🚀 DeepSeek Local Skeleton with Go Backend

Welcome to the DeepSeek Local Skeleton project! This is a foundational setup to work with DeepSeek locally and build a Go backend to interact with it. Whether you're experimenting or building a full-fledged application, this skeleton provides the essential structure to get started.

---

🛠️ Prerequisites

Before diving in, ensure you have the following installed and configured:

1. Ollama:

   • Download and install Ollama from https://ollama.com/.
   • If you move the Ollama folder, set the PATH environment variable to point to its new location.
   • Set the OLLAMA_MODELS environment variable to specify where your models will be stored.
   • Verify the installation by running:

     ollama --version

2. DeepSeek Model:

   • Install the DeepSeek model of your choice. You can find models on Hugging Face or the Ollama library.
   • For example, to install the deepseek-r1:8b model, run:

     ollama run deepseek-r1:8b

3. PostgreSQL:

   • Ensure PostgreSQL is installed and running.
   • Check the status of PostgreSQL:

     pg_ctl status -D <path-to-postgresql>\PostgreSQL\data

   • Start PostgreSQL if it’s not running:

     pg_ctl start -D <path-to-postgresql>\PostgreSQL\data

   • Create the database for the project:

     CREATE DATABASE material_todo_go;

---

🏗️ Project Structure

Here’s an overview of the project structure:

📂 deepseekBackend
 ├── 📁 controllers    # API controllers (auth, user, notes)
 ├── 📁 models         # Database models (User, Note)
 ├── 📁 database       # Database connection (PostgreSQL)
 ├── 📁 routes         # API route definitions
 ├── 📁 utils          # Utility functions (JWT handling)
 ├── 🌍 main.go        # Entry point of the app
 ├── 📜 go.mod         # Go modules
 ├── 📜 README.md      # Project documentation

---

🚀 Getting Started

1. Clone the Repository:
   Clone this repository to your local machine.

2. Install Dependencies:
   Run the following command to install the required Go dependencies:

   go mod tidy

3. Configure Environment Variables:
   Set up the necessary environment variables for the database connection, JWT secrets, and Ollama configurations.

4. Run the Application:
   Start the Go backend by running:

   go run main.go

5. Test the API:
   Use tools like Postman or cURL to test the API endpoints defined in the routes folder.

---

☁️ API Endpoint Example

To interact with the DeepSeek model, you can use the following API endpoint:

Start a Chat with DeepSeek

• Endpoint: POST http://localhost:2626/api/chats/start
• Request Body:

  {
      "prompt": "How much water should I drink a day?"
  }

Example Request (Postman or cURL):

• Postman:

  1. Set the request type to POST.
  2. Enter the URL: http://localhost:2626/api/chats/start.
  3. Go to the Body tab, select raw, and choose JSON format.
  4. Paste the JSON payload:

     {
         "prompt": "How much water should I drink a day?"
     }

  5. Click Send to get the response.

• cURL:

  curl -X POST http://localhost:2626/api/chats/start \
  -H "Content-Type: application/json" \
  -d '{"prompt": "How much water should I drink a day?"}'

Example Response:

{
    "response": "The general recommendation is to drink about 8 glasses (64 ounces) of water per day, but individual needs may vary based on factors like age, weight, activity level, and climate."
}

---

🧩 Features

• DeepSeek Integration: Work with DeepSeek models locally using Ollama.
• PostgreSQL Database: Store and manage data efficiently.
• RESTful API: Build scalable and maintainable APIs with Go.
• JWT Authentication: Secure your application with token-based authentication.

---

📜 License

This project is open-source and available under the MIT License. Feel free to use, modify, and distribute it as needed.

---

🙌 Contributing

Contributions are welcome! If you have any suggestions, bug reports, or feature requests, please open an issue or submit a pull request.

---

Happy coding! 🎉
Let’s build something amazing with DeepSeek and Go! 🚀