Agentic Web Search & URL Fetching π
Open WebUI's web search has evolved from simple result injection to a fully agentic research system. By enabling Native Function Calling (Agentic Mode), you allow quality models to independently explore the web, verify facts, and follow links autonomously.
Agentic web search works best with frontier models like GPT-5, Claude 4.5+, Gemini 3+, or MiniMax M2.1 that can reason about search results and decide when to dig deeper. Small local models may struggle with the multi-step reasoning required.
For comprehensive information about all built-in agentic tools (including web search, knowledge bases, memory, and more), see the Native/Agentic Mode Tools Guide.
Native Mode vs. Traditional RAGβ
| Feature | Traditional RAG (Default) | Agentic Search (Native Mode) |
|---|---|---|
| Search Decision | Open WebUI decides based on prompt analysis. | The Model decides if and when it needs to search. |
| Data Processing | Fetches ALL results, chunks them, and performs RAG. | Returns Snippets directly; no chunking or Vector DB. |
| Link Following | Snippets from top results are injected. | Model uses fetch_url to read a Full Page directly. |
| Model Context | Only gets relevant fragments (Top-K chunks). | Gets the whole text (up to ~50k chars) via fetch_url. |
| Reasoning | Model processes data after system injection. | Model can search, read, check, and search again. |
How to Enable Agentic Behaviorβ
To unlock these features, your model must support native tool calling and have strong reasoning capabilities (e.g., GPT-5, Claude 4.5 Sonnet, Gemini 3 Flash, MiniMax M2.1). Administrator-level configuration for these built-in system tools is handled via the Central Tool Calling Guide.
- Enable Web Search: Ensure a search engine is configured in Admin Panel > Settings > Web Search.
- Enable Native Mode (Agentic Mode):
- Go to Admin Panel > Settings > Models.
- Navigate to Model Specific Settings for your target model.
- Under Advanced Parameters, set Function Calling to
Native.
- Use a Quality Model: Ensure you're using a frontier model with strong reasoning capabilities for best results.
- Chat Features: Ensure the Web Search feature is toggled ON for your chat session.
How Native Tools Handle Data (Agentic Mode)β
π It is important to understand that Native Mode (Agentic Mode) works fundamentally differently from the global "Web Search" toggle found in standard models.
search_web (Snippets only)β
When the model invokes search_web:
- Action: It queries your search engine and receives a list of titles, links, and snippets.
- No RAG: Unlike traditional search, no data is stored in a Vector DB. No chunking or embedding occurs.
- Result: The model sees exactly what a human sees on a search results page. If the snippet contains the answer, the model responds. If not, the model must decide to "deep dive" into a link.
fetch_url (Full Page Context)β
If the model determines that a search snippet is insufficient, it will call fetch_url:
- Direct Access: The tool visits the specific URL and extracts the main text using your configured Web Loader.
- Raw Context: The extracted text is injected directly into the model's context window (hard-coded truncation at exactly 50,000 characters to prevent context overflow).
- Agentic Advantage: Because it doesn't use RAG, the model has the "full picture" of the page rather than isolated fragments. This allows it to follow complex instructions on specific pages (e.g., "Summarize the technical specifications table from this documentation link").
By keeping search_web and fetch_url separate and RAG-free, the model acts as its own Information Retrieval agent, choosing exactly which sources are worth reading in full.
Deep Research & Interleaved Thinking π§ β
Because the model can call search_web multiple times and decide autonomously when to dive deeper, it can perform genuine "Deep Research" using Interleaved Thinking. This creates a powerful research loop where the model acts as its own research assistant.
How Interleaved Thinking Worksβ
Interleaved Thinking is the ability for models to alternate between reasoning and action in a continuous cycle. Instead of searching once and answering, the model can:
π Detailed Research Cycle Example
User asks: "What are the latest security vulnerabilities in the React ecosystem?"
Step 1: Initial Analysis π€
- Model thinks: "I need current information about React security. Let me start with a broad search."
Step 2: First Search π
Model calls: search_web("React security vulnerabilities 2026")
- Receives snippets from 5-10 search results
- Sees references to npm packages and CVE databases
Step 3: Gap Analysis π€
- Model thinks: "The snippets mention CVEs but don't have enough detail. I should fetch a specific security advisory page."
Step 4: Targeted Fetch π
Model calls: fetch_url("https://example.com/react-security-advisory-2026")
- Reads full 50k characters of detailed security documentation
- Identifies specific vulnerability types (XSS, injection, etc.)
Step 5: Refinement π€
- Model thinks: "I found server-side vulnerabilities. Let me search specifically for client-side issues."
Step 6: Refined Search π
Model calls: search_web("React client-side XSS CVE 2026")
- Gets more specific results about cross-site scripting issues
- Identifies mitigation strategies
Step 7: Synthesis π€
- Model thinks: "I now have comprehensive information from multiple authoritative sources. Time to synthesize."
Step 8: Final Answer β
- Provides detailed, grounded response citing multiple sources
- Includes specific CVE numbers, affected versions, and mitigation steps
The Agentic Research Loopβ
The model continuously cycles through these phases until it has sufficient information:
- π€ THINK: Analyze current knowledge gaps and determine what information is missing
- π ACT: Search the web or fetch specific URLs to gather relevant content
- π EVALUATE: Assess the quality and completeness of the information retrieved
- β DECIDE: Determine if more research is needed or if enough context has been gathered
- π ITERATE: If gaps remain, return to step 1 with refined focus and more specific queries
- β SYNTHESIZE: Once sufficient information is gathered, compile and present the final answer
This cycle repeats autonomously until the model has comprehensive, verified information to answer your question with high confidence.
Key Advantagesβ
π― Adaptive Precision: The model doesn't just search once and accept whatever results appear. Instead, it continuously refines its search strategy based on what it discovers. If initial broad searches return surface-level information, the model automatically pivots to more specific technical terms, product names, version numbers, or specialized terminology. Each iteration becomes progressively more targeted, drilling down from general concepts to specific details, ensuring the final answer is both comprehensive and precise.
π Deep Link Following & Discovery: Unlike traditional RAG systems that only use search result snippets, the model can read full pages when snippets aren't sufficient. Even more powerfully, when the model uses fetch_url to read a page, it can discover and follow new URLs mentioned within that content. For example, if a fetched page references a technical specification document, an official changelog, or a related research paper, the model can autonomously call fetch_url again on those discovered URLs to dive even deeper. This creates a natural "web browsing" behavior where the model follows citation chains, explores linked resources, and builds a comprehensive understanding by reading multiple interconnected sourcesβjust like a human researcher would.
β Fact Verification & Cross-Referencing: The model can autonomously verify information by cross-referencing multiple independent sources. If one source makes a claim, the model can search for corroborating evidence from authoritative sources, compare version numbers across official documentation, or validate facts against primary sources. This multi-source verification significantly reduces hallucination and increases answer reliability, as the model builds confidence by finding consistent information across diverse, credible sources.