docs: fix chat payload and cURL
This commit is contained in:
Ho Duc Hieu
parent
9cf1701471
commit
2a6e5bc338
@ -1,31 +1,31 @@
|
||||
---
|
||||
openapi: 3.0.0
|
||||
info:
|
||||
title: API Reference
|
||||
description: >
|
||||
# Introduction
|
||||
|
||||
Jan API is compatible with the [OpenAI
|
||||
API](https://platform.openai.com/docs/api-reference).
|
||||
Jan API is compatible with the [OpenAI API](https://platform.openai.com/docs/api-reference).
|
||||
version: 0.1.8
|
||||
contact:
|
||||
name: Jan Discord
|
||||
url: "https://discord.gg/7EcEz7MrvA"
|
||||
url: https://discord.gg/7EcEz7MrvA
|
||||
license:
|
||||
name: AGPLv3
|
||||
url: "https://github.com/janhq/nitro/blob/main/LICENSE"
|
||||
url: https://github.com/janhq/nitro/blob/main/LICENSE
|
||||
servers:
|
||||
- url: "http://localhost:1337/v1/"
|
||||
- url: http://localhost:1337/v1/
|
||||
tags:
|
||||
- name: Models
|
||||
description: List and describe the various models available in the API.
|
||||
- name: Chat
|
||||
description: >
|
||||
Given a list of messages comprising a conversation, the model will return
|
||||
a response.
|
||||
Given a list of messages comprising a conversation, the model will
|
||||
return a response.
|
||||
- name: Messages
|
||||
description: >
|
||||
Messages capture a conversation's content. This can include the content
|
||||
from LLM responses and other metadata from [chat
|
||||
Messages capture a conversation's content. This can include the
|
||||
content from LLM responses and other metadata from [chat
|
||||
completions](/specs/chats).
|
||||
- name: Threads
|
||||
- name: Assistants
|
||||
@ -49,36 +49,39 @@ paths:
|
||||
summary: |
|
||||
Create chat completion
|
||||
description: >
|
||||
Creates a model response for the given chat conversation. <a href =
|
||||
"https://platform.openai.com/docs/api-reference/chat/create"> Equivalent
|
||||
to OpenAI's create chat completion. </a>
|
||||
Creates a model response for the given chat conversation. <a href
|
||||
= "https://platform.openai.com/docs/api-reference/chat/create">
|
||||
Equivalent to OpenAI's create chat completion. </a>
|
||||
requestBody:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/chat.yaml#/components/schemas/ChatCompletionRequest"
|
||||
$ref: specs/chat.yaml#/components/schemas/ChatCompletionRequest
|
||||
responses:
|
||||
"200":
|
||||
description: OK
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/chat.yaml#/components/schemas/ChatCompletionResponse"
|
||||
$ref: specs/chat.yaml#/components/schemas/ChatCompletionResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: >
|
||||
curl -X POST
|
||||
'http://localhost:3982/inferences/llamacpp/chat_completion' \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"llama_model_path": "/path/to/your/model.gguf",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "hello"
|
||||
},
|
||||
]
|
||||
}'
|
||||
source: |
|
||||
curl http://localhost:1337/v1/chat/completions \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"model": "tinyllama-1.1b",
|
||||
"messages": [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful assistant."
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Hello!"
|
||||
}
|
||||
]
|
||||
}'
|
||||
/models:
|
||||
get:
|
||||
operationId: listModels
|
||||
@ -86,17 +89,17 @@ paths:
|
||||
- Models
|
||||
summary: List models
|
||||
description: >
|
||||
Lists the currently available models, and provides basic information
|
||||
about each one such as the owner and availability. <a href =
|
||||
"https://platform.openai.com/docs/api-reference/models/list"> Equivalent
|
||||
to OpenAI's list model. </a>
|
||||
Lists the currently available models, and provides basic
|
||||
information about each one such as the owner and availability. <a href
|
||||
= "https://platform.openai.com/docs/api-reference/models/list">
|
||||
Equivalent to OpenAI's list model. </a>
|
||||
responses:
|
||||
"200":
|
||||
description: OK
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/models.yaml#/components/schemas/ListModelsResponse"
|
||||
$ref: specs/models.yaml#/components/schemas/ListModelsResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -114,7 +117,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/models.yaml#/components/schemas/DownloadModelResponse"
|
||||
$ref: specs/models.yaml#/components/schemas/DownloadModelResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -126,8 +129,8 @@ paths:
|
||||
- Models
|
||||
summary: Retrieve model
|
||||
description: >
|
||||
Get a model instance, providing basic information about the model such
|
||||
as the owner and permissioning. <a href =
|
||||
Get a model instance, providing basic information about the model
|
||||
such as the owner and permissioning. <a href =
|
||||
"https://platform.openai.com/docs/api-reference/models/retrieve">
|
||||
Equivalent to OpenAI's retrieve model. </a>
|
||||
parameters:
|
||||
@ -145,7 +148,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/models.yaml#/components/schemas/GetModelResponse"
|
||||
$ref: specs/models.yaml#/components/schemas/GetModelResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -174,7 +177,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/models.yaml#/components/schemas/DeleteModelResponse"
|
||||
$ref: specs/models.yaml#/components/schemas/DeleteModelResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -202,7 +205,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/models.yaml#/components/schemas/StartModelResponse"
|
||||
$ref: specs/models.yaml#/components/schemas/StartModelResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -229,7 +232,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/models.yaml#/components/schemas/StopModelResponse"
|
||||
$ref: specs/models.yaml#/components/schemas/StopModelResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -255,14 +258,14 @@ paths:
|
||||
type: array
|
||||
description: Initial set of messages for the thread.
