You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
"description": "Media type (used just to enable compatibility)",
3326
+
"description": "Media type for the response format",
3211
3327
"examples": [
3212
-
"application/json"
3328
+
"application/json",
3329
+
"text/plain"
3213
3330
]
3214
3331
}
3215
3332
},
@@ -3219,7 +3336,7 @@
3219
3336
"query"
3220
3337
],
3221
3338
"title": "QueryRequest",
3222
-
"description": "Model representing a request for the LLM (Language Model).\n\nAttributes:\n query: The query string.\n conversation_id: The optional conversation ID (UUID).\n provider: The optional provider.\n model: The optional model.\n system_prompt: The optional system prompt.\n attachments: The optional attachments.\n no_tools: Whether to bypass all tools and MCP servers (default: False).\n\nExample:\n ```python\n query_request = QueryRequest(query=\"Tell me about Kubernetes\")\n ```",
3339
+
"description": "Model representing a request for the LLM (Language Model).\n\nAttributes:\n query: The query string.\n conversation_id: The optional conversation ID (UUID).\n provider: The optional provider.\n model: The optional model.\n system_prompt: The optional system prompt.\n attachments: The optional attachments.\n no_tools: Whether to bypass all tools and MCP servers (default: False).\n media_type: The optional media type for response format (application/json or text/plain).\n\nExample:\n ```python\n query_request = QueryRequest(query=\"Tell me about Kubernetes\")\n ```",
3223
3340
"examples": [
3224
3341
{
3225
3342
"attachments": [
@@ -3312,17 +3429,69 @@
3312
3429
}
3313
3430
]
3314
3431
]
3432
+
},
3433
+
"truncated": {
3434
+
"type": "boolean",
3435
+
"title": "Truncated",
3436
+
"description": "Whether conversation history was truncated",
3437
+
"default": false,
3438
+
"examples": [
3439
+
false,
3440
+
true
3441
+
]
3442
+
},
3443
+
"input_tokens": {
3444
+
"type": "integer",
3445
+
"title": "Input Tokens",
3446
+
"description": "Number of tokens sent to LLM",
3447
+
"default": 0,
3448
+
"examples": [
3449
+
150,
3450
+
250,
3451
+
500
3452
+
]
3453
+
},
3454
+
"output_tokens": {
3455
+
"type": "integer",
3456
+
"title": "Output Tokens",
3457
+
"description": "Number of tokens received from LLM",
3458
+
"default": 0,
3459
+
"examples": [
3460
+
50,
3461
+
100,
3462
+
200
3463
+
]
3464
+
},
3465
+
"available_quotas": {
3466
+
"additionalProperties": {
3467
+
"type": "integer"
3468
+
},
3469
+
"type": "object",
3470
+
"title": "Available Quotas",
3471
+
"description": "Quota available as measured by all configured quota limiters",
3472
+
"examples": [
3473
+
{
3474
+
"daily": 1000,
3475
+
"monthly": 50000
3476
+
}
3477
+
]
3315
3478
}
3316
3479
},
3317
3480
"type": "object",
3318
3481
"required": [
3319
3482
"response"
3320
3483
],
3321
3484
"title": "QueryResponse",
3322
-
"description": "Model representing LLM response to a query.\n\nAttributes:\n conversation_id: The optional conversation ID (UUID).\n response: The response.\n rag_chunks: List of RAG chunks used to generate the response.\n referenced_documents: The URLs and titles for the documents used to generate the response.\n tool_calls: List of tool calls made during response generation.\nTODO: truncated: Whether conversation history was truncated.\nTODO: input_tokens: Number of tokens sent to LLM.\nTODO: output_tokens: Number of tokens received from LLM.\nTODO: available_quotas: Quota available as measured by all configured quota limiters\n TODO: tool_results: List of tool results.",
3485
+
"description": "Model representing LLM response to a query.\n\nAttributes:\n conversation_id: The optional conversation ID (UUID).\n response: The response.\n rag_chunks: List of RAG chunks used to generate the response.\n referenced_documents: The URLs and titles for the documents used to generate the response.\n tool_calls: List of tool calls made during response generation.\n truncated: Whether conversation history was truncated.\n input_tokens: Number of tokens sent to LLM.\n output_tokens: Number of tokens received from LLM.\n available_quotas: Quota available as measured by all configured quota limiters.",
0 commit comments