flexstack.ai
  • Welcome to Flexstack AI
  • How Flexstack AI works
    • Three roles in Flexstack AI
    • AI Stack architecture
    • Models Directory
    • Open Source AI Demo
      • Image generation
      • LLM (Text completion)
      • Video generation
  • Flexstack AI API: Start making things with Flexstack AI
    • Environment setup
    • Restful APIs
      • User Endpoints
        • Login
        • Refresh Token
        • User Profile
        • Task History
      • LLMs
        • Models
        • Text Completion
      • Image Generation
        • Models
        • LoRA
          • List Types
          • List Categories
          • List Models
        • Create Image
        • Get Result
      • Video Generation
        • Models
        • Create video
        • Get Result
      • Audio Generation
        • Models
        • Music / Sound Effects Generation
          • Create audio
          • Get Result
        • Speech Generation
          • Create audio
          • Get Result
      • Text Embeddings
        • Models
        • Create embedding
        • Get Result
      • Feedback & Retrain model
        • Train LORA
        • Feedback
        • Feedback Request
      • Error Handling
        • Error Response
  • Flexstack AI Host: Start contributing
    • Prerequisites
    • Deployment Guideline
      • RunPod
      • VALDI
  • Flexstack AI Validator
    • LLM Validation
      • Methodology
      • Restful APIs
  • Additional Information
    • Technical support
Powered by GitBook
On this page

Was this helpful?

  1. Flexstack AI API: Start making things with Flexstack AI
  2. Restful APIs
  3. Text Embeddings

Create embedding

HTTP request

POST /ai/text_embedding

Authorization

Include your ACCESS TOKEN in HTTP Authorization header.

Authorization: Bearer Token

Request Parameters

KEY
TYPE
VALUE

text

String

The text for which you want to generate an embedding. Example: “Hello, have a good day!”.

configs

JSON

This parameter is a JSON object encompassing a variety of settings you can adjust to customize the image generation process. It includes several parameters, which we will describe next, allowing you to control different aspects of the generation.

model

String

Specifies the AI model used for generating text embedding. There are two models like: "mistral" and "gte-large". Default is "mistral".

Example Request

{
  "text": "Hello, have a good day.",
  "configs": {
    "model": "mistral"
  }
}

Parrot API

text_embedd_task = parrot.create_text_embedding(text, model)

Response

Returns the ID of the successful task.

{
  "data": {
    "text": "Hello, have a good day!",
    "config": {
      "model": "mistral",
      "task_name": "tasks.parrot_mistral_embeddings_task",
      "task_type": "EMBEDDING"
    },
    "task_id": "1277338fd22f4d25890bfca3e6014ee6"
  },
  "errors": [],
  "error_description": "",
  "start_time": "2024-03-15 20:58:40.044957",
  "end_time": "2024-03-15 20:58:40.065424",
  "host_of_client_call_request": "103.186.100.36",
  "total_time_by_second": 0.020472,
  "status": "success"
}
PreviousModelsNextGet Result

Last updated 1 year ago

Was this helpful?