docs: update API Reference page
This commit is contained in:
hieu-jan
parent
fe1baed116
commit
0afdee4a98
@ -67,21 +67,32 @@ paths:
|
|||||||
x-codeSamples:
|
x-codeSamples:
|
||||||
- lang: cURL
|
- lang: cURL
|
||||||
source: |
|
source: |
|
||||||
curl http://localhost:1337/v1/chat/completions \
|
curl -X 'POST' \
|
||||||
-H "Content-Type: application/json" \
|
'http://127.0.0.1:1337/v1/chat/completions' \
|
||||||
|
-H 'accept: application/json' \
|
||||||
|
-H 'Content-Type: application/json' \
|
||||||
-d '{
|
-d '{
|
||||||
"model": "tinyllama-1.1b",
|
"messages": [
|
||||||
"messages": [
|
{
|
||||||
{
|
"content": "You are a helpful assistant.",
|
||||||
"role": "system",
|
"role": "system"
|
||||||
"content": "You are a helpful assistant."
|
},
|
||||||
},
|
{
|
||||||
{
|
"content": "Hello!",
|
||||||
"role": "user",
|
"role": "user"
|
||||||
"content": "Hello!"
|
}
|
||||||
}
|
],
|
||||||
]
|
"model": "tinyllama-1.1b",
|
||||||
}'
|
"stream": true,
|
||||||
|
"max_tokens": 2048,
|
||||||
|
"stop": [
|
||||||
|
"hello"
|
||||||
|
],
|
||||||
|
"frequency_penalty": 0,
|
||||||
|
"presence_penalty": 0,
|
||||||
|
"temperature": 0.7,
|
||||||
|
"top_p": 0.95
|
||||||
|
}'
|
||||||
/models:
|
/models:
|
||||||
get:
|
get:
|
||||||
operationId: listModels
|
operationId: listModels
|
||||||
@ -103,7 +114,9 @@ paths:
|
|||||||
x-codeSamples:
|
x-codeSamples:
|
||||||
- lang: cURL
|
- lang: cURL
|
||||||
source: |
|
source: |
|
||||||
curl http://localhost:1337/v1/models
|
curl -X 'GET' \
|
||||||
|
'http://127.0.0.1:1337/v1/models' \
|
||||||
|
-H 'accept: application/json'
|
||||||
"/models/download/{model_id}":
|
"/models/download/{model_id}":
|
||||||
get:
|
get:
|
||||||
operationId: downloadModel
|
operationId: downloadModel
|
||||||
@ -131,7 +144,9 @@ paths:
|
|||||||
x-codeSamples:
|
x-codeSamples:
|
||||||
- lang: cURL
|
- lang: cURL
|
||||||
source: |
|
source: |
|
||||||
curl -X POST http://localhost:1337/v1/models/download/{model_id}
|
curl -X 'GET' \
|
||||||
|
'http://127.0.0.1:1337/v1/models/download/{model_id}' \
|
||||||
|
-H 'accept: application/json'
|
||||||
"/models/{model_id}":
|
"/models/{model_id}":
|
||||||
get:
|
get:
|
||||||
operationId: retrieveModel
|
operationId: retrieveModel
|
||||||
@ -162,7 +177,9 @@ paths:
|
|||||||
x-codeSamples:
|
x-codeSamples:
|
||||||
- lang: cURL
|
- lang: cURL
|
||||||
source: |
|
source: |
|
||||||
curl http://localhost:1337/v1/models/{model_id}
|
curl -X 'GET' \
|
||||||
|
'http://127.0.0.1:1337/v1/models/{model_id}' \
|
||||||
|
-H 'accept: application/json'
|
||||||
delete:
|
delete:
|
||||||
operationId: deleteModel
|
operationId: deleteModel
|
||||||
tags:
|
tags:
|
||||||
@ -191,7 +208,9 @@ paths:
|
|||||||
x-codeSamples:
|
x-codeSamples:
|
||||||
- lang: cURL
|
- lang: cURL
|
||||||
source: |
|
source: |
|
||||||
curl -X DELETE http://localhost:1337/v1/models/{model_id}
|
curl -X 'DELETE' \
|
||||||
|
'http://127.0.0.1:1337/v1/models/{model_id}' \
|
||||||
|
-H 'accept: application/json'
|
||||||
/threads:
|
/threads:
|
||||||
post:
|
post:
|
||||||
operationId: createThread
|
operationId: createThread
|
||||||
|
|||||||
@ -18,106 +18,77 @@ components:
|
|||||||
Model:
|
Model:
|
||||||
type: object
|
type: object
|
||||||
properties:
|
properties:
|
||||||
type:
|
|
||||||
type: string
|
|
||||||
default: model
|
|
||||||
description: The type of the object.
