Merge remote-tracking branch 'origin/main'

Author: mtiessler

Dockerfile

@@ -1,28 +1,20 @@
-# Use Python 3.9 as base image
 FROM python:3.9
 
 WORKDIR /wsgi
 
-# Copy only dependency files first to leverage Docker caching
 COPY Pipfile Pipfile.lock /wsgi/
 
-# Install Pipenv and dependencies
 RUN pip install pipenv && pipenv install --deploy --ignore-pipfile
 
-# Install CPU-only PyTorch (avoids CUDA errors)
 RUN pipenv run pip install torch --index-url https://download.pytorch.org/whl/cpu
 
-# Download spaCy model inside the virtual environment
 RUN pipenv run python -m spacy download en_core_web_sm
 
-# Copy the application files
 COPY . /wsgi
 
-# Unset HF_TOKEN to prevent conflicts
+# To prevent conflicts with .env
 ENV HF_TOKEN=""
 
-# Expose the port for Flask
 EXPOSE 3008
 
-# Run Flask
 CMD ["pipenv", "run", "flask", "run", "--host=0.0.0.0", "--port=3008"]

README.md

@@ -3,12 +3,14 @@
 ---
 
 ## Introduction
-FeaClustRE (**Feature Clustering and Analysis Visualization Tool**) is an advanced tool designed to **analyze, cluster, and visualize structured data features** using machine learning techniques. It provides **hierarchical clustering, dendrogram visualizations, and feature-based insights** to help researchers and data scientists explore complex datasets.
+FeaClustRE (**Feature Clustering and Analysis Visualization Tool**) is an advanced tool designed to **analyze, cluster, and visualize structured hierarchical features** using NLP and LLM models and techniques. It provides **hierarchical clustering, dendrogram visualizations, and evaluations** to help to explore complex lists of features.
 
 This tool uses **Meta's LLaMA model** for feature embedding and **Hugging Face's Transformers** for feature family clustering. 
 
 With a flexible **backend API**, a **CLI client**, and **visualization tools**, FeaClustRE supports both **interactive analysis and automated batch processing**.
 
+This tool is part of the RE-Miner Ecosystem, which can be explored in the [GESSI-NLP4SE repository](https://github.com/nlp4se).
+
 ### Key Features
 - **Custom Clustering Algorithm** – Uses a hand-made affinity-based clustering approach to automatically group similar features.
 - **Dendrogram Visualization** – Generates hierarchical visualizations to explore feature relationships.
@@ -48,7 +50,7 @@ This project uses **Meta's LLaMA model**, which is **gated** and requires **manu
 ### **Using Your Hugging Face Token**
 To authenticate, you **must set your Hugging Face token** before running the project.
 
-#### **1️⃣ Set the Token in `.env`**
+#### **Set the Token in `.env`**
 In the `.env` file in the project root, add:
 
 ```