yahboom
HomeTutorialsProduct
Solution
Blog
Online Store
About Us
EN/中文
Store
Jetson Orin NANO Developer Kit📖
01.Get started
  • 01. Learning route
  • 02. Get started quickly
  • 03. System Update Notes
  • 04. Disabling automatic updates and troubleshooting issues
  • 05. Jetson Orin Nano official kit screwdriver instructions
02.Jetson basic course
  • 01.Jetson board introduction
  • 02.Write Jetson original system
  • 03.Installing Jetson environment
  • 04.Backup SSD system
  • 05.Restore initial image system
  • 06.Upgrade to SUPER version (Optional)
  • 07.Write SUPER boot (Must read)
  • 08.SSD expansion
  • 09.Jetpack old system upgraded to Yahboom SUPER factory system
  • 10.Write the system onto your own SSD
03.Basic setting course
  • 01.Basic knowledge
  • 02.Network configuration
  • 03.SSH remote login
  • 04.VNC remote control
  • 05.RDP remote control
  • 06.Remote file transfer
  • 07.Jtop tool
  • 08.Exchange space expansion
  • 09.Use VSCode
  • 10.Use VMware
  • 11.Modify screen resolution
04.GPIO control course
  • 01.GPIO description
  • 02.GPIO library installation
  • 03.GPIO reading
  • 04.GPIO output
  • 05.Serial communication
  • 06.I2C communication
05.Vision basic course
  • 01.CSI camera preview
  • 02.USB camera preview
  • 03.Use Jupyter Lab
  • 04.Use JetCam
06.OpenCV basic course
  • 01.Image reading
  • 02.Image saving
  • 03.Image modification
  • 04.Image scaling
  • 05.Image cropping
  • 06.Image translation
  • 07.Image mirroring
  • 08.Image grayscale conversion
  • 09.Image binarization
  • 10.Image edge detection
  • 11.Add line segments
  • 12.Add rectangles
  • 13.Add circular shape
  • 14.Add ellipses
  • 15.Add polygons
  • 16.Add Text
  • 17.Preview USB camera image
  • 18.Preview CSI camera image
07.Vision advanced course
01.Environment construction
  • 01.TensorFlow
  • 02.PyTorch
  • 03.Torchvision
02.DeepStream development
  • 01.DeepStream environment
  • 02.License plate detection and recognition
  • 03.Parallel multi-model inference
  • 04.Object embedding vector generation
  • 05.Pose recognition
  • 06.NV optical flow anomaly detection
  • 07.Single-view 3D tracking
  • 08.Multi-view 3D tracking
03.NVIDIA TAO toolkit application
  • 01.Traffic scene object detection
  • 02.Person object detection
  • 03.Vehicle brand classification
  • 04.Vehicle model classification
  • 05.License plate detection and recognition
  • 06.Person semantic segmentation
  • 07.Retail product detection and recognition
  • 08.Person feature extraction and matching (ReID)
  • 09.Person action and pose classification
  • 10.Transformer-based person detection
  • 11.3D human skeleton detection
  • 12.LiDAR 3D point cloud detection
04.YOLO11 development
  • 01.YOLO environment construction
  • 02.CLI use
  • 03.Object detection
  • 04.Instance segmentation
  • 05.Pose estimation
  • 06.Image classification
  • 07.Oriented object detection
  • 08.Model conversion
  • 09.Dataset annotation
  • 10.Model training conversion
  • 11.Model prediction
05.Mediapipe development
  • 01.Mediapipe environment
  • 02.Hand detection
  • 03.Face detection
  • 04.Face effects
  • 05.3D object recognition
  • 06.Virtual brush
  • 07.Gesture recognition
  • 08.Finger control
  • 09.Posture estimation
  • 10.Face mask
  • 11.Overall detection
  • 12.Green scene removal(Human)
06.YOLO26 development
  • 01.YOLO environment construction
  • 02.CLI use
  • 03.Object detection
  • 04.Instance segmentation
  • 05.Pose estimation
  • 06.Image classification
  • 07.Oriented object detection
  • 08.Model conversion
  • 09.Dataset annotation
  • 10.Model training conversion
  • 11.Model prediction
07.QR code recognition
  • QR code recognition
08.Docker basic course
  • 01.Docker introduction
  • 02.Docker installation
  • 03.Docker command
  • 04.Docker usage
  • 05.Docker interaction
09.ROS2-Jazzy
01.ROS2 basic course
  • 1.Introduction to ROS2
  • 2.ROS2 install Jazzy
  • 3.ROS2 development environment
  • 4.ROS2 workspace
  • 5.ROS2 function package
  • 6.ROS2 node
  • 7.ROS2 topic communication
  • 8.ROS2 service communication
  • 9.ROS2 action communication
