mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-05 12:21:52 +00:00
Test fixes in openai_compat
This commit is contained in:
parent
e56a3f266c
commit
d60514b57b
7 changed files with 221 additions and 7 deletions
83
docs/_static/llama-stack-spec.html
vendored
83
docs/_static/llama-stack-spec.html
vendored
|
@ -6372,6 +6372,9 @@
|
|||
"$ref": "#/components/schemas/TokenLogProbs"
|
||||
},
|
||||
"description": "Optional log probabilities for generated tokens"
|
||||
},
|
||||
"usage": {
|
||||
"$ref": "#/components/schemas/UsageInfo"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
|
@ -6430,6 +6433,31 @@
|
|||
"title": "TokenLogProbs",
|
||||
"description": "Log probabilities for generated tokens."
|
||||
},
|
||||
"UsageInfo": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"completion_tokens": {
|
||||
"type": "integer",
|
||||
"description": "Number of tokens generated"
|
||||
},
|
||||
"prompt_tokens": {
|
||||
"type": "integer",
|
||||
"description": "Number of tokens in the prompt"
|
||||
},
|
||||
"total_tokens": {
|
||||
"type": "integer",
|
||||
"description": "Total number of tokens processed"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"completion_tokens",
|
||||
"prompt_tokens",
|
||||
"total_tokens"
|
||||
],
|
||||
"title": "UsageInfo",
|
||||
"description": "Usage information for a model."
|
||||
},
|
||||
"BatchCompletionRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
@ -10939,6 +10967,31 @@
|
|||
"title": "OpenAIChatCompletionToolCallFunction",
|
||||
"description": "Function call details for OpenAI-compatible tool calls."
|
||||
},
|
||||
"OpenAIChatCompletionUsage": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"prompt_tokens": {
|
||||
"type": "integer",
|
||||
"description": "The number of tokens in the prompt"
|
||||
},
|
||||
"completion_tokens": {
|
||||
"type": "integer",
|
||||
"description": "The number of tokens in the completion"
|
||||
},
|
||||
"total_tokens": {
|
||||
"type": "integer",
|
||||
"description": "The total number of tokens used"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"prompt_tokens",
|
||||
"completion_tokens",
|
||||
"total_tokens"
|
||||
],
|
||||
"title": "OpenAIChatCompletionUsage",
|
||||
"description": "Usage information for an OpenAI-compatible chat completion response."
|
||||
},
|
||||
"OpenAIChoice": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
@ -11276,6 +11329,13 @@
|
|||
"OpenAICompletionWithInputMessages": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"metrics": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/MetricInResponse"
|
||||
},
|
||||
"description": "(Optional) List of metrics associated with the API response"
|
||||
},
|
||||
"id": {
|
||||
"type": "string",
|
||||
"description": "The ID of the chat completion"
|
||||
|
@ -11301,6 +11361,9 @@
|
|||
"type": "string",
|
||||
"description": "The model that was used to generate the chat completion"
|
||||
},
|
||||
"usage": {
|
||||
"$ref": "#/components/schemas/OpenAIChatCompletionUsage"
|
||||
},
|
||||
"input_messages": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
|
@ -13062,6 +13125,13 @@
|
|||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"metrics": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/MetricInResponse"
|
||||
},
|
||||
"description": "(Optional) List of metrics associated with the API response"
|
||||
},
|
||||
"id": {
|
||||
"type": "string",
|
||||
"description": "The ID of the chat completion"
|
||||
|
@ -13087,6 +13157,9 @@
|
|||
"type": "string",
|
||||
"description": "The model that was used to generate the chat completion"
|
||||
},
|
||||
"usage": {
|
||||
"$ref": "#/components/schemas/OpenAIChatCompletionUsage"
|
||||
},
|
||||
"input_messages": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
|
@ -14478,6 +14551,13 @@
|
|||
"OpenAIChatCompletion": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"metrics": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/MetricInResponse"
|
||||
},
|
||||
"description": "(Optional) List of metrics associated with the API response"
|
||||
},
|
||||
"id": {
|
||||
"type": "string",
|
||||
"description": "The ID of the chat completion"
|
||||
|
@ -14502,6 +14582,9 @@
|
|||
"model": {
|
||||
"type": "string",
|
||||
"description": "The model that was used to generate the chat completion"
|
||||
},
|
||||
"usage": {
|
||||
"$ref": "#/components/schemas/OpenAIChatCompletionUsage"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
|
|
65
docs/_static/llama-stack-spec.yaml
vendored
65
docs/_static/llama-stack-spec.yaml
vendored
|
@ -4548,6 +4548,8 @@ components:
|
|||
$ref: '#/components/schemas/TokenLogProbs'
|
||||
description: >-
|
||||
Optional log probabilities for generated tokens
|
||||
usage:
|
||||
$ref: '#/components/schemas/UsageInfo'
|
||||
additionalProperties: false
|
||||
required:
|
||||
- completion_message
|
||||
|
@ -4589,6 +4591,25 @@ components:
|
|||
- logprobs_by_token
|
||||
title: TokenLogProbs
|
||||
description: Log probabilities for generated tokens.
