Hieu
GitHub
commit
53e97046aa
@ -67,20 +67,31 @@ paths:
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
curl http://localhost:1337/v1/chat/completions \
|
||||
-H "Content-Type: application/json" \
|
||||
curl -X 'POST' \
|
||||
'http://localhost:1337/v1/chat/completions' \
|
||||
-H 'accept: application/json' \
|
||||
-H 'Content-Type: application/json' \
|
||||
-d '{
|
||||
"model": "tinyllama-1.1b",
|
||||
"messages": [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are a helpful assistant."
|
||||
"content": "You are a helpful assistant.",
|
||||
"role": "system"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Hello!"
|
||||
"content": "Hello!",
|
||||
"role": "user"
|
||||
}
|
||||
]
|
||||
],
|
||||
"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:
|
||||
get:
|
||||
@ -103,7 +114,9 @@ paths:
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
curl http://localhost:1337/v1/models
|
||||
curl -X 'GET' \
|
||||
'http://localhost:1337/v1/models' \
|
||||
-H 'accept: application/json'
|
||||
"/models/download/{model_id}":
|
||||
get:
|
||||
operationId: downloadModel
|
||||
@ -131,7 +144,9 @@ paths:
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
curl -X POST http://localhost:1337/v1/models/download/{model_id}
|
||||
curl -X 'GET' \
|
||||
'http://localhost:1337/v1/models/download/{model_id}' \
|
||||
-H 'accept: application/json'
|
||||
"/models/{model_id}":
|
||||
get:
|
||||
operationId: retrieveModel
|
||||
@ -162,7 +177,9 @@ paths:
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
curl http://localhost:1337/v1/models/{model_id}
|
||||
curl -X 'GET' \
|
||||
'http://localhost:1337/v1/models/{model_id}' \
|
||||
-H 'accept: application/json'
|
||||
delete:
|
||||
operationId: deleteModel
|
||||
tags:
|
||||
@ -191,7 +208,9 @@ paths:
|
||||
x-codeSamples:
|
||||
- lang: cURL
|
||||
source: |
|
||||
curl -X DELETE http://localhost:1337/v1/models/{model_id}
|
||||
curl -X 'DELETE' \
|
||||
'http://localhost:1337/v1/models/{model_id}' \
|
||||
-H 'accept: application/json'
|
||||
/threads:
|
||||
post:
|
||||
operationId: createThread
|
||||
|
||||
@ -1,3 +1,4 @@
|
||||
---
|
||||
components:
|
||||
schemas:
|
||||
MessageObject:
|
||||
@ -75,7 +76,7 @@ components:
|
||||
example: msg_abc123
|
||||
object:
|
||||
type: string
|
||||
description: "Type of the object, indicating it's a thread message."
|
||||
description: Type of the object, indicating it's a thread message.
|
||||
default: thread.message
|
||||
created_at:
|
||||
type: integer
|
||||
@ -88,7 +89,7 @@ components:
|
||||
example: thread_abc123
|
||||
role:
|
||||
type: string
|
||||
description: "Role of the sender, either 'user' or 'assistant'."
|
||||
description: Role of the sender, either 'user' or 'assistant'.
|
||||
example: user
|
||||
content:
|
||||
type: array
|
||||
@ -97,7 +98,7 @@ components:
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
description: "Type of content, e.g., 'text'."
|
||||
description: Type of content, e.g., 'text'.
|
||||
example: text
|
||||
text:
|
||||
type: object
|
||||
@ -110,21 +111,21 @@ components:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: "Annotations for the text content, if any."
|
||||
description: Annotations for the text content, if any.
|
||||
example: []
|
||||
file_ids:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: "Array of file IDs associated with the message, if any."
|
||||
description: Array of file IDs associated with the message, if any.
|
||||
example: []
|
||||
assistant_id:
|
||||
type: string
|
||||
description: "Identifier of the assistant involved in the message, if applicable."
|
||||
description: Identifier of the assistant involved in the message, if applicable.
|
||||
example: null
|
||||
run_id:
|
||||
type: string
|
||||
description: "Run ID associated with the message, if applicable."
|
||||
description: Run ID associated with the message, if applicable.
|
||||
example: null
|
||||
metadata:
|
||||
type: object
|
||||
@ -139,7 +140,7 @@ components:
|
||||
example: msg_abc123
|
||||
object:
|
||||
type: string
|
||||
description: "Type of the object, indicating it's a thread message."