  • 10.ROS2 custom interface message
  • 11.ROS2 parameter service case
  • 12.ROS2 meta-function package
  • 13.ROS2 distributed communication
  • 14.ROS2 DDS
  • 15.ROS2 time related API
  • 16.ROS2 common command tools
  • 17.ROS2 rviz2 use
  • 18.ROS2 rqt toolbox
  • 19.ROS2 Launch startup file configuration
  • 20.ROS2 recording and playback tool
  • 21.ROS2 URDF model
  • 22.ROS2 Gazebo simulation platform
  • 23.ROS2 TF2 coordinate transformation
02.ROS2 vision course
  • 01.Camera preview (USB)
  • 02.Camera preview (CSI)
  • 03.Camera calibration (USB)
  • 04.Camera calibration (CSI)
  • 05.AR vision (USB)
  • 06.AR vision (CSI)
10.Large model basic course
01.Offline large model
  • 01.AI large model environment deployment
  • 02.Install large model dialogue platform
  • 03.Meta AI - Llama model
  • 04.Alibaba Cloud - Qwen model
  • 05.Microsoft - Phi-4-mini model
  • 06.DeepSeek - DeepSeek model
  • 07.Alibaba Cloud - Qwen-VL visual multimodal large model
  • 08.Google - Gemma visual multimodal large model
  • 9.Llava visual multimodal large model
  • 10.MiniCPM-V visual multimodal large model
  • 11.High-quality vision-language grounding (LocateAnything)
02.Online large model
  • 01.Tongyi Qianwen large model
  • 02.OpenRouter large model API aggregation platform
11.Large model application practice
01.Voice interaction application
  • 1.Voice interaction hardware connection (Must read)
  • 2.Offline speech to text (ASR)
  • 3.Offline text to speech (TTS)
  • 4.AI large model voice interaction
  • 5.AI large model offline voice assistant
02.Multimodal large model application (Online_Offline large model + Text_Voice interaction)
  • 01.Multimodal visual understand application
  • 02.Multimodal text image application
  • 03.Multimodal video analysis application
  • 04.Multi module visual position application
  • 05.Multimodal table scanning application
  • 06.Multimodal autonomous agent application
12.NVIDIA Isaac ROS course
  • 01.Build Isaac ROS environment
  • 02.Deep segmentation
  • 03.DNN stereoscopic depth
  • 04.Free space segmentation
  • 05.Image distortion processing
  • 06.Image segmentation
  • 07.3D scene reconstruction and mapping
  • 08.Object detection
  • 09.3D attitude estimation
  • 10.Visual SLAM
13.OpenClaw deployment and basic usage
01.OpenClaw deployment and introduction
  • 01.Quick start with the pre-configured environment (Recommended)
  • 02.OpenClaw Deployment
  • 03.OpenClaw WhatsApp Plugin Application
  • 04.OpenClaw WebChat Interaction
  • 05.OpenClaw TUI Interaction
  • 06.OpenClaw Tools Introduction
  • 07.OpenClawGate Gateway User Manual
  • 08.OpenClaw Features Overview
  • 09.OpenClawHub Introduction (Skill Installation)
02.OpenClaw basic application
  • 01.OpenClaw Application - File Management
  • 02.OpenClaw Application - Camera
  • 03.OpenClaw Application - Browser Control
  • 04.OpenClaw Application - Script Execution
  • 05.OpenClaw Application - AI Programming (Peripheral & GPIO Control)
  • 06.OpenClaw Application - Dedicated AI Assistant
  • 07.OpenClaw Web Search Capability Configuration
03.NVIDIA official Agent Skills application
  • 01.AI-assisted development with VS Code or Cursor
  • 02.Jetson device skills
  • 03.Jetson BSP custom agent skills
14.OpenClaw advanced development
01.Preparation Before Use
  • 01.Peripheral Hardware Configuration
  • 02.OpenClaw API-KEY Configuration
  • 03.OpenClaw Model Switching
  • 04.OpenClaw Prompts
  • 05.AI Voice Interaction Configuration
  • 06.Three Dialogue Configuration Tests
02.OpenClaw AI Programming Peripheral Control
  • 1. Servo Control
  • 2. RGB Strip
  • 3. OLED Display
  • 4. Temperature and Humidity Sensor
  • 5. Camera Application
  • 6. AI Script Peripheral Control
03.OpenClaw Peripheral Integration Applications
  • 1. Plant Care Assistant
  • 2. AI Calorie Estimation
  • 3. AI Rock Paper Scissors Game
  • 4. AI Pet
  • 5. AI Weather Station
  • 6. Temperature Humidity Dashboard
  • 7. Scheduled Tasks
Download
  • System_File
  • VMFile_BootFile
  • 3D Model File
  • DataSheet
  • Software_Tools
  • Code
  • Manual
Download ZIP

