same order.

In [6]python · cell 13

python

# 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)

In [7]python · cell 14

python

# 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')

Uploading the file

In [8]python · cell 16

python

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

In [9]python · cell 17

python

print(batch_file)

Output

FileObject(id='file-lx16f1KyIxQ2UHVvkG3HLfNR', bytes=1127310, created_at=1721144107, filename='batch_tasks_movies.jsonl', object='file', purpose='batch', status='processed', status_details=None)

Creating the batch job

In [10]python · cell 19

python

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

Checking batch status

Note: this can take up to 24h, but it will usually be completed faster.

You can continue checking until the status is 'completed'.

In [ ]python · cell 21

python

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

Retrieving results

In [13]python · cell 23

python

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

In [14]python · cell 24

python

result_file_name = "data/batch_job_results_movies.jsonl"

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

In [15]python · cell 25

python

# 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 results

Reminder: the results are not in the same order as in the input file. Make sure to check the custom_id to match the results against the input requests

In [16]python · cell 27

python

# 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")

Output

TITLE: American Psycho
OVERVIEW: A wealthy New York City investment banking executive, Patrick Bateman, hides his alternate psychopathic ego from his co-workers and friends as he delves deeper into his violent, hedonistic fantasies.

RESULT: {
    "categories": ["thriller", "psychological", "drama"],
    "summary": "A wealthy investment banker in New York City conceals his psychopathic alter ego while indulging in violent and hedonistic fantasies."
}


----------------------------


TITLE: Lethal Weapon
OVERVIEW: Two newly paired cops who are complete opposites must put aside their differences in order to catch a gang of drug smugglers.

RESULT: {
    "categories": ["action", "comedy", "crime"],
    "summary": "An action-packed comedy about two mismatched cops teaming up to take down a drug smuggling gang."
}


----------------------------


TITLE: A Star Is Born
OVERVIEW: A musician helps a young singer find fame as age and alcoholism send his own career into a downward spiral.

RESULT: {
    "categories": ["drama", "music"],
    "summary": "A musician's career spirals downward as he helps a young singer find fame amidst struggles with age and alcoholism."
}


----------------------------


TITLE: From Here to Eternity
OVERVIEW: In Hawaii in 1941, a private is cruelly punished for not boxing on his unit's team, while his captain's wife and second-in-command are falling in love.

RESULT: {
    "categories": ["drama", "romance", "war"],
    "summary": "A drama set in Hawaii in 1941, where a private faces punishment for not boxing on his unit's team, amidst a forbidden love affair between his captain's wife and second-in-command."
}


----------------------------


TITLE: The Jungle Book
OVERVIEW: Bagheera the Panther and Baloo the Bear have a difficult time trying to convince a boy to leave the jungle for human civilization.

RESULT: {
    "categories": ["adventure", "animation", "family"],
    "summary": "An adventure-filled animated movie about a panther and a bear trying to persuade a boy to leave the jungle for human civilization."
}


----------------------------

Second example: Captioning images

In this example, we will use gpt-4-turbo to caption images of furniture items.

We will use the vision capabilities of the model to analyze the images and generate the captions.

Loading data

We will use the Amazon furniture dataset for this example.

In [12]python · cell 30

python

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

Output

         asin                                   url  \
0  B0CJHKVG6P  https://www.amazon.com/dp/B0CJHKVG6P   
1  B0B66QHB23  https://www.amazon.com/dp/B0B66QHB23   
2  B0BXRTWLYK  https://www.amazon.com/dp/B0BXRTWLYK   
3  B0C1MRB2M8  https://www.amazon.com/dp/B0C1MRB2M8   
4  B0CG1N9QRC  https://www.amazon.com/dp/B0CG1N9QRC   

                                               title            brand   price  \
0  GOYMFK 1pc Free Standing Shoe Rack, Multi-laye...           GOYMFK  $24.99   
1  subrtex Leather ding Room, Dining Chairs Set o...          subrtex     NaN   
2  Plant Repotting Mat MUYETOL Waterproof Transpl...          MUYETOL   $5.98   
3  Pickleball Doormat, Welcome Doormat Absorbent ...          VEWETOL  $13.99   
4  JOIN IRON Foldable TV Trays for Eating Set of ...  JOIN IRON Store  $89.99   

                          availability  \
0  Only 13 left in stock - order soon.   
1                                  NaN   
2                             In Stock   
3  Only 10 left in stock - order soon.   
4    Usually ships within 5 to 6 weeks   

                                          categories  \
0  ['Home & Kitchen', 'Storage & Organization', '...   
1  ['Home & Kitchen', 'Furniture', 'Dining Room F...   
2  ['Patio, Lawn & Garden', 'Outdoor Décor', 'Doo...   
3  ['Patio, Lawn & Garden', 'Outdoor Décor', 'Doo...   
4  ['Home & Kitchen', 'Furniture', 'Game & Recrea...   

