Update app.py

app.py

@@ -1,7 +1,7 @@
 import streamlit as st  
 from langchain_core.messages import HumanMessage, AIMessage, SystemMessage
 from langchain_core.prompts import ChatPromptTemplate, SystemMessagePromptTemplate, HumanMessagePromptTemplate
-
+import os 
 
 st.title(':blue[Langchain:] A Rag System on “Leave No Context Behind” Paper')
 st.header("AI Chatbot :robot_face:")
@@ -29,8 +29,7 @@ chat_template = ChatPromptTemplate.from_messages([
 
 from langchain_google_genai import ChatGoogleGenerativeAI  
 
-chat_model = ChatGoogleGenerativeAI(google_api_key=KEY, 
-                                model="gemini-1.5-pro-latest")
+chat_model = ChatGoogleGenerativeAI(model="gemini-1.5-pro-latest")
 
 from langchain_core.output_parsers import StrOutputParser
 
@@ -38,8 +37,8 @@ output_parser = StrOutputParser()
 
 chain = chat_template | chat_model | output_parser
 
-from langchain_community.document_loaders import PDFMinerLoader  # type: ignore
-dat = PDFMinerLoader(r"D:\Langchain\rag_system\2404.07143.pdf")
+from langchain_community.document_loaders import PDFMinerLoader
+dat = PDFMinerLoader(r"2404.07143.pdf")
 dat_nik =dat.load()
 # Split the document into chunks
 
@@ -52,12 +51,11 @@ chunks = text_splitter.split_documents(dat_nik)
 # We are just loading OpenAIEmbeddings
 from langchain_google_genai import GoogleGenerativeAIEmbeddings  # type: ignore
 
-embedding_model = GoogleGenerativeAIEmbeddings(google_api_key=KEY, 
-                                            model="models/embedding-001")
+embedding_model = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
 
 # vectors = embeddings.embed_documents(chunks)
 # Store the chunks in vector store
-from langchain_community.vectorstores import Chroma  # type: ignore
+from langchain_community.vectorstores import Chroma  
 
 # Creating a New Chroma Database
 db = Chroma.from_documents(chunks, embedding_model, persist_directory="./chroma_db_1")