Перейти к основному содержимому

REST API

Compressa Pods Dispatcher (0.1.0)

Download OpenAPI specification:Download

Models

Responses

Response samples

Content type
application/json
{
  • "object": "string",
  • "data": [
    ]
}

Models

Responses

Response samples

Content type
application/json
{
  • "object": "string",
  • "data": [
    ]
}

Proxy Chat Completions

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: application/json
model
required
string (Model)
required
Array of objects (Messages)
Array of Tools (objects) or Tools (null) (Tools)
Tool Choice (string) or Tool Choice (null) (Tool Choice)
stream
boolean (Stream)
Default: false
temperature
number (Temperature)
Default: 0
Max Tokens (integer) or Max Tokens (null) (Max Tokens)

Responses

Request samples

Content type
application/json
{
  • "model": "string",
  • "messages": [
    ],
  • "tools": [
    ],
  • "tool_choice": "string",
  • "stream": false,
  • "temperature": 0,
  • "max_tokens": 0
}

Response samples

Content type
application/json
null

Proxy Chat Completions

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: application/json
model
required
string (Model)
required
Array of objects (Messages)
Array of Tools (objects) or Tools (null) (Tools)
Tool Choice (string) or Tool Choice (null) (Tool Choice)
stream
boolean (Stream)
Default: false
temperature
number (Temperature)
Default: 0
Max Tokens (integer) or Max Tokens (null) (Max Tokens)

Responses

Request samples

Content type
application/json
{
  • "model": "string",
  • "messages": [
    ],
  • "tools": [
    ],
  • "tool_choice": "string",
  • "stream": false,
  • "temperature": 0,
  • "max_tokens": 0
}

Response samples

Content type
application/json
null

Proxy Completions

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: application/json
model
required
string (Model)
prompt
required
string (Prompt)
stream
boolean (Stream)
Default: false
temperature
number (Temperature)
Default: 0
Max Tokens (integer) or Max Tokens (null) (Max Tokens)
Tool Choice (string) or Tool Choice (null) (Tool Choice)

Responses

Request samples

Content type
application/json
{
  • "model": "string",
  • "prompt": "string",
  • "stream": false,
  • "temperature": 0,
  • "max_tokens": 0,
  • "tool_choice": "string"
}

Response samples

Content type
application/json
null

Proxy Completions

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: application/json
model
required
string (Model)
prompt
required
string (Prompt)
stream
boolean (Stream)
Default: false
temperature
number (Temperature)
Default: 0
Max Tokens (integer) or Max Tokens (null) (Max Tokens)
Tool Choice (string) or Tool Choice (null) (Tool Choice)

Responses

Request samples

Content type
application/json
{
  • "model": "string",
  • "prompt": "string",
  • "stream": false,
  • "temperature": 0,
  • "max_tokens": 0,
  • "tool_choice": "string"
}

Response samples

Content type
application/json
null

Proxy Embeddings

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: application/json
model
required
string (Model)
required
Input (string) or Array of Input (strings) (Input)
encoding_format
string (Encoding Format)
Default: "float"

Responses

Request samples

Content type
application/json
{
  • "model": "string",
  • "input": "string",
  • "encoding_format": "float"
}

Response samples

Content type
application/json
null

Proxy Embeddings

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: application/json
model
required
string (Model)
required
Input (string) or Array of Input (strings) (Input)
encoding_format
string (Encoding Format)
Default: "float"

Responses

Request samples

Content type
application/json
{
  • "model": "string",
  • "input": "string",
  • "encoding_format": "float"
}

Response samples

Content type
application/json
null

Proxy Rerank

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: application/json
model
required
string (Model)
query
required
string (Query)
documents
required
Array of strings (Documents)

Responses

Request samples

Content type
application/json
{
  • "model": "string",
  • "query": "string",
  • "documents": [
    ]
}

Response samples

Content type
application/json
null

Proxy Rerank

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: application/json
model
required
string (Model)
query
required
string (Query)
documents
required
Array of strings (Documents)

