Update app.py

app.py

@@ -2,27 +2,27 @@ import os
 import streamlit as st
 from groq import Groq
 from langchain.chains import RetrievalQA
-from langchain.vectorstores import FAISS  # This import should work now
+from langchain.vectorstores import FAISS
 from langchain.document_loaders import PyPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.llms import OpenAI
+from io import BytesIO
 
 # Set up Groq API key
 GROQ_API_KEY = "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"
 
-# Define a custom embedding class for Groq (since Langchain may not support direct Groq API integration)
+# Define a custom embedding class for Groq
 class GroqEmbedding:
     def __init__(self, model="groq-embedding-model"):
         self.model = model
         self.client = Groq(api_key=GROQ_API_KEY)
 
     def embed_documents(self, texts):
-        # Use Groq's API to generate embeddings
+        # Use Groq's API to generate embeddings for documents
         embeddings = self.client.embed_documents(texts, model=self.model)
         return embeddings
     
     def embed_query(self, query):
-        # Use Groq's API to generate query embedding
+        # Use Groq's API to generate embedding for a query
         return self.client.embed_query(query, model=self.model)
 
 # Streamlit App UI
@@ -32,7 +32,11 @@ uploaded_file = st.file_uploader("Upload a PDF", type="pdf")
 
 # Process the uploaded PDF
 if uploaded_file is not None:
-    loader = PyPDFLoader(uploaded_file)
+    # Convert the uploaded file to a BytesIO object to read it in-memory
+    pdf_file = BytesIO(uploaded_file.read())
+    
+    # Load the PDF file with PyPDFLoader
+    loader = PyPDFLoader(pdf_file)
     documents = loader.load()
     
     # Split documents into smaller chunks for better processing
@@ -40,13 +44,13 @@ if uploaded_file is not None:
     split_docs = text_splitter.split_documents(documents)
 
     # Create embeddings using Groq
-    embeddings = GroqEmbedding(api_key=GROQ_API_KEY)
+    embeddings = GroqEmbedding(model="groq-embedding-model")  # Use your preferred Groq model
     
-    # Create a FAISS vector store
+    # Create a FAISS vector store with the embeddings
     vector_db = FAISS.from_documents(split_docs, embeddings)
     
     # Initialize the retrieval-based QA system
-    qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", vectorstore=vector_db)
+    qa = RetrievalQA.from_chain_type(llm=None, chain_type="stuff", vectorstore=vector_db)
     
     # User input for querying the PDF content
     query = st.text_input("Ask a question about the PDF:")