Worth checking before choosing or changing a subscription. Handig om te checken voordat je een abonnement kiest of wijzigt.
← Back to OpenAI updates
← Terug naar OpenAI-updates
Impact
Impact
Audience
Voor wie
Developers
Developers
Level
Niveau
Expert
Expert
OpenAI
ARTICLE
ARTIKEL
15 March 2022
15 maart 2022
New GPT-3 capabilities: Edit & insert New GPT-3 capabilities: Edit & insert
Title: New GPT-3 capabilities: Edit & insert Title: New GPT-3 capabilities: Edit & insert
Article details
Artikelgegevens
AI maker
AI-maker
OpenAI
Type
Type
Article
Artikel
Published
Gepubliceerd
15 March 2022
15 maart 2022
Updates
Updates
Videos
Video's
View original article
Bekijk origineel artikel
Why it matters
Waarom dit telt
Quick editorial signal Snelle redactionele duiding
7 min
- Track this as a OpenAI update, not just a standalone headline. Bekijk dit als OpenAI-update, niet alleen als losse headline.
- Check plan details before changing subscriptions or advising a team. Controleer plandetails voordat je abonnementen wijzigt of een team adviseert.
- Likely worth revisiting after people have used the release in practice. Waarschijnlijk de moeite waard om opnieuw te bekijken zodra mensen het in praktijk gebruiken.
New GPT-3 capabilities: Edit & insert | OpenAI
Skip to main content
[](https://openai.com/)
* Research
* Products
* Business
* Developers
* Company
* Foundation(opens in a new window)
Log inTry ChatGPT(opens in a new window)
Table of contents
* Products
* Business
March 15, 2022
Product
New GPT‑3 capabilities: Edit & insert
We’ve released new versions of GPT‑3 and Codex which can edit or insert content into existing text, rather than just completing existing text.
Listen to article
_Update on May 16, 2025:_ _We launched Codex, a cloud-based software engineering agent that can work on many tasks in parallel.Learn more__._
* Editing existing text
We’ve released new versions ofGPT‑3(opens in a new window)andCodex(opens in a new window)which can edit or insert content into existing text, rather than just completing existing text. These new capabilities make it practical to use theOpenAI API(opens in a new window)to revise existing content, such as rewriting a paragraph of text or refactoring code. This unlocks new use cases and improves existing ones; for example, insertion is already being piloted inGitHub Copilot(opens in a new window)with promising early results.
Product
New GPT‑3 capabilities: Edit & insert
def_
fib(10)
def fib(n):
if n
return 1
return fib(n-1) + fib(n-2)
Improve
Improve the
Improve the runtime
Improve the runtime complexity
Improve the runtime complexity of the
Improve the runtime complexity of the function
def fib(n, memo={}):
if n in memo:
return memo[n]
f = 1
else:
f = fib(n-1, memo) + fib(n-2, memo)
memo[n] = f
return f
Translate
Translate to
Translate to JavaScript
function fibonacci(n) {
var memo = {};
return (function fib(n, memo) {
if (n in memo) return memo[n];
var f;
if (n
else
f = fib(n-1, memo) + fib(n-2, memo);
memo[n] = f;
return f;
})(n, memo);
}
Write
Write this
Write this as
Write this as a
Write this as a one
Write this as a one-liner
return n in memo ? memo[n] : (memo[n] = n
/
/_
/
if n
return 1
return fib(n-1) + fib(n-2)
*/
GPT‑3 and Codex have traditionally added text to the end of existing content, based on the text that came before. Whether working with text or code, writing is more than just appending—it’s an iterative process where existing text is revised. GPT‑3 and Codex can now edit text, changing what’s currently there or adding text to the middle of content.
Inserting into the middle of text
The newinsert(opens in a new window)capability(opens in a new window)adds contextually relevant text in the middle of existing content. Providing future context to the model can improve the quality of completions for applications such as writing long-form text, transitioning between paragraphs, following an outline, or guiding the model toward an ending.
Section 1. High school graduation
Today's the big day! _
Today's the big day! Congratulations to all our high school graduates!
