Update app.py

app.py

@@ -1,22 +1,20 @@
-# ✅ app.py
-
-import os
-from typing import List, Optional
-import gradio as gr
-
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain_community.vectorstores import FAISS
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.document_loaders import PyMuPDFLoader
 from langchain.chains import RetrievalQA
 from langchain.llms.base import LLM
+
 from groq import Groq
+from typing import List, Optional
+import os
+import gradio as gr
+
 
 
-# ✅ Custom GroqLLM that reads key from Hugging Face Secret
 class GroqLLM(LLM):
     model: str = "llama3-8b-8192"
-    api_key: str = os.getenv("GROQ_API_KEY")  # ✅ secure access to private Hugging Face secret
+    api_key: str = "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"
     temperature: float = 0.0
 
     def _call(self, prompt: str, stop: Optional[List[str]] = None) -> str:
@@ -37,7 +35,6 @@ class GroqLLM(LLM):
         return "groq-llm"
 
 
-# ✅ PDF processing logic
 def process_pdf(pdf_path):
     loader = PyMuPDFLoader(pdf_path)
     documents = loader.load()
@@ -49,7 +46,7 @@ def process_pdf(pdf_path):
     vectorstore = FAISS.from_documents(chunks, embedding)
 
     retriever = vectorstore.as_retriever()
-    llm = GroqLLM()
+    llm = GroqLLM(api_key="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")
 
     qa = RetrievalQA.from_chain_type(
         llm=llm,
@@ -60,35 +57,25 @@ def process_pdf(pdf_path):
     return qa
 
 
-# ✅ Global QA chain
-qa_chain = None
 
+qa_chain = None
 
 def upload_file(file):
     global qa_chain
-    try:
-        qa_chain = process_pdf(file.name)
-        return "✅ PDF processed! Ask your questions below."
-    except Exception as e:
-        return f"❌ Error processing PDF: {str(e)}"
-
+    qa_chain = process_pdf(file.name)
+    return "PDF processed! You can now ask questions."
 
 def ask_question(query):
     if qa_chain is None:
-        return "⚠️ Please upload a PDF first."
-    try:
-        result = qa_chain({"query": query})
-        return result["result"]
-    except Exception as e:
-        return f"❌ Error during response: {str(e)}"
+        return "Please upload a PDF first."
+    result = qa_chain({"query": query})
+    return result["result"]
 
 
-# ✅ Gradio App
 with gr.Blocks() as demo:
-    gr.Markdown("# 📚 PDF Q&A Chatbot with Groq LLaMA3 (via Hugging Face Spaces)")
-
+    gr.Markdown("# 🧠 PDF Q&A with GROQ + LangChain")
     with gr.Row():
-        uploader = gr.File(label="📤 Upload PDF")
+        uploader = gr.File(label="Upload your PDF")
         status = gr.Textbox(label="Status")
 
     uploader.change(fn=upload_file, inputs=uploader, outputs=status)
@@ -98,4 +85,6 @@ with gr.Blocks() as demo:
 
     question.submit(fn=ask_question, inputs=question, outputs=answer)
 
-demo.launch()
+demo.launch(share=True)
+
+