|
||||
description: Type of the object, indicating it's a thread message.
|
||||
example: thread.message
|
||||
created_at:
|
||||
type: integer
|
||||
@ -152,7 +153,7 @@ components:
|
||||
example: thread_abc123
|
||||
role:
|
||||
type: string
|
||||
description: "Role of the sender, either 'user' or 'assistant'."
|
||||
description: Role of the sender, either 'user' or 'assistant'.
|
||||
example: user
|
||||
content:
|
||||
type: array
|
||||
@ -161,7 +162,7 @@ components:
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
description: "Type of content, e.g., 'text'."
|
||||
description: Type of content, e.g., 'text'.
|
||||
example: text
|
||||
text:
|
||||
type: object
|
||||
@ -174,21 +175,21 @@ components:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: "Annotations for the text content, if any."
|
||||
description: Annotations for the text content, if any.
|
||||
example: []
|
||||
file_ids:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: "Array of file IDs associated with the message, if any."
|
||||
description: Array of file IDs associated with the message, if any.
|
||||
example: []
|
||||
assistant_id:
|
||||
type: string
|
||||
description: "Identifier of the assistant involved in the message, if applicable."
|
||||
description: Identifier of the assistant involved in the message, if applicable.
|
||||
example: null
|
||||
run_id:
|
||||
type: string
|
||||
description: "Run ID associated with the message, if applicable."
|
||||
description: Run ID associated with the message, if applicable.
|
||||
example: null
|
||||
metadata:
|
||||
type: object
|
||||
@ -199,7 +200,7 @@ components:
|
||||
properties:
|
||||
object:
|
||||
type: string
|
||||
description: "Type of the object, indicating it's a list."
|
||||
description: Type of the object, indicating it's a list.
|
||||
default: list
|
||||
data:
|
||||
type: array
|
||||
@ -226,7 +227,7 @@ components:
|
||||
example: msg_abc123
|
||||
object:
|
||||
type: string
|
||||
description: "Type of the object, indicating it's a thread message."
|
||||
description: Type of the object, indicating it's a thread message.
|
||||
example: thread.message
|
||||
created_at:
|
||||
type: integer
|
||||
@ -239,7 +240,7 @@ components:
|
||||
example: thread_abc123
|
||||
role:
|
||||
type: string
|
||||
description: "Role of the sender, either 'user' or 'assistant'."
|
||||
description: Role of the sender, either 'user' or 'assistant'.
|
||||
example: user
|
||||
content:
|
||||
type: array
|
||||
@ -248,7 +249,7 @@ components:
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
description: "Type of content, e.g., 'text'."
|
||||
description: Type of content, e.g., 'text'.
|
||||
text:
|
||||
type: object
|
||||
properties:
|
||||
@ -260,20 +261,20 @@ components:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: "Annotations for the text content, if any."
|
||||
description: Annotations for the text content, if any.
|
||||
file_ids:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: "Array of file IDs associated with the message, if any."
|
||||
description: Array of file IDs associated with the message, if any.
|
||||
example: []
|
||||
assistant_id:
|
||||
type: string
|
||||
description: "Identifier of the assistant involved in the message, if applicable."
|
||||
description: Identifier of the assistant involved in the message, if applicable.
|
||||
example: null
|
||||
run_id:
|
||||
type: string
|
||||
description: "Run ID associated with the message, if applicable."
|
||||
description: Run ID associated with the message, if applicable.
|
||||
example: null
|
||||
metadata:
|
||||
type: object
|
||||
|
||||
@ -18,114 +18,82 @@ components:
|
||||
Model:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
source_url:
|
||||
type: string
|
||||
default: model
|
||||
description: The type of the object.
|
||||
version:
|
||||
type: string
|
||||
default: "1"
|
||||
description: The version number of the model.
|
||||
format: uri
|
||||
description: URL to the source of the model.
|
||||
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
|
||||
description:
|
||||
Unique identifier used in chat-completions model_name, matches
|
||||
folder name.
|
||||
example: zephyr-7b
|
||||
example: trinity-v1.2-7b
|
||||
object:
|
||||
type: string
|
||||
example: model
|
||||
name:
|
||||
type: string
|
||||
description: Name of the model.