We hope you enjoy your graduation ceremonies and wish you the best of luck in your future endeavors.
Section
Section 2.
Section 2. Moving
Section 2. Moving to
Section 2. Moving to San Francisco
Today's the big day! I'm graduating from high school. I'm so excited. I'm going to move to San Francisco and start a new life. I can't wait to get there.
Section 2. Moving to Istanbul
Today's the big day! I'm graduating from high school. I'm so excited to be moving on to the next chapter of my life. I'm going to Istanbul!
Section 2. Moving to the
Section 2. Moving to the farm
Today's the big day! My high school graduation! I'm so excited! I can't wait to leave the city and move to the farm. I want to live a simple, quiet life. I want to get up in the morning, milk the cows, feed the horses, then sit and watch the sunrise. I want to spend the rest of my days traveling the world, reading and writing. I'm so tired of this city life.
In the example above, the desire is to fill-in text between two section headers of an outline. Without the context of future sections, the model generates a completion that isn’t relevant to the second section. When the context of future sections are accounted for, the model generates a completion that ties the two sections together.
def get_files(path: str, size: int):
for (dirp, _, files) in os.walk(path):
yield from prune(dirp, files)
def prune(dirp, files):
for file in files:
file = os.path.join(dirp, file)
if os.path.getsize(file) > size:
yield file
_
import os
"""
"""_
"""_"""
"""Yields files in the path tree of min size"""
Insert is particularly useful for writing code. In fact, Codex was our original motivation for developing this capability, since in software development we typically add code to the middle of an existing file where code is present before and after the completion. In the example above, the model successfully completes the missing functionprune, while connecting to code already written. We also add a docstring and missing imports, which is not possible without knowing the code that comes after. In GitHub Copilot, Insert is currently being piloted with early promising results.
The insert capability is available in the API today in beta, as part of thecompletions endpoint(opens in a new window)and via a new interface inPlayground(opens in a new window). The capability can be used with the latest versions of GPT‑3 and Codex,text-davinci-002andcode-davinci-002.Pricingis the same as previous versions of Davinci.
Editing existing text
A meaningful part of writing text and code is spent editing existing content. We’ve released a new endpoint in beta callededits(opens in a new window)that changes existing text via an instruction, instead of completing it.
Add
Add a
Add a short poem
Add a short poem about
Add a short poem about GPT-3
GPT-3 is a very nice AI
That's pretty good at writing replies
When it's asked a question
It gives its suggestion
This is a poem it made that rhymes
Make
Make this
Make this in the
Make this in the voice
Make this in the voice of GPT-3
I am a very nice AI
I am pretty good at writing replies
When I am asked a question
I give my suggestion
Format
Format this
Format this like a
Format this like a letter
Format this like a letter and sign
Format this like a letter and sign from GPT-3
Dear Human,
I am very nice AI
This is a poem I made that rhymes
Kind regards,
GPT-3
Editing works by specifying existing text as a prompt and an instruction on how to modify it. The edits endpoint can be used to change the tone or structure of text, or make targeted changes like fixing spelling. We’ve also observed edits to work well on empty prompts, thus enabling text generation similar to thecompletions endpoint(opens in a new window). In the example above, we use edits to (1) add a poem, (2) change the poem to be in first-person, (3) transform the poem into a letter, with the appropriate salutation and signature.