|
||||
UsageInfo:
|
||||
type: object
|
||||
properties:
|
||||
completion_tokens:
|
||||
type: integer
|
||||
description: Number of tokens generated
|
||||
prompt_tokens:
|
||||
type: integer
|
||||
description: Number of tokens in the prompt
|
||||
total_tokens:
|
||||
type: integer
|
||||
description: Total number of tokens processed
|
||||
additionalProperties: false
|
||||
required:
|
||||
- completion_tokens
|
||||
- prompt_tokens
|
||||
- total_tokens
|
||||
title: UsageInfo
|
||||
description: Usage information for a model.
|
||||
BatchCompletionRequest:
|
||||
type: object
|
||||
properties:
|
||||
|
@ -8103,6 +8124,26 @@ components:
|
|||
title: OpenAIChatCompletionToolCallFunction
|
||||
description: >-
|
||||
Function call details for OpenAI-compatible tool calls.
|
||||
OpenAIChatCompletionUsage:
|
||||
type: object
|
||||
properties:
|
||||
prompt_tokens:
|
||||
type: integer
|
||||
description: The number of tokens in the prompt
|
||||
completion_tokens:
|
||||
type: integer
|
||||
description: The number of tokens in the completion
|
||||
total_tokens:
|
||||
type: integer
|
||||
description: The total number of tokens used
|
||||
additionalProperties: false
|
||||
required:
|
||||
- prompt_tokens
|
||||
- completion_tokens
|
||||
- total_tokens
|
||||
title: OpenAIChatCompletionUsage
|
||||
description: >-
|
||||
Usage information for an OpenAI-compatible chat completion response.
|
||||
OpenAIChoice:
|
||||
type: object
|
||||
properties:
|
||||
|
@ -8365,6 +8406,12 @@ components:
|
|||
OpenAICompletionWithInputMessages:
|
||||
type: object
|
||||
properties:
|
||||
metrics:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/MetricInResponse'
|
||||
description: >-
|
||||
(Optional) List of metrics associated with the API response
|
||||
id:
|
||||
type: string
|
||||
description: The ID of the chat completion
|
||||
|
@ -8387,6 +8434,8 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
The model that was used to generate the chat completion
|
||||
usage:
|
||||
$ref: '#/components/schemas/OpenAIChatCompletionUsage'
|
||||
input_messages:
|
||||
type: array
|
||||
items:
|
||||
|
@ -9682,6 +9731,12 @@ components:
|
|||
items:
|
||||
type: object
|
||||
properties:
|
||||
metrics:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/MetricInResponse'
|
||||
description: >-
|
||||
(Optional) List of metrics associated with the API response
|
||||
id:
|
||||
type: string
|
||||
description: The ID of the chat completion
|
||||
|
@ -9704,6 +9759,8 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
The model that was used to generate the chat completion
|
||||
usage:
|
||||
$ref: '#/components/schemas/OpenAIChatCompletionUsage'
|
||||
input_messages:
|
||||
type: array
|
||||
items:
|
||||
|
@ -10719,6 +10776,12 @@ components:
|
|||
OpenAIChatCompletion:
|
||||
type: object
|
||||
properties:
|
||||
metrics:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/MetricInResponse'
|
||||
description: >-
|
||||
(Optional) List of metrics associated with the API response
|
||||
id:
|
||||
type: string
|
||||
description: The ID of the chat completion
|
||||
|
@ -10741,6 +10804,8 @@ components:
|
|||
type: string
|
||||
description: >-
|
||||
The model that was used to generate the chat completion
|
||||
usage:
|
||||
$ref: '#/components/schemas/OpenAIChatCompletionUsage'
|
||||
additionalProperties: false
|
||||
required:
|
||||
- id
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue