Skip to main content

Web Search Tool

Search the internet for current information using Brave Search.

Overview​

The web search tool lets AI access real-time information from the internet. It uses Brave Search for fast, accurate results.

Configuration​

Set up Brave Search API key:

# In .env file
BRAVE_SEARCH_API_KEY=your-brave-search-api-key

Get your API key from Brave Search.

Parameters​

ParameterTypeRequiredDefaultDescription
querystringYes-Search query text
countintegerNo5Number of results
time_rangestringNono_limitTime filter: day, week, month, year

Usage Examples​

import requests

response = requests.post(
    "http://localhost/api/v1/agent/tool-calling",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "tool_name": "web_search",
        "parameters": {
            "query": "latest AI developments 2024",
            "count": 5
        }
    }
)

results = response.json()["results"]
for result in results:
    print(f"Title: {result['title']}")
    print(f"URL: {result['url']}")
    print(f"Snippet: {result['snippet']}\n")

Search with Time Filter​

response = requests.post(
    "http://localhost/api/v1/agent/tool-calling",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "tool_name": "web_search",
        "parameters": {
            "query": "tech news",
            "count": 10,
            "time_range": "week"
        }
    }
)

results = response.json()["results"]
print(f"Found {len(results)} results from the past week")

Search for Current Events​

response = requests.post(
    "http://localhost/api/v1/agent/tool-calling",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "tool_name": "web_search",
        "parameters": {
            "query": "today's stock market",
            "count": 5,
            "time_range": "day"
        }
    }
)

Use in Agent​

# Create agent with web search
response = requests.post(
    "http://localhost/api/v1/agent/configs",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "name": "research_agent",
        "system_prompt": "You are a research assistant. Use web search to find current information and real-time data.",
        "model": "gpt-4",
        "builtin_tools": ["web_search"],
        "tool_config": {
            "web_search": {
                "count": 10,
                "time_range": "week"
            }
        },
        "tool_choice": "auto",
        "max_iterations": 3
    }
)

agent_id = response.json()["id"]

# Chat with agent
chat_response = requests.post(
    "http://localhost/api/v1/agent/chat",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "agent_id": agent_id,
        "message": "What are the latest developments in AI?"
    }
)

result = chat_response.json()
print(f"Response: {result['response']}")
print(f"Sources used: {[t.get('result', {}).get('url', '') for t in result.get('tool_calls', [])]}")

JavaScript Usage​

const response = await fetch('http://localhost/api/v1/agent/tool-calling', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    tool_name: 'web_search',
    parameters: {
      query: 'latest AI developments',
      count: 5,
      time_range: 'week'
    }
  })
});

const results = await response.json();
results.results.forEach(result => {
  console.log(`Title: ${result.title}`);
  console.log(`URL: ${result.url}`);
  console.log(`Snippet: ${result.snippet}\n`);
});

cURL Usage​

curl -X POST http://localhost/api/v1/agent/tool-calling \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tool_name": "web_search",
    "parameters": {
      "query": "AI regulation news 2024",
      "count": 10,
      "time_range": "month"
    }
  }'

Response Format​

{
  "results": [
    {
      "title": "Latest AI Regulations in 2024",
      "url": "https://example.com/ai-regulations",
      "snippet": "Breaking news about AI regulations...",
      "published_date": "2024-01-15"
    }
  ]
}

Time Range Options​

Time RangeDescription
dayResults from the last 24 hours
weekResults from the last 7 days
monthResults from the last 30 days
yearResults from the last 365 days
no_limitNo time filter (default)

Use Cases​

Research​

# Research recent developments
query = "AI regulation developments 2024"
time_range = "month"

Current Events​

# Get today's news
query = "breaking news today"
time_range = "day"
# Find trending topics
query = "trending technology topics"
time_range = "week"

Price Updates​

# Check current prices
query = "iPhone 15 price today"
time_range = "day"

Best Practices​

Query Quality​

Good QueriesPoor Queries
"What are the latest AI regulations?""AI regulations"
"Current stock price of AAPL""AAPL price"
"Breaking news about tech today""tech news"
"Recent developments in quantum computing""quantum computing"

Time Range Selection​

  • Use day for time-sensitive queries (prices, breaking news)
  • Use week for recent developments
  • Use month for broader research
  • Use no_limit for general queries

Result Count​

  • Use 3-5 for quick answers
  • Use 10-15 for comprehensive research
  • Use 20-30 for extensive research

Troubleshooting​

API Key Not Configured​

Problem: {"error": "BRAVE_SEARCH_API_KEY not configured"}

Solution:

  • Set BRAVE_SEARCH_API_KEY in .env file
  • Restart Enclava service
  • Verify API key is valid

Rate Limiting​

Problem: Too many search requests

Solution:

  • Reduce search frequency
  • Implement caching
  • Upgrade API tier if needed
  • Use longer time ranges

No Relevant Results​

Problem: Search returns irrelevant results

Solution:

  • Refine query terms
  • Add more specific keywords
  • Try different time range
  • Increase result count

Best Practices​

  1. Be specific - Use detailed, precise queries
  2. Set time range - Use appropriate time filters
  3. Limit results - Don't fetch unnecessary data
  4. Cache results - Store frequent searches
  5. Monitor usage - Track API costs and quota

Next Steps​