|
||||
example: Zephyr 7B
|
||||
owned_by:
|
||||
example: Trinity-v1.2 7B Q4
|
||||
version:
|
||||
type: string
|
||||
description: Compatibility field for OpenAI.
|
||||
default: ""
|
||||
created:
|
||||
type: integer
|
||||
format: int64
|
||||
description: Unix timestamp representing the creation time.
|
||||
default: "1.0"
|
||||
description: The version number of the model.
|
||||
description:
|
||||
type: string
|
||||
description: Description of the model.
|
||||
state:
|
||||
type: string
|
||||
enum:
|
||||
- null
|
||||
- downloading
|
||||
- ready
|
||||
- starting
|
||||
- stopping
|
||||
description: Current state 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: ggufv3
|
||||
source:
|
||||
type: array
|
||||
items:
|
||||
type: object
|
||||
properties:
|
||||
url:
|
||||
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
|
||||
filename:
|
||||
type: string
|
||||
description: Filename of the model.
|
||||
example: zephyr-7b-beta.Q4_K_M.gguf
|
||||
example: gguf
|
||||
settings:
|
||||
type: object
|
||||
properties:
|
||||
ctx_len:
|
||||
type: string
|
||||
type: integer
|
||||
description: Context length.
|
||||
example: "4096"
|
||||
ngl:
|
||||
example: 4096
|
||||
prompt_template:
|
||||
type: string
|
||||
description: Number of layers.
|
||||
example: "100"
|
||||
embedding:
|
||||
type: string
|
||||
description: Indicates if embedding is enabled.
|
||||
example: "true"
|
||||
n_parallel:
|
||||
type: string
|
||||
description: Number of parallel processes.
|
||||
example: "4"
|
||||
example: "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
|
||||
additionalProperties: false
|
||||
parameters:
|
||||
type: object
|
||||
properties:
|
||||
temperature:
|
||||
type: string
|
||||
description: Temperature setting for the model.
|
||||
example: "0.7"
|
||||
token_limit:
|
||||
type: string
|
||||
description: Token limit for the model.
|
||||
example: "4096"
|
||||
top_k:
|
||||
type: string
|
||||
description: Top-k setting for the model.
|
||||
example: "0"
|
||||
example: 0.7
|
||||
top_p:
|
||||
type: string
|
||||
description: Top-p setting for the model.
|
||||
example: "1"
|
||||
example: 0.95
|
||||
stream:
|
||||
type: string
|
||||
description: Indicates if streaming is enabled.
|
||||
example: "true"
|
||||
example: true
|
||||
max_tokens:
|
||||
example: 4096
|
||||
stop:
|
||||
example: []
|
||||
frequency_penalty:
|
||||
example: 0
|
||||
presence_penalty:
|
||||
example: 0
|
||||
additionalProperties: false
|
||||
metadata:
|
||||
type: object
|
||||
description: Additional metadata.
|
||||
assets:
|
||||
type: array
|
||||
items:
|
||||
author:
|
||||
type: string
|
||||
description: List of assets related to the model.
|
||||
required:
|
||||
- source
|
||||
example: Jan
|
||||
tags:
|
||||
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:
|
||||
type: object
|
||||
properties:
|
||||
@ -133,7 +101,7 @@ components:
|
||||
type: string
|
||||
description: |
|
||||
The identifier of the model.
|
||||
example: zephyr-7b
|
||||
example: trinity-v1.2-7b
|
||||
object:
|
||||
type: string
|
||||
description: |
|
||||
@ -153,197 +121,89 @@ components:
|
||||
GetModelResponse:
|
||||
type: object
|
||||
properties:
|
||||
source_url:
|
||||
type: string
|
||||
format: uri
|
||||
description: URL to the source of the model.
|
||||
example: https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/mistral-7b-instruct-v0.2.Q4_K_M.gguf
|
||||
id:
|
||||
type: string
|
||||
description: The identifier of the model.
|
||||
example: zephyr-7b
|
||||
description:
|
||||
Unique identifier used in chat-completions model_name, matches
|
||||
folder name.
|
||||
example: mistral-ins-7b-q4
|
||||
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:
|
||||
example: model
|
||||
name:
|
||||
type: string
|
||||
description: The entity that owns the model.
|
||||
example: _
|
||||
state:
|
||||
description: Name of the model.