|
||||
items:
|
||||
$ref: "specs/threads.yaml#/components/schemas/ThreadMessageObject"
|
||||
$ref: specs/threads.yaml#/components/schemas/ThreadMessageObject
|
||||
responses:
|
||||
"200":
|
||||
description: Thread created successfully
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/threads.yaml#/components/schemas/CreateThreadResponse"
|
||||
$ref: specs/threads.yaml#/components/schemas/CreateThreadResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -293,7 +296,7 @@ paths:
|
||||
schema:
|
||||
type: array
|
||||
items:
|
||||
$ref: "specs/threads.yaml#/components/schemas/ThreadObject"
|
||||
$ref: specs/threads.yaml#/components/schemas/ThreadObject
|
||||
example:
|
||||
- id: thread_abc123
|
||||
object: thread
|
||||
@ -340,7 +343,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/threads.yaml#/components/schemas/GetThreadResponse"
|
||||
$ref: specs/threads.yaml#/components/schemas/GetThreadResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -374,14 +377,14 @@ paths:
|
||||
type: array
|
||||
description: Set of messages to update in the thread.
|
||||
items:
|
||||
$ref: "specs/threads.yaml#/components/schemas/ThreadMessageObject"
|
||||
$ref: specs/threads.yaml#/components/schemas/ThreadMessageObject
|
||||
responses:
|
||||
"200":
|
||||
description: Thread modified successfully
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/threads.yaml#/components/schemas/ModifyThreadResponse"
|
||||
$ref: specs/threads.yaml#/components/schemas/ModifyThreadResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -421,7 +424,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/threads.yaml#/components/schemas/DeleteThreadResponse"
|
||||
$ref: specs/threads.yaml#/components/schemas/DeleteThreadResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -448,7 +451,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/threads.yaml#/components/schemas/GetThreadResponse"
|
||||
$ref: specs/threads.yaml#/components/schemas/GetThreadResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -484,7 +487,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/threads.yaml#/components/schemas/GetThreadResponse"
|
||||
$ref: specs/threads.yaml#/components/schemas/GetThreadResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -513,7 +516,7 @@ paths:
|
||||
created_at: 1698984975
|
||||
name: Math Tutor
|
||||
description: null
|
||||
avatar: "https://pic.png"
|
||||
avatar: https://pic.png
|
||||
models:
|
||||
- model_id: model_0
|
||||
instructions: Be concise
|
||||
@ -527,7 +530,7 @@ paths:
|
||||
created_at: 1698984975
|
||||
name: Physics Tutor
|
||||
description: null
|
||||
avatar: "https://pic.png"
|
||||
avatar: https://pic.png
|
||||
models:
|
||||
- model_id: model_1
|
||||
instructions: Be concise!
|
||||
@ -559,8 +562,7 @@ paths:
|
||||
properties:
|
||||
models:
|
||||
type: array
|
||||
description: >-
|
||||
List of models associated with the assistant. Jan-specific
|
||||
description: List of models associated with the assistant. Jan-specific
|
||||
property.
