Update app.py

app.py

@@ -1,24 +1,21 @@
 import os
 import streamlit as st
-from langchain.embeddings import Embedding
 from groq import Groq
 from langchain.chains import RetrievalQA
 from langchain.vectorstores import FAISS
 from langchain.document_loaders import PyPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.llms import OpenAI
-from langchain.agents import initialize_agent
-from langchain.agents import Tool
 
-# Set up Groq API
-groq_client = Groq(api_key=os.getenv("GROQ_API_KEY"))
+# Set up Groq API key
+GROQ_API_KEY = "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"
 
-# Define a custom embedding class for Groq
-class GroqEmbedding(Embedding):
-    def __init__(self, model="groq-embedding-model", api_key=None):
+# Define a custom embedding class for Groq (since Langchain may not support direct Groq API integration)
+class GroqEmbedding:
+    def __init__(self, model="groq-embedding-model"):
         self.model = model
-        self.client = Groq(api_key=api_key or os.getenv("GROQ_API_KEY"))
-    
+        self.client = Groq(api_key=GROQ_API_KEY)
+
     def embed_documents(self, texts):
         # Use Groq's API to generate embeddings
         embeddings = self.client.embed_documents(texts, model=self.model)
@@ -43,7 +40,7 @@ if uploaded_file is not None:
     split_docs = text_splitter.split_documents(documents)
 
     # Create embeddings using Groq
-    embeddings = GroqEmbedding(api_key=os.getenv("GROQ_API_KEY"))
+    embeddings = GroqEmbedding(api_key=GROQ_API_KEY)
     
     # Create a FAISS vector store
     vector_db = FAISS.from_documents(split_docs, embeddings)
@@ -57,4 +54,3 @@ if uploaded_file is not None:
     if query:
         result = qa.run(query)
         st.write("Answer:", result)
-