Update README.md

README.md

@@ -92,7 +92,7 @@ This project addresses these challenges by:
 └───────────────────────────────┬─────────────────────────────────┘
                                 ▼
 ┌─────────────────────────────────────────────────────────────────┐
-│                    MCP SERVER (FastMCP)                          │
+│                    MCP SERVER (Gradio)                           │
 │  ┌─────────────┐ ┌────────────┐ ┌──────────────┐ ┌────────────┐ │
 │  │search_nodes │ │go_to_def   │ │find_usages   │ │get_neighbors│ │
 │  └─────────────┘ └────────────┘ └──────────────┘ └────────────┘ │
@@ -161,10 +161,6 @@ The system also detects **API endpoints** for web frameworks (FastAPI, Flask, Sp
 ### Quick Start with Docker
 
 ```bash
-# Clone the repository
-git clone https://github.com/lailanelkoussy/mcp-first-birthday.git
-cd mcp-first-birthday
-
 # Start the MCP server with a sample knowledge graph
 docker-compose up
 ```
@@ -172,7 +168,7 @@ docker-compose up
 ### Building a Knowledge Graph from Your Repository
 
 ```python
-from pedagogia_graph_code_repo.RepoKnowledgeGraphLib import RepoKnowledgeGraph
+from RepoKnowledgeGraphLib.RepoKnowledgeGraph import RepoKnowledgeGraph
 
 # From a local path
 kg = RepoKnowledgeGraph.from_path(
@@ -186,14 +182,11 @@ kg = RepoKnowledgeGraph.from_path(
 kg.save_graph_to_file("my_knowledge_graph.json")
 ```
 
-### Running the MCP Server
+### Running the MCP using Gradio
 
 ```bash
-# Using the Gradio interface (recommended for exploration)
 python gradio_mcp.py --graph-file my_knowledge_graph.json --host 0.0.0.0 --port 7860
 
-# Or directly as an MCP server
-python pedagogia_graph_code_repo/run_mcp_server.py --graph-file my_knowledge_graph.json
 ```
 
 ## 📊 Interactive Explorer (Gradio UI)
@@ -211,7 +204,7 @@ The application supports loading knowledge graphs from multiple sources:
 
 ### 1. HuggingFace Hub Dataset (Recommended for Sharing)
 
-Load directly from a HuggingFace dataset:
+Load directly from a HuggingFace dataset created by the library (cf. Publishing to Huggingface Hub):
 
 ```bash
 python gradio_mcp.py --host 0.0.0.0 --port 7860 --hf-dataset "username/dataset-name"
@@ -250,74 +243,22 @@ kg.to_hf_dataset("username/my-knowledge-graph", save_embeddings=False, private=F
 kg.to_hf_dataset("username/my-knowledge-graph-with-embeddings", save_embeddings=True)
 ```
 
-## 🐳 Docker Configuration
-
-The default Dockerfile uses a local JSON file. To use HuggingFace datasets instead, modify the CMD line in `Dockerfile`:
-
-```dockerfile
-# Using HuggingFace dataset (recommended for smaller Docker image)
-CMD ["python", "-u", "gradio_mcp.py", "--host", "0.0.0.0", "--port", "7860", "--hf-dataset", "username/dataset-name"]
-
-# Using local file (requires large data file in image)
-CMD ["python", "-u", "gradio_mcp.py", "--host", "0.0.0.0", "--port", "7860", "--graph-file", "/app/data/multihop_knowledge_graph_with_embeddings.json"]
-```
-
-## 💻 Local Development
-
-To run locally:
-
-```bash
-docker build -t gradio-mcp-space .
-docker run -p 7860:7860 gradio-mcp-space
-```
-
-Or without Docker:
-
-```bash
-pip install -r requirements.txt
-python gradio_mcp.py --host 0.0.0.0 --port 7860 --hf-dataset "username/dataset-name"
-```
-
-## ☁️ Deployment to HuggingFace Spaces
-
-### Option 1: Using HuggingFace Dataset (Recommended)
-
-1. First, push your knowledge graph to a HuggingFace dataset
-2. Update the Dockerfile CMD to use `--hf-dataset`
-3. Push to the Space repository (no large files needed)
-
-### Option 2: Using Local JSON File
-
-1. Create a new Space on HuggingFace with Docker SDK
-2. Enable Git LFS in your Space repository
-3. Push this directory to the Space repository:
-   ```bash
-   git lfs install
-   git lfs track "data/*.json"
-   git add .
-   git commit -m "Initial commit"
-   git push
-   ```
 
 ## 🏗️ Architecture Overview
 
 ```
-mcp-first-birthday/
-├── gradio_mcp.py              # Main Gradio web interface
+root/
 ├── Dockerfile                  # Docker configuration
 ├── requirements.txt            # Python dependencies
-├── pedagogia_graph_code_repo/  # Core library
-│   ├── RepoKnowledgeGraphLib/  # Knowledge graph implementation
-│   │   ├── RepoKnowledgeGraph.py    # Main graph class
-│   │   ├── KnowledgeGraphMCPServer.py # MCP server implementation
-│   │   ├── EntityExtractor.py       # AST-based entity extraction
-│   │   ├── CodeParser.py            # Code chunking
-│   │   ├── CodeIndex.py             # Hybrid search (LanceDB/Weaviate)
-│   │   ���── ModelService.py          # Embedding generation
-│   │   └── Node.py                  # Graph node types
-│   ├── run_mcp_server.py            # Standalone MCP server
-│   └── tests/                       # Test suite
-└── docker-compose*.yml         # Docker configurations
+├── RepoKnowledgeGraphLib/  # Knowledge graph implementation
+│   ├── RepoKnowledgeGraph.py    # Main graph class
+│   ├── KnowledgeGraphMCPServer.py # MCP server implementation
+│   ├── EntityExtractor.py       # AST-based entity extraction
+│   ├── CodeParser.py            # Code chunking
+│   ├── CodeIndex.py             # Hybrid search (LanceDB/Weaviate)
+│   ├── ModelService.py          # Embedding generation
+│   └── Node.py                  # Graph node types
+└── gradio_mcp_space.py              # Main Gradio web interface
 ```
 
 
@@ -341,7 +282,7 @@ This project is developed as part of research at EPITA / Ionis Group.
 ## 🔗 Related Resources
 
 - [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) - The protocol standard
-- [FastMCP](https://github.com/jlowin/fastmcp) - Python MCP framework used
+- [Gradio](https://gradio.app/) - Python web interface framework with MCP support
 - [LanceDB](https://lancedb.github.io/lancedb/) - Vector database for code indexing
 - [Salesforce SFR-Embedding-Code](https://huggingface.co/Salesforce/SFR-Embedding-Code-400M_R) - Code embedding model