|
||||
items:
|
||||
type: object
|
||||
@ -574,8 +576,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: >-
|
||||
specs/assistants.yaml#/components/schemas/CreateAssistantResponse
|
||||
$ref: specs/assistants.yaml#/components/schemas/CreateAssistantResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -613,8 +614,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: >-
|
||||
specs/assistants.yaml#/components/schemas/RetrieveAssistantResponse
|
||||
$ref: specs/assistants.yaml#/components/schemas/RetrieveAssistantResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -647,8 +647,7 @@ paths:
|
||||
properties:
|
||||
models:
|
||||
type: array
|
||||
description: >-
|
||||
List of models associated with the assistant. Jan-specific
|
||||
description: List of models associated with the assistant. Jan-specific
|
||||
property.
|
||||
items:
|
||||
type: object
|
||||
@ -670,8 +669,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: >-
|
||||
specs/assistants.yaml#/components/schemas/ModifyAssistantResponse
|
||||
$ref: specs/assistants.yaml#/components/schemas/ModifyAssistantResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -710,8 +708,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: >-
|
||||
specs/assistants.yaml#/components/schemas/DeleteAssistantResponse
|
||||
$ref: specs/assistants.yaml#/components/schemas/DeleteAssistantResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -741,7 +738,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/messages.yaml#/components/schemas/ListMessagesResponse"
|
||||
$ref: specs/messages.yaml#/components/schemas/ListMessagesResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -794,7 +791,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/messages.yaml#/components/schemas/CreateMessageResponse"
|
||||
$ref: specs/messages.yaml#/components/schemas/CreateMessageResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
@ -838,12 +835,12 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/messages.yaml#/components/schemas/GetMessageResponse"
|
||||
$ref: specs/messages.yaml#/components/schemas/GetMessageResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: >
|
||||
curl
|
||||
http://localhost:1337/v1/threads/{thread_id}/messages/{message_id} \
|
||||
curl http://localhost:1337/v1/threads/{thread_id}/messages/{message_id}
|
||||
\
|
||||
-H "Content-Type: application/json"
|
||||
"/threads/{thread_id}/messages/{message_id}/files":
|
||||
get:
|
||||
@ -879,8 +876,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: >-
|
||||
specs/messages.yaml#/components/schemas/ListMessageFilesResponse
|
||||
$ref: specs/messages.yaml#/components/schemas/ListMessageFilesResponse
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: >
|
||||
@ -895,8 +891,8 @@ paths:
|
||||
- Messages
|
||||
summary: Retrieve message file
|
||||
description: >
|
||||
Retrieves a file associated with a specific message in a thread. <a
|
||||
href =
|
||||
Retrieves a file associated with a specific message in a
|
||||
thread. <a href =
|
||||
"https://platform.openai.com/docs/api-reference/messages/getMessageFile">
|
||||
Equivalent to OpenAI's retrieve message file. </a>
|
||||
parameters:
|
||||
@ -930,7 +926,7 @@ paths:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/messages.yaml#/components/schemas/MessageFileObject"
|
||||
$ref: specs/messages.yaml#/components/schemas/MessageFileObject
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: >
|
||||
@ -953,14 +949,15 @@ x-webhooks:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/models.yaml#/components/schemas/ModelObject"
|
||||
$ref: specs/models.yaml#/components/schemas/ModelObject
|
||||
AssistantObject:
|
||||
post:
|
||||
summary: The assistant object
|
||||
description: >
|
||||
Build assistants that can call models and use tools to perform tasks.
|
||||
<a href = "https://platform.openai.com/docs/api-reference/assistants">
|
||||
Equivalent to OpenAI's assistants object. </a>
|
||||
Build assistants that can call models and use tools to perform
|
||||
tasks. <a href =
|
||||
"https://platform.openai.com/docs/api-reference/assistants"> Equivalent
|
||||
to OpenAI's assistants object. </a>
|
||||
operationId: AssistantObjects
|
||||
tags:
|
||||
- Assistants
|
||||
@ -968,7 +965,7 @@ x-webhooks:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/assistants.yaml#/components/schemas/AssistantObject"
|
||||
$ref: specs/assistants.yaml#/components/schemas/AssistantObject
|
||||
MessageObject:
|
||||
post:
|
||||
summary: The message object
|
||||
@ -983,12 +980,11 @@ x-webhooks:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/messages.yaml#/components/schemas/MessageObject"
|
||||
$ref: specs/messages.yaml#/components/schemas/MessageObject
|
||||
ThreadObject:
|
||||
post:
|
||||
summary: The thread object
|
||||
description: >-
|
||||
Represents a thread that contains messages. <a href =
|
||||
description: Represents a thread that contains messages. <a href =
|
||||
"https://platform.openai.com/docs/api-reference/threads/object">
|
||||
Equivalent to OpenAI's thread object. </a>
|
||||
operationId: ThreadObject
|
||||
@ -998,4 +994,4 @@ x-webhooks:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: "specs/threads.yaml#/components/schemas/ThreadObject"
|
||||
$ref: specs/threads.yaml#/components/schemas/ThreadObject
|
||||
@ -1,3 +1,4 @@
|
||||
---
|
||||
components:
|
||||
schemas:
|
||||
AssistantObject:
|
||||
@ -9,7 +10,7 @@ components:
|
||||
example: asst_abc123
|
||||
object:
|
||||
type: string
|
||||
description: "Type of the object, indicating it's an assistant."
