ramene/mae-video-ingestion

Public

0 runs

Run ramene/mae-video-ingestion with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
video_url	string		YouTube URL or direct https .mp4 URL
profile	None	ai-systems-research	Prompt profile (archetype). Determines extraction schema.
chunk_duration_sec	integer	300 Min: 60 Max: 600	Seconds per video chunk (smaller = more chunks, more memory headroom)
video_fps	number	0.5 Min: 0.1 Max: 2	Sample fps per chunk (higher = denser visual capture, more memory)
video_max_pixels	integer	151200 Min: 10000 Max: 500000	Per-frame pixel budget (360*420=151200 default)
max_new_tokens	integer	2048 Min: 512 Max: 8192	Per-chunk LLM output cap
prompt_override	string		Optional: paste custom prompt to bypass PROFILE entirely

{
  "type": "object",
  "title": "Input",
  "required": [
    "video_url"
  ],
  "properties": {
    "profile": {
      "enum": [
        "trading-education",
        "trading-intelligence",
        "general-summary",
        "ai-systems-research",
        "paper-author-talk",
        "coding-tutorial",
        "product-announcement"
      ],
      "type": "string",
      "title": "profile",
      "description": "Prompt profile (archetype). Determines extraction schema.",
      "default": "ai-systems-research",
      "x-order": 1
    },
    "video_fps": {
      "type": "number",
      "title": "Video Fps",
      "default": 0.5,
      "maximum": 2,
      "minimum": 0.1,
      "x-order": 3,
      "description": "Sample fps per chunk (higher = denser visual capture, more memory)"
    },
    "video_url": {
      "type": "string",
      "title": "Video Url",
      "x-order": 0,
      "description": "YouTube URL or direct https .mp4 URL"
    },
    "max_new_tokens": {
      "type": "integer",
      "title": "Max New Tokens",
      "default": 2048,
      "maximum": 8192,
      "minimum": 512,
      "x-order": 5,
      "description": "Per-chunk LLM output cap"
    },
    "prompt_override": {
      "type": "string",
      "title": "Prompt Override",
      "default": "",
      "x-order": 6,
      "description": "Optional: paste custom prompt to bypass PROFILE entirely"
    },
    "video_max_pixels": {
      "type": "integer",
      "title": "Video Max Pixels",
      "default": 151200,
      "maximum": 500000,
      "minimum": 10000,
      "x-order": 4,
      "description": "Per-frame pixel budget (360*420=151200 default)"
    },
    "chunk_duration_sec": {
      "type": "integer",
      "title": "Chunk Duration Sec",
      "default": 300,
      "maximum": 600,
      "minimum": 60,
      "x-order": 2,
      "description": "Seconds per video chunk (smaller = more chunks, more memory headroom)"
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "object",
  "title": "Output",
  "additionalProperties": true
}