rag_executeWorkflow

Process user questions by executing a complete RAG workflow: configure setups, generate embeddings, perform semantic searches, and retrieve relevant context chunks for accurate answer generation using Teradata MCP Server.

Instructions

Execute complete RAG workflow to answer user questions based on document context.

This function handles the entire RAG pipeline:

Configuration setup (using configurable values from rag_config.yml)
Store user query (with /rag prefix stripping)
Generate query embeddings (tokenization + embedding)
Perform semantic search against chunk embeddings
Return retrieved context chunks for answer generation

The function uses configuration values from rag_config.yml with fallback defaults.

Arguments: question - user question to process k - number of top-k results to return (optional, uses config default if not provided)

Returns: Returns the top-k most relevant chunks with metadata for context-grounded answer generation.

Input Schema

Name	Required	Description	Default
`k`	No
`question`	Yes

Input Schema (JSON Schema)

{
  "properties": {
    "k": {
      "default": null,
      "title": "K",
      "type": "integer"
    },
    "question": {
      "title": "Question",
      "type": "string"
    }
  },
  "required": [
    "question"
  ],
  "title": "handle_rag_executeWorkflowArguments",
  "type": "object"
}

Teradata MCP Server