Skip to main content
POST
/
chat
/
completions
Generate a model response to a conversation that can include references to video content
curl --request POST \
  --url https://api.cloudglue.dev/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "nimbus-001",
  "messages": [
    {
      "role": "system",
      "content": "<string>",
      "name": "<string>"
    }
  ],
  "collections": [
    "<string>"
  ],
  "filter": {
    "metadata": [
      {
        "path": "<string>",
        "operator": "NotEqual",
        "valueText": "<string>",
        "valueTextArray": [
          "<string>"
        ]
      }
    ],
    "video_info": [
      {
        "path": "<string>",
        "operator": "NotEqual",
        "valueText": "<string>",
        "valueTextArray": [
          "<string>"
        ]
      }
    ],
    "file": [
      {
        "path": "<string>",
        "operator": "NotEqual",
        "valueText": "<string>",
        "valueTextArray": [
          "<string>"
        ]
      }
    ]
  },
  "temperature": 0.7
}
'
{
  "id": "<string>",
  "object": "<string>",
  "created_at": 123,
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "system",
        "content": "<string>",
        "name": "<string>"
      },
      "citations": [
        {
          "collection_id": "<string>",
          "file_id": "<string>",
          "segment_id": "<string>",
          "start_time": "<string>",
          "end_time": "<string>",
          "text": "<string>",
          "context": "<string>",
          "relevant_sources": [
            {
              "text": "<string>"
            }
          ],
          "visual_scene_description": [
            {
              "text": "<string>",
              "start_time": 123,
              "end_time": 123
            }
          ],
          "scene_text": [
            {
              "text": "<string>",
              "start_time": 123,
              "end_time": 123
            }
          ],
          "speech": [
            {
              "speaker": "<string>",
              "text": "<string>",
              "start_time": 123,
              "end_time": 123
            }
          ],
          "audio_description": [
            {
              "text": "<string>",
              "start_time": 123,
              "end_time": 123
            }
          ]
        }
      ]
    }
  ],
  "payload": {
    "messages": [
      {
        "role": "system",
        "content": "<string>",
        "name": "<string>"
      }
    ],
    "temperature": 123,
    "filter": {
      "metadata": [
        {
          "path": "<string>",
          "operator": "NotEqual",
          "valueText": "<string>",
          "valueTextArray": [
            "<string>"
          ],
          "scope": "file"
        }
      ],
      "video_info": [
        {
          "path": "duration_seconds",
          "operator": "NotEqual",
          "valueText": "<string>",
          "valueTextArray": [
            "<string>"
          ]
        }
      ],
      "file": [
        {
          "path": "bytes",
          "operator": "NotEqual",
          "valueText": "<string>",
          "valueTextArray": [
            "<string>"
          ]
        }
      ]
    },
    "collections": [
      "3c90c3cc-0d44-4b50-8888-8dd25736052a"
    ]
  },
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123
  }
}

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Chat completion parameters

model
enum<string>
required

Name of the video understanding model to use.

Available options:
nimbus-001
messages
object[]
required

A list of messages comprising the conversation so far

collections
string[]
required

List of collection IDs to use as context for the chat.

Note that 'nimbus-001' only supports collections with collection_type 'media-descriptions' or 'rich-transcripts'

Required array length: 1 element
filter
object

Filter criteria to constrain search results used in chat

temperature
number
default:0.7

Sampling temperature to use, between 0 and 2

Required range: 0 <= x <= 2

Response

Successful response

id
string

Unique identifier for this chat completion

object
string

Object type, always "chat.completion"

created_at
integer

Unix timestamp in milliseconds when the chat completion was created

model
string

The model used for the chat completion

choices
object[]

The generated responses

payload
object
usage
object

Usage statistics for the completion request