|
|
||||||
version:
|
|
||||||
type: string
|
|
||||||
default: "1"
|
|
||||||
description: The version number of the model.
|
|
||||||
id:
|
|
||||||
type: string
|
|
||||||
description: Unique identifier used in chat-completions model_name, matches
|
|
||||||
folder name.
|
|
||||||
example: zephyr-7b
|
|
||||||
name:
|
|
||||||
type: string
|
|
||||||
description: Name of the model.
|
|
||||||
example: Zephyr 7B
|
|
||||||
owned_by:
|
|
||||||
type: string
|
|
||||||
description: Compatibility field for OpenAI.
|
|
||||||
default: ""
|
|
||||||
created:
|
|
||||||
type: integer
|
|
||||||
format: int64
|
|
||||||
description: Unix timestamp representing the creation time.
|
|
||||||
description:
|
|
||||||
type: string
|
|
||||||
description: Description of the model.
|
|
||||||
state:
|
|
||||||
type: string
|
|
||||||
enum:
|
|
||||||
- null
|
|
||||||
- downloading
|
|
||||||
- ready
|
|
||||||
- starting
|
|
||||||
- stopping
|
|
||||||
description: Current state of the model.
|
|
||||||
format:
|
|
||||||
type: string
|
|
||||||
description: State format of the model, distinct from the engine.
|
|
||||||
example: ggufv3
|
|
||||||
source_url:
|
source_url:
|
||||||
type: string
|
type: string
|
||||||
format: uri
|
format: uri
|
||||||
description: URL to the source of the model.
|
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/janhq/trinity-v1.2-GGUF/resolve/main/trinity-v1.2.Q4_K_M.gguf
|
||||||
|
id:
|
||||||
|
type: string
|
||||||
|
description:
|
||||||
|
Unique identifier used in chat-completions model_name, matches
|
||||||
|
folder name.
|
||||||
|
example: trinity-v1.2-7b
|
||||||
|
object:
|
||||||
|
type: string
|
||||||
|
example: model
|
||||||
|
name:
|
||||||
|
type: string
|
||||||
|
description: Name of the model.
|
||||||
|
example: Trinity-v1.2 7B Q4
|
||||||
|
version:
|
||||||
|
type: string
|
||||||
|
default: "1.0"
|
||||||
|
description: The version number of the model.
|
||||||
|
description:
|
||||||
|
type: string
|
||||||
|
description: Description of the model.
|
||||||
|
example: Trinity is an experimental model merge using the Slerp method. Recommended for daily assistance purposes.
|
||||||
|
format:
|
||||||
|
type: string
|
||||||
|
description: State format of the model, distinct from the engine.
|
||||||
|
example: gguf
|
||||||
settings:
|
settings:
|
||||||
type: object
|
type: object
|
||||||
properties:
|
properties:
|
||||||
ctx_len:
|
ctx_len:
|
||||||
type: string
|
type: integer
|
||||||
description: Context length.
|
description: Context length.
|
||||||
example: "2048"
|
example: 4096
|
||||||
ngl:
|
prompt_template:
|
||||||
type: string
|
type: string
|
||||||
description: Number of layers.