                                       primary_image  \
0  https://m.media-amazon.com/images/I/416WaLx10j...   
1  https://m.media-amazon.com/images/I/31SejUEWY7...   
2  https://m.media-amazon.com/images/I/41RgefVq70...   
3  https://m.media-amazon.com/images/I/61vz1Igler...   
4  https://m.media-amazon.com/images/I/41p4d4VJnN...   

                                              images  upc  ...          color  \
0  ['https://m.media-amazon.com/images/I/416WaLx1...  NaN  ...          White   
1  ['https://m.media-amazon.com/images/I/31SejUEW...  NaN  ...          Black   
2  ['https://m.media-amazon.com/images/I/41RgefVq...  NaN  ...          Green   
3  ['https://m.media-amazon.com/images/I/61vz1Igl...  NaN  ...          A5589   
4  ['https://m.media-amazon.com/images/I/41p4d4VJ...  NaN  ...  Grey Set of 4   

       material              style important_information  \
0         Metal             Modern                    []   
1        Sponge  Black Rubber Wood                    []   
2  Polyethylene             Modern                    []   
3        Rubber             Modern                    []   
4          Iron    X Classic Style                    []   

                                    product_overview  \
0  [{'Brand': ' GOYMFK '}, {'Color': ' White '}, ...   
1                                                NaN   
2  [{'Brand': ' MUYETOL '}, {'Size': ' 26.8*26.8 ...   
3  [{'Brand': ' VEWETOL '}, {'Size': ' 16*24INCH ...   
4                                                NaN   

                                          about_item  \
0  ['Multiple layers: Provides ample storage spac...   
1  ['【Easy Assembly】: Set of 2 dining room chairs...   
2  ['PLANT REPOTTING MAT SIZE: 26.8" x 26.8", squ...   
3  ['Specifications: 16x24 Inch ', " High-Quality...   
4  ['Includes 4 Folding Tv Tray Tables And one Co...   

                                         description  \
0  multiple shoes, coats, hats, and other items E...   
1                     subrtex Dining chairs Set of 2   
2                                                NaN   
3  The decorative doormat features a subtle textu...   
4  Set of Four Folding Trays With Matching Storag...   

                                      specifications  \
0  ['Brand: GOYMFK', 'Color: White', 'Material: M...   
1  ['Brand: subrtex', 'Color: Black', 'Product Di...   
2  ['Brand: MUYETOL', 'Size: 26.8*26.8', 'Item We...   
3  ['Brand: VEWETOL', 'Size: 16*24INCH', 'Materia...   
4  ['Brand: JOIN IRON', 'Shape: Rectangular', 'In...   

                                uniq_id           scraped_at  
0  02593e81-5c09-5069-8516-b0b29f439ded  2024-02-02 15:15:08  
1  5938d217-b8c5-5d3e-b1cf-e28e340f292e  2024-02-02 15:15:09  
2  b2ede786-3f51-5a45-9a5b-bcf856958cd8  2024-02-02 15:15:09  
3  8fd9377b-cfa6-5f10-835c-6b8eca2816b5  2024-02-02 15:15:10  
4  bdc9aa30-9439-50dc-8e89-213ea211d66a  2024-02-02 15:15:11  

[5 rows x 25 columns]

.dataframe tbody tr th:only-of-type { vertical-align: middle; } .dataframe tbody tr th { vertical-align: top; } .dataframe thead th { text-align: right; }

