Last Update: 7/13/2025

SenseFlow Text Completion API

The SenseFlow Text Completion API allows you to generate text content without maintaining conversation context. This is suitable for tasks like translation, article writing, and AI summarization.

Endpoints

Generate Completion

POST https://platform.llmprovider.ai/v1/agent/completion-messages

Request Headers

Header	Value
Authorization	Bearer YOUR_API_KEY
Content-Type	application/json

Request Body

Parameter	Type	Description
agent	string	model name.
inputs	object	(Optional) Key-value pairs of variables defined in the app.
response_mode	string	Response mode: streaming (recommended) or blocking
user	string	Unique identifier for the end user
files	array	(Optional) Array of file objects for upload

Files Object Structure

Field	Type	Description
type	string	File type (currently only supports 'image')
transfer_method	string	remote_url or local_file
url	string	Image URL (when transfer_method is remote_url)
upload_file_id	string	File ID (when transfer_method is local_file)

Example Request

{
  "model": "",
  "inputs": {
    "query": "Hello, world!"
  },
  "response_mode": "streaming",
  "user": "abc-123"
}

Response

The response varies based on the response_mode:

• For blocking mode: Returns a ChatCompletionResponse object
• For streaming mode: Returns a stream of ChunkChatCompletionResponse objects

ChatCompletionResponse Structure

Field	Type	Description
message_id	string	Unique message identifier
mode	string	Fixed as "chat"
answer	string	Complete response content
metadata	object	Metadata information
usage	object	Model usage information
created_at	integer	Message creation timestamp

Streaming Response Events

Each streaming chunk starts with data: and chunks are separated by \n\n. Example:

data: {"event": "message", "task_id": "900bbd43-dc0b-4383-a372-aa6e6c414227", "message_id": "663c5084", "answer": "Hi", "created_at": 1705398420}\n\n

Different event types in the stream:

Event Type	Description	Fields
message	Text chunk from LLM	task_id, message_id, answer, created_at
message_end	Message completion	task_id, message_id, metadata, usage, retriever_resources
tts_message	Speech synthesis chunk	task_id, message_id, audio (base64), created_at
tts_message_end	Speech synthesis completion	task_id, message_id, audio (empty), created_at
message_replace	Content moderation replacement	task_id, message_id, answer, created_at
error	Stream error event	task_id, message_id, status, code, message
ping	Keep-alive ping (every 10s)	-

Example Responses

For blocking mode:

{
  "id": "0b089b9a-24d9-48cc-94f8-762677276261",
  "answer": "Hello! How can I help you today?",
  "created_at": 1679586667
}

For streaming mode:

data: {"event": "message", "task_id": "5ad4cb98", "message_id": "a8bdc41c", "answer": "Hello!", "created_at": 1721205487}
data: {"event": "tts_message", "task_id": "3bf8a0bb", "message_id": "a8bdc41c", "audio": "base64_audio_data", "created_at": 1721205487}
data: {"event": "message_end", "task_id": "5ad4cb98", "message_id": "a8bdc41c", "metadata": {}, "usage": {"total_tokens": 10}}
data: {"event": "tts_message_end", "task_id": "3bf8a0bb", "message_id": "a8bdc41c", "audio": "", "created_at": 1721205487}

Example Request

Shell

curl -X POST 'https://platform.llmprovider.ai/v1/agent/completion-messages' \
--header 'Authorization: Bearer $YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "",
    "inputs": {"query": "Hello, world!"},
    "response_mode": "streaming",
    "user": "abc-123"
}'