|
example: "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
|
||||||
example: "100"
|
|
||||||
embedding:
|
|
||||||
type: string
|
|
||||||
description: Indicates if embedding is enabled.
|
|
||||||
example: "true"
|
|
||||||
n_parallel:
|
|
||||||
type: string
|
|
||||||
description: Number of parallel processes.
|
|
||||||
example: "4"
|
|
||||||
additionalProperties: false
|
additionalProperties: false
|
||||||
parameters:
|
parameters:
|
||||||
type: object
|
type: object
|
||||||
properties:
|
properties:
|
||||||
temperature:
|
temperature:
|
||||||
type: string
|
example: 0.7
|
||||||
description: Temperature setting for the model.
|
|
||||||
example: "0.7"
|
|
||||||
token_limit:
|
|
||||||
type: string
|
|
||||||
description: Token limit for the model.
|
|
||||||
example: "2048"
|
|
||||||
top_k:
|
|
||||||
type: string
|
|
||||||
description: Top-k setting for the model.
|
|
||||||
example: "0"
|
|
||||||
top_p:
|
top_p:
|
||||||
type: string
|
example: 0.95
|
||||||
description: Top-p setting for the model.
|
|
||||||
example: "1"
|
|
||||||
stream:
|
stream:
|
||||||
type: string
|
example: true
|
||||||
description: Indicates if streaming is enabled.
|
max_tokens:
|
||||||
example: "true"
|
example: 4096
|
||||||
|
stop:
|
||||||
|
example: []
|
||||||
|
frequency_penalty:
|
||||||
|
example: 0
|
||||||
|
presence_penalty:
|
||||||
|
example: 0
|
||||||
additionalProperties: false
|
additionalProperties: false
|
||||||
metadata:
|
metadata:
|
||||||
type: object
|
author:
|
||||||
description: Additional metadata.
|
|
||||||
assets:
|
|
||||||
type: array
|
|
||||||
items:
|
|
||||||
type: string
|
type: string
|
||||||
description: List of assets related to the model.
|
example: Jan
|
||||||
required:
|
tags:
|
||||||
- source_url
|
example: ["7B", "Merged", "Featured"]
|
||||||
|
size:
|
||||||
|
example: 4370000000,
|
||||||
|
cover:
|
||||||
|
example: "https://raw.githubusercontent.com/janhq/jan/main/models/trinity-v1.2-7b/cover.png"
|
||||||
|
engine:
|
||||||
|
example: nitro
|
||||||
ModelObject:
|
ModelObject:
|
||||||
type: object
|
type: object
|
||||||
properties:
|
properties:
|
||||||
@ -125,7 +96,7 @@ components:
|
|||||||
type: string
|
type: string
|
||||||
description: |
|
description: |
|
||||||
The identifier of the model.
|
The identifier of the model.
|
||||||
example: zephyr-7b
|
example: ztrinity-v1.2-7b
|
||||||
object:
|
object:
|
||||||
type: string
|
type: string
|
||||||
description: |
|
description: |
|
||||||
@ -145,197 +116,82 @@ components:
|
|||||||
GetModelResponse:
|
GetModelResponse:
|
||||||
type: object
|
type: object
|
||||||
properties:
|
properties:
|
||||||
id:
|
|
||||||
type: string
|
|
||||||
description: The identifier of the model.
|
|
||||||
example: zephyr-7b
|
|
||||||
object:
|
|
||||||
type: string
|
|
||||||
description: Type of the object, indicating it's a model.
|
|
||||||
default: model
|
|
||||||
created:
|
|
||||||
type: integer
|
|
||||||
format: int64
|
|
||||||
description: Unix timestamp representing the creation time of the model.
|
|
||||||
owned_by:
|
|
||||||
type: string
|
|
||||||
description: The entity that owns the model.
