plano/demos/use_cases/rag_agent/test.rest

@baseUrl = http://0.0.0.0:10502
@model = gpt-4o

# Health Check
GET {{baseUrl}}/health

###

# Test 1: Simple Non-Streaming Chat Completion
POST {{baseUrl}}/v1/chat/completions
Content-Type: application/json

{
  "model": "{{model}}",
  "messages": [
    {
      "role": "user",
      "content": "Hello! Can you help me understand what machine learning is?"
    }
  ]
}

###

# Test 2: Simple Streaming Chat Completion
POST {{baseUrl}}/v1/chat/completions
Content-Type: application/json

{
  "model": "{{model}}",
  "messages": [
    {
      "role": "user",
      "content": "Explain the concept of artificial intelligence in simple terms."
    }
  ],
  "stream": true
}

### Test 3
POST http://localhost:8001/v1/chat/completions
Content-Type: application/json

{
  "model": "{{model}}",
  "messages": [
    {
      "role": "user",
      "content": "What is the guaranteed uptime percentage for TechCorp's cloud services?"
    }
  ],
  "stream": true
}

### send request to context builder agent
POST http://localhost:10501/v1/chat/completions
Content-Type: application/json

{
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "user",
      "content": "What is the guaranteed uptime percentage for TechCorp's cloud services?"
    }
  ]
}

### test fast-llm
POST http://localhost:12000/v1/chat/completions
Content-Type: application/json

{
  "model": "fast-llm",
  "messages": [
    {
      "role": "user",
      "content": "hello"
    }
  ]
}

### test smart-llm
POST http://localhost:12000/v1/chat/completions
Content-Type: application/json

{
  "model": "smart-llm",
  "messages": [
    {
      "role": "user",
      "content": "hello"
    }
  ]
}