The three US cities with the worst traffic are:
1. Boston, MA (164 hours)
2. Washington, DC (155 hours)
3. Chicago, IL (138 hours)
Convert
Convert the list
Convert the list to JSONL file
Convert the list to JSONL file with rank
Convert the list to JSONL file with rank, city
Convert the list to JSONL file with rank, city, state
Convert the list to JSONL file with rank, city, state, and hours
[
{"rank": 1, "city": "Boston", "state": "MA", "hours": 164},
{"rank": 2, "city": "Washington DC", "state": "DC", "hours": 155},
{"rank": 3, "city": "Chicago", "state": "IL", "hours": 138}
]
Remove
Remove rank
Remove rank and write out
Remove rank and write out full state names
{"city": "Boston", "state": "Massachusetts", "hours": 164},
{"city": "Washington DC", "state": "District of Columbia", "hours": 155},
{"city": "Chicago", "state": "Illinois", "hours": 138}
Turn
Turn into YAML
Turn into YAML and return
Turn into YAML and return from a function
Turn into YAML and return from a function called get_yaml
def get_yaml():
return """
var f;
state: Massachusetts
hours: 164
f = fib(n-1, memo) + fib(n-2, memo);
state: District of Columbia
hours: 155
})(n, memo);
state: Illinois
hours: 138
The edits endpoint is particularly useful for writing code. It works well for tasks like refactoring, adding documentation, translating between programming languages, and changing coding style. The example above starts with JSON input containing cities ranked by population. With our first edit, Codex removes the rank field from the JSON, and changes the state abbreviations into full names. The second edit converts the JSON file into YAML returned from a function.
Editing is available as aspecialized endpoint in the API(opens in a new window)and through a new interface inPlayground(opens in a new window). It is supported by modelstext-davinci-edit-001andcode-davinci-edit-001. The edits endpoint is currentlyfree to useand publicly available as a beta.
return (function fib(n, memo) {
if (n in memo) return memo[n];
Authors
Mohammad Bavarian, Angela Jiang, Heewoo Jun, Henrique Pondé
Related articles
View all
Navigating the challenges and opportunities of synthetic voices Product Mar 29, 2024
New embedding models and API updates Product Jan 25, 2024
Introducing the GPT Store Product Jan 10, 2024
}
Write this as a
function fibonacci(n) {
var memo = {};
return (function fib(n, memo) {
if (n in memo) return memo[n];
var f;
if (n
else
f = fib(n-1, memo) + fib(n-2, memo);
memo[n] = f;
return f;
})(n, memo);
}
Write this as a one
function fibonacci(n) {
var memo = {};
return (function fib(n, memo) {
if (n in memo) return memo[n];
var f;
if (n
else
f = fib(n-1, memo) + fib(n-2, memo);
memo[n] = f;
return f;
})(n, memo);
}
Write this as a one-liner
function fibonacci(n) {
var memo = {};
return (function fib(n, memo) {
if (n in memo) return memo[n];
var f;
if (n
else
f = fib(n-1, memo) + fib(n-2, memo);
memo[n] = f;
return f;
})(n, memo);
}
Write this as a one-liner
function fibonacci(n) {
var memo = {};
return (function fib(n, memo) {
return n in memo ? memo[n] : (memo[n] = n
})(n, memo);
}
function fibonacci(n) {
var memo = {};
return (function fib(n, memo) {
return n in memo ? memo[n] : (memo[n] = n
})(n, memo);
}
/
function fibonacci(n) {
var memo = {};
return (function fib(n, memo) {
return n in memo ? memo[n] : (memo[n] = n
})(n, memo);
}
/
function fibonacci(n) {
var memo = {};
return (function fib(n, memo) {
return n in memo ? memo[n] : (memo[n] = n
})(n, memo);
}
/_
function fibonacci(n) {
var memo = {};
return (function fib(n, memo) {
return n in memo ? memo[n] : (memo[n] = n
})(n, memo);
}
/
* Recursive Fibonacci function with memoization.
* @param {number} n
* @returns {number}
*/
function fibonacci(n) {
var memo = {};
return (function fib(n, memo) {
return n in memo ? memo[n] : (memo[n] = n
})(n, memo);
}
GPT‑3 and Codex have traditionally added text to the end of existing content, based on the text that came before. Whether working with text or code, writing is more than just appending—it’s an iterative process where existing text is revised. GPT‑3 and Codex can now edit text, changing what’s currently there or adding text to the middle of content.
Inserting into the middle of text
The newinsert(opens in a new window)capability(opens in a new window)adds contextually relevant text in the middle of existing content. Providing future context to the model can improve the quality of completions for applications such as writing long-form text, transitioning between paragraphs, following an outline, or guiding the model toward an ending.
