Update README.md

README.md

@@ -11,19 +11,19 @@ license: apache-2.0
 short_description: Analyse sensitive survey data in offline mode
 ---
 
-This space build from https://huggingface.co/spaces/VIDraft/EveryRAG and provides adjustements for this work offline with ollama when __working with sensitive data__ that can come with data protection concerns.
+This space build from https://huggingface.co/spaces/VIDraft/EveryRAG and provide adjustements for this work offline with ollama when __working with sensitive data__ that can come with data protection concerns.
 
-The app now works completely offline (after downloading the model) which means that you do not need to share any data on the cloud... 
+The app now works completely offline (after downloading the model) wich means that you do not need to share any data on the cloud... 
 
 ## Requirements:
 
 1. Install [Ollama](https://ollama.com/download) and run in a shell: `ollama serve`
 
-2. Pull the [Mistral-Nemo model](https://ollama.com/library/mistral-nemo), a model that excel in data analysis but can still run on regular consumer hardware: `ollama pull mistral-nemo`
+2.  Pull at least one model, for instance [phi3 3.8b](https://ollama.com/library/phi3), with `ollama pull phi3` a 2.2Gb model that run well on regular consumer hardware or [Mistral-Nemo model](https://ollama.com/library/mistral-nemo), a slightly bigger one with `ollama pull mistral-nemo`
 
-3. Install [Visual Studio Code](https://code.visualstudio.com/), the last [stable version of python language](https://www.python.org/downloads/) and [git](https://git-scm.com/downloads)
+3.  Install [Visual Studio Code](https://code.visualstudio.com/) and make sure to install the last [stable version of python language](https://www.python.org/downloads/)
 
-4. Clone this repo on your computer and open the folder in Visual Studio
+4. Clone this repo in visual studio,
 
 5. Create a virtual environment in Python development. This is essential for managing dependencies, avoiding conflicts, and ensuring reproducibility. It allows you to isolate project-specific libraries and versions, preventing interference with other projects or the global Python installation. This isolation helps maintain a clean development environment, simplifies project setup for collaborators, and enhances security by reducing the risk of introducing vulnerabilities. Overall, virtual environments provide a consistent and organized way to manage your Python projects effectively.
 
@@ -37,9 +37,9 @@ The app now works completely offline (after downloading the model) which means t
 
 1. Run the app.py script > `python app.py`
 
-2. Open in your browser the localhost using the link from your terminal  
+2. Open [your localhost ](http://127.0.0.1:7860) and upload your survey data file (text, code, CSV, or Parquet)
 
-3. Upload your survey data file (text, code, CSV, or Parquet) and the app will automatically analyze the file structure
+3. The app will automatically analyze the file structure
 
 4. __Et voilà!__ Ask questions about your file in natural language. The model can help you to write quickly any analysis notebook!