Update app.py

app.py

@@ -4,11 +4,9 @@ import fitz  # PyMuPDF
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain_community.vectorstores import FAISS
-from langchain.chains import RetrievalQA
-from langchain_community.llms import HuggingFaceEndpoint
 import requests
 import os
-import json
+import time
 
 # Page configuration
 st.set_page_config(
@@ -68,17 +66,22 @@ st.markdown("""
         animation: fadeIn 0.5s ease-in-out;
     }
     
+    .error {
+        background-color: #ffebee;
+        border-left: 4px solid #f44336;
+        padding: 10px;
+    }
+    
+    .info {
+        background-color: #e3f2fd;
+        border-left: 4px solid #2196f3;
+        padding: 10px;
+    }
+    
     @keyframes fadeIn {
         from { opacity: 0; }
         to { opacity: 1; }
     }
-    
-    .spinner {
-        display: flex;
-        justify-content: center;
-        align-items: center;
-        height: 100px;
-    }
 </style>
 """, unsafe_allow_html=True)
 
@@ -97,10 +100,11 @@ if 'history' not in st.session_state:
 def load_embedding_model():
     return HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
 
-def query_hf_inference_api(prompt, model="google/flan-t5-xxl", max_tokens=200):
-    """Query Hugging Face Inference API directly"""
-    API_URL = f"https://api-inference.huggingface.co/models/{model}"
-    headers = {"Authorization": f"Bearer {os.getenv('HF_API_KEY')}"}
+def query_hf_inference_api(prompt, max_tokens=200):
+    """Query Hugging Face Inference API with error handling and retry"""
+    MODEL = "google/flan-t5-large"  # Smaller, freely accessible model
+    API_URL = f"https://api-inference.huggingface.co/models/{MODEL}"
+    headers = {"Authorization": f"Bearer {os.getenv('HF_API_KEY')}"} if os.getenv('HF_API_KEY') else {}
     payload = {
         "inputs": prompt,
         "parameters": {
@@ -112,11 +116,36 @@ def query_hf_inference_api(prompt, model="google/flan-t5-xxl", max_tokens=200):
     
     try:
         response = requests.post(API_URL, headers=headers, json=payload)
-        response.raise_for_status()
-        result = response.json()
-        return result[0]['generated_text'] if result else ""
+        
+        if response.status_code == 200:
+            result = response.json()
+            return result[0]['generated_text'] if result else ""
+        
+        elif response.status_code == 403:
+            st.error("403 Forbidden: Please check your Hugging Face API token and model access")
+            st.markdown("""
+            <div class="info">
+                <h4>How to fix this:</h4>
+                <ol>
+                    <li>Get your free Hugging Face token from <a href="https://huggingface.co/settings/tokens" target="_blank">https://huggingface.co/settings/tokens</a></li>
+                    <li>Add it to your Space secrets as <code>HF_API_KEY</code></li>
+                    <li>Accept terms for the model: <a href="https://huggingface.co/google/flan-t5-large" target="_blank">https://huggingface.co/google/flan-t5-large</a></li>
+                </ol>
+            </div>
+            """, unsafe_allow_html=True)
+            return ""
+        
+        elif response.status_code == 429:
+            st.warning("Rate limit exceeded. Waiting and retrying...")
+            time.sleep(5)  # Wait 5 seconds before retrying
+            return query_hf_inference_api(prompt, max_tokens)
+        
+        else:
+            st.error(f"API Error {response.status_code}: {response.text[:200]}")
+            return ""
+            
     except Exception as e:
-        st.error(f"Error querying model: {str(e)}")
+        st.error(f"Connection error: {str(e)}")
         return ""
 
 def process_pdf(pdf_file):
@@ -201,6 +230,8 @@ def generate_qa_for_chapter(start_page, end_page):
                 question = query_hf_inference_api(prompt, max_tokens=100)
                 if question and not question.endswith("?"):
                     question += "?"
+                if question:  # Only add if we got a valid question
+                    qa_pairs.append((question, ""))
             else:  # Generate answer
                 if qa_pairs:  # Ensure we have a question to answer
                     prompt = f"Answer this question: {qa_pairs[-1][0]} using this context: {chunk[:500]}"
@@ -212,6 +243,20 @@ def generate_qa_for_chapter(start_page, end_page):
 # App header
 st.markdown("<h1 class='header'>📚 PDF Study Assistant</h1>", unsafe_allow_html=True)
 
+# API Token Instructions
+if not os.getenv("HF_API_KEY"):
+    st.markdown("""
+    <div class="info">
+        <h4>Setup Required:</h4>
+        <p>This app requires a free Hugging Face API token to work:</p>
+        <ol>
+            <li>Get your token from <a href="https://huggingface.co/settings/tokens" target="_blank">https://huggingface.co/settings/tokens</a></li>
+            <li>Add it to your Space secrets as <code>HF_API_KEY</code></li>
+            <li>Accept terms for the model: <a href="https://huggingface.co/google/flan-t5-large" target="_blank">google/flan-t5-large</a></li>
+        </ol>
+    </div>
+    """, unsafe_allow_html=True)
+
 # PDF Upload Section
 with st.container():
     st.subheader("📤 Upload Your Textbook/Notes")
@@ -246,11 +291,12 @@ if pdf_file:
             if user_question:
                 with st.spinner("🤔 Thinking..."):
                     answer, docs = ask_question(user_question)
-                    st.markdown(f"<div class='card'><b>Answer:</b> {answer}</div>", unsafe_allow_html=True)
-                    
-                    with st.expander("🔍 See source passages"):
-                        for i, doc in enumerate(docs):
-                            st.markdown(f"**Passage {i+1}:** {doc.page_content[:500]}...")
+                    if answer:
+                        st.markdown(f"<div class='card'><b>Answer:</b> {answer}</div>", unsafe_allow_html=True)
+                        
+                        with st.expander("🔍 See source passages"):
+                            for i, doc in enumerate(docs):
+                                st.markdown(f"**Passage {i+1}:** {doc.page_content[:500]}...")
         
         # Chapter Q&A Generation Tab
         elif selected_tab == "Generate Chapter Q&A":
@@ -293,6 +339,6 @@ if pdf_file:
 st.markdown("---")
 st.markdown("""
 <div style="text-align: center; padding: 20px;">
-    Built with ❤️ for students | PDF Study Assistant v2.0
+    Built with ❤️ for students | PDF Study Assistant v3.0
 </div>
 """, unsafe_allow_html=True)