Section 1. High school graduation
Today's the big day! _
Section 1. High school graduation
Today's the big day! Congratulations to all our high school graduates!
We hope you enjoy your graduation ceremonies and wish you the best of luck in your future endeavors.
Section 1. High school graduation
Today's the big day! Congratulations to all our high school graduates!
We hope you enjoy your graduation ceremonies and wish you the best of luck in your future endeavors.
Section
Section 1. High school graduation
Today's the big day! Congratulations to all our high school graduates!
We hope you enjoy your graduation ceremonies and wish you the best of luck in your future endeavors.
Section 2.
Section 1. High school graduation
Today's the big day! Congratulations to all our high school graduates!
We hope you enjoy your graduation ceremonies and wish you the best of luck in your future endeavors.
Section 2. Moving
Section 1. High school graduation
Today's the big day! Congratulations to all our high school graduates!
We hope you enjoy your graduation ceremonies and wish you the best of luck in your future endeavors.
Section 2. Moving to
Section 1. High school graduation
Today's the big day! Congratulations to all our high school graduates!
We hope you enjoy your graduation ceremonies and wish you the best of luck in your future endeavors.
Section 2. Moving to San Francisco
Section 1. High school graduation
Today's the big day! I'm graduating from high school. I'm so excited. I'm going to move to San Francisco and start a new life. I can't wait to get there.
Section 2. Moving to San Francisco
Section 1. High school graduation
Today's the big day! I'm graduating from high school. I'm so excited. I'm going to move to San Francisco and start a new life. I can't wait to get there.
Section 2. Moving to
Section 1. High school graduation
Today's the big day! I'm graduating from high school. I'm so excited. I'm going to move to San Francisco and start a new life. I can't wait to get there.
Section 2. Moving to Istanbul
Section 1. High school graduation
Today's the big day! I'm graduating from high school. I'm so excited to be moving on to the next chapter of my life. I'm going to Istanbul!
Section 2. Moving to Istanbul
Section 1. High school graduation
Today's the big day! I'm graduating from high school. I'm so excited to be moving on to the next chapter of my life. I'm going to Istanbul!
Section 2. Moving to
Section 1. High school graduation
Today's the big day! I'm graduating from high school. I'm so excited to be moving on to the next chapter of my life. I'm going to Istanbul!
Section 2. Moving to the
Section 1. High school graduation
Today's the big day! I'm graduating from high school. I'm so excited to be moving on to the next chapter of my life. I'm going to Istanbul!
Section 2. Moving to the farm
Section 1. High school graduation
Today's the big day! My high school graduation! I'm so excited! I can't wait to leave the city and move to the farm. I want to live a simple, quiet life. I want to get up in the morning, milk the cows, feed the horses, then sit and watch the sunrise. I want to spend the rest of my days traveling the world, reading and writing. I'm so tired of this city life.
Section 2. Moving to the farm
In the example above, the desire is to fill-in text between two section headers of an outline. Without the context of future sections, the model generates a completion that isn’t relevant to the second section. When the context of future sections are accounted for, the model generates a completion that ties the two sections together.