Responses

Request samples

Content type
application/json
{
  • "model": "string",
  • "query": "string",
  • "documents": [
    ]
}

Response samples

Content type
application/json
null

Proxy Tts

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: application/json
model
required
string (Model)
input
required
string (Input)
voice
string (Voice)
Default: "Zofija Kendrick"
Enum: "Zofija Kendrick" "Craig Gutsy" "Filip Traverse" "Damjan Chapman" "Wulf Carlevaro" "Aaron Dreschner" "Kumar Dahl"
language
string (Language)
Default: "ru"
Enum: "ru" "en"

Responses

Request samples

Content type
application/json
{
  • "model": "string",
  • "input": "string",
  • "voice": "Zofija Kendrick",
  • "language": "ru"
}

Response samples

Content type
application/json
null

Proxy Tts

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: application/json
model
required
string (Model)
input
required
string (Input)
voice
string (Voice)
Default: "Zofija Kendrick"
Enum: "Zofija Kendrick" "Craig Gutsy" "Filip Traverse" "Damjan Chapman" "Wulf Carlevaro" "Aaron Dreschner" "Kumar Dahl"
language
string (Language)
Default: "ru"
Enum: "ru" "en"

Responses

Request samples

Content type
application/json
{
  • "model": "string",
  • "input": "string",
  • "voice": "Zofija Kendrick",
  • "language": "ru"
}

Response samples

Content type
application/json
null

Proxy Asr

Proxy ASR transcription request to the appropriate pod.

Args: request: FastAPI request object file: Audio file to transcribe model: Model name for transcription stream: Stream flag authorization: Authorization header accept: Accept header

Returns: Response from the pod with transcription results

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: multipart/form-data
required
file
required
string <binary> (File)
model
required
string (Model)
stream
boolean (Stream)
Default: false

Responses

Response samples

Content type
application/json
null

Proxy Asr

Proxy ASR transcription request to the appropriate pod.

Args: request: FastAPI request object file: Audio file to transcribe model: Model name for transcription stream: Stream flag authorization: Authorization header accept: Accept header

Returns: Response from the pod with transcription results

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: multipart/form-data
required
file
required
string <binary> (File)
model
required
string (Model)
stream
boolean (Stream)
Default: false

Responses

Response samples

Content type
application/json
null

Proxy Performance

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: application/json
pod_id
required
string (Pod Id)
required
object (PerformancePayload)

Responses

Request samples

Content type
application/json
{
  • "pod_id": "string",
  • "payload": {
    }
}

Response samples

Content type
application/json
null

Proxy Performance Status

query Parameters
pod_id
required
string (Pod Id)
header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)

Responses

Response samples

Content type
application/json
null

Proxy Performance

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: application/json
pod_id
required
string (Pod Id)
required
object (PerformancePayload)

Responses

Request samples

Content type
application/json
{
  • "pod_id": "string",
  • "payload": {
    }
}

Response samples

Content type
application/json
null

Proxy Performance Status

query Parameters
pod_id
required
string (Pod Id)
header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)

Responses

Response samples

Content type
application/json
null

Proxy Performance Interrupt

query Parameters
pod_id
required
string (Pod Id)
header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)

Responses

Response samples

Content type
application/json
null

Proxy Performance Interrupt

query Parameters
pod_id
required
string (Pod Id)
header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)

Responses

Response samples

Content type
application/json
null

Proxy Observability

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: application/json
pod_id
required
string (Pod Id)
dataset
required
string (Dataset)
num_examples
required
integer (Num Examples)
required
CustomDataset (object) or null

Responses

Request samples

Content type
application/json
{
  • "pod_id": "string",
  • "dataset": "string",
  • "num_examples": 0,
  • "custom_data": {
    }
}

Response samples

Content type
application/json
null

Proxy Observability Status

query Parameters
pod_id
required
string (Pod Id)
header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)

Responses

Response samples

Content type
application/json
null

Proxy Observability

header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)
Request Body schema: application/json
pod_id
required
string (Pod Id)
dataset
required
string (Dataset)
num_examples
required
integer (Num Examples)
required
CustomDataset (object) or null