|
||||
example: Mistral Instruct 7B Q4
|
||||
version:
|
||||
type: string
|
||||
enum:
|
||||
- not_downloaded
|
||||
- downloaded
|
||||
- running
|
||||
- stopped
|
||||
description: The current state of the model.
|
||||
source:
|
||||
type: array
|
||||
items:
|
||||
type: object
|
||||
properties:
|
||||
url:
|
||||
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
|
||||
filename:
|
||||
type: string
|
||||
description: Filename of the model.
|
||||
example: zephyr-7b-beta.Q4_K_M.gguf
|
||||
engine_parameters:
|
||||
type: object
|
||||
properties:
|
||||
pre_prompt:
|
||||
type: string
|
||||
description: Predefined prompt used for setting up internal configurations.
|
||||
default: ""
|
||||
example: Initial setup complete.
|
||||
system_prompt:
|
||||
type: string
|
||||
description: Prefix used for system-level prompts.
|
||||
default: "SYSTEM: "
|
||||
user_prompt:
|
||||
type: string
|
||||
description: Prefix used for user prompts.
|
||||
default: "USER: "
|
||||
ai_prompt:
|
||||
type: string
|
||||
description: Prefix used for assistant prompts.
|
||||
default: "ASSISTANT: "
|
||||
ngl:
|
||||
type: integer
|
||||
description: Number of neural network layers loaded onto the GPU for
|
||||
acceleration.
|
||||
minimum: 0
|
||||
maximum: 100
|
||||
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: 4096
|
||||
example: 4096
|
||||
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:
|
||||
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:
|
||||
type: object
|
||||
properties:
|
||||
ctx_len:
|
||||
type: integer
|
||||
description: Maximum context length the model can handle.
|
||||
minimum: 0
|
||||
maximum: 4096
|
||||
default: 4096
|
||||
description: Context length.
|
||||
example: 4096
|
||||
ngl:
|
||||
type: integer
|
||||
description: Number of layers in the neural network.
|
||||
minimum: 1
|
||||
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
|
||||
prompt_template:
|
||||
type: string
|
||||
example: "[INST] {prompt} [/INST]"
|
||||
additionalProperties: false
|
||||
parameters:
|
||||
type: object
|
||||
properties:
|
||||
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
|
||||
token_limit:
|
||||
type: integer
|
||||
description: Maximum number of tokens the model can generate in a single
|
||||
response.
|
||||
minimum: 1
|
||||
maximum: 4096
|
||||
default: 4096
|
||||
example: 4096
|
||||
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:
|
||||
type: number
|
||||
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
|
||||
example: 1
|
||||
example: 0.95
|
||||
stream:
|
||||
example: true
|
||||
max_tokens:
|
||||
example: 4096
|
||||
stop:
|
||||
example: []
|
||||
frequency_penalty:
|
||||
example: 0
|
||||
presence_penalty:
|
||||
example: 0
|
||||
additionalProperties: false
|
||||
metadata:
|
||||
type: object
|
||||
properties:
|
||||
engine:
|
||||
type: string
|
||||
description: The engine used by the model.
|
||||
enum:
|
||||
- nitro
|
||||
- openai
|
||||
- hf_inference
|
||||
quantization:
|
||||
type: string
|
||||
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
|
||||
- parameters
|
||||
- metadata
|
||||
author:
|
||||
type: string
|
||||
example: MistralAI
|
||||
tags:
|
||||
example:
|
||||
- 7B
|
||||
- Featured
|
||||
- Foundation Model
|
||||
size:
|
||||
example: 4370000000,
|
||||
cover:
|
||||
example: https://raw.githubusercontent.com/janhq/jan/main/models/mistral-ins-7b-q4/cover.png
|
||||
engine:
|
||||
example: nitro
|
||||
DeleteModelResponse:
|
||||
type: object
|
||||
properties:
|
||||
id:
|
||||
type: string
|
||||
description: The identifier of the model that was deleted.
|
||||
example: model-zephyr-7B
|
||||
example: mistral-ins-7b-q4
|
||||
object:
|
||||
type: string
|
||||
description: Type of the object, indicating it's a model.
|
||||
|
||||
@ -142,7 +142,7 @@ components:
|
||||
example: Jan
|
||||
instructions:
|
||||
type: string
|
||||
description: |
|
||||
description: >
|
||||
The instruction of assistant, defaults to "Be my grammar corrector"
|
||||
model:
|
||||
type: object
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user