Web

Enable agents to search the web and fetch page content

Web capabilities let agents search the internet and fetch page content to answer questions with up-to-date information.

from praisonaiagents import Agent

agent = Agent(
    name="News Agent",
    instructions="Answer with up-to-date web results",
    web="duckduckgo",  # search only — no API key
)
agent.start("What are today's AI headlines?")

Quick Start

1. Enable Web

   from praisonaiagents import Agent
   
   agent = Agent(
       name="Web Agent",
       instructions="You search the web for information",
       web=True  # Enable web search and fetch
   )
   
   agent.start("What are the latest AI news today?")
   
2. With Configuration

   from praisonaiagents import Agent, WebConfig
   
   agent = Agent(
       name="Research Agent",
       instructions="You do thorough web research",
       web=WebConfig(
           search=True,                    # Enable search
           fetch=True,                     # Enable page fetch
           search_provider="duckduckgo",   # Search provider
           max_results=10,                 # Results per search
       )
   )
   

---

Web Features

Web Search

Find relevant pages for a query:

agent = Agent(
    instructions="You answer questions using web search",
    web=WebConfig(search=True)
)

agent.start("What is the current price of Bitcoin?")

Page Fetch

Retrieve full content from URLs:

agent = Agent(
    instructions="You analyze web pages",
    web=WebConfig(fetch=True)
)

agent.start("Summarize the content at https://example.com/article")

---

Configuration Options

from praisonaiagents import WebConfig

config = WebConfig(
    search=True,                    # Enable web search
    fetch=True,                     # Enable page fetch
    search_provider="duckduckgo",   # Search provider
    max_results=5,                  # Max results per search
    search_config={},               # Provider-specific config
    fetch_config={},                # Fetch-specific config
)

Option	Type	Default	Description
search	bool	True	Enable web search
fetch	bool	True	Enable page fetch
search_provider	str	"duckduckgo"	Search provider
max_results	int	5	Results per search
search_config	dict	{}	Provider config
fetch_config	dict	{}	Fetch config

Provider preset strings disable fetch by default. Passing a provider name as a string (e.g. web="duckduckgo", web="tavily") enables search only so the tool set stays compatible with OpenAI models. Enable fetch explicitly with WebConfig(search=True, fetch=True, search_provider="duckduckgo") or use web=True for both.

---

Choosing the right form

Form	Search	Fetch
web="duckduckgo"	✅	❌
web="tavily"	✅	❌
web="google"	✅	❌
web="bing"	✅	❌
web="serper"	✅	❌
web="search_only"	✅	❌
web="fetch_only"	❌	✅
web=True or WebConfig(search=True, fetch=True)	✅	✅

---

Search Providers

Provider	API Key	Best For
duckduckgo	❌ Not needed	General use, free
google	✅ Required	Comprehensive results
tavily	✅ Required	AI-optimized search
serper	✅ Required	Google results API
bing	✅ Required	Microsoft ecosystem

Using Different Providers

# Provider string — search only (default for presets)
agent = Agent(web="duckduckgo")

# Search + fetch explicitly
agent = Agent(
    web=WebConfig(search=True, fetch=True, search_provider="duckduckgo")
)

# DuckDuckGo via WebConfig (search only unless fetch=True)
agent = Agent(
    web=WebConfig(search_provider="duckduckgo")
)

# Tavily (AI-optimized)
agent = Agent(
    web=WebConfig(
        search_provider="tavily",
        search_config={"api_key": "your-key"}
    )
)

# Google
agent = Agent(
    web=WebConfig(
        search_provider="google",
        search_config={
            "api_key": "your-key",
            "cx": "your-search-engine-id"
        }
    )
)

---

How It Works

---

Use Cases

Research

Find and synthesize information from multiple sources

News

Get current events and latest updates

Fact-Checking

Verify claims with web sources

Monitoring

Track topics and get updates

---

Combining with Knowledge

Web search complements local knowledge:

agent = Agent(
    instructions="You answer using docs and web",
    knowledge=["docs/"],  # Local documents
    web=True,             # Web search fallback
)

# Agent checks local docs first, then searches web

---

Best Practices

Use DuckDuckGo for simple needs

Free and requires no API key - good for basic search needs.

Use Tavily for AI applications

Tavily is optimized for AI agents with better structured results.

Limit results for speed

Lower max_results for faster responses when you don’t need many sources.

Combine with knowledge for best results

Use local knowledge for domain-specific info, web for current events.

---

Related

Knowledge

Local document search

RAG

Retrieval augmented generation