Video Chat

Developer could interact with an LLM AI assistant based on the context of one or multiple videos. By simply providing the videoNos, developers can request the LLM to analyze, summarize, annotate, and more for all uploaded videos. Additionally, this API supports streaming these responses to minimize latency during response generation.

Host URL

• https://mavi-backend.memories.ai

POST /api/serve/video/chat

Request Example

import requests

headers = {"Authorization": token} # access token
data = {
    "videoNos": <list of videoNos>,
    "message": "<your prompt>",
    "history": [],
    "stream": False,
}
response = requests.post(
    "https://mavi-backend.memories.ai/api/serve/video/chat", 
    headers=headers,
    json=data
)

Request Body

{
  "videoNos": [
    "string"
  ],
  "message": "string",
  "history": [
    {
      "robot": "string",
      "user": "string"
    }
  ],
  "stream": true
}

Request Parameters

Name	Location	Type	Required	Description
Authorization	header	string	Yes	authorization token
videoNos	body	[string]	Yes	list of video numbers
message	body	string	Yes	natural language prompt
history	body	[object]	No	list of JSON
» robot	body	string	Yes	historical LLM response
» user	body	string	Yes	historical message sent to LLM
stream	body	boolean	Yes	whether to stream the response

Response Example

Status code 200

{
  "code": "string",
  "msg": "string",
  "data": {
    "msg": "string"
  }
}

Response Result

Status code	Status code msg	Description	Data
200	OK	none	Inline

Response Structure

Status code 200

Name	Type	Required	Restriction	Description
code	string	true	none	response code
msg	string	true	none	message with response code
data	object	true	none	JSON data
» msg	string	true	none	message returned by LLM