	asin	url	title	brand	price	availability	categories	primary_image	images	upc	...	color	material	style	important_information	product_overview	about_item	description	specifications	uniq_id	scraped_at
0	B0CJHKVG6P	https://www.amazon.com/dp/B0CJHKVG6P	GOYMFK 1pc Free Standing Shoe Rack, Multi-laye...	GOYMFK	$24.99	Only 13 left in stock - order soon.	['Home & Kitchen', 'Storage & Organization', '...	https://m.media-amazon.com/images/I/416WaLx10j...	['https://m.media-amazon.com/images/I/416WaLx1...	NaN	...	White	Metal	Modern	[]	[{'Brand': ' GOYMFK '}, {'Color': ' White '}, ...	['Multiple layers: Provides ample storage spac...	multiple shoes, coats, hats, and other items E...	['Brand: GOYMFK', 'Color: White', 'Material: M...	02593e81-5c09-5069-8516-b0b29f439ded	2024-02-02 15:15:08
1	B0B66QHB23	https://www.amazon.com/dp/B0B66QHB23	subrtex Leather ding Room, Dining Chairs Set o...	subrtex	NaN	NaN	['Home & Kitchen', 'Furniture', 'Dining Room F...	https://m.media-amazon.com/images/I/31SejUEWY7...	['https://m.media-amazon.com/images/I/31SejUEW...	NaN	...	Black	Sponge	Black Rubber Wood	[]	NaN	['【Easy Assembly】: Set of 2 dining room chairs...	subrtex Dining chairs Set of 2	['Brand: subrtex', 'Color: Black', 'Product Di...	5938d217-b8c5-5d3e-b1cf-e28e340f292e	2024-02-02 15:15:09
2	B0BXRTWLYK	https://www.amazon.com/dp/B0BXRTWLYK	Plant Repotting Mat MUYETOL Waterproof Transpl...	MUYETOL	$5.98	In Stock	['Patio, Lawn & Garden', 'Outdoor Décor', 'Doo...	https://m.media-amazon.com/images/I/41RgefVq70...	['https://m.media-amazon.com/images/I/41RgefVq...	NaN	...	Green	Polyethylene	Modern	[]	[{'Brand': ' MUYETOL '}, {'Size': ' 26.8*26.8 ...	['PLANT REPOTTING MAT SIZE: 26.8" x 26.8", squ...	NaN	['Brand: MUYETOL', 'Size: 26.8*26.8', 'Item We...	b2ede786-3f51-5a45-9a5b-bcf856958cd8	2024-02-02 15:15:09
3	B0C1MRB2M8	https://www.amazon.com/dp/B0C1MRB2M8	Pickleball Doormat, Welcome Doormat Absorbent ...	VEWETOL	$13.99	Only 10 left in stock - order soon.	['Patio, Lawn & Garden', 'Outdoor Décor', 'Doo...	https://m.media-amazon.com/images/I/61vz1Igler...	['https://m.media-amazon.com/images/I/61vz1Igl...	NaN	...	A5589	Rubber	Modern	[]	[{'Brand': ' VEWETOL '}, {'Size': ' 16*24INCH ...	['Specifications: 16x24 Inch ', " High-Quality...	The decorative doormat features a subtle textu...	['Brand: VEWETOL', 'Size: 16*24INCH', 'Materia...	8fd9377b-cfa6-5f10-835c-6b8eca2816b5	2024-02-02 15:15:10
4	B0CG1N9QRC	https://www.amazon.com/dp/B0CG1N9QRC	JOIN IRON Foldable TV Trays for Eating Set of ...	JOIN IRON Store	$89.99	Usually ships within 5 to 6 weeks	['Home & Kitchen', 'Furniture', 'Game & Recrea...	https://m.media-amazon.com/images/I/41p4d4VJnN...	['https://m.media-amazon.com/images/I/41p4d4VJ...	NaN	...	Grey Set of 4	Iron	X Classic Style	[]	NaN	['Includes 4 Folding Tv Tray Tables And one Co...	Set of Four Folding Trays With Matching Storag...	['Brand: JOIN IRON', 'Shape: Rectangular', 'In...	bdc9aa30-9439-50dc-8e89-213ea211d66a	2024-02-02 15:15:11

5 rows × 25 columns

Processing step

Again, we will first prepare our requests with the Chat Completions endpoint, and create the batch file afterwards.

In [13]python · cell 32

python

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

In [14]python · cell 33

python

# 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")

Output

<IPython.core.display.Image object>

CAPTION: A stylish white free-standing shoe rack featuring multiple layers and eight double hooks, perfect for organizing shoes and accessories in living rooms, bathrooms, or hallways.

<IPython.core.display.Image object>

CAPTION: Set of 2 black leather dining chairs featuring a sleek design with vertical stitching and sturdy wooden legs.

<IPython.core.display.Image object>

CAPTION: The MUYETOL Plant Repotting Mat is a waterproof, portable, and foldable gardening work mat measuring 26.8" x 26.8", designed for easy soil changing and indoor transplanting.

<IPython.core.display.Image object>

CAPTION: Absorbent non-slip doormat featuring the phrase "It's a good day to play PICKLEBALL" with paddle graphics, measuring 16x24 inches.

<IPython.core.display.Image object>

CAPTION: Set of 4 foldable TV trays in grey, featuring a compact design with a stand for easy storage, perfect for small spaces.

Creating the batch job

As with the first example, we will create an array of json tasks to generate a jsonl file and use it to create the batch job.

In [16]python · cell 35

python

# 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)

In [17]python · cell 36

python

# 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')

In [18]python · cell 37

python

# Uploading the file 

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

In [19]python · cell 38

python

# Creating the job

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

In [ ]python · cell 39

python

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

Getting results

As with the first example, we can retrieve results once the batch job is done.

Reminder: the results are not in the same order as in the input file. Make sure to check the custom_id to match the results against the input requests

In [41]python · cell 41

python

# Retrieving result file

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

In [42]python · cell 42

python

result_file_name = "data/batch_job_results_furniture.jsonl"

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

In [43]python · cell 43

python

# 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)

In [44]python · cell 44

python

# 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")

Output

<IPython.core.display.Image object>

CAPTION: Brushed brass pedestal towel rack with a sleek, modern design, featuring multiple bars for hanging towels, measuring 25.75 x 14.44 x 32 inches.

<IPython.core.display.Image object>

CAPTION: Black round end table featuring a tempered glass top and a metal frame, with a lower shelf for additional storage.

