Image Caption

Use this API to analyze images and automatically generate captions or descriptive text.

Prerequisites

• You’re familiar with the concepts described on the Platform overview page.
• You have created a memories.ai API key.
• Supported file formats: image/png, image/jpeg

Host URL

• https://security.memories.ai

Endpoints

• POST /v1/understand/uploadImg – Upload image by URL
• POST /v1/understand/uploadImg – Upload image by local file (multipart form)

---

Request Example (Upload by URL)

import requests, json

url = "https://security.memories.ai/v1/understand/uploadImg"
headers = {"Authorization": "<API_KEY>"}

json_body = {
    "url": "https://example.com/test_image.png",
    "user_prompt": "What's happening in this picture?",
    "system_prompt": "You are an image understanding system.",
    "thinking": False
}

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

Replace the following placeholders:

• API_KEY: Your actual memories.ai API key.
• url: Publicly accessible image URL.

---

Request Example (Upload by Local File)

import requests, json

url = "https://security.memories.ai/v1/understand/uploadImg"
headers = {"Authorization": "<API_KEY>"}

data = {
    "user_prompt": "What's happening in this picture?",
    "system_prompt": "You are an image understanding system.",
    "thinking": False
}

files = [
    ("req", ("req.json", json.dumps(data), "application/json")),
    ("file", ("test_image.png", open("test_image.png", "rb"), "image/png"))
]

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

---

Response Example

Status code 200

{
  "code": 0,
  "msg": "success",
  "data": {
    "text": "It shows a person lying on the ground. The person's clothing and posture are indistinct due to the poor image quality. It's impossible to determine if they are injured, unconscious, or simply resting.",
    "token": {
      "input": 273,
      "output": 79,
      "total": 352
    }
  }
}

Response Structure

Name	Type	Required	Description
code	int	Yes	Status code (0 for success, -1 for failure)
msg	string	Yes	Message text
data	object	Yes	Response data
» text	string	Yes	Generated caption or descriptive text
» token	object	Yes	Token usage details
» input	int	Yes	Number of input tokens
» output	int	Yes	Number of output tokens
» total	int	Yes	Total token count

Note: The thinking parameter allows toggling reasoning mode for more detailed responses.