Merge pull request #9 from Acuspeedster/main

Update README.m

Author: Acuspeedster

README.md

@@ -11,6 +11,7 @@ API and MCP services that generate fully functional Rust projects from natural l
 - **Vector Search** 🔍 - Search for similar projects and errors.
 - **Docker Containerization** 🐳 - Easy deployment with Docker.
 - **Asynchronous Processing** ⏳ - Handle long-running operations efficiently.
+- **Multiple Service Interfaces** 🔄 - REST API and MCP (Model-Compiler-Processor) interface.
 
 ---
 
@@ -24,14 +25,15 @@ Or, if you want to run the services directly on your own computer:
 
 - **Python 3.8+** 🐍
 - **Rust Compiler and cargo tools** 🦀 
+- **Rust Compiler and cargo tools** 🦀 
 
 ---
 
 ## 📦 Install
 
 ```bash
-git clone <repository-url>
-cd Rust_coder_lfx
+git clone https://github.com/WasmEdge/Rust_coder
+cd Rust_coder
 ```
 
 ## 🚀 Configure and run
@@ -65,15 +67,15 @@ docker-compose stop
 By default, you will need a [Qdrant server](https://qdrant.tech/documentation/quickstart/) running on `localhost` port `6333`. You also need a [local Gaia node](https://github.com/GaiaNet-AI/node-configs/tree/main/qwen-2.5-coder-3b-instruct-gte). Set the following environment variables in your terminal to point to the Qdrant and Gaia instances, as well as your Rust compiler tools.
 
 ```
-QDRANT_HOST
-QDRANT_PORT
-LLM_API_BASE
-LLM_MODEL
-LLM_EMBED_MODEL
-LLM_API_KEY
-LLM_EMBED_SIZE
-CARGO_PATH
-RUST_COMPILER_PATH
+QDRANT_HOST=localhost
+QDRANT_PORT=6333
+LLM_API_BASE=http://localhost:8080/v1
+LLM_MODEL=Qwen2.5-Coder-3B-Instruct
+LLM_EMBED_MODEL=nomic-embed
+LLM_API_KEY=your_api_key
+LLM_EMBED_SIZE=768
+CARGO_PATH=/path/to/cargo
+RUST_COMPILER_PATH=/path/to/rustc
 ```
 
 Start the services.
@@ -114,9 +116,18 @@ The API provides the following endpoints:
 
 ```
 [filename: Cargo.toml]
+[package]
+name = "calculator"
+version = "0.1.0"
+edition = "2021"
+
+[dependencies]
 ... ...
 
 [filename: src/main.rs]
+fn main() {
+    // Calculator implementation
+}
 ... ...
 ```
 
@@ -352,23 +363,32 @@ Rust_coder_lfx/
 ├── app/                  # Application code
 │   ├── compiler.py       # Rust compilation handling
 │   ├── llm_client.py     # LLM API client
-│   ├── main.py           # FastAPI application
+│   ├── llm_tools.py      # Tools for LLM interactions
+│   ├── load_data.py      # Data loading utilities
+│   ├── main.py           # FastAPI application & endpoints
+│   ├── mcp_server.py     # MCP server implementation
 │   ├── mcp_service.py    # Model-Compiler-Processor service
+│   ├── mcp_tools.py      # MCP-specific tools
 │   ├── prompt_generator.py # LLM prompt generation
 │   ├── response_parser.py # Parse LLM responses into files
-│   ├── vector_store.py   # Vector database interface
-│   └── ...
+│   ├── utils.py          # Utility functions
+│   └── vector_store.py   # Vector database interface
 ├── data/                 # Data storage
 │   ├── error_examples/   # Error examples for vector search
 │   └── project_examples/ # Project examples for vector search
 ├── docker-compose.yml    # Docker Compose configuration
 ├── Dockerfile            # Docker configuration
 ├── examples/             # Example scripts for using the API
-├── output/               # Generated project output
+│   ├── compile_endpoint.txt        # Example for compile endpoint
+│   ├── compile_and_fix_endpoint.txt # Example for compile-and-fix endpoint
+│   ├── mcp_client_example.py       # Example MCP client usage
+│   └── run_mcp_server.py           # Example for running MCP server
+├── templates/            # Prompt templates
+│   └── project_prompts.txt # Templates for project generation
+├── mcp-proxy-config.json # MCP proxy configuration
 ├── parse_and_save_qna.py # Q&A parsing utility
-├── qdrant_data/          # Vector database storage
 ├── requirements.txt      # Python dependencies
-└── templates/            # API templates
+└── .env                  # Environment variables
 ```
 
 ---
@@ -384,10 +404,46 @@ Compilation Feedback Loop: Automatically compiles, detects errors, and fixes the
 
 File Parsing: Converts LLM responses into project files with `response_parser.py`.
 
+#### Architecture
+
+REST API Interface (app/main.py): FastAPI application exposing HTTP endpoints for project generation, compilation, and error fixing.
+
+MCP Interface (mcp_server.py, app/mcp_service.py): Server-Sent Events interface for the same functionality.
+
+Vector Database (app/vector_store.py): Qdrant is used for storing and searching similar projects and error examples.
+
+LLM Integration (app/llm_client.py): Communicates with LLM APIs (like Gaia nodes) for code generation and error fixing.
+
+Compilation Pipeline (app/compiler.py): Handles Rust code compilation, error detection, and provides feedback for fixing.
+
+#### Process Flow
+
+Project Generation:
+
+User provides a description and requirements
+System creates a prompt using templates (templates/project_prompts.txt)
+LLM generates a complete Rust project
+Response is parsed into individual files (app/response_parser.py)
+Project is compiled to verify correctness
+
+Error Fixing:
+
+System attempts to compile the provided code
+If errors occur, they're extracted and analyzed
+Vector search may find similar past errors
+LLM receives the errors and original code to generate fixes
+Process repeats until successful or max attempts reached
+
 ---
 
 ## 🤝 Contributing
-Contributions are welcome! Feel free to submit a Pull Request. 🚀
+Contributions are welcome! Feel free to submit a Pull Request.
+
+Fork the repository
+Create your feature branch (git checkout -b feature/amazing-feature)
+Commit your changes (git commit -m 'Add some amazing feature')
+Push to the branch (git push origin feature/amazing-feature)
+Open a Pull Request
 
 ---