Welcome to Jetson Orin NANO Developer Kit repository

07.OpenClaw Web Search Capability Configuration

Configuring Web Search Capabilities

Why Configure Web Search Capabilities?

While OpenClaw's local models are powerful, their knowledge is static, containing only the data available at the time of their training. This means:

  • ❌ They cannot answer questions about the latest news and events.

  • ❌ They do not know what the weather is like today.

  • ❌ They cannot look up specific information on demand.

  • ❌ They cannot access the most up-to-date technical documentation.

By configuring web search capabilities, OpenClaw can:

  • ✅ Search the internet for information in real-time.

  • ✅ Retrieve the latest news and updates.

  • ✅ Query real-time data (weather, stock prices, etc.).

  • ✅ Access the newest technical documentation and tutorials.

  • ✅ Conduct in-depth research and fact-checking.

In this section, we will configure OpenClaw's web search capabilities. OpenClaw supports various search engines; the default web_search tool utilizes the Brave API. However, as of the publication of this tutorial, the Brave API has discontinued its free tier; therefore, we will use Tavily Web Search as an alternative.

Tavily Web Search is a search engine specifically optimized for AI agents, providing structured search results.

Prerequisites

Before you begin, please ensure the following:

  1. ✅ OpenClaw is installed and running correctly.

  2. ✅ At least one model (either a local Ollama model or a cloud-based model) has been configured.

  3. ✅ You have an active internet connection.

  4. ✅ You have a valid email address (required to register for Tavily).

Step 1: Obtain a Tavily API Key

Tavily is an AI-optimized search engine that offers a free usage tier, providing 1,000 free searches per month—which is more than sufficient for typical daily use. (Policies are subject to change; specific quotas are based on actual limits.)

1.1 Visit the Tavily Website

Open the following URL in your browser: https://tavily.com

Visit the Tavily Website

1.2 Sign Up for an Account

Click the "Sign Up" or "Register" button on the page:

image-20260310205926352

Fill in your registration details:

  • Email Address: Enter your valid email address.

  • Code: The graphical verification code.

Click "Continue" to create your account.

1.3 Verify Your Email

Tavily will send a verification email to your inbox. Open your email client, locate the email from Tavily, and click the verification link. Once successfully verified, you will be automatically redirected to the Tavily dashboard.

 

1.4 Obtain Your API Key

After logging in, navigate to the "API Keys" page:

image-20260310210402296

You will see an API key displayed, formatted similarly to this:

tvly-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

⚠️ Important Note:

  • Please keep this key secure and do not share it with anyone else.

  • Do not commit this key to code repositories or public platforms.

Copy this API key; we will need it later.

image-20260310210643258

Step 2: Install the Tavily Web Search Skill

OpenClaw uses ClawHub to manage skills; we can install this plugin directly by interacting with OpenClaw via chat.

2.1 Open the Terminal

Open a terminal window on your Jetson device. (For the Jetson Nano, you must enter the Docker container environment.) Ensure that you have a terminal window open with the openclaw gateway running.

