Search-Enabled Agents

payload = {
    "agent_config": {
        "agent_name": "Current Events Researcher",
        "description": "Specializes in current events and breaking news",
        "system_prompt": "You research current events and provide factual summaries.",
        "model_name": "gpt-4.1",
        "max_tokens": 2048
    },
    "task": "Summarize the latest developments in climate change policy.",
    "tools_enabled": ["auto_search"]
}

payload = {
    "agent_config": {
        "agent_name": "Market Researcher",
        "description": "Market trends and competitive analysis",
        "system_prompt": "You analyze market trends and provide competitive intelligence.",
        "model_name": "gpt-4.1",
        "max_tokens": 4096
    },
    "task": "What are the current market trends in electric vehicles?",
    "tools_enabled": ["auto_search"]
}

payload = {
    "agent_config": {
        "agent_name": "Technical Researcher",
        "description": "Research latest technical developments",
        "system_prompt": "You research technical topics and explain complex concepts.",
        "model_name": "gpt-4.1",
        "max_tokens": 4096
    },
    "task": "What are the latest advancements in machine learning algorithms?",
    "tools_enabled": ["auto_search"]
}

payload = {
    "agent_config": {
        "agent_name": "Product Researcher",
        "description": "Product reviews and comparisons",
        "system_prompt": "You research products and provide detailed comparisons.",
        "model_name": "gpt-4.1",
        "max_tokens": 2048
    },
    "task": "Compare the latest smartphones from different manufacturers.",
    "tools_enabled": ["auto_search"]
}

payload = {
    "agent_config": {
        "agent_name": "Fact Checker",
        "description": "Verifies information with reliable sources",
        "system_prompt": "You verify facts and cite reliable sources.",
        "model_name": "gpt-4.1",
        "max_tokens": 2048
    },
    "task": "Verify the accuracy of recent claims about renewable energy adoption rates.",
    "tools_enabled": ["auto_search"]
}

payload = {
    "agent_config": {
        "agent_name": "Recent News Analyst",
        "description": "Focuses on the most recent information",
        "system_prompt": "You prioritize the most recent and relevant information.",
        "model_name": "gpt-4.1",
        "max_tokens": 2048
    },
    "task": "What are the most recent developments in space exploration from the past week?",
    "tools_enabled": ["auto_search"]
}

payload = {
    "agent_config": {
        "agent_name": "Research Conversationalist",
        "description": "Maintains context while researching",
        "system_prompt": "You maintain conversation context while researching current information.",
        "model_name": "gpt-4.1",
        "max_tokens": 4096
    },
    "task": "Based on our previous discussion about AI, what are the latest regulatory developments?",
    "tools_enabled": ["auto_search"],
    "history": {
        "previous_context": {
            "role": "user",
            "content": "Tell me about AI safety concerns"
        },
        "ai_response": {
            "role": "assistant",
            "content": "AI safety involves alignment, robustness, and ethical considerations..."
        }
    }
}

try:
    response = requests.post(
        f"{BASE_URL}/v1/agent/completions",
        headers=headers,
        json=payload,
        timeout=60
    )

    if response.status_code == 200:
        result = response.json()
        print("Search Results:", result['outputs'])

    elif response.status_code == 429:
        print("Rate limit exceeded for search operations")
    else:
        print(f"Search error: {response.status_code} - {response.text}")

except requests.exceptions.Timeout:
    print("Search request timed out")
except requests.exceptions.ConnectionError:
    print("Failed to connect to search service")
except Exception as e:
    print(f"Search integration error: {e}")

{
  "job_id": "agent-09a9c0f9ba19419abf64f5538b4b7d59",
  "success": true,
  "name": "Research Assistant",
  "outputs": [
    {
      "role": "Research Assistant",
      "content": "Comprehensive analysis based on current web data...",
      "timestamp": "2026-02-05T00:58:15.121915",
      "message_id": "85b70f9d-e281-4a98-b9ad-5a2d39f8ffcb"
    }
  ],
  "usage": {
    "input_tokens": 150,
    "output_tokens": 300,
    "total_tokens": 450,
    "img_cost": 0.0,
    "total_cost": 0.006525
  },
  "timestamp": "2026-02-05T00:58:15.252392+00:00"
}

import time

def search_with_backoff(payload, max_retries=3):
    for attempt in range(max_retries):
        response = requests.post(f"{BASE_URL}/v1/agent/completions", json=payload, headers=headers)

        if response.status_code == 429:
            wait_time = 2 ** attempt  # Exponential backoff
            print(f"Rate limited, waiting {wait_time} seconds...")
            time.sleep(wait_time)
            continue

        return response

    raise Exception("Max retries exceeded for search request")