<IPython.core.display.Image object>

CAPTION: Black collapsible and height-adjustable telescoping stool, portable and designed for makeup artists and hairstylists, shown in various stages of folding for easy transport.

<IPython.core.display.Image object>

CAPTION: Ergonomic pink gaming chair featuring breathable fabric, adjustable height, lumbar support, a footrest, and a swivel recliner function.

<IPython.core.display.Image object>

CAPTION: A set of two Glitzhome adjustable bar stools featuring a mid-century modern design with swivel seats, PU leather upholstery, and wooden backrests.

Wrapping up

In this cookbook, we have seen two examples of how to use the new Batch API, but keep in mind that the Batch API works the same way as the Chat Completions endpoint, supporting the same parameters and most of the recent models (gpt-4o, gpt-4o-mini, gpt-4-turbo, gpt-3.5-turbo...).

By using this API, you can significantly reduce costs, so we recommend switching every workload that can happen async to a batch job with this new API.

Chapter 31

batch processing

NotebookPython 3 (ipykernel)45 cells

Batch processing with the Batch API

The new Batch API allows to create async batch jobs for a lower price and with higher rate limits.

Batches will be completed within 24h, but may be processed sooner depending on global usage.

Ideal use cases for the Batch API include:

Tagging, captioning, or enriching content on a marketplace or blog
Categorizing and suggesting answers for support tickets
Performing sentiment analysis on large datasets of customer feedback
Generating summaries or translations for collections of documents or articles

and much more!

This cookbook will walk you through how to use the Batch API with a couple of practical examples.

We will start with an example to categorize movies using gpt-4o-mini, and then cover how we can use the vision capabilities of this model to caption images.

Please note that multiple models are available through the Batch API, and that you can use the same parameters in your Batch API calls as with the Chat Completions endpoint.

Setup

In [ ]python · cell 3

python

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

In [1]python · cell 4

python

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

In [2]python · cell 5

python

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

First example: Categorizing movies

In this example, we will use gpt-4o-mini to extract movie categories from a description of the movie. We will also extract a 1-sentence summary from this description.

We will use JSON mode to extract categories as an array of strings and the 1-sentence summary in a structured format.

For each movie, we want to get a result that looks like this:

code

{
    categories: ['category1', 'category2', 'category3'],
    summary: '1-sentence summary'
}

Loading data

We will use the IMDB top 1000 movies dataset for this example.

In [3]python · cell 8

python

dataset_path = "data/imdb_top_1000.csv"

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

Output

                                         Poster_Link  \
0  https://m.media-amazon.com/images/M/MV5BMDFkYT...   
1  https://m.media-amazon.com/images/M/MV5BM2MyNj...   
2  https://m.media-amazon.com/images/M/MV5BMTMxNT...   
3  https://m.media-amazon.com/images/M/MV5BMWMwMG...   
4  https://m.media-amazon.com/images/M/MV5BMWU4N2...   

               Series_Title Released_Year Certificate  Runtime  \
0  The Shawshank Redemption          1994           A  142 min   
1             The Godfather          1972           A  175 min   
2           The Dark Knight          2008          UA  152 min   
3    The Godfather: Part II          1974           A  202 min   
4              12 Angry Men          1957           U   96 min   

                  Genre  IMDB_Rating  \
0                 Drama          9.3   
1          Crime, Drama          9.2   
2  Action, Crime, Drama          9.0   
3          Crime, Drama          9.0   
4          Crime, Drama          9.0   

                                            Overview  Meta_score  \
0  Two imprisoned men bond over a number of years...        80.0   
1  An organized crime dynasty's aging patriarch t...       100.0   
2  When the menace known as the Joker wreaks havo...        84.0   
3  The early life and career of Vito Corleone in ...        90.0   
4  A jury holdout attempts to prevent a miscarria...        96.0   

               Director           Star1           Star2          Star3  \
0        Frank Darabont     Tim Robbins  Morgan Freeman     Bob Gunton   
1  Francis Ford Coppola   Marlon Brando       Al Pacino     James Caan   
2     Christopher Nolan  Christian Bale    Heath Ledger  Aaron Eckhart   
3  Francis Ford Coppola       Al Pacino  Robert De Niro  Robert Duvall   
4          Sidney Lumet     Henry Fonda     Lee J. Cobb  Martin Balsam   

            Star4  No_of_Votes        Gross  
0  William Sadler      2343110   28,341,469  
1    Diane Keaton      1620367  134,966,411  
2   Michael Caine      2303232  534,858,444  
3    Diane Keaton      1129952   57,300,000  
4    John Fiedler       689845    4,360,000

.dataframe tbody tr th:only-of-type { vertical-align: middle; } .dataframe tbody tr th { vertical-align: top; } .dataframe thead th { text-align: right; }