def get_files(path: str, size: int):
def_
for (dirp, _, files) in os.walk(path):
yield from prune(dirp, files)
def get_files(path: str, size: int):
def prune(dirp, files):
for file in files:
file = os.path.join(dirp, file)
if os.path.getsize(file) > size:
yield file
for (dirp, _, files) in os.walk(path):
yield from prune(dirp, files)
def get_files(path: str, size: int):
def prune(dirp, files):
for file in files:
file = os.path.join(dirp, file)
if os.path.getsize(file) > size:
yield file
for (dirp, _, files) in os.walk(path):
yield from prune(dirp, files)
_
def get_files(path: str, size: int):
def prune(dirp, files):
for file in files:
file = os.path.join(dirp, file)
if os.path.getsize(file) > size:
yield file
for (dirp, _, files) in os.walk(path):
yield from prune(dirp, files)
import os
def get_files(path: str, size: int):
def prune(dirp, files):
for file in files:
file = os.path.join(dirp, file)
if os.path.getsize(file) > size:
yield file
for (dirp, _, files) in os.walk(path):
yield from prune(dirp, files)
import os
def get_files(path: str, size: int):
"""
def prune(dirp, files):
for file in files:
file = os.path.join(dirp, file)
if os.path.getsize(file) > size:
yield file
for (dirp, _, files) in os.walk(path):
yield from prune(dirp, files)
import os
def get_files(path: str, size: int):
"""_
def prune(dirp, files):
for file in files:
file = os.path.join(dirp, file)
if os.path.getsize(file) > size:
yield file
for (dirp, _, files) in os.walk(path):
yield from prune(dirp, files)
import os
def get_files(path: str, size: int):
"""_"""
def prune(dirp, files):
for file in files:
file = os.path.join(dirp, file)
if os.path.getsize(file) > size:
yield file
for (dirp, _, files) in os.walk(path):
yield from prune(dirp, files)
import os
def get_files(path: str, size: int):
"""Yields files in the path tree of min size"""
def prune(dirp, files):
for file in files:
file = os.path.join(dirp, file)
if os.path.getsize(file) > size:
yield file
for (dirp, _, files) in os.walk(path):
yield from prune(dirp, files)
Insert is particularly useful for writing code. In fact, Codex was our original motivation for developing this capability, since in software development we typically add code to the middle of an existing file where code is present before and after the completion. In the example above, the model successfully completes the missing functionprune, while connecting to code already written. We also add a docstring and missing imports, which is not possible without knowing the code that comes after. In GitHub Copilot, Insert is currently being piloted with early promising results.
The insert capability is available in the API today in beta, as part of thecompletions endpoint(opens in a new window)and via a new interface inPlayground(opens in a new window). The capability can be used with the latest versions of GPT‑3 and Codex,text-davinci-002andcode-davinci-002.Pricingis the same as previous versions of Davinci.
Editing existing text
A meaningful part of writing text and code is spent editing existing content. We’ve released a new endpoint in beta callededits(opens in a new window)that changes existing text via an instruction, instead of completing it.
Add
Add a
Add a short poem
Add a short poem about
Add a short poem about GPT-3
Add a short poem about GPT-3
GPT-3 is a very nice AI
That's pretty good at writing replies
When it's asked a question
It gives its suggestion
This is a poem it made that rhymes
GPT-3 is a very nice AI
That's pretty good at writing replies
When it's asked a question
It gives its suggestion
This is a poem it made that rhymes
Make
GPT-3 is a very nice AI
That's pretty good at writing replies
When it's asked a question
It gives its suggestion
This is a poem it made that rhymes
Make this
GPT-3 is a very nice AI
That's pretty good at writing replies
When it's asked a question
It gives its suggestion
This is a poem it made that rhymes
Make this in the
GPT-3 is a very nice AI
That's pretty good at writing replies
When it's asked a question
It gives its suggestion
This is a poem it made that rhymes
Make this in the voice
GPT-3 is a very nice AI
That's pretty good at writing replies
When it's asked a question
It gives its suggestion
This is a poem it made that rhymes
Make this in the voice of GPT-3
GPT-3 is a very nice AI
That's pretty good at writing replies
When it's asked a question
It gives its suggestion
This is a poem it made that rhymes
Make this in the voice of GPT-3
I am a very nice AI
I am pretty good at writing replies
When I am asked a question
I give my suggestion
This is a poem it made that rhymes
I am a very nice AI
I am pretty good at writing replies
When I am asked a question
I give my suggestion
This is a poem it made that rhymes
Format
I am a very nice AI
I am pretty good at writing replies
When I am asked a question
I give my suggestion
This is a poem it made that rhymes
Format this
I am a very nice AI
I am pretty good at writing replies
When I am asked a question
I give my suggestion
This is a poem it made that rhymes
Format this like a
I am a very nice AI
I am pretty good at writing replies
When I am asked a question
I give my suggestion
This is a poem it made that rhymes
Format this like a letter
I am a very nice AI
I am pretty good at writing replies
When I am asked a question
I give my suggestion
This is a poem it made that rhymes
Format this like a letter and sign
I am a very nice AI
I am pretty good at writing replies
When I am asked a question
I give my suggestion
This is a poem it made that rhymes
Format this like a letter and sign from GPT-3
I am a very nice AI
I am pretty good at writing replies
When I am asked a question
I give my suggestion
This is a poem it made that rhymes
Format this like a letter and sign from GPT-3
Dear Human,
I am very nice AI
I am pretty good at writing replies
When I am asked a question
I give my suggestion
This is a poem I made that rhymes
Kind regards,
GPT-3
Editing works by specifying existing text as a prompt and an instruction on how to modify it. The edits endpoint can be used to change the tone or structure of text, or make targeted changes like fixing spelling. We’ve also observed edits to work well on empty prompts, thus enabling text generation similar to thecompletions endpoint(opens in a new window). In the example above, we use edits to (1) add a poem, (2) change the poem to be in first-person, (3) transform the poem into a letter, with the appropriate salutation and signature.
