Logo IconGuided Mind
v2.4Sign In
RAG Wizard

API Endpoints

Get your API key and choose your integration interface in Step 5 of the wizard.

The final step of the RAG Wizard generates your API key and provides access to your RAG system through three interfaces: REST API, Python SDK, and MCP.

Your API Key

After completing the wizard, you'll receive an API key that starts with rk_. This key authenticates all requests to your RAG project.

rk_12345678_abcdef1234567890abcdef12

Copy your API key now. You won't see it again in full. You can regenerate it from the dashboard if lost.

Storing Your API Key

# .env file (add to .gitignore)
GUIDEDMIND_API_KEY=rk_your_key_here
# Python - read from environment
import os
api_key = os.environ["GUIDEDMIND_API_KEY"]
Do
  • Store in environment variables or secrets manager
  • Use separate keys for dev/staging/production
  • Rotate keys regularly
  • Add .env to .gitignore
Don't
  • Hardcode in source code
  • Commit to version control
  • Share across environments
  • Expose in client-side JavaScript

Choose Your Interface

REST API

Direct HTTP access. Works with any language or tool.

curl -X POST "https://api.guidedmind.ai/rag/search" \
  -H "X-API-Key: rk_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{"query": "What is the return policy?"}'

Available endpoints:

  • POST /rag/search — Search your document index
  • POST /rag/upload — Upload a document
  • POST /rag/upload-and-process — Upload and process immediately
Full API Reference →

Python SDK

Type-safe client with async support and automatic retries.

pip install guidedmind-rag-sdk-python
from guidedmind import Client
 
client = Client()  # reads GUIDEDMIND_API_KEY from env
 
response = client.search(query="What is the return policy?")
for result in response.results:
    print(f"{result.score:.3f}  {result.content[:80]}...")
Python SDK Docs →

MCP (Model Context Protocol)

Integrate with AI agents like Claude Desktop, LangChain, or any MCP-compatible client.

# Connect via SSE
GET /api/v1/mcp/sse?api_key=rk_your_key_here

# Send JSON-RPC messages
POST /api/v1/mcp/messages?session_id=YOUR_SESSION_ID
MCP Integration Docs →

Rate Limiting

All requests are rate-limited based on your subscription plan.

HeaderDescription
X-RateLimit-LimitMax requests per window
X-RateLimit-RemainingRequests left
X-RateLimit-ResetUnix timestamp when limit resets

When rate limited, you'll receive a 429 Too Many Requests response.

Testing Your API

Verify your API key works immediately:

curl -X POST "https://api.guidedmind.ai/rag/search" \
  -H "X-API-Key: rk_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{"query": "test", "options": {"limit": 1}}'

Expected response:

{
  "query": "test",
  "results": [...],
  "metadata": {
    "project_id": 42,
    "project_name": "My RAG Project",
    "processing_time_ms": 150,
    "chunks_retrieved": 1,
    "search_method_used": "hybrid"
  }
}

Managing Your API Key

From the dashboard API Endpoints tab:

  • View — See key prefix and creation date
  • Regenerate — Create a new key (old key is revoked immediately)
  • Revoke — Disable the current key
  • Usage — View request count and rate limit status

Next Steps

← PreviousGraph RAG ConfigNext →Testing & Evaluation