This tutorial series is designed for python developers who want to empower their watsonx.ai agents with real-time web access, enabling agents to utilize up-to-date information as context. Live web information is critical for AI agents tasked with performing research, answering questions accurately, monitoring trends, or providing up-to-date recommendations. You'll learn how to build AI agents that search the web, extract valuable content, navigate websites intelligently, and integrate real-time web information into private knowledge bases. By the end, you'll be equipped to build sophisticated web agents that can fetch timely data, improving your agent's accuracy and reliability.
This tutorial series follows a step-by-step learning path with three stand-alone tutorials:
-
In tutorial #1, we'll cover the basics of web access.
-
In tutorial #2, we'll build a watsonx agent that can search, scrape, and crawl the web.
-
Finally, In tutorial #3, we'll develop a system that combines real-time web information with private knowledge base data.
📁 agent-with-tavily-web-access/
├── 📓 search-extract-crawl.ipynb # Tutorial notebook 1
├── 📓 web-agent-tutorial.ipynb # Tutorial notebook 2
├── 📓 hybrid-agent-tutorial.ipynb # Tutorial notebook 3
├── 📁 assets/ # Diagrams and screenshots
│ ├── 🖼️ web-agent.svg
| ├── 🖼️ hybrid.svg
| ├── 🖼️ api-key.png
│ └── 🖼️ sign-up.png
├── 📁 supplemental/ # Supplemental materials
│ ├── 📓 vectorize_tutorial.ipynb # Vectorize your own documents
│ ├── 📁 docs/ # Sample CRM documents
│ └── 📁 db/ # Pre-built Chroma vector database
└── 📄 README.md # This file