	Poster_Link	Series_Title	Released_Year	Certificate	Runtime	Genre	IMDB_Rating	Overview	Meta_score	Director	Star1	Star2	Star3	Star4	No_of_Votes	Gross
0	https://m.media-amazon.com/images/M/MV5BMDFkYT...	The Shawshank Redemption	1994	A	142 min	Drama	9.3	Two imprisoned men bond over a number of years...	80.0	Frank Darabont	Tim Robbins	Morgan Freeman	Bob Gunton	William Sadler	2343110	28,341,469
1	https://m.media-amazon.com/images/M/MV5BM2MyNj...	The Godfather	1972	A	175 min	Crime, Drama	9.2	An organized crime dynasty's aging patriarch t...	100.0	Francis Ford Coppola	Marlon Brando	Al Pacino	James Caan	Diane Keaton	1620367	134,966,411
2	https://m.media-amazon.com/images/M/MV5BMTMxNT...	The Dark Knight	2008	UA	152 min	Action, Crime, Drama	9.0	When the menace known as the Joker wreaks havo...	84.0	Christopher Nolan	Christian Bale	Heath Ledger	Aaron Eckhart	Michael Caine	2303232	534,858,444
3	https://m.media-amazon.com/images/M/MV5BMWMwMG...	The Godfather: Part II	1974	A	202 min	Crime, Drama	9.0	The early life and career of Vito Corleone in ...	90.0	Francis Ford Coppola	Al Pacino	Robert De Niro	Robert Duvall	Diane Keaton	1129952	57,300,000
4	https://m.media-amazon.com/images/M/MV5BMWU4N2...	12 Angry Men	1957	U	96 min	Crime, Drama	9.0	A jury holdout attempts to prevent a miscarria...	96.0	Sidney Lumet	Henry Fonda	Lee J. Cobb	Martin Balsam	John Fiedler	689845	4,360,000

Processing step

Here, we will prepare our requests by first trying them out with the Chat Completions endpoint.

Once we're happy with the results, we can move on to creating the batch file.

In [4]python · cell 10

python

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

In [5]python · cell 11

python

# 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")

Output

TITLE: The Shawshank Redemption
OVERVIEW: Two imprisoned men bond over a number of years, finding solace and eventual redemption through acts of common decency.

RESULT: {
    "categories": ["drama"],
    "summary": "Two imprisoned men develop a deep bond over the years, ultimately finding redemption through their shared acts of kindness."
}


----------------------------


TITLE: The Godfather
OVERVIEW: An organized crime dynasty's aging patriarch transfers control of his clandestine empire to his reluctant son.

RESULT: {
    "categories": ["crime", "drama"],
    "summary": "An aging crime lord hands over his empire to his hesitant son."
}


----------------------------


TITLE: The Dark Knight
OVERVIEW: When the menace known as the Joker wreaks havoc and chaos on the people of Gotham, Batman must accept one of the greatest psychological and physical tests of his ability to fight injustice.

RESULT: {
    "categories": ["action", "thriller", "superhero"],
    "summary": "Batman faces a formidable challenge as the Joker unleashes chaos on Gotham City."
}


----------------------------


TITLE: The Godfather: Part II
OVERVIEW: The early life and career of Vito Corleone in 1920s New York City is portrayed, while his son, Michael, expands and tightens his grip on the family crime syndicate.

RESULT: {
    "categories": ["crime", "drama"],
    "summary": "The film depicts the early life of Vito Corleone and the rise of his son Michael within the family crime syndicate in 1920s New York City."
}


----------------------------


TITLE: 12 Angry Men
OVERVIEW: A jury holdout attempts to prevent a miscarriage of justice by forcing his colleagues to reconsider the evidence.

RESULT: {
    "categories": ["drama", "thriller"],
    "summary": "A jury holdout fights to ensure justice is served by challenging his fellow jurors to reevaluate the evidence."
}


----------------------------

Creating the batch file

The batch file, in the jsonl format, should contain one line (json object) per request. Each request is defined as such:

code

{
    "custom_id": <REQUEST_ID>,
    "method": "POST",
    "url": "/v1/chat/completions",
    "body": {
        "model": <MODEL>,
        "messages": <MESSAGES>,
        // other parameters
    }
}

Note: the request ID should be unique per batch. This is what you can use to match results to the initial input files, as requests will not be returned in the same order.

In [6]python · cell 13

python

# 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)

In [7]python · cell 14

python

# 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')

Uploading the file

In [8]python · cell 16

python

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

In [9]python · cell 17

python

print(batch_file)

Output

FileObject(id='file-lx16f1KyIxQ2UHVvkG3HLfNR', bytes=1127310, created_at=1721144107, filename='batch_tasks_movies.jsonl', object='file', purpose='batch', status='processed', status_details=None)

Creating the batch job

In [10]python · cell 19

python

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

Checking batch status

Note: this can take up to 24h, but it will usually be completed faster.

You can continue checking until the status is 'completed'.