Python

import requests
import json

api_key = 'YOUR_API_KEY'
url = 'https://platform.llmprovider.ai/v1/agent/completion-messages'

headers = {
    'Authorization': f'Bearer {api_key}',
    'Content-Type': 'application/json'
}

data = {
    'model': '',
    'inputs': {'query': 'Hello, world!'},
    'response_mode': 'streaming',
    'user': 'abc-123'
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Node.js

const axios = require('axios');

const apiKey = 'YOUR_API_KEY';
const url = 'https://api.dify.ai/v1/agent/completion-messages';

const data = {
    model: '',
    inputs: {query: 'Hello, world!'},
    response_mode: 'streaming',
    user: 'abc-123'
};

const headers = {
    'Authorization': `Bearer ${apiKey}`,
    'Content-Type': 'application/json'
};

axios.post(url, data, {headers})
    .then(response => console.log(response.data))
    .catch(error => console.error(error));

Stop Response

POST https://platform.llmprovider.ai/v1/agent/completion-messages/:task_id/stop

Stop a streaming response. Only available for streaming mode.

Request Headers

Header	Value
Authorization	Bearer YOUR_API_KEY
Content-Type	application/json

Path Parameters

Parameter	Type	Description
task_id	string	Task ID obtained from the streaming response

Request Body Parameters

Parameter	Type	Required	Description
model	string	Yes	agent name
user	string	Yes	User identifier (must match the message API user ID)

Response

Field	Type	Description
result	string	upload result

Example Response

{
  "result": "success"
}

Example Request

Shell

curl -X POST 'https://platform.llmprovider.ai/v1/agent/completion-messages/task_123/stop' \
--header 'Authorization: Bearer $YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data-raw '{
        "model": "",
        "user": "abc-123"
}'

Python

import requests
import json

api_key = 'YOUR_API_KEY'
url = 'https://platform.llmprovider.ai/v1/agent/completion-messages/task_123/stop'

headers = {
        'Authorization': f'Bearer {api_key}',
        'Content-Type': 'application/json'
}

data = {
        'model': '',
        'user': 'abc-123'
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Node.js

const axios = require('axios');

const apiKey = 'YOUR_API_KEY';
const url = 'https://platform.llmprovider.ai/v1/agent/completion-messages/task_123/stop';

const data = {
    model: '',
    user: 'abc-123'
};

const headers = {
    'Authorization': `Bearer ${apiKey}`,
    'Content-Type': 'application/json'
};

axios.post(url, data, {headers})
    .then(response => console.log(response.data))
    .catch(error => console.error(error));

Message Feedback

POST https://platform.llmprovider.ai/v1/agent/messages/:message_id/feedbacks

Submit user feedback (likes/dislikes) for messages to help developers optimize output.

Path Parameters

Parameter	Type	Description
message_id	string	Message ID

Request Headers

Header	Value
Authorization	Bearer YOUR_API_KEY
Content-Type	application/json

Request Body Parameters

Parameter	Type	Description
model	string	agent name
rating	string	Feedback type: "like", "dislike", or null
user	string	User identifier
content	string	Optional feedback details

Response

Field	Type	Description
result	string	result

Example Response

{
  "result": "success"
}

Example Request

Shell

curl -X POST 'https://platform.llmprovider.ai/v1/agent/messages/msg_123/feedbacks' \
--header 'Authorization: Bearer $YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "",
    "rating": "like",
    "user": "abc-123",
    "content": "This response was helpful"
}'

Python

import requests
import json

api_key = 'YOUR_API_KEY'
url = 'https://platform.llmprovider.ai/v1/agent/messages/msg_123/feedbacks'

headers = {
    'Authorization': f'Bearer {api_key}',
    'Content-Type': 'application/json'
}

data = {
    'model': '',
    'rating': 'like',
    'user': 'abc-123',
    'content': 'This response was helpful'
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Node.js

const axios = require('axios');

const apiKey = 'YOUR_API_KEY';
const url = 'https://platform.llmprovider.ai/v1/agent/messages/msg_123/feedbacks';

const data = {
    model: '',
    rating: 'like',
    user: 'abc-123',
    content: 'This response was helpful'
};

const headers = {
    'Authorization': `Bearer ${apiKey}`,
    'Content-Type': 'application/json'
};

axios.post(url, data, {headers})
    .then(response => console.log(response.data))
    .catch(error => console.error(error));