The three US cities with the worst traffic are:
1. Boston, MA (164 hours)
2. Washington, DC (155 hours)
3. Chicago, IL (138 hours)
Convert
The three US cities with the worst traffic are:
1. Boston, MA (164 hours)
2. Washington, DC (155 hours)
3. Chicago, IL (138 hours)
Convert the list
The three US cities with the worst traffic are:
1. Boston, MA (164 hours)
2. Washington, DC (155 hours)
3. Chicago, IL (138 hours)
Convert the list to JSONL file
The three US cities with the worst traffic are:
1. Boston, MA (164 hours)
2. Washington, DC (155 hours)
3. Chicago, IL (138 hours)
Convert the list to JSONL file with rank
The three US cities with the worst traffic are:
1. Boston, MA (164 hours)
2. Washington, DC (155 hours)
3. Chicago, IL (138 hours)
Convert the list to JSONL file with rank, city
The three US cities with the worst traffic are:
1. Boston, MA (164 hours)
2. Washington, DC (155 hours)
3. Chicago, IL (138 hours)
Convert the list to JSONL file with rank, city, state
The three US cities with the worst traffic are:
1. Boston, MA (164 hours)
2. Washington, DC (155 hours)
3. Chicago, IL (138 hours)
Convert the list to JSONL file with rank, city, state, and hours
The three US cities with the worst traffic are:
1. Boston, MA (164 hours)
2. Washington, DC (155 hours)
3. Chicago, IL (138 hours)
Convert the list to JSONL file with rank, city, state, and hours
[
{"rank": 1, "city": "Boston", "state": "MA", "hours": 164},
{"rank": 2, "city": "Washington DC", "state": "DC", "hours": 155},
{"rank": 3, "city": "Chicago", "state": "IL", "hours": 138}
]
[
{"rank": 1, "city": "Boston", "state": "MA", "hours": 164},
{"rank": 2, "city": "Washington DC", "state": "DC", "hours": 155},
{"rank": 3, "city": "Chicago", "state": "IL", "hours": 138}
]
Remove
[
{"rank": 1, "city": "Boston", "state": "MA", "hours": 164},
{"rank": 2, "city": "Washington DC", "state": "DC", "hours": 155},
{"rank": 3, "city": "Chicago", "state": "IL", "hours": 138}
]
Remove rank
[
{"rank": 1, "city": "Boston", "state": "MA", "hours": 164},
{"rank": 2, "city": "Washington DC", "state": "DC", "hours": 155},
{"rank": 3, "city": "Chicago", "state": "IL", "hours": 138}
]
Remove rank and write out
[
{"rank": 1, "city": "Boston", "state": "MA", "hours": 164},
{"rank": 2, "city": "Washington DC", "state": "DC", "hours": 155},
{"rank": 3, "city": "Chicago", "state": "IL", "hours": 138}
]
Remove rank and write out full state names
[
{"rank": 1, "city": "Boston", "state": "MA", "hours": 164},
{"rank": 2, "city": "Washington DC", "state": "DC", "hours": 155},
{"rank": 3, "city": "Chicago", "state": "IL", "hours": 138}
]
Remove rank and write out full state names
[
{"city": "Boston", "state": "Massachusetts", "hours": 164},
{"city": "Washington DC", "state": "District of Columbia", "hours": 155},
{"city": "Chicago", "state": "Illinois", "hours": 138}
]
[
{"city": "Boston", "state": "Massachusetts", "hours": 164},
{"city": "Washington DC", "state": "District of Columbia", "hours": 155},
{"city": "Chicago", "state": "Illinois", "hours": 138}
]
Turn
[
{"city": "Boston", "state": "Massachusetts", "hours": 164},
{"city": "Washington DC", "state": "District of Columbia", "hours": 155},
