Update app.py

app.py

@@ -1,24 +1,25 @@
+import os
 import streamlit as st
 from dotenv import load_dotenv
 from PyPDF2 import PdfReader
 from langchain.text_splitter import CharacterTextSplitter
-from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
 from langchain.vectorstores import FAISS
-from langchain.chat_models import ChatOpenAI
 from langchain.memory import ConversationBufferMemory
 from langchain.chains import ConversationalRetrievalChain
-from htmlTemplates import css, bot_template, user_template
 from langchain.llms import HuggingFaceHub
+from langchain.embeddings import HuggingFaceEmbeddings
 
 def get_pdf_text(pdf_docs):
     text = ""
     for pdf in pdf_docs:
-        pdf_reader = PdfReader(pdf)
-        for page in pdf_reader.pages:
-            text += page.extract_text()
+        try:
+            pdf_reader = PdfReader(pdf)
+            for page in pdf_reader.pages:
+                text += page.extract_text()
+        except Exception as e:
+            st.error(f"Error reading {pdf.name}: {e}. Skipping this file.")
     return text
 
-
 def get_text_chunks(text):
     text_splitter = CharacterTextSplitter(
         separator="\n",
@@ -29,17 +30,23 @@ def get_text_chunks(text):
     chunks = text_splitter.split_text(text)
     return chunks
 
-
 def get_vectorstore(text_chunks):
-    embeddings = OpenAIEmbeddings()
-    # embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
-    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
-    return vectorstore
-
+    try:
+        embedding = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+        vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embedding)
+        return vectorstore
+    except Exception as e:
+        st.error(f"Error creating vector store: {e}")
+        return None
 
 def get_conversation_chain(vectorstore):
-    llm = ChatOpenAI()
-    # llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
+    # Fetch the HuggingFace API token from environment variable
+    api_token = os.getenv("HUGGINGFACE_API_TOKEN ")
+    if not api_token:
+        st.error("HuggingFace API token not found. Please ensure it is set in the environment variables.")
+        return None
+
+    llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature": 0.5, "max_length": 512}, huggingfacehub_api_token=api_token)
 
     memory = ConversationBufferMemory(
         memory_key='chat_history', return_messages=True)
@@ -50,25 +57,13 @@ def get_conversation_chain(vectorstore):
     )
     return conversation_chain
 
-
 def handle_userinput(user_question):
     response = st.session_state.conversation({'question': user_question})
     st.session_state.chat_history = response['chat_history']
 
-    for i, message in enumerate(st.session_state.chat_history):
-        if i % 2 == 0:
-            st.write(user_template.replace(
-                "{{MSG}}", message.content), unsafe_allow_html=True)
-        else:
-            st.write(bot_template.replace(
-                "{{MSG}}", message.content), unsafe_allow_html=True)
-
-
 def main():
     load_dotenv()
-    st.set_page_config(page_title="Chat with multiple PDFs",
-                       page_icon=":books:")
-    st.write(css, unsafe_allow_html=True)
+    st.set_page_config(page_title="Chat with multiple PDFs", page_icon=":books:")
 
     if "conversation" not in st.session_state:
         st.session_state.conversation = None
@@ -89,16 +84,16 @@ def main():
                 # get pdf text
                 raw_text = get_pdf_text(pdf_docs)
 
-                # get the text chunks
-                text_chunks = get_text_chunks(raw_text)
-
-                # create vector store
-                vectorstore = get_vectorstore(text_chunks)
+                if raw_text:  # Proceed only if there is valid text
+                    # get the text chunks
+                    text_chunks = get_text_chunks(raw_text)
 
-                # create conversation chain
-                st.session_state.conversation = get_conversation_chain(
-                    vectorstore)
+                    # create vector store
+                    vectorstore = get_vectorstore(text_chunks)
 
+                    if vectorstore:  # Check if vectorstore is valid
+                        # create conversation chain
+                        st.session_state.conversation = get_conversation_chain(vectorstore)
 
 if __name__ == '__main__':
-    main()
+    main()