In [ ]python · cell 21

python

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

Retrieving results

In [13]python · cell 23

python

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

In [14]python · cell 24

python

result_file_name = "data/batch_job_results_movies.jsonl"

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

In [15]python · cell 25

python

# 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 results

Reminder: the results are not in the same order as in the input file. Make sure to check the custom_id to match the results against the input requests

In [16]python · cell 27

python

# 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")

Output

TITLE: American Psycho
OVERVIEW: A wealthy New York City investment banking executive, Patrick Bateman, hides his alternate psychopathic ego from his co-workers and friends as he delves deeper into his violent, hedonistic fantasies.

RESULT: {
    "categories": ["thriller", "psychological", "drama"],
    "summary": "A wealthy investment banker in New York City conceals his psychopathic alter ego while indulging in violent and hedonistic fantasies."
}


----------------------------


TITLE: Lethal Weapon
OVERVIEW: Two newly paired cops who are complete opposites must put aside their differences in order to catch a gang of drug smugglers.

RESULT: {
    "categories": ["action", "comedy", "crime"],
    "summary": "An action-packed comedy about two mismatched cops teaming up to take down a drug smuggling gang."
}


----------------------------


TITLE: A Star Is Born
OVERVIEW: A musician helps a young singer find fame as age and alcoholism send his own career into a downward spiral.

RESULT: {
    "categories": ["drama", "music"],
    "summary": "A musician's career spirals downward as he helps a young singer find fame amidst struggles with age and alcoholism."
}


----------------------------


TITLE: From Here to Eternity
OVERVIEW: In Hawaii in 1941, a private is cruelly punished for not boxing on his unit's team, while his captain's wife and second-in-command are falling in love.

RESULT: {
    "categories": ["drama", "romance", "war"],
    "summary": "A drama set in Hawaii in 1941, where a private faces punishment for not boxing on his unit's team, amidst a forbidden love affair between his captain's wife and second-in-command."
}


----------------------------


TITLE: The Jungle Book
OVERVIEW: Bagheera the Panther and Baloo the Bear have a difficult time trying to convince a boy to leave the jungle for human civilization.

RESULT: {
    "categories": ["adventure", "animation", "family"],
    "summary": "An adventure-filled animated movie about a panther and a bear trying to persuade a boy to leave the jungle for human civilization."
}


----------------------------

Second example: Captioning images

In this example, we will use gpt-4-turbo to caption images of furniture items.

We will use the vision capabilities of the model to analyze the images and generate the captions.

Loading data

We will use the Amazon furniture dataset for this example.

In [12]python · cell 30

python

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

Output

         asin                                   url  \
0  B0CJHKVG6P  https://www.amazon.com/dp/B0CJHKVG6P   
1  B0B66QHB23  https://www.amazon.com/dp/B0B66QHB23   
2  B0BXRTWLYK  https://www.amazon.com/dp/B0BXRTWLYK   
3  B0C1MRB2M8  https://www.amazon.com/dp/B0C1MRB2M8   
4  B0CG1N9QRC  https://www.amazon.com/dp/B0CG1N9QRC   

                                               title            brand   price  \
0  GOYMFK 1pc Free Standing Shoe Rack, Multi-laye...           GOYMFK  $24.99   
1  subrtex Leather ding Room, Dining Chairs Set o...          subrtex     NaN   
2  Plant Repotting Mat MUYETOL Waterproof Transpl...          MUYETOL   $5.98   
3  Pickleball Doormat, Welcome Doormat Absorbent ...          VEWETOL  $13.99   
4  JOIN IRON Foldable TV Trays for Eating Set of ...  JOIN IRON Store  $89.99   

                          availability  \
0  Only 13 left in stock - order soon.   
1                                  NaN   
2                             In Stock   
3  Only 10 left in stock - order soon.   
4    Usually ships within 5 to 6 weeks   

                                          categories  \
0  ['Home & Kitchen', 'Storage & Organization', '...   
1  ['Home & Kitchen', 'Furniture', 'Dining Room F...   
2  ['Patio, Lawn & Garden', 'Outdoor Décor', 'Doo...   
3  ['Patio, Lawn & Garden', 'Outdoor Décor', 'Doo...   
4  ['Home & Kitchen', 'Furniture', 'Game & Recrea...   

                                       primary_image  \
0  https://m.media-amazon.com/images/I/416WaLx10j...   
1  https://m.media-amazon.com/images/I/31SejUEWY7...   
2  https://m.media-amazon.com/images/I/41RgefVq70...   
3  https://m.media-amazon.com/images/I/61vz1Igler...   
4  https://m.media-amazon.com/images/I/41p4d4VJnN...   