|
|
||||||
example: _
|
|
||||||
state:
|
|
||||||
type: string
|
|
||||||
enum:
|
|
||||||
- not_downloaded
|
|
||||||
- downloaded
|
|
||||||
- running
|
|
||||||
- stopped
|
|
||||||
description: The current state of the model.
|
|
||||||
source_url:
|
source_url:
|
||||||
type: string
|
type: string
|
||||||
format: uri
|
format: uri
|
||||||
description: URL to the source of the model.
|
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/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/mistral-7b-instruct-v0.2.Q4_K_M.gguf
|
||||||
engine_parameters:
|
id:
|
||||||
type: object
|
type: string
|
||||||
properties:
|
description:
|
||||||
pre_prompt:
|
Unique identifier used in chat-completions model_name, matches
|
||||||
type: string
|
folder name.
|
||||||
description: Predefined prompt used for setting up internal configurations.
|
example: mistral-ins-7b-q4
|
||||||
default: ""
|
object:
|
||||||
example: Initial setup complete.
|
type: string
|
||||||
system_prompt:
|
example: model
|
||||||
type: string
|
name:
|
||||||
description: Prefix used for system-level prompts.
|
type: string
|
||||||
default: "SYSTEM: "
|
description: Name of the model.
|
||||||
user_prompt:
|
example: Mistral Instruct 7B Q4
|
||||||
type: string
|
version:
|
||||||
description: Prefix used for user prompts.
|
type: string
|
||||||
default: "USER: "
|
default: "1.0"
|
||||||
ai_prompt:
|
description: The version number of the model.
|
||||||
type: string
|
description:
|
||||||
description: Prefix used for assistant prompts.
|
type: string
|
||||||
default: "ASSISTANT: "
|
description: Description of the model.
|
||||||
ngl:
|
example: Trinity is an experimental model merge using the Slerp method. Recommended for daily assistance purposes.
|
||||||
type: integer
|
format:
|
||||||
description: Number of neural network layers loaded onto the GPU for
|
type: string
|
||||||
acceleration.
|
description: State format of the model, distinct from the engine.
|
||||||
minimum: 0
|
example: gguf
|
||||||
maximum: 100
|
settings:
|
||||||
default: 100
|
|
||||||
example: 100
|
|
||||||
ctx_len:
|
|
||||||
type: integer
|
|
||||||
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.
|
|
||||||
minimum: 1
|
|
||||||
maximum: 10
|
|
||||||
default: 1
|
|
||||||
example: 4
|
|
||||||
cont_batching:
|
|
||||||
type: boolean
|
|
||||||
description: Indicates if continuous batching is used for processing.
|
|
||||||
default: false
|
|
||||||
example: false
|
|
||||||
cpu_threads:
|
|
||||||
type: integer
|
|
||||||
description: Number of threads allocated for CPU-based inference.
|
|
||||||
minimum: 1
|
|
||||||
example: 8
|
|
||||||
embedding:
|
|
||||||
type: boolean
|
|
||||||
description: Indicates if embedding layers are enabled in the model.
|
|
||||||
default: true
|
|
||||||
example: true
|
|
||||||
model_parameters:
|
|
||||||
type: object
|
type: object
|
||||||
properties:
|
properties:
|
||||||
ctx_len:
|
ctx_len:
|
||||||
type: integer
|
type: integer
|
||||||
description: Maximum context length the model can handle.
|
description: Context length.
|
||||||
minimum: 0
|
example: 4096
|
||||||
maximum: 4096
|
prompt_template:
|
||||||
default: 2048
|
type: string
|
||||||
example: 2048
|
example: "[INST] {prompt} [/INST]"
|
||||||
ngl:
|
additionalProperties: false
|
||||||
type: integer
|
parameters:
|
||||||
description: Number of layers in the neural network.
