Update app.py

app.py

@@ -1,17 +1,17 @@
-import streamlit as st 
+import streamlit as st
 import os
 import base64
 import time
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM 
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 from transformers import pipeline
-import torch 
-import textwrap 
-from langchain.document_loaders import PyPDFLoader, DirectoryLoader, PDFMinerLoader 
-from langchain.text_splitter import RecursiveCharacterTextSplitter 
-from langchain.embeddings import SentenceTransformerEmbeddings 
-from langchain.vectorstores import Chroma 
+import torch
+import textwrap
+from langchain.document_loaders import PyPDFLoader, DirectoryLoader, PDFMinerLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import SentenceTransformerEmbeddings
+from langchain.vectorstores import Chroma
 from langchain.llms import HuggingFacePipeline
-from langchain.chains import RetrievalQA 
+from langchain.chains import RetrievalQA
 from constants import CHROMA_SETTINGS
 from streamlit_chat import message
 
@@ -28,16 +28,6 @@ base_model = AutoModelForSeq2SeqLM.from_pretrained(
     torch_dtype=torch.float32
 )
 
-
-# checkpoint = "LaMini-T5-738M"
-# tokenizer = AutoTokenizer.from_pretrained(checkpoint)
-# base_model = AutoModelForSeq2SeqLM.from_pretrained(
-#     checkpoint,
-#     device_map="auto",
-#     torch_dtype = torch.float32,
-#     from_tf=True
-# )
-
 persist_directory = "db"
 
 @st.cache_resource
@@ -55,7 +45,7 @@ def data_ingestion():
     #create vector store here
     db = Chroma.from_documents(texts, embeddings, persist_directory=persist_directory, client_settings=CHROMA_SETTINGS)
     db.persist()
-    db=None 
+    db=None
 
 @st.cache_resource
 def llm_pipeline():
@@ -100,8 +90,11 @@ def get_file_size(file):
     file.seek(0)
     return file_size
 
+# Specify the path to your PDF document directly
+filepath = "removed_null.pdf"
+
 @st.cache_data
-#function to display the PDF of a given file 
+#function to display the PDF of a given file
 def displayPDF(file):
     # Opening file from file path
     with open(file, "rb") as f:
@@ -125,57 +118,40 @@ def main():
 
     st.markdown("<h2 style='text-align: center; color:red;'>Upload your Legal Document 👇</h2>", unsafe_allow_html=True)
 
-    uploaded_file = st.file_uploader("", type=["pdf"])
-
-    if uploaded_file is not None:
-        file_details = {
-            "Filename": uploaded_file.name,
-            "File size": get_file_size(uploaded_file)
-        }
-        filepath = uploaded_file.name
-        with open(filepath, "wb") as temp_file:
-                temp_file.write(uploaded_file.read())
-
-        col1, col2= st.columns([1,2])
-        with col1:
-            st.markdown("<h4 style color:black;'>File details</h4>", unsafe_allow_html=True)
-            st.json(file_details)
-            st.markdown("<h4 style color:black;'>File preview</h4>", unsafe_allow_html=True)
-            pdf_view = displayPDF(filepath)
-
-        with col2:
-            with st.spinner('Embeddings are in process...'):
-                ingested_data = data_ingestion()
-            st.success('Embeddings are created successfully!')
-            st.markdown("<h4 style color:black;'>Chat Here</h4>", unsafe_allow_html=True)
-
-
-            user_input = st.text_input("", key="input")
-
-            # Initialize session state for generated responses and past messages
-            if "generated" not in st.session_state:
-                st.session_state["generated"] = ["I am ready to help you"]
-            if "past" not in st.session_state:
-                st.session_state["past"] = ["Hey there!"]
-                
-            # Search the database for a response based on user input and update session state
-            if user_input:
-                answer = process_answer({'query': user_input})
-                st.session_state["past"].append(user_input)
-                response = answer
-                st.session_state["generated"].append(response)
-
-            # Display conversation history using Streamlit messages
-            if st.session_state["generated"]:
-                display_conversation(st.session_state)
-        
-
-        
-
-
-
+    col1, col2= st.columns([1,2])
+    with col1:
+        st.markdown("<h4 style color:black;'>File details</h4>", unsafe_allow_html=True)
+        # You can display any additional file details here if needed
+        st.markdown("<h4 style color:black;'>File preview</h4>", unsafe_allow_html=True)
+        pdf_view = displayPDF(filepath)
+
+    with col2:
+        with st.spinner('Embeddings are in process...'):
+            ingested_data = data_ingestion()
+        st.success('Embeddings are created successfully!')
+        st.markdown("<h4 style color:black;'>Chat Here</h4>", unsafe_allow_html=True)
+
+        user_input = st.text_input("", key="input")
+
+        # Initialize session state for generated responses and past messages
+        if "generated" not in st.session_state:
+            st.session_state["generated"] = ["I am ready to help you"]
+        if "past" not in st.session_state:
+            st.session_state["past"] = ["Hey there!"]
+
+        # Search the database for a response based on user input and update session state
+        if user_input:
+            answer = process_answer({'query': user_input})
+            st.session_state["past"].append(user_input)
+            response = answer
+            st.session_state["generated"].append(response)
+
+        # Display conversation history using Streamlit messages
+        if st.session_state["generated"]:
+            display_conversation(st.session_state)
 
 if __name__ == "__main__":
     main()
 
 
+