|
||||
description: Type of the object, indicating it's an assistant.
|
||||
default: assistant
|
||||
version:
|
||||
type: integer
|
||||
@ -31,7 +32,7 @@ components:
|
||||
avatar:
|
||||
type: string
|
||||
description: URL of the assistant's avatar. Jan-specific property.
|
||||
example: "https://pic.png"
|
||||
example: https://pic.png
|
||||
models:
|
||||
type: array
|
||||
description: List of models associated with the assistant. Jan-specific property.
|
||||
@ -70,7 +71,7 @@ components:
|
||||
example: asst_abc123
|
||||
object:
|
||||
type: string
|
||||
description: "Type of the object, indicating it's an assistant."
|
||||
description: Type of the object, indicating it's an assistant.
|
||||
default: assistant
|
||||
version:
|
||||
type: integer
|
||||
@ -92,7 +93,7 @@ components:
|
||||
avatar:
|
||||
type: string
|
||||
description: URL of the assistant's avatar. Jan-specific property.
|
||||
example: "https://pic.png"
|
||||
example: https://pic.png
|
||||
models:
|
||||
type: array
|
||||
description: List of models associated with the assistant. Jan-specific property.
|
||||
@ -130,7 +131,7 @@ components:
|
||||
example: asst_abc123
|
||||
object:
|
||||
type: string
|
||||
description: "Type of the object, indicating it's an assistant."
|
||||
description: Type of the object, indicating it's an assistant.
|
||||
default: assistant
|
||||
version:
|
||||
type: integer
|
||||
@ -152,7 +153,7 @@ components:
|
||||
avatar:
|
||||
type: string
|
||||
description: URL of the assistant's avatar. Jan-specific property.
|
||||
example: "https://pic.png"
|
||||
example: https://pic.png
|
||||
models:
|
||||
type: array
|
||||
description: List of models associated with the assistant. Jan-specific property.
|
||||
@ -190,7 +191,7 @@ components:
|
||||
example: asst_abc123
|
||||
object:
|
||||
type: string
|
||||
description: "Type of the object, indicating it's an assistant."
|
||||
description: Type of the object, indicating it's an assistant.
|
||||
default: assistant
|
||||
version:
|
||||
type: integer
|
||||
@ -212,7 +213,7 @@ components:
|
||||
avatar:
|
||||
type: string
|
||||
description: URL of the assistant's avatar. Jan-specific property.
|
||||
example: "https://pic.png"
|
||||
example: https://pic.png
|
||||
models:
|
||||
type: array
|
||||
description: List of models associated with the assistant. Jan-specific property.
|
||||
@ -250,7 +251,7 @@ components:
|
||||
example: asst_abc123
|
||||
object:
|
||||
type: string
|
||||
description: "Type of the object, indicating it's an assistant."
|
||||
description: Type of the object, indicating it's an assistant.
|
||||
default: assistant
|
||||
version:
|
||||
type: integer
|
||||
@ -272,7 +273,7 @@ components:
|
||||
avatar:
|
||||
type: string
|
||||
description: URL of the assistant's avatar. Jan-specific property.
|
||||
example: "https://pic.png"
|
||||
example: https://pic.png
|
||||
models:
|
||||
type: array
|
||||
description: List of models associated with the assistant. Jan-specific property.
|
||||
@ -310,7 +311,7 @@ components:
|
||||
example: asst_abc123
|
||||
object:
|
||||
type: string
|
||||
description: "Type of the object, indicating the assistant has been deleted."
|
||||
description: Type of the object, indicating the assistant has been deleted.
|
||||
example: assistant.deleted
|
||||
deleted:
|
||||
type: boolean
|
||||
|
||||
@ -1,3 +1,4 @@
|
||||
---
|
||||
components:
|
||||
schemas:
|
||||
ChatObject:
|
||||
@ -15,8 +16,7 @@ components:
|
||||
stream:
|
||||
type: boolean
|
||||
default: true
|
||||
description: >-
|
||||
Enables continuous output generation, allowing for streaming of
|
||||
description: Enables continuous output generation, allowing for streaming of
|
||||
model responses.
