Re-structure folder for prompt engineering

README.md

@@ -143,17 +143,37 @@ results = collection.query(
 
 Combine retrieved context with the user's question and generate an answer.
 
-1. **Build prompt** — Create a structured prompt with system instructions, retrieved context, and the user's question
+1. **Build prompt** — Load the template from [`prompts/rag_prompt.txt`](prompts/rag_prompt.txt), inject retrieved context and the user's question
 2. **Call LLM API** — Send the prompt to the Hugging Face Inference API (Zephyr-7B)
 3. **Return response** — The LLM generates an answer grounded in the provided context
 
+The prompt template (`prompts/rag_prompt.txt`):
+
+```
+<|system|>
+You are a helpful assistant. Answer the user's question based ONLY on the provided context.
+If the context does not contain enough information to answer, say "I don't have enough information to answer this question."
+Always be concise and factual.</s>
+<|user|>
+Context:
+{context}
+
+Question: {question}</s>
+<|assistant|>
+```
+
+The template is loaded once at startup and filled at query time:
+
 ```python
-from huggingface_hub import InferenceClient
+RAG_PROMPT_TEMPLATE = Path("prompts/rag_prompt.txt").read_text(encoding="utf-8")
 
-client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta", token=HF_TOKEN)
+# At query time:
+prompt = RAG_PROMPT_TEMPLATE.format(context=context_text, question=user_query)
 response = client.text_generation(prompt, max_new_tokens=512)
 ```
 
+> **Tip:** Edit `prompts/rag_prompt.txt` to tune the model's behaviour (tone, language, output format) without touching application code.
+
 ### Step 6: API Endpoint (`/query`)
 
 The FastAPI endpoint ties everything together for the evaluation system.
@@ -247,18 +267,44 @@ System health check.
 # Clone the repository
 git clone https://huggingface.co/spaces/YOUR_USERNAME/Example-App-Hackathon-Gustave-Eiffel-2026
 cd Example-App-Hackathon-Gustave-Eiffel-2026
+```
+
+#### Set Up a Python Virtual Environment
 
+Using a virtual environment isolates project dependencies from your global Python installation.
+
+```bash
+# Create the virtual environment (Python 3.11+ required)
+python -m venv ~/.venv/hackathon-eiffel
+
+# Activate it
+# macOS / Linux
+source ~/.venv/hackathon-eiffel/bin/activate
+# Windows (PowerShell)
+~\.venv\hackathon-eiffel\Scripts\Activate.ps1
+# Windows (Command Prompt)
+~\.venv\hackathon-eiffel\Scripts\activate.bat
+```
+
+Once your virtual environment is active, install dependencies and run the app:
+
+```bash
 # Install dependencies
 pip install -r requirements.txt
 
 # Set your HF token
+# macOS / Linux
 export HF_TOKEN="hf_your_token_here"
+# Windows (PowerShell)
+$env:HF_TOKEN = "hf_your_token_here"
 
 # Run the application
 python app.py
 # Server starts at http://localhost:7860
 ```
 
+> **Tip:** To deactivate the virtual environment when you are done, run `deactivate` (venv) or `conda deactivate` (conda).
+
 ### Deploy to Hugging Face Spaces
 
 1. Create a new Space on huggingface.co (select Gradio SDK)

app.py

@@ -49,6 +49,10 @@ TOP_K_RESULTS = 3
 # HF_TOKEN is set as a Space secret for authenticated Inference API calls
 HF_TOKEN = os.environ.get("HF_TOKEN")
 
+# Prompt template loaded from file so it can be edited without touching application code
+_PROMPT_TEMPLATE_PATH = Path(__file__).parent / "prompts" / "rag_prompt.txt"
+RAG_PROMPT_TEMPLATE = _PROMPT_TEMPLATE_PATH.read_text(encoding="utf-8")
+
 # ---------------------------------------------------------------------------
 # Step 1: Initialize the Embedding Model
 # ---------------------------------------------------------------------------
@@ -231,17 +235,7 @@ def build_rag_prompt(query: str, contexts: list[dict]) -> str:
         f"[Source: {ctx['source']}]\n{ctx['text']}" for ctx in contexts
     )
 
-    prompt = f"""<|system|>
-You are a helpful assistant. Answer the user's question based ONLY on the provided context.
-If the context does not contain enough information to answer, say "I don't have enough information to answer this question."
-Always be concise and factual.</s>
-<|user|>
-Context:
-{context_text}
-
-Question: {query}</s>
-<|assistant|>
-"""
+    prompt = RAG_PROMPT_TEMPLATE.format(context=context_text, question=query)
     return prompt
 
 

prompts/rag_prompt.txt

@@ -0,0 +1,10 @@
+<|system|>
+You are a helpful assistant. Answer the user's question based ONLY on the provided context.
+If the context does not contain enough information to answer, say "I don't have enough information to answer this question."
+Always be concise and factual.</s>
+<|user|>
+Context:
+{context}
+
+Question: {question}</s>
+<|assistant|>