                                              images  upc  ...          color  \
0  ['https://m.media-amazon.com/images/I/416WaLx1...  NaN  ...          White   
1  ['https://m.media-amazon.com/images/I/31SejUEW...  NaN  ...          Black   
2  ['https://m.media-amazon.com/images/I/41RgefVq...  NaN  ...          Green   
3  ['https://m.media-amazon.com/images/I/61vz1Igl...  NaN  ...          A5589   
4  ['https://m.media-amazon.com/images/I/41p4d4VJ...  NaN  ...  Grey Set of 4   

       material              style important_information  \
0         Metal             Modern                    []   
1        Sponge  Black Rubber Wood                    []   
2  Polyethylene             Modern                    []   
3        Rubber             Modern                    []   
4          Iron    X Classic Style                    []   

                                    product_overview  \
0  [{'Brand': ' GOYMFK '}, {'Color': ' White '}, ...   
1                                                NaN   
2  [{'Brand': ' MUYETOL '}, {'Size': ' 26.8*26.8 ...   
3  [{'Brand': ' VEWETOL '}, {'Size': ' 16*24INCH ...   
4                                                NaN   

                                          about_item  \
0  ['Multiple layers: Provides ample storage spac...   
1  ['【Easy Assembly】: Set of 2 dining room chairs...   
2  ['PLANT REPOTTING MAT SIZE: 26.8" x 26.8", squ...   
3  ['Specifications: 16x24 Inch ', " High-Quality...   
4  ['Includes 4 Folding Tv Tray Tables And one Co...   

                                         description  \
0  multiple shoes, coats, hats, and other items E...   
1                     subrtex Dining chairs Set of 2   
2                                                NaN   
3  The decorative doormat features a subtle textu...   
4  Set of Four Folding Trays With Matching Storag...   

                                      specifications  \
0  ['Brand: GOYMFK', 'Color: White', 'Material: M...   
1  ['Brand: subrtex', 'Color: Black', 'Product Di...   
2  ['Brand: MUYETOL', 'Size: 26.8*26.8', 'Item We...   
3  ['Brand: VEWETOL', 'Size: 16*24INCH', 'Materia...   
4  ['Brand: JOIN IRON', 'Shape: Rectangular', 'In...   

                                uniq_id           scraped_at  
0  02593e81-5c09-5069-8516-b0b29f439ded  2024-02-02 15:15:08  
1  5938d217-b8c5-5d3e-b1cf-e28e340f292e  2024-02-02 15:15:09  
2  b2ede786-3f51-5a45-9a5b-bcf856958cd8  2024-02-02 15:15:09  
3  8fd9377b-cfa6-5f10-835c-6b8eca2816b5  2024-02-02 15:15:10  
4  bdc9aa30-9439-50dc-8e89-213ea211d66a  2024-02-02 15:15:11  

[5 rows x 25 columns]

.dataframe tbody tr th:only-of-type { vertical-align: middle; } .dataframe tbody tr th { vertical-align: top; } .dataframe thead th { text-align: right; }

	asin	url	title	brand	price	availability	categories	primary_image	images	upc	...	color	material	style	important_information	product_overview	about_item	description	specifications	uniq_id	scraped_at
0	B0CJHKVG6P	https://www.amazon.com/dp/B0CJHKVG6P	GOYMFK 1pc Free Standing Shoe Rack, Multi-laye...	GOYMFK	$24.99	Only 13 left in stock - order soon.	['Home & Kitchen', 'Storage & Organization', '...	https://m.media-amazon.com/images/I/416WaLx10j...	['https://m.media-amazon.com/images/I/416WaLx1...	NaN	...	White	Metal	Modern	[]	[{'Brand': ' GOYMFK '}, {'Color': ' White '}, ...	['Multiple layers: Provides ample storage spac...	multiple shoes, coats, hats, and other items E...	['Brand: GOYMFK', 'Color: White', 'Material: M...	02593e81-5c09-5069-8516-b0b29f439ded	2024-02-02 15:15:08
1	B0B66QHB23	https://www.amazon.com/dp/B0B66QHB23	subrtex Leather ding Room, Dining Chairs Set o...	subrtex	NaN	NaN	['Home & Kitchen', 'Furniture', 'Dining Room F...	https://m.media-amazon.com/images/I/31SejUEWY7...	['https://m.media-amazon.com/images/I/31SejUEW...	NaN	...	Black	Sponge	Black Rubber Wood	[]	NaN	['【Easy Assembly】: Set of 2 dining room chairs...	subrtex Dining chairs Set of 2	['Brand: subrtex', 'Color: Black', 'Product Di...	5938d217-b8c5-5d3e-b1cf-e28e340f292e	2024-02-02 15:15:09
2	B0BXRTWLYK	https://www.amazon.com/dp/B0BXRTWLYK	Plant Repotting Mat MUYETOL Waterproof Transpl...	MUYETOL	$5.98	In Stock	['Patio, Lawn & Garden', 'Outdoor Décor', 'Doo...	https://m.media-amazon.com/images/I/41RgefVq70...	['https://m.media-amazon.com/images/I/41RgefVq...	NaN	...	Green	Polyethylene	Modern	[]	[{'Brand': ' MUYETOL '}, {'Size': ' 26.8*26.8 ...	['PLANT REPOTTING MAT SIZE: 26.8" x 26.8", squ...	NaN	['Brand: MUYETOL', 'Size: 26.8*26.8', 'Item We...	b2ede786-3f51-5a45-9a5b-bcf856958cd8	2024-02-02 15:15:09
3	B0C1MRB2M8	https://www.amazon.com/dp/B0C1MRB2M8	Pickleball Doormat, Welcome Doormat Absorbent ...	VEWETOL	$13.99	Only 10 left in stock - order soon.	['Patio, Lawn & Garden', 'Outdoor Décor', 'Doo...	https://m.media-amazon.com/images/I/61vz1Igler...	['https://m.media-amazon.com/images/I/61vz1Igl...	NaN	...	A5589	Rubber	Modern	[]	[{'Brand': ' VEWETOL '}, {'Size': ' 16*24INCH ...	['Specifications: 16x24 Inch ', " High-Quality...	The decorative doormat features a subtle textu...	['Brand: VEWETOL', 'Size: 16*24INCH', 'Materia...	8fd9377b-cfa6-5f10-835c-6b8eca2816b5	2024-02-02 15:15:10
4	B0CG1N9QRC	https://www.amazon.com/dp/B0CG1N9QRC	JOIN IRON Foldable TV Trays for Eating Set of ...	JOIN IRON Store	$89.99	Usually ships within 5 to 6 weeks	['Home & Kitchen', 'Furniture', 'Game & Recrea...	https://m.media-amazon.com/images/I/41p4d4VJnN...	['https://m.media-amazon.com/images/I/41p4d4VJ...	NaN	...	Grey Set of 4	Iron	X Classic Style	[]	NaN	['Includes 4 Folding Tv Tray Tables And one Co...	Set of Four Folding Trays With Matching Storag...	['Brand: JOIN IRON', 'Shape: Rectangular', 'In...	bdc9aa30-9439-50dc-8e89-213ea211d66a	2024-02-02 15:15:11

