Document search with Paradigm (with & without vision)

RAG analysis can be 100% generated with the Paradigm API. It allows users to submit a query, which the system processes to provide relevant answers by leveraging associated documents.

 

This endpoint is useful for:

  • Searching content across multiple documents and scopes.
  • Integrating document search into chat-based workflows.
  • Enabling contextual and scoped responses using specific file or workspace data.

 

Example of API request using the requests package:

 

import requests

url = "https://paradigm.lighton.ai/api/v2"

headers = {
    "Authorization": f"Bearer {api_key}",
    "Content-Type": "application/json"
}

payload = {
    "query": "What is the termination clause in the contract?",
    # Optional parameters (if not filled, same as UI search)
    # "file_ids": ["abc123-file-id"],
    "model": "alfred-4",
    # "workspace_ids": [], # No workspace included
    "company_scope": True, # Documents from the user's company will be added to the scope
    "private_scope": True, # Private documents included
    "tool": "DocumentSearch" # No vision (enter "VisionDocumentSearch" to enable vision)
}

response = requests.post(url, headers=headers, json=payload)

if response.status_code == 200:
    data = response.json()
    print("Answer:", data["answer"])
else:
    print("Error:", response.status_code, response.text)