Responses

Request samples

Content type
application/json
{
  • "pod_id": "string",
  • "dataset": "string",
  • "num_examples": 0,
  • "custom_data": {
    }
}

Response samples

Content type
application/json
null

Proxy Observability Status

query Parameters
pod_id
required
string (Pod Id)
header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)

Responses

Response samples

Content type
application/json
null

Proxy Observability Interrupt

query Parameters
pod_id
required
string (Pod Id)
header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)

Responses

Response samples

Content type
application/json
null

Proxy Observability Interrupt

query Parameters
pod_id
required
string (Pod Id)
header Parameters
Authorization (string) or Authorization (null) (Authorization)
Accept (string) or Accept (null) (Accept)

Responses

Response samples

Content type
application/json
null

Create Pods

Responses

Response samples

Content type
application/json
null

Deploy Pods

query Parameters
Id (integer) or Id (null) (Id)

Responses

Response samples

Content type
application/json
null

Set Pods Info

Request Body schema: application/json
Any of
Pod Id (string) or Pod Id (null) (Pod Id)
Engine (string) or Engine (null) (Engine)
Task (string) or Task (null) (Task)
Status (string) or Status (null) (Status)
Model Name (string) or Model Name (null) (Model Name)
Served Model Name (string) or Served Model Name (null) (Served Model Name)
Pod Address (string) or Pod Address (null) (Pod Address)
Connections (integer) or Connections (null) (Connections)
Gpu Memory Utilization (number) or Gpu Memory Utilization (null) (Gpu Memory Utilization)
Gpu Memory Used Mb (number) or Gpu Memory Used Mb (null) (Gpu Memory Used Mb)
Gpu Utilization Pct (number) or Gpu Utilization Pct (null) (Gpu Utilization Pct)
Cpu Utilization Pct (number) or Cpu Utilization Pct (null) (Cpu Utilization Pct)
Ram Usage Gb (number) or Ram Usage Gb (null) (Ram Usage Gb)
Requests Success Total (integer) or Requests Success Total (null) (Requests Success Total)
Default: 0
Requests Latency Ms (number) or Requests Latency Ms (null) (Requests Latency Ms)
Default: 0
Requests Payload Size (number) or Requests Payload Size (null) (Requests Payload Size)
Default: 0
Requests Num Running (integer) or Requests Num Running (null) (Requests Num Running)
Default: 0
Requests Total Tokens (integer) or Requests Total Tokens (null) (Requests Total Tokens)
Default: 0
Requests Prompt Tokens (integer) or Requests Prompt Tokens (null) (Requests Prompt Tokens)
Default: 0
Requests Completion Tokens (integer) or Requests Completion Tokens (null) (Requests Completion Tokens)
Default: 0
Time Per Output Token (number) or Time Per Output Token (null) (Time Per Output Token)
Default: 0
Time To First Token (number) or Time To First Token (null) (Time To First Token)
Restarted (boolean) or Restarted (null) (Restarted)
Default: false
Dead (boolean) or Dead (null) (Dead)
Default: false

Responses

Request samples

Content type
application/json
Example
{
  • "pod_id": "string",
  • "engine": "string",
  • "task": "string",
  • "status": "string",
  • "model_name": "string",
  • "served_model_name": "string",
  • "pod_address": "string",
  • "connections": 0,
  • "gpu_memory_utilization": 0,
  • "gpu_memory_used_mb": 0,
  • "gpu_utilization_pct": 0,
  • "cpu_utilization_pct": 0,
  • "ram_usage_gb": 0,
  • "requests_success_total": 0,
  • "requests_latency_ms": 0,
  • "requests_payload_size": 0,
  • "requests_num_running": 0,
  • "requests_total_tokens": 0,
  • "requests_prompt_tokens": 0,
  • "requests_completion_tokens": 0,
  • "time_per_output_token": 0,
  • "time_to_first_token": 0,
  • "restarted": false,
  • "dead": false
}

Response samples

Content type
application/json
null