You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The maximum number of [tokens](/tokenizer) to generate in the completion.
1364
1507
1365
-
The token count of your prompt plus `max_tokens` cannot exceed the model's context length. Most models have a context length of 2048 tokens (except `code-davinci-001`, which supports 4096).
1508
+
The token count of your prompt plus `max_tokens` cannot exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096).
1366
1509
temperature:
1367
1510
type: number
1368
1511
minimum: 0
@@ -1536,6 +1679,83 @@ components:
1536
1679
description: ID of the model to use for completion.
1537
1680
type: string
1538
1681
1682
+
CreateEditRequest:
1683
+
type: object
1684
+
properties:
1685
+
input:
1686
+
description:
1687
+
The input text to use as a starting point for the edit.
1688
+
type: string
1689
+
default: ""
1690
+
nullable: true
1691
+
example: "What day of the wek is it?"
1692
+
instruction:
1693
+
description:
1694
+
The instruction that tells the model how to edit the prompt.
1695
+
type: string
1696
+
example: "Fix the spelling mistakes."
1697
+
temperature:
1698
+
type: number
1699
+
minimum: 0
1700
+
maximum: 2
1701
+
default: 1
1702
+
example: 1
1703
+
nullable: true
1704
+
description: *completions_temperature_description
1705
+
top_p:
1706
+
type: number
1707
+
minimum: 0
1708
+
maximum: 1
1709
+
default: 1
1710
+
example: 1
1711
+
nullable: true
1712
+
description: *completions_top_p_description
1713
+
required:
1714
+
- instruction
1715
+
1716
+
CreateEditResponse:
1717
+
type: object
1718
+
properties:
1719
+
id:
1720
+
type: string
1721
+
object:
1722
+
type: string
1723
+
created:
1724
+
type: integer
1725
+
model:
1726
+
type: string
1727
+
choices:
1728
+
type: array
1729
+
items:
1730
+
type: object
1731
+
properties:
1732
+
text:
1733
+
type: string
1734
+
index:
1735
+
type: integer
1736
+
logprobs:
1737
+
type: object
1738
+
nullable: true
1739
+
properties:
1740
+
tokens:
1741
+
type: array
1742
+
items:
1743
+
type: string
1744
+
token_logprobs:
1745
+
type: array
1746
+
items:
1747
+
type: number
1748
+
top_logprobs:
1749
+
type: array
1750
+
items:
1751
+
type: object
1752
+
text_offset:
1753
+
type: array
1754
+
items:
1755
+
type: integer
1756
+
finish_reason:
1757
+
type: string
1758
+
1539
1759
CreateSearchRequest:
1540
1760
type: object
1541
1761
properties:
@@ -2027,6 +2247,16 @@ components:
2027
2247
example: [0.6, 1, 1.5, 2]
2028
2248
default: null
2029
2249
nullable: true
2250
+
suffix:
2251
+
description: |
2252
+
A string of up to 40 characters that will be added to your fine-tuned model name.
2253
+
2254
+
For example, a `suffix` of "custom-model-name" would produce a model name like `ada:ft-your-org:custom-model-name-2022-02-15-04-21-04`.
2255
+
type: string
2256
+
minLength: 1
2257
+
maxLength: 40
2258
+
default: null
2259
+
nullable: true
2030
2260
required:
2031
2261
- training_file
2032
2262
@@ -2201,6 +2431,10 @@ oaiMeta:
2201
2431
title: Completions
2202
2432
description: |
2203
2433
Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.
2434
+
- id: edits
2435
+
title: Edits
2436
+
description: |
2437
+
Given a prompt and an instruction, the model will return an edited version of the prompt.
0 commit comments