Update app.py

app.py

@@ -3,16 +3,21 @@ import os
 from langchain.vectorstores import FAISS
 from langchain.embeddings import OpenAIEmbeddings
 from langchain.document_loaders import PyPDFLoader
-from langchain.chains import RetrievalQA
 from groq import Groq
 
-# Set the API Key directly (Not recommended for production)
+# Set API Keys (Use your provided keys)
 GROQ_API_KEY = "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"
+OPENAI_API_KEY = "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"
+
+# Initialize API Keys
+def initialize_keys():
+    """Set environment variables for API keys."""
+    os.environ["GROQ_API_KEY"] = GROQ_API_KEY
+    os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY
 
 # Initialize Groq client
 def initialize_groq_client():
     """Initialize the Groq client with the API key."""
-    os.environ["GROQ_API_KEY"] = GROQ_API_KEY
     return Groq(api_key=GROQ_API_KEY)
 
 # Generate response using Groq API
@@ -39,7 +44,7 @@ def process_pdf(pdf_path):
 # Create FAISS vector database
 def create_vector_db(documents):
     """Create a FAISS vector database from documents."""
-    embeddings = OpenAIEmbeddings()  # Use OpenAI embeddings for vectorization
+    embeddings = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY)  # Use OpenAI API key
     vector_db = FAISS.from_documents(documents, embeddings)
     return vector_db
 
@@ -62,25 +67,24 @@ def main():
         documents = process_pdf("uploaded_act.pdf")
         st.success("PDF Loaded and Processed Successfully!")
 
-        # Initialize Groq Client
-        try:
-            groq_client = initialize_groq_client()
-            st.success("Groq Client Initialized Successfully!")
-
-            # Build Vector DB and QA Chain
-            vector_db = create_vector_db(documents)
-            retriever, client = build_rag_pipeline(vector_db, groq_client)
+        # Initialize Groq client
+        initialize_keys()
+        groq_client = initialize_groq_client()
 
-            # Step 3: Ask Questions
-            query = st.text_input("Ask a question:")
-            if query:
-                with st.spinner("Fetching Answer..."):
-                    response = generate_response(client, query)
-                    st.write("### Answer:")
-                    st.write(response)
+        # Step 2: Build Vector DB and QA Chain
+        vector_db = create_vector_db(documents)
+        retriever, groq_client = build_rag_pipeline(vector_db, groq_client)
 
-        except Exception as e:
-            st.error(f"Error loading client or processing query: {e}")
+        # Step 3: Ask Questions
+        query = st.text_input("Ask a question:")
+        if query:
+            with st.spinner("Fetching Answer..."):
+                # Use Groq API to generate answer
+                answer = generate_response(groq_client, query)
+                
+                # Display Answer
+                st.write("### Answer:")
+                st.write(answer)
 
 if __name__ == "__main__":
     main()