mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-14 06:12:36 +00:00
feat: Add max_output_tokens to Response API
Responses and Completions have a max_output_tokens field. It is currently missing from the create and response object in Responses API. This PR fixes it. fixes: #3562 Signed-off-by: Abhishek Bongale <abhishekbongale@outlook.com>
This commit is contained in:
parent
92219fd8fb
commit
bb58da22a1
14 changed files with 127 additions and 20 deletions
10
docs/static/stainless-llama-stack-spec.yaml
vendored
10
docs/static/stainless-llama-stack-spec.yaml
vendored
|
|
@ -7105,6 +7105,10 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
(Optional) Truncation strategy applied to the response
|
||||
max_output_tokens:
|
||||
type: integer
|
||||
description: >-
|
||||
(Optional) Upper bound for response tokens generation
|
||||
input:
|
||||
type: array
|
||||
items:
|
||||
|
|
@ -7459,6 +7463,8 @@ components:
|
|||
(Optional) Additional fields to include in the response.
|
||||
max_infer_iters:
|
||||
type: integer
|
||||
max_output_tokens:
|
||||
type: integer
|
||||
additionalProperties: false
|
||||
required:
|
||||
- input
|
||||
|
|
@ -7522,6 +7528,10 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
(Optional) Truncation strategy applied to the response
|
||||
max_output_tokens:
|
||||
type: integer
|
||||
description: >-
|
||||
(Optional) Upper bound for response tokens generation
|
||||
additionalProperties: false
|
||||
required:
|
||||
- created_at
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue