Core Resources
Turn
A Turn is a series of Messages and Annotations that are relevant to the Turn.
Turns are distinct breaks between messages in a Thread. Turns contain a user message and any LLM response(s) to that user message.
Annotations at the Turn level apply to group of Messages in that turn. For example, the annotation for message preference is at the turn level.
The schema is of type object
.
Copy
Ask AI
{
"id": "turn_abc123",
"messages": [
{
"role": "system",
"content": {
"text": "<string>",
"reference_texts": [
{
"content": "<string>",
"category": "<string>",
"url": "<string>"
}
],
"attachments": [
{
"content": "aSDinaTvuI8gbWludGxpZnk=",
"mime_type": "text/plain",
"scale_url": "<string>",
"url": "<string>",
"name": "<string>"
}
],
"chunks": [
{
"type": "<string>",
"annotations": [
{
"id": "an_abc123efg456",
"key": "formatting",
"type": "<string>",
"title": "Response Formatting",
"description": "Does the response contain issues with formatting?",
"labels": [
"Major Issues",
"Minor Issues",
"No Issues"
],
"metadata": {
"criteria": "overall_quality"
},
"value": 3,
"possible_values": [
[
1,
2,
3
]
]
}
],
"text": "<string>"
}
],
"reasoning": [
{
"content": "<string>"
}
]
},
"source_id": "source_abc123",
"model_parameters": {
"model": "my-model-123",
"temperature": 0.9,
"max_completion_tokens": 1000,
"top_p": 0.9,
"top_k": 4
},
"annotations": [
{
"id": "an_abc123efg456",
"key": "formatting",
"type": "<string>",
"title": "Response Formatting",
"description": "Does the response contain issues with formatting?",
"labels": [
"Major Issues",
"Minor Issues",
"No Issues"
],
"metadata": {
"criteria": "overall_quality"
},
"value": 3,
"possible_values": [
[
1,
2,
3
]
]
}
]
}
],
"annotations": [
{
"id": "an_abc123efg456",
"key": "formatting",
"type": "<string>",
"title": "Response Formatting",
"description": "Does the response contain issues with formatting?",
"labels": [
"Major Issues",
"Minor Issues",
"No Issues"
],
"metadata": {
"criteria": "overall_quality"
},
"value": 3,
"possible_values": [
[
1,
2,
3
]
]
}
]
}
Assistant
Responses are generated using AI and may contain mistakes.