Skip to content

Commit

Permalink
Merge pull request #85 from openai/jc-sync
Browse files Browse the repository at this point in the history 
Sync API spec updates
  • Loading branch information
@jeffchan
jeffchan committed Sep 12, 2023
2 parents b0ab1c3 + 8eb463d commit 4f3366c
Showing 1 changed file with 107 additions and 41 deletions.
148 changes: 107 additions & 41 deletions openapi.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1098,47 +1098,96 @@ paths:
name: Create fine-tuning job
returns: A [fine-tuning.job](/docs/api-reference/fine-tuning/object) object.
examples:
request:
curl: |
curl https://api.openai.com/v1/fine_tuning/jobs \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"training_file": "file-abc123"
"model": "gpt-3.5-turbo",
}'
python: |
import os
import openai
openai.api_key = os.getenv("OPENAI_API_KEY")
openai.FineTuningJob.create(training_file="file-abc123", model="gpt-3.5-turbo")
node.js: |
import OpenAI from "openai";
- title: No hyperparameters
request:
curl: |
curl https://api.openai.com/v1/fine_tuning/jobs \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"training_file": "file-abc123"
"model": "gpt-3.5-turbo",
}'
python: |
import os
import openai
openai.api_key = os.getenv("OPENAI_API_KEY")
openai.FineTuningJob.create(training_file="file-abc123", model="gpt-3.5-turbo")
node.js: |
import OpenAI from "openai";
const openai = new OpenAI();
const openai = new OpenAI();
async function main() {
const fineTune = await openai.fineTuning.jobs.create({
training_file: "file-abc123"
});
async function main() {
const fineTune = await openai.fineTuning.jobs.create({
training_file: "file-abc123"
});
console.log(fineTune);
console.log(fineTune);
}
main();
response: |
{
"object": "fine_tuning.job",
"id": "ft-AF1WoRqd3aJAHsqc9NY7iL8F",
"model": "gpt-3.5-turbo-0613",
"created_at": 1614807352,
"fine_tuned_model": null,
"organization_id": "org-123",
"result_files": [],
"status": "pending",
"validation_file": null,
"training_file": "file-abc123",
}
- title: Hyperparameters
request:
curl: |
curl https://api.openai.com/v1/fine_tuning/jobs \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"training_file": "file-abc123"
"model": "gpt-3.5-turbo",
"hyperparameters": {
"n_epochs": 2
}
}'
python: |
import os
import openai
openai.api_key = os.getenv("OPENAI_API_KEY")
openai.FineTuningJob.create(training_file="file-abc123", model="gpt-3.5-turbo", hyperparameters={"n_epochs":2})
node.js: |
import OpenAI from "openai";
main();
response: |
{
"object": "fine_tuning.job",
"id": "ft-AF1WoRqd3aJAHsqc9NY7iL8F",
"model": "gpt-3.5-turbo-0613",
"created_at": 1614807352,
"fine_tuned_model": null,
"organization_id": "org-123",
"result_files": [],
"status": "pending",
"validation_file": null,
"training_file": "file-abc123",
}
const openai = new OpenAI();
async function main() {
const fineTune = await openai.fineTuning.jobs.create({
training_file: "file-abc123",
model: "gpt-3.5-turbo",
hyperparameters: { n_epochs: 2 },
});
console.log(fineTune);
}
main();
response: |
{
"object": "fine_tuning.job",
"id": "ft-AF1WoRqd3aJAHsqc9NY7iL8F",
"model": "gpt-3.5-turbo-0613",
"created_at": 1614807352,
"fine_tuned_model": null,
"organization_id": "org-123",
"result_files": [],
"status": "pending",
"validation_file": null,
"training_file": "file-abc123",
"hyperparameters":{"n_epochs":2},
}
get:
operationId: listPaginatedFineTuningJobs
tags:
Expand Down Expand Up @@ -2643,7 +2692,7 @@ components:
items:
$ref: "#/components/schemas/ChatCompletionFunctions"
function_call:
description: Controls how the model responds to function calls. "none" means the model does not call a function, and responds to the end-user. "auto" means the model can pick between an end-user or calling a function. Specifying a particular function via `{"name":\ "my_function"}` forces the model to call that function. "none" is the default when no functions are present. "auto" is the default if functions are present.
description: "Controls how the model responds to function calls. `none` means the model does not call a function, and responds to the end-user. `auto` means the model can pick between an end-user or calling a function. Specifying a particular function via `{\"name\": \"my_function\"}` forces the model to call that function. `none` is the default when no functions are present. `auto` is the default if functions are present."
oneOf:
- type: string
enum: [none, auto]
Expand Down Expand Up @@ -2698,6 +2747,7 @@ components:
The total length of input tokens and generated tokens is limited by the model's context length. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb) for counting tokens.
default: inf
type: integer
nullable: true
presence_penalty:
type: number
default: 0
Expand Down Expand Up @@ -3294,7 +3344,7 @@ components:
default: auto
suffix:
description: |
A string of up to 40 characters that will be added to your fine-tuned model name.
A string of up to 18 characters that will be added to your fine-tuned model name.
For example, a `suffix` of "custom-model-name" would produce a model name like `ft:gpt-3.5-turbo:openai:custom-model-name:7p4lURel`.
type: string
Expand Down Expand Up @@ -3511,7 +3561,7 @@ components:
x-oaiTypeLabel: string
input:
description: |
Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. Each input must not exceed the max input tokens for the model (8191 tokens for `text-embedding-ada-002`). [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb) for counting tokens.
Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. Each input must not exceed the max input tokens for the model (8191 tokens for `text-embedding-ada-002`) and cannot be an empty string. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb) for counting tokens.
example: "The quick brown fox jumped over the lazy dog"
oneOf:
- type: string
Expand Down Expand Up @@ -3844,14 +3894,29 @@ components:
description: The file ID used for validation. You can retrieve the validation results with the [Files API](/docs/api-reference/files/retrieve-contents).
result_files:
type: array
description: The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the [Files API](/docs/api-reference/files/retrieve-contents).
description: The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the [Files API](/docs/api-reference/files/retrieve-contents).
items:
type: string
example: file-abc123
trained_tokens:
type: integer
nullable: true
description: The total number of billable tokens processed by this fine-tuning job. The value will be null if the fine-tuning job is still running.
error:
type: object
nullable: true
description: For fine-tuning jobs that have `failed`, this will contain more information on the cause of the failure.
properties:
message:
type: string
description: A human-readable error message.
code:
type: string
description: A machine-readable error code.
param:
type: string
description: The parameter that was invalid, usually `training_file` or `validation_file`. This field will be null if the failure was not parameter-specific.
nullable: true
required:
- id
- object
Expand All @@ -3863,9 +3928,10 @@ components:
- status
- hyperparameters
- training_file
- trained_tokens
- validation_file
- result_files
- trained_tokens
- error
x-oaiMeta:
name: The fine-tuning job object
example: *fine_tuning_example
Expand Down

0 comments on commit 4f3366c

Please sign in to comment.