5 rows × 25 columns

Processing step

Again, we will first prepare our requests with the Chat Completions endpoint, and create the batch file afterwards.

In [13]python · cell 32

python

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

In [14]python · cell 33

python

# 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")

Output

<IPython.core.display.Image object>

CAPTION: A stylish white free-standing shoe rack featuring multiple layers and eight double hooks, perfect for organizing shoes and accessories in living rooms, bathrooms, or hallways.

<IPython.core.display.Image object>

CAPTION: Set of 2 black leather dining chairs featuring a sleek design with vertical stitching and sturdy wooden legs.

<IPython.core.display.Image object>

CAPTION: The MUYETOL Plant Repotting Mat is a waterproof, portable, and foldable gardening work mat measuring 26.8" x 26.8", designed for easy soil changing and indoor transplanting.

<IPython.core.display.Image object>

CAPTION: Absorbent non-slip doormat featuring the phrase "It's a good day to play PICKLEBALL" with paddle graphics, measuring 16x24 inches.

<IPython.core.display.Image object>

CAPTION: Set of 4 foldable TV trays in grey, featuring a compact design with a stand for easy storage, perfect for small spaces.

Creating the batch job

As with the first example, we will create an array of json tasks to generate a jsonl file and use it to create the batch job.

In [16]python · cell 35

python

# 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)

In [17]python · cell 36

python

# 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')

In [18]python · cell 37

python

# Uploading the file 

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

In [19]python · cell 38

python

# Creating the job

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

In [ ]python · cell 39

python

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

Getting results

As with the first example, we can retrieve results once the batch job is done.

Reminder: the results are not in the same order as in the input file. Make sure to check the custom_id to match the results against the input requests

In [41]python · cell 41

python

# Retrieving result file

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

In [42]python · cell 42

python

result_file_name = "data/batch_job_results_furniture.jsonl"

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

In [43]python · cell 43

python

# 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)

In [44]python · cell 44

python

# 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")

Output

<IPython.core.display.Image object>

CAPTION: Brushed brass pedestal towel rack with a sleek, modern design, featuring multiple bars for hanging towels, measuring 25.75 x 14.44 x 32 inches.

<IPython.core.display.Image object>

CAPTION: Black round end table featuring a tempered glass top and a metal frame, with a lower shelf for additional storage.

<IPython.core.display.Image object>

CAPTION: Black collapsible and height-adjustable telescoping stool, portable and designed for makeup artists and hairstylists, shown in various stages of folding for easy transport.

<IPython.core.display.Image object>

CAPTION: Ergonomic pink gaming chair featuring breathable fabric, adjustable height, lumbar support, a footrest, and a swivel recliner function.

<IPython.core.display.Image object>

CAPTION: A set of two Glitzhome adjustable bar stools featuring a mid-century modern design with swivel seats, PU leather upholstery, and wooden backrests.

Wrapping up

By using this API, you can significantly reduce costs, so we recommend switching every workload that can happen async to a batch job with this new API.