Update app.py

app.py

@@ -1,64 +1,92 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from langchain_community.document_loaders import PyMuPDFLoader, TextLoader
+from langchain_text_splitters import CharacterTextSplitter
+from langchain_community.vectorstores import FAISS
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain.chains import RetrievalQA
+from transformers import pipeline, AutoTokenizer
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+def load_documents(file_path="file.pdf"):
+    # Supports both PDF and TXT files
+    documents = []
+    for filename in os.listdir(file_path):
+        path = os.path.join(file_path, filename)
+        if filename.endswith(".pdf"):
+            loader = PyMuPDFLoader(path)
+            documents.extend(loader.load())
+        elif filename.endswith(".txt"):
+            loader = TextLoader(path)
+            documents.extend(loader.load())
+    return documents
 
+def create_qa_system():
+    try:
+        # 1. Load study materials
+        documents = load_documents()
+        if not documents:
+            raise ValueError("📚 No PDF/TXT files found in 'study_materials' folder")
+        
+        # 2. Smart text splitting for educational content
+        text_splitter = CharacterTextSplitter(
+            chunk_size=800,  # Optimized for textbook content
+            chunk_overlap=100,
+            separator="\n\n"  # Preserve paragraph structure
+        )
+        texts = text_splitter.split_documents(documents)
+        
+        # 3. Educational-focused embeddings
+        embeddings = HuggingFaceEmbeddings(
+            model_name="sentence-transformers/all-MiniLM-L6-v2"
+        )
+        
+        # 4. Create knowledge base
+        db = FAISS.from_documents(texts, embeddings)
+        
+        # 5. Configure student-friendly AI
+        qa_pipeline = pipeline(
+            "text2text-generation",
+            model="google/flan-t5-base",
+            tokenizer=AutoTokenizer.from_pretrained("google/flan-t5-base"),
+            max_length=300,  # Longer answers for explanations
+            temperature=0.3,  # Balance creativity/facts
+            device=-1  # Force CPU usage
+        )
+        
+        return RetrievalQA.from_chain_type(
+            llm=qa_pipeline,
+            chain_type="stuff",
+            retriever=db.as_retriever(search_kwargs={"k": 2}),
+            return_source_documents=True
+        )
+    except Exception as e:
+        raise gr.Error(f"🚨 Study Assistant Setup Failed: {str(e)}")
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Initialize system
+try:
+    qa = create_qa_system()
+except Exception as e:
+    print(f"Critical Error: {str(e)}")
+    raise
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+def ask_question(question, history):
+    try:
+        result = qa({"query": question})
+        answer = result["result"]
+        sources = list({doc.metadata['source'] for doc in result['source_documents']})
+        return f"{answer}\n\n📚 Sources: {', '.join(sources)}"
+    except Exception as e:
+        return f"❌ Error: {str(e)[:150]}"
 
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+# Student-friendly interface
+gr.ChatInterface(
+    ask_question,
+    title="Study Buddy AI",
+    description="Ask questions about your course materials!",
+    examples=[
+        "Explain the key points from Chapter 3",
+        "What's the difference between mitosis and meiosis?",
+        "List the main causes of World War II"
     ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+    theme="soft"
+).launch()