2.2 Installing Skills

Before installing any skills, you first need to log in to ClawHub. This is an open-source distribution hub for OpenClaw skills—think of it as an "App Store" for your mobile device.

If you do not log in, you may encounter download speed limitations when attempting to download skills.

Open a terminal window and enter the following command:

xxxxxxxxxx
npm i -g clawhub

Next, visit the official ClawHub website at https://clawhub.ai/ and click to log in using your GitHub account. (You must be logged into GitHub beforehand; we will not demonstrate that step here. To ensure you can proceed even if you encounter network issues preventing access to GitHub, we have pre-installed this specific skill in the factory-provided system image. You may therefore skip directly to Step 3: Configuring API Keys.)

image-20260310215246202

You will be redirected to an authorization page; click "Authorize" to proceed.

image-20260310215313331

Click on your username, then click "Settings."

image-20260310215334012

Scroll down to the "API tokens" section and click "Create token."

image-20260310215430372

Copy the generated token. —which you will need to use below:

image-20260310215453992

Next, run the following command on your server, replacing the placeholder with the Token you just copied. Note that there is a space following --token.

xxxxxxxxxx
clawhub login --token YourToken

You should see a confirmation indicating that the login was successful:

image-20260310215817395

 

Next, we need to install the tavily-web-search Skill. While there are several ways to do this, we will use a common, general-purpose method here: enter the following command in your terminal:

xxxxxxxxxx
npx clawhub@latest install tavily-search

If you encounter a ✖ Rate limit exceeded error, it indicates that there was an issue with the login step you performed earlier; please attempt to log in again.

 

2.3 Verifying the Installation

To view a list of your installed skills, run the following command:

xxxxxxxxxx
npx clawhub@latest list

image-20260311100958972

You should now be able to see tavily-web-search listed among the installed skills.

Step 3: Configure API Key

Now we need to configure the Tavily API key within OpenClaw.

3.1 Method 1: Temporary Configuration via Environment Variables

Set the environment variable in your terminal:

xxxxxxxxxx
export TAVILY_API_KEY=tvly-your-api-key-here

Note: Replace tvly-your-api-key-here with the actual API key you obtained in Step 1.

3.2 Method 2: Making Environment Variables Permanent

If you want the API key to be set automatically every time you launch your terminal, you can add it to your shell configuration file.

For Bash Users:

xxxxxxxxxx
echo 'export TAVILY_API_KEY=tvly-your-api-key-here' >> ~/.bashrc
source ~/.bashrc

3.3 Apply Changes

Restart the OpenClaw Gateway to apply the configuration:

xxxxxxxxxx
openclaw gateway restart

Step 4: Test the Web Search Functionality

Now, let's test whether the web search feature is working correctly.

4.1 Test Using the TUI

Launch the TUI in your terminal:

xxxxxxxxxx
openclaw tui

image-20260311170619242

Then, tell OpenClaw what your API key is:

“This is my tavily key: tvlxxxxxxxxxxxxxxxxxx”

image-20260326171351128

4.2 Test Basic Search

In the TUI, enter a query that requires up-to-date information—for example:

xxxxxxxxxx
What are the major news headlines today?

image-20260311170722651

OpenClaw will:

  1. Identify when the latest information needs to be searched for.

  2. Call the Tavily API to perform the search.

  3. Retrieve the search results.

  4. Answer your question based on the search results.

 

 

Advanced Usage Tips

Tip 1: Restricting Search Sources

If you only want to search for content on specific websites:

xxxxxxxxxx
Search only within MDN documentation: CSS Flexbox usage

image-20260311171033053

Tip 2: Retrieving Original Content

If you need to retrieve the full content of a webpage:

xxxxxxxxxx
Extract the full content of this page and summarize it: [https://www.yahboom.com/study/K230]

image-20260311171351907

 

Frequently Asked Questions

Question 1: Search returns "Invalid API Key" error

Error Message:

xxxxxxxxxx
Error: Invalid API key

Possible Causes:

  1. The API key was entered incorrectly.

  2. The environment variable was not set correctly.

  3. The API key has expired.

Solution:

  1. Check if the API key was copied correctly:

xxxxxxxxxx
echo $TAVILY_API_KEY
  1. Reset the environment variable:

xxxxxxxxxx
export TAVILY_API_KEY=tvly-your-api-key-here
  1. If the key has expired, log in to the official Tavily website to obtain a new one.