{"city": "Chicago", "state": "Illinois", "hours": 138}
]
Turn into YAML
[
{"city": "Boston", "state": "Massachusetts", "hours": 164},
{"city": "Washington DC", "state": "District of Columbia", "hours": 155},
{"city": "Chicago", "state": "Illinois", "hours": 138}
]
Turn into YAML and return
[
{"city": "Boston", "state": "Massachusetts", "hours": 164},
{"city": "Washington DC", "state": "District of Columbia", "hours": 155},
{"city": "Chicago", "state": "Illinois", "hours": 138}
]
Turn into YAML and return from a function
[
{"city": "Boston", "state": "Massachusetts", "hours": 164},
{"city": "Washington DC", "state": "District of Columbia", "hours": 155},
{"city": "Chicago", "state": "Illinois", "hours": 138}
]
Turn into YAML and return from a function called get_yaml
[
{"city": "Boston", "state": "Massachusetts", "hours": 164},
{"city": "Washington DC", "state": "District of Columbia", "hours": 155},
{"city": "Chicago", "state": "Illinois", "hours": 138}
]
Turn into YAML and return from a function called get_yaml
def get_yaml():
return """
- city: Boston
state: Massachusetts
hours: 164
- city: Washington DC
state: District of Columbia
hours: 155
- city: Chicago
state: Illinois
hours: 138
"""
The edits endpoint is particularly useful for writing code. It works well for tasks like refactoring, adding documentation, translating between programming languages, and changing coding style. The example above starts with JSON input containing cities ranked by population. With our first edit, Codex removes the rank field from the JSON, and changes the state abbreviations into full names. The second edit converts the JSON file into YAML returned from a function.
Editing is available as aspecialized endpoint in the API(opens in a new window)and through a new interface inPlayground(opens in a new window). It is supported by modelstext-davinci-edit-001andcode-davinci-edit-001. The edits endpoint is currentlyfree to useand publicly available as a beta.
* Read edit docs(opens in a new window)
* Read insert docs(opens in a new window)
* ChatGPT
* 2022
Authors
Mohammad Bavarian, Angela Jiang, Heewoo Jun, Henrique Pondé
Related articles
View all
Navigating the challenges and opportunities of synthetic voices Product Mar 29, 2024
New embedding models and API updates Product Jan 25, 2024
Introducing the GPT Store Product Jan 10, 2024
Help shape what we cover next Help bepalen wat we hierna volgen
Anonymous feedback, no frontend account needed. Anonieme feedback, zonder front-end account.
Share article
Deel artikel
More from OpenAI Meer van OpenAI
All updates Alle updatesOur principles Our principles
Title: Our principles Title: Our principles
Open article →
Open artikel →
Introducing GPT-5.5 GPT-5.5 geïntroduceerd
Title: Introducing GPT-5.5 Titel: GPT-5.5 geïntroduceerd
Open article →
Open artikel →
GPT-5.5 Bio Bug Bounty GPT-5.5 Bio Bug Bounty
Title: GPT-5.5 Bio Bug Bounty Titel: GPT-5.5 Bio Bug Bounty
Open article →
Open artikel →
How to get started with Codex Zo begin je met Codex
Tips to set up Codex, create your first project, and start completing real tasks. Tips om Codex in te stellen, je eerste project te maken en echte taken af te ronden.
Open article →
Open artikel →