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": 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
}
]
}
]
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
}
}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": 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
}
]
}
]
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
}
}Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Chat completion parameters
Name of the video understanding model to use.
nimbus-001 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'
1 elementFilter criteria to constrain search results used in chat
Show child attributes
Filter by file metadata using JSON path expressions
Show child attributes
JSON path on metadata object (e.g. 'my_custom_field', 'category.subcategory')
Comparison operator to apply
NotEqual, Equal, LessThan, GreaterThan, In, ContainsAny, ContainsAll Text value for scalar comparison (used with NotEqual, Equal, LessThan, GreaterThan, In)
Array of values for array comparisons (used with ContainsAny, ContainsAll)
Filter by video information using JSON path expressions
Show child attributes
JSON path on video_info object (e.g. 'has_audio', 'duration_seconds')
Comparison operator to apply
NotEqual, Equal, LessThan, GreaterThan, In, ContainsAny, ContainsAll Text value for scalar comparison (used with NotEqual, Equal, LessThan, GreaterThan, In)
Array of values for array comparisons (used with ContainsAny, ContainsAll)
Filter by file properties using JSON path expressions
Show child attributes
JSON path on file object (e.g. 'uri', 'id', 'filename', 'created_at', 'bytes')
Comparison operator to apply
NotEqual, Equal, LessThan, GreaterThan, In, ContainsAny, ContainsAll Text value for scalar comparison (used with NotEqual, Equal, LessThan, GreaterThan, In)
Array of values for array comparisons (used with ContainsAny, ContainsAll)
Sampling temperature to use, between 0 and 2
0 <= x <= 2Successful response
Unique identifier for this chat completion
Object type, always "chat.completion"
Unix timestamp of when the chat completion was created
The model used for the chat completion
The generated responses
Show child attributes
The index of this choice
The chat message generated by the model
Citations to specific video segments that informed the response
Show child attributes
ID of the collection containing the cited video
ID of the file being cited
ID of the segment being cited
Start time of the cited segment in seconds
End time of the cited segment in seconds
(Deprecated) Relevant text from the segment; use context and relevant_sources instead
Short explanation of the relevance of the segment to the query provided as context
Array of speech transcriptions