Update app.py

app.py

@@ -2,20 +2,17 @@ from langchain_openai import ChatOpenAI
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.vectorstores import Chroma
-from langchain_community.document_loaders import PyPDFLoader
-from langchain_community.document_loaders import PDFPlumberLoader
 from langchain.chains import ConversationalRetrievalChain
 from langchain_community.chat_message_histories import ChatMessageHistory
 from langchain.memory import ConversationBufferMemory
 from langchain_core.prompts import PromptTemplate
+from langchain_core.document_loaders import BaseLoader
+from langchain_core.documents import Document
 import streamlit as st
 import os
 from io import BytesIO
-from langchain_core.document_loaders import BaseLoader
-from langchain_core.documents import Document
 import pdfplumber
 
-
 class InMemoryPDFLoader(BaseLoader):
     def __init__(self, file_bytes: bytes):
         self.file_bytes = file_bytes
@@ -30,7 +27,6 @@ class InMemoryPDFLoader(BaseLoader):
 
 # Access the OpenAI API key from the environment
 open_ai_key = os.getenv("OPENAI_API_KEY")
-
 llm = ChatOpenAI(api_key=open_ai_key)
 
 template = """Use the following pieces of information to answer the user's question.
@@ -45,71 +41,51 @@ Helpful answer:
 
 prompt = PromptTemplate(template=template, input_variables=["context", "question"])
 
-with st.chat_message("user"):
-    pdf_file = st.file_uploader("Upload your pdf",type="pdf")
-
-
-# upload PDF
-# pdf_file = st.file_uploader("Upload your pdf",type="pdf")
+pdf_file = st.file_uploader("Upload your PDF", type="pdf")
 question = st.chat_input("Ask your question")
 
-
 if pdf_file is not None:
-    try:   
+    try:
         pdf_bytes = pdf_file.read()
         loader = InMemoryPDFLoader(file_bytes=pdf_bytes)
-        # Load and process the PDF
-        # loader = PDFPlumberLoader(pdf_file)
         pdf_data = loader.load()
-        
+
         # Split the text into chunks
         text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
         docs = text_splitter.split_documents(pdf_data)
-        
+
         # Create a Chroma vector store
         embeddings = HuggingFaceEmbeddings(model_name="embaas/sentence-transformers-multilingual-e5-base")
         db = Chroma.from_documents(docs, embeddings)
-        
+
         # Initialize message history for conversation
         message_history = ChatMessageHistory()
-        
+
         # Memory for conversational context
         memory = ConversationBufferMemory(
-               memory_key="chat_history",
-               output_key="answer",
-               chat_memory=message_history,
-               return_messages=True,
-           )
-        
+            memory_key="chat_history",
+            output_key="answer",
+            chat_memory=message_history,
+            return_messages=True,
+        )
+
         # Create a chain that uses the Chroma vector store
         chain = ConversationalRetrievalChain.from_llm(
-                llm=llm,
-                chain_type="stuff",
-                retriever=db.as_retriever(),
-                memory=memory,
-                return_source_documents=False,
-                combine_docs_chain_kwargs={'prompt': prompt}
-            )
-        st.write("you can ask ")
+            llm=llm,
+            chain_type="stuff",
+            retriever=db.as_retriever(),
+            memory=memory,
+            return_source_documents=False,
+            combine_docs_chain_kwargs={'prompt': prompt}
+        )
+
         if question:
-             with st.chat_message("user"):
-                 
+            with st.chat_message("user"):
                 st.markdown(question)
-
-        
             with st.chat_message("assistant"):
-                # Process the question
                 res = chain({"question": question})
                 answer = res["answer"]
                 st.write(f"{answer}")
-            
-            # Process the question
-            # res = chain({"question": question})
-            # answer = res["answer"]
-            st.write_stream(chain({"question": question})["answer"])
-            # st.markdoun(answer)
-            # st.text(f"{answer}")
 
     except Exception as e:
         st.error(f"An error occurred: {e}")
-