Update app.py

app.py

@@ -1,22 +1,23 @@
 # =========================
 # IMPORTS
 # =========================
-from langchain_community.document_loaders import PyPDFLoader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
+import os
+import tempfile
 
+import gradio as gr
+from groq import Groq
+from duckduckgo_search import DDGS
 
+from langchain_community.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain_community.vectorstores import Chroma
-from groq import Groq
-from duckduckgo_search import DDGS
-import gradio as gr
 
 
 # =========================
 # CONFIG
 # =========================
-import os
-GROQ_API_KEY = os.getenv("Ai_tutor")  # 🔥 set in HF secrets instead
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")  # ✅ Hugging Face Secret
 
 client = Groq(api_key=GROQ_API_KEY)
 
@@ -45,7 +46,7 @@ ANSWER:
 
 
 # =========================
-# WEB SEARCH
+# WEB SEARCH (FALLBACK)
 # =========================
 def web_search(query):
     results = []
@@ -56,21 +57,26 @@ def web_search(query):
 
 
 # =========================
-# PROCESS PDF
+# PROCESS PDF (FIXED FOR HF)
 # =========================
 def process_pdf(file):
 
     global vectorstore, retriever
 
-    loader = PyPDFLoader(file.name)
+    # ✅ SAFE HF FILE HANDLING
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp:
+        tmp.write(file.read())
+        tmp_path = tmp.name
+
+    loader = PyPDFLoader(tmp_path)
     documents = loader.load()
 
-    text_splitter = RecursiveCharacterTextSplitter(
+    splitter = RecursiveCharacterTextSplitter(
         chunk_size=600,
         chunk_overlap=100
     )
 
-    chunks = text_splitter.split_documents(documents)
+    chunks = splitter.split_documents(documents)
 
     embedding_model = HuggingFaceEmbeddings(
         model_name="sentence-transformers/all-MiniLM-L6-v2"
@@ -83,26 +89,26 @@ def process_pdf(file):
 
     retriever = vectorstore.as_retriever(search_kwargs={"k": 4})
 
-    return "✅ PDF processed. Ask questions."
+    return "✅ PDF processed successfully. You can now ask questions."
 
 
 # =========================
-# RAG FUNCTION (HYBRID)
+# HYBRID RAG FUNCTION
 # =========================
 def ask_rag(query):
 
     global retriever
 
     if retriever is None:
-        return "⚠️ Upload a PDF first."
+        return "⚠️ Please upload a PDF first."
 
     docs = retriever.invoke(query)
     pdf_context = "\n\n".join([d.page_content for d in docs])
 
-    # Hybrid fallback
+    # fallback if weak retrieval
     if len(pdf_context.strip()) < 50:
         web_context = web_search(query)
-        context = pdf_context + "\n\nWEB:\n" + web_context
+        context = pdf_context + "\n\nWEB CONTEXT:\n" + web_context
     else:
         context = pdf_context
 
@@ -117,25 +123,30 @@ def ask_rag(query):
 
 
 # =========================
-# CHAT
+# CHAT FUNCTION (SAFE)
 # =========================
 def chat(user_message, history):
 
     response = ask_rag(user_message)
+
+    if history is None:
+        history = []
+
     history.append((user_message, response))
 
     return history, history
 
 
 # =========================
-# UI
+# GRADIO UI (HF SAFE)
 # =========================
 with gr.Blocks() as app:
 
-    gr.Markdown("# 🧠 Hybrid RAG Chatbot (PDF + Web)")
+    gr.Markdown("# 🧠 Hybrid RAG Chatbot (PDF + Web Search)")
 
     file = gr.File(label="Upload PDF")
     status = gr.Textbox(label="Status")
+
     chatbot = gr.Chatbot()
     msg = gr.Textbox(placeholder="Ask your question...")
     state = gr.State([])