|
||||
model:
|
||||
type: string
|
||||
@ -25,27 +25,23 @@ components:
|
||||
max_tokens:
|
||||
type: number
|
||||
default: 2048
|
||||
description: >-
|
||||
The maximum number of tokens the model will generate in a single
|
||||
description: The maximum number of tokens the model will generate in a single
|
||||
response.
|
||||
stop:
|
||||
type: arrays
|
||||
example:
|
||||
- hello
|
||||
description: >-
|
||||
Defines specific tokens or phrases at which the model will stop
|
||||
description: Defines specific tokens or phrases at which the model will stop
|
||||
generating further output/
|
||||
frequency_penalty:
|
||||
type: number
|
||||
default: 0
|
||||
description: >-
|
||||
Adjusts the likelihood of the model repeating words or phrases in
|
||||
description: Adjusts the likelihood of the model repeating words or phrases in
|
||||
its output.
|
||||
presence_penalty:
|
||||
type: number
|
||||
default: 0
|
||||
description: >-
|
||||
Influences the generation of new and varied concepts in the model's
|
||||
description: Influences the generation of new and varied concepts in the model's
|
||||
output.
|
||||
temperature:
|
||||
type: number
|
||||
@ -71,13 +67,13 @@ components:
|
||||
description: |
|
||||
Contains input data or prompts for the model to process.
|
||||
example:
|
||||
- content: "Hello there :wave:"
|
||||
role: assistant
|
||||
- content: Can you write a long story
|
||||
- content: You are a helpful assistant.
|
||||
role: system
|
||||
- content: Hello!
|
||||
role: user
|
||||
model:
|
||||
type: string
|
||||
example: model-zephyr-7B
|
||||
example: tinyllama-1.1b
|
||||
description: |
|
||||
Specifies the model being used for inference or processing tasks.
|
||||
stream:
|
||||
@ -139,7 +135,7 @@ components:
|
||||
type: string
|
||||
nullable: true
|
||||
example: null
|
||||
description: "Reason for finishing the response, if applicable"
|
||||
description: Reason for finishing the response, if applicable
|
||||
index:
|
||||
type: integer
|
||||
example: 0
|
||||
|
||||
@ -1,3 +1,4 @@
|
||||
---
|
||||
components:
|
||||
schemas:
|
||||
ListModelsResponse:
|
||||
@ -27,8 +28,7 @@ components:
|
||||
description: The version number of the model.
|
||||
id:
|
||||
type: string
|
||||
description: >-
|
||||
Unique identifier used in chat-completions model_name, matches
|
||||
description: Unique identifier used in chat-completions model_name, matches
|
||||
folder name.
|
||||
example: zephyr-7b
|
||||
name:
|
||||
@ -57,14 +57,13 @@ components:
|
||||
description: Current state of the model.
|
||||
format:
|
||||
type: string
|
||||
description: "State format of the model, distinct from the engine."
|
||||
description: State format of the model, distinct from the engine.
|
||||
example: ggufv3
|
||||
source_url:
|
||||
type: string
|
||||
format: uri
|
||||
description: URL to the source of the model.
|
||||
example: >-
|
||||
https://huggingface.co/TheBloke/zephyr-7B-beta-GGUF/blob/main/zephyr-7b-beta.Q4_K_M.gguf
|
||||
example: https://huggingface.co/TheBloke/zephyr-7B-beta-GGUF/blob/main/zephyr-7b-beta.Q4_K_M.gguf
|
||||
settings:
|
||||
type: object
|
||||
properties:
|
||||
@ -152,7 +151,7 @@ components:
|
||||
example: zephyr-7b
|
||||
object:
|
||||
type: string
|
||||
description: "Type of the object, indicating it's a model."
|
||||
description: Type of the object, indicating it's a model.
|
||||
default: model
|
||||
created:
|
||||
type: integer
|
||||
@ -174,8 +173,7 @@ components:
|
||||
type: string
|
||||
format: uri
|
||||
description: URL to the source of the model.
