Skip to main content
POST
Detect Intent

Authorizations

Authorization
string
header
required

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

Body

application/json

Request to detect intent from user input.

Attributes: user_request: The user's natural language request to analyze include_collection_analysis: Whether to analyze existing collections

user_request
string
required

User's natural language request

include_collection_analysis
boolean
default:true

Whether to check existing collections

Response

Successful Response

Result of intent detection analysis.

This model represents the agent's understanding of whether the user wants to:

  • Execute queries on existing data (execution mode)
  • Create new resources/infrastructure (setup mode)
  • Or if the request is ambiguous and needs clarification

Attributes: intent: The detected intent ("execution", "setup", or "ambiguous") confidence: Confidence score 0.0-1.0 reasoning: Explanation of why this intent was detected suitable_collections: Existing collections that might fulfill the request recommended_action: What the agent should do next clarification_needed: Whether to ask user for clarification clarification_options: Options to present if clarification needed keywords_found: Keywords that influenced the classification

intent
string
required

Detected intent: 'execution', 'setup', or 'ambiguous'

Pattern: ^(execution|setup|ambiguous)$
confidence
number
required

Confidence in classification

Required range: 0 <= x <= 1
reasoning
string
required

Why this intent was detected

Next action to take (e.g., 'setup_pipeline', 'execute_retriever')

clarification_needed
boolean
required

Whether to ask user for clarification

suitable_collections
SuitableCollection · object[]

Existing collections that might help

clarification_options
ClarificationOption · object[]

Options for user if clarification needed

keywords_found
Keywords Found · object

Keywords found (setup_keywords, execution_keywords, neutral_keywords)