|
type: object
|
||||||
minimum: 1
|
properties:
|
||||||
maximum: 100
|
|
||||||
default: 100
|
|
||||||
example: 100
|
|
||||||
embedding:
|
|
||||||
type: boolean
|
|
||||||
description: Indicates if embedding layers are used.
|
|
||||||
default: true
|
|
||||||
example: true
|
|
||||||
n_parallel:
|
|
||||||
type: integer
|
|
||||||
description: Number of parallel processes the model can run.
|
|
||||||
minimum: 1
|
|
||||||
maximum: 10
|
|
||||||
default: 1
|
|
||||||
example: 4
|
|
||||||
temperature:
|
temperature:
|
||||||
type: number
|
|
||||||
description: Controls randomness in model's responses. Higher values lead to
|
|
||||||
more random responses.
|
|
||||||
minimum: 0
|
|
||||||
maximum: 2
|
|
||||||
default: 0.7
|
|
||||||
example: 0.7
|
example: 0.7
|
||||||
token_limit:
|
|
||||||
type: integer
|
|
||||||
description: Maximum number of tokens the model can generate in a single
|
|
||||||
response.
|
|
||||||
minimum: 1
|
|
||||||
maximum: 4096
|
|
||||||
default: 2048
|
|
||||||
example: 2048
|
|
||||||
top_k:
|
|
||||||
type: integer
|
|
||||||
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:
|
top_p:
|
||||||
type: number
|
example: 0.95
|
||||||
description: Nucleus sampling parameter. The model considers the smallest set of
|
stream:
|
||||||
tokens whose cumulative probability exceeds the top_p value.
|
example: true
|
||||||
minimum: 0
|
max_tokens:
|
||||||
maximum: 1
|
example: 4096
|
||||||
default: 1
|
stop:
|
||||||
example: 1
|
example: []
|
||||||
|
frequency_penalty:
|
||||||
|
example: 0
|
||||||
|
presence_penalty:
|
||||||
|
example: 0
|
||||||
|
additionalProperties: false
|
||||||
metadata:
|
metadata:
|
||||||
type: object
|
author:
|
||||||
properties:
|
type: string
|
||||||
engine:
|
example: MistralAI
|
||||||
type: string
|
tags:
|
||||||
description: The engine used by the model.
|
example: ["7B", "Featured", "Foundation Model"]
|
||||||
enum:
|
size:
|
||||||
- nitro
|
example: 4370000000,
|
||||||
- openai
|
cover:
|
||||||
- hf_inference
|
example: "https://raw.githubusercontent.com/janhq/jan/main/models/mistral-ins-7b-q4/cover.png"
|
||||||
quantization:
|
engine:
|
||||||
type: string
|
example: nitro
|
||||||
description: Quantization parameter of the model.
|
|
||||||
example: Q3_K_L
|
|
||||||
size:
|
|
||||||
type: string
|
|
||||||
description: Size of the model.
|
|
||||||
example: 7B
|
|
||||||
required:
|
|
||||||
- id
|
|
||||||
- object
|
|
||||||
- created
|
|
||||||
- owned_by
|
|
||||||
- state
|
|
||||||
- source_url
|
|
||||||
- parameters
|
|
||||||
- metadata
|
|
||||||
DeleteModelResponse:
|
DeleteModelResponse:
|
||||||
type: object
|
type: object
|
||||||
properties:
|
properties:
|
||||||
id:
|
message:
|
||||||
type: string
|
example: Not found
|
||||||
description: The identifier of the model that was deleted.
|
|
||||||
example: model-zephyr-7B
|
|
||||||
object:
|
|
||||||
type: string
|
|
||||||
description: Type of the object, indicating it's a model.
|
|
||||||
default: model
|
|
||||||
deleted:
|
|
||||||
type: boolean
|
|
||||||
description: Indicates whether the model was successfully deleted.
|
|
||||||
example: true
|
|
||||||
StartModelResponse:
|
StartModelResponse:
|
||||||
type: object
|
type: object
|
||||||
properties:
|
properties:
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user