Question 2: Search yields no results

Symptoms: After sending a search request, the AI ​​responds with "Unable to find relevant information."

Possible Causes:

  1. Network connection issues.

  2. The Tavily service is temporarily unavailable.

  3. Search keywords are too vague

Solution:

  1. Check network connection:

xxxxxxxxxx
ping tavily.com
  1. Try more specific search keywords

  2. Try again later

Issue 3: Search is very slow

Symptoms: Search requests take a long time to return results

Possible Causes:

  1. Deep search mode is being used

  2. High network latency

  3. High load on Tavily servers

Solution:

  1. Use fast search mode:

xxxxxxxxxx
Fast Search: [Your Query]
  1. Check network speed:

xxxxxxxxxx
curl -o /dev/null -s -w "%{time_total}\n" https://tavily.com
  1. If it remains slow, try switching to a different network environment

Issue 4: Quota exhausted

Error Message:

xxxxxxxxxx
Error: API quota exceeded

Possible Cause: The free quota (1,000 requests per month) has been exhausted

Solution:

  1. Log in to the Tavily console to check usage

  2. Wait for the quota to reset next month

Issue 5: Skill installation failed

Error Message:

xxxxxxxxxx
Error: Failed to install skill

Possible Causes:

  1. Network connection issues

  2. Outdated npm version

  3. Insufficient permissions (rate-limited because you are not logged in)

Solution:

  1. Check network connection

  2. Update npm:

xxxxxxxxxx
npm install -g npm@latest
  1. Install with sudo privileges (if necessary):

xxxxxxxxxx
sudo npx clawhub@latest install tavily-web-search

Search Mode Comparison

ModeSpeed ​​CoverageUse CaseExample
Basic Mode1-2 secondsGoodQuick fact-checking, simple searches"What is the weather like today?"
Advanced Mode5-10 secondsExcellentComplex research, comprehensive answers"Compare the pros and cons of two technologies"
News Mode2-3 secondsLast 7 daysCurrent events, Breaking news"What's the latest tech news?"

Best Practices

1. Use Search Quotas Wisely

  • ✅ Prioritize using the "Quick Search" mode.

  • ✅ Avoid repeatedly searching for the same content.

  • ✅ Leverage the AI's memory capabilities to avoid redundant queries.

  • ❌ Do not frequently test the search functionality.

2. Optimize Search Keywords

  • ✅ Use specific and precise questions.

  • ✅ Include key information (time, location, subject).

  • ✅ Describe your needs using natural language.

  • ❌ Avoid overly vague queries.

3. Verify Search Results

  • ✅ Cross-reference important information.

  • ✅ Check the reliability of the search result sources.

  • ✅ Pay attention to the timeliness of the information.

  • ❌ Do not rely entirely on a single source.

4. Combine with Local Knowledge

  • ✅ For static knowledge, prioritize using local models.

  • ✅ For dynamic information, use web search.

  • ✅ Combine both approaches to obtain the best answers.

  • ❌ Do not use search for every single question.

Advanced Configuration

Configuration 1: Adjust Search Depth

In the OpenClaw configuration file, you can adjust the default search depth:

xxxxxxxxxx
{
  "skills": {
    "entries": {
      "tavily-web-search": {
        "enabled": true,
        "apiKey": "tvly-your-api-key-here",
        "config": {
          "searchDepth": "basic",
          "maxResults": 10,
          "includeAnswer": true,
          "includeRawContent": false
        }
      }
    }
  }
}

Configuration Details:

  • searchDepth: basic or advanced

  • maxResults: The maximum number of results to return (1-10)

  • includeAnswer: Whether to include an AI-generated answer summary

  • includeRawContent: Whether to include the raw page content

Configuration 2: Set Domain Filters

If you only want to search for content on specific websites:

xxxxxxxxxx
{
  "skills": {
    "entries": {
      "tavily-web-search": {
        "enabled": true,
        "apiKey": "tvly-your-api-key-here",
        "config": {
          "includeDomains": ["github.com", "stackoverflow.com"],
          "excludeDomains": ["ads.example.com"]
        }
      }
    }
  }
}