|
||||
example: >-
|
||||
https://huggingface.co/TheBloke/zephyr-7B-beta-GGUF/blob/main/zephyr-7b-beta.Q4_K_M.gguf
|
||||
example: https://huggingface.co/TheBloke/zephyr-7B-beta-GGUF/blob/main/zephyr-7b-beta.Q4_K_M.gguf
|
||||
engine_parameters:
|
||||
type: object
|
||||
properties:
|
||||
@ -198,8 +196,7 @@ components:
|
||||
default: "ASSISTANT: "
|
||||
ngl:
|
||||
type: integer
|
||||
description: >-
|
||||
Number of neural network layers loaded onto the GPU for
|
||||
description: Number of neural network layers loaded onto the GPU for
|
||||
acceleration.
|
||||
minimum: 0
|
||||
maximum: 100
|
||||
@ -207,18 +204,16 @@ components:
|
||||
example: 100
|
||||
ctx_len:
|
||||
type: integer
|
||||
description: >-
|
||||
Context length for model operations, varies based on the
|
||||
specific model.
|
||||
description: Context length for model operations, varies based on the specific
|
||||
model.
|
||||
minimum: 128
|
||||
maximum: 4096
|
||||
default: 2048
|
||||
example: 2048
|
||||
n_parallel:
|
||||
type: integer
|
||||
description: >-
|
||||
Number of parallel operations, relevant when continuous batching
|
||||
is enabled.
|
||||
description: Number of parallel operations, relevant when continuous batching is
|
||||
enabled.
|
||||
minimum: 1
|
||||
maximum: 10
|
||||
default: 1
|
||||
@ -269,8 +264,7 @@ components:
|
||||
example: 4
|
||||
temperature:
|
||||
type: number
|
||||
description: >-
|
||||
Controls randomness in model's responses. Higher values lead to
|
||||
description: Controls randomness in model's responses. Higher values lead to
|
||||
more random responses.
|
||||
minimum: 0
|
||||
maximum: 2
|
||||
@ -278,8 +272,7 @@ components:
|
||||
example: 0.7
|
||||
token_limit:
|
||||
type: integer
|
||||
description: >-
|
||||
Maximum number of tokens the model can generate in a single
|
||||
description: Maximum number of tokens the model can generate in a single
|
||||
response.
|
||||
minimum: 1
|
||||
maximum: 4096
|
||||
@ -287,18 +280,16 @@ components:
|
||||
example: 2048
|
||||
top_k:
|
||||
type: integer
|
||||
description: >-
|
||||
Limits the model to consider only the top k most likely next
|
||||
tokens at each step.
|
||||
description: Limits the model to consider only the top k most likely next tokens
|
||||
at each step.
|
||||
minimum: 0
|
||||
maximum: 100
|
||||
default: 0
|
||||
example: 0
|
||||
top_p:
|
||||
type: number
|
||||
description: >-
|
||||
Nucleus sampling parameter. The model considers the smallest set
|
||||
of tokens whose cumulative probability exceeds the top_p value.
|
||||
description: Nucleus sampling parameter. The model considers the smallest set of
|
||||
tokens whose cumulative probability exceeds the top_p value.
|
||||
minimum: 0
|
||||
maximum: 1
|
||||
default: 1
|
||||
|
||||
@ -1,3 +1,4 @@
|
||||
---
|
||||
components:
|
||||
schemas:
|
||||
ThreadObject:
|
||||
@ -39,13 +40,13 @@ components:
|
||||
settings:
|
||||
type: object
|
||||
description: >
|
||||
Defaults to and overrides assistant.json's "settings" (and
|
||||
if none, then model.json "settings")
|
||||
Defaults to and overrides assistant.json's "settings" (and if none,
|
||||
then model.json "settings")
|
||||
parameters:
|
||||
type: object
|
||||
description: >
|
||||
Defaults to and overrides assistant.json's "parameters"
|
||||
(and if none, then model.json "parameters")
|
||||
Defaults to and overrides assistant.json's "parameters" (and if
|
||||
none, then model.json "parameters")
|
||||
created:
|
||||
type: integer
|
||||
format: int64
|
||||
@ -141,7 +142,7 @@ components:
|
||||
example: thread_abc123
|
||||
object:
|
||||
type: string
|
||||
description: "Type of the object, indicating it's a thread."
|
||||
description: Type of the object, indicating it's a thread.
|
||||
example: thread
|
||||
created_at:
|
||||
type: integer
|
||||
@ -161,7 +162,7 @@ components:
|
||||
example: thread_abc123
|
||||
object:
|
||||
type: string
|
||||
description: "Type of the object, indicating the thread has been deleted."
|
||||
description: Type of the object, indicating the thread has been deleted.
|
||||
example: thread.deleted
|
||||
deleted:
|
||||
type: boolean
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user