Create app.py

app.py

@@ -0,0 +1,109 @@
+# app.py — Hugging Face deployable RAG Study Supervisor
+
+import os
+import gradio as gr
+import fitz  # PyMuPDF
+import docx
+import numpy as np
+import faiss
+import requests
+from sentence_transformers import SentenceTransformer
+
+# 🔐 Read Groq API Key from environment (set it in HF secrets)
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+MODEL = "llama3-8b-8192"
+
+# 💬 Prompt templates
+system_template = "You are a helpful and knowledgeable study supervisor. You are given excerpts from a document, and your job is to answer student questions based on that information. Be precise and explain clearly like a teacher."
+user_template = """Context: {context}
+
+Question: {question}
+
+Answer like a teacher:"""
+
+# 📚 Embedding model
+embedder = SentenceTransformer("all-MiniLM-L6-v2")
+
+def extract_text(file):
+    ext = file.name.split(".")[-1].lower()
+    if ext == "pdf":
+        doc = fitz.open(file.name)
+        return "\n".join([page.get_text() for page in doc])
+    elif ext in ["docx", "doc"]:
+        doc = docx.Document(file.name)
+        return "\n".join([p.text for p in doc.paragraphs])
+    return ""
+
+def chunk_text(text, size=300, overlap=50):
+    words = text.split()
+    return [" ".join(words[i:i + size]) for i in range(0, len(words), size - overlap)]
+
+def embed_chunks(chunks):
+    return embedder.encode(chunks).astype("float32")
+
+def store_faiss(chunks, vectors):
+    index = faiss.IndexFlatL2(vectors.shape[1])
+    index.add(vectors)
+    return {"documents": chunks, "vectors": vectors, "index": index}
+
+def get_context(query, state, k=3):
+    if state is None or "index" not in state:
+        return "⚠️ Please upload a document first.", None
+    q_vec = embedder.encode([query]).astype("float32")
+    _, I = state["index"].search(q_vec, k)
+    return [state["documents"][i] for i in I[0]], state
+
+def query_llm(context, question):
+    prompt = user_template.format(context="\n".join(context), question=question)
+    response = requests.post(
+        "https://api.groq.com/openai/v1/chat/completions",
+        headers={"Authorization": f"Bearer {GROQ_API_KEY}"},
+        json={
+            "model": MODEL,
+            "messages": [
+                {"role": "system", "content": system_template},
+                {"role": "user", "content": prompt}
+            ],
+            "temperature": 0.3
+        }
+    )
+    if response.status_code == 200:
+        return response.json()["choices"][0]["message"]["content"]
+    else:
+        return f"❌ Error: {response.json()}"
+
+def upload_file(file):
+    text = extract_text(file)
+    if not text.strip():
+        return "⚠️ File is empty or unreadable.", None
+    chunks = chunk_text(text)
+    vectors = embed_chunks(chunks)
+    state = store_faiss(chunks, vectors)
+    return "✅ Document processed!", state
+
+def ask_question(question, state):
+    if not question.strip():
+        return "❗ Please enter a question.", state
+    context, state = get_context(question, state)
+    if isinstance(context, str):  # error message
+        return context, state
+    return query_llm(context, question), state
+
+# 🎛️ Gradio Interface
+with gr.Blocks() as demo:
+    gr.Markdown("# 📘 Study Supervisor Chatbot\nUpload a document and ask questions about it.")
+
+    state = gr.State()
+
+    with gr.Row():
+        file = gr.File(file_types=[".pdf", ".docx", ".doc"], label="📂 Upload Document")
+        upload_btn = gr.Button("📤 Upload and Process")
+
+    status = gr.Textbox(label="Status", interactive=False)
+    question = gr.Textbox(label="❓ Ask a Question")
+    answer = gr.Textbox(label="📚 Answer", lines=8)
+
+    upload_btn.click(upload_file, inputs=file, outputs=[status, state])
+    question.submit(ask_question, inputs=[question, state], outputs=[answer, state])
+
+demo.launch()