Update app.py

app.py

@@ -9,22 +9,20 @@ from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.chains import RetrievalQA
 from langchain.prompts import PromptTemplate
 from langchain.llms.base import LLM
-from typing import Optional, List, Mapping, Any
+from pydantic import Field
+from typing import Optional, List
 import streamlit as st
 
 # Custom wrapper for Groq API
 class GroqLLM(LLM):
-    def __init__(self, api_key: str, model: str = "llama-3.3-70b-versatile"):
-        self.api_key = api_key
-        self.model = model
+    api_key: str = Field(..., env="GROQ_API_KEY")
+    model: str = "llama-3.3-70b-versatile"
 
     @property
     def _llm_type(self) -> str:
         return "groq"
 
     def _call(self, prompt: str, stop: Optional[List[str]] = None) -> str:
-        import requests
-
         headers = {"Authorization": f"Bearer {self.api_key}"}
         json_data = {
             "model": self.model,
@@ -42,7 +40,7 @@ class GroqLLM(LLM):
         return data["choices"][0]["message"]["content"]
 
 # Initialize Groq API LLM
-llm = GroqLLM(api_key=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)
+llm = GroqLLM()
 
 # Function to extract content from a public Google Drive PDF link
 def extract_pdf_content(drive_url):
@@ -104,15 +102,4 @@ if text:
         )
 
         # Create a RetrievalQA chain
-        qa_chain = RetrievalQA(
-            retriever=retriever,
-            llm=llm,
-            prompt=prompt_template
-        )
-
-        # Run the query through the QA chain
-        result = qa_chain.run(query)
-        st.write("Answer:", result)
-else:
-    st.error("Failed to extract content from the document.")
-
+        qa_chain =