Configuration 3: Configuring News Mode

Set the default search mode to News Mode:

xxxxxxxxxx
{
  "skills": {
    "entries": {
      "tavily-web-search": {
        "enabled": true,
        "apiKey": "tvly-your-api-key-here",
        "config": {
          "searchDepth": "basic",
          "topic": "news",
          "days": 7
        }
      }
    }
  }
}

Configuration Details:

  • topic: general or news

  • days: The time range (in days) for news searches (1-30)

Practical Use Case Examples

Scenario 1: Learning New Technologies

xxxxxxxxxx
Search for the latest React tutorials suitable for beginners.

OpenClaw:

  • Searches for the latest introductory React tutorials.

  • Filters content from multiple sources to identify resources suitable for beginners.

  • Provides links to tutorials along with brief descriptions.

  • Offers learning recommendations.

Scenario 2: Shopping Decisions

xxxxxxxxxx
Search for a detailed comparison between the iPhone 15 and iPhone 15 Pro, including price and performance.

OpenClaw:

  • Searches for the latest product comparison information.

  • Summarizes differences in price, performance, and features.

  • Provides purchasing recommendations.

  • Offers official purchase links.

Scenario 3: Travel Planning

xxxxxxxxxx
Search for a comparison of transportation options from Beijing to Shanghai, including travel time, cost, and comfort levels.

OpenClaw:

  • Searches for the latest transportation information.

  • Compares options such as flights, high-speed trains, and buses.

  • Provides price and travel time estimates.

  • Offers recommended travel plans.

Scenario 4: Health Consultation

xxxxxxxxxx
Search for natural remedies to alleviate insomnia, based on authoritative medical websites.

OpenClaw:

  • Searches for information on authoritative medical websites

  • Provides scientifically validated methods

  • Outlines important precautions

  • Recommends consulting a medical professional

Scenario 5: Programming Questions

You:

xxxxxxxxxx
Search for how to implement asynchronous programming in Python, including code examples.

OpenClaw:

  • Searches for the latest programming tutorials

  • Provides detailed code examples

  • Explains key concepts

  • Offers best practice recommendations

Security & Privacy

Data Privacy

Tavily's Privacy Policy:

  • ✅ Zero Data Retention: Search data is not permanently stored

  • ✅ SOC 2 Certified: Complies with international security standards

  • ✅ Prompt Injection Protection: Prevents malicious queries

  • ✅ No Collection of Personally Identifiable Information (PII)

Security Recommendations

  1. Protect API Keys

  • Do not include keys in public code

  • Rotate keys regularly

  • Use environment variables or a secrets manager

  1. Verify Search Results

  • Check the credibility of information sources

  • Cross-reference critical information

  • Pay attention to the timeliness of the information

  1. Responsible Use

  • Adhere to Tavily's Terms of Use

  • Do not misuse the search functionality

  • Respect website content policies

Conclusion

Congratulations! You have successfully configured web search capabilities; OpenClaw can now access real-time information from the internet!

Next steps:

  • 📖 Continue learning about other skill configurations

  • 🎮 Explore more practical use cases

  • 🔧 Dive deeper into OpenClaw's advanced features

  • 💡 Unleash your creativity to build more applications


Tip: If you encounter any issues, you can run openclaw doctor at any time to perform a diagnostic check, or visit the Official Tavily Documentation for further assistance.

OpenClaw Application - Dedicated AI Assistant
AI-assisted development with VS Code or Cursor

COMPANY

  • About us
  • Team Style
  • Blog

LEARNING & EXPLORATION

  • Tutorials
  • Edge AI hardware
  • Educational robots
  • Embedded intelligent hardware

WHERE TO BUY

  • Yahboom Online Store
  • Amazon
  • Alibaba
  • AliExpress
  • Mercado

TECHNOLOGY SUPPORT

  • Email: support@yahboom.com

BE A DISTRIBUTOR

  • Email: sales@yahboom.com
QR Code

Copyright © 2017-2026 Yahboom. All Rights Reserved.

EN/中文