Agentic Web Search with Google API is an intelligent assistant that uses Agentic AI and the Google Custom Search API to perform live, deep web searches in response to user queries
# 🤖 Agentic Web Search with Google API Agentic Web Search with Google API is an intelligent assistant that uses Agentic AI and the Google Custom Search API to perform live, deep web searches in response to user queries. It integrates multiple LLMs (GPT, DeepSeek, DeepSeek, LLaMA(localhost)) with a deep search tool that extracts and summarizes content from the latest sources on the web. ## 📌 Features - 🧠 Uses OpenAI Agents SDK - 🔍 Uses Google Custom Search API for up-to-date web results - 🧠 Integrates LLMs including GPT, DeepSeek, DeepSeek, and LLaMA(locally in your machine, at no cost and no need for APIs) - 🌐 Fetches and parses multiple URLs to extract relevant content - 🛠️ Exposes a `deep_search_tool()` for structured information gathering - 📥 Automatically appends source URLs in responses - ⚡ Async execution for fast multi-agent querying - ✅ Designed to be accurate, current, and grounded in recent web data This project is designed to provide **free**, real-time, deep-search capability — ideal for research, trend tracking, and live information discovery. — It is not designed to get local time or weather, you need to add a new @function_tool to do so with APIs keys from a provider. ## 📂 Project Structure ``` web-search-agent/ ├── Agentic_Web_Search.ipynb # Main interactive notebook ├── requirements.txt # Python dependencies ├── README.md # This file ├── LICENSE # Open-source license └── .gitignore # Ignore .env and cache files ``` ## ⚙️ Setup Instructions ### 1. Clone the Repository ```bash git clone https://github.com/bahathabet/agentic-search.git cd agentic-search ``` ### 2. Install Dependencies ```bash pip install -r requirements.txt ``` ### 3. Set Up API Keys Create a `.env` file with the following variables in the project root directory: ```env OPENAI_API_KEY=your_openai_key GOOGLE_API_KEY=your_google_key DEEPSEEK_API_KEY=your_deepseek_key ANTHROPI
HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型