Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,181 +1,278 @@
-import streamlit as st
-import os
-from langchain_groq import ChatGroq
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.chains.combine_documents import create_stuff_documents_chain
-from langchain_core.prompts import ChatPromptTemplate
-from langchain.chains import create_retrieval_chain
-from langchain_community.vectorstores import FAISS
-from langchain_community.document_loaders import PyPDFDirectoryLoader
-from langchain_google_genai import GoogleGenerativeAIEmbeddings
-from dotenv import load_dotenv
-from  PDFprocess_sample import process_pdf
+# import streamlit as st
+# import os
+# from langchain_groq import ChatGroq
+# from langchain.text_splitter import RecursiveCharacterTextSplitter
+# from langchain.chains.combine_documents import create_stuff_documents_chain
+# from langchain_core.prompts import ChatPromptTemplate
+# from langchain.chains import create_retrieval_chain
+# from langchain_community.vectorstores import FAISS
+# from langchain_community.document_loaders import PyPDFDirectoryLoader
+# from langchain_google_genai import GoogleGenerativeAIEmbeddings
+# from dotenv import load_dotenv
+# from  PDFprocess_sample import process_pdf
+
+# # Loading GROQ and Google API
+# load_dotenv()
+
+# GROQ_API_KEY = os.getenv('GROQ_API_KEY')
+# os.environ["GOOGLE_API_KEY"]= os.getenv('GOOGLE_API_KEY')
+
+# #Loading CSS files
+
+# # def load_css(file_name):
+# #     with open(file_name) as f:
+# #         css = f.read()
+# #     st.markdown(f"<style>{css}</style>", unsafe_allow_html=True)
+
+# import os
 
-# Loading GROQ and Google API
-load_dotenv()
+# def load_css(file_name):
+#     current_dir = os.path.dirname(__file__)
+#     file_path = os.path.join(current_dir, file_name)
+#     with open(file_path, "r") as f:
+#         st.markdown(f"<style>{f.read()}</style>", unsafe_allow_html=True)
 
-GROQ_API_KEY = os.getenv('GROQ_API_KEY')
-os.environ["GOOGLE_API_KEY"]= os.getenv('GOOGLE_API_KEY')
+# load_css("CSS/style.css")
 
-#Loading CSS files
 
-# def load_css(file_name):
-#     with open(file_name) as f:
-#         css = f.read()
-#     st.markdown(f"<style>{css}</style>", unsafe_allow_html=True)
 
-import os
+# #setting up LLM
+# llm = ChatGroq(
+#     api_key=GROQ_API_KEY,
+#     model_name="Llama3-8b-8192"
+# )
 
-def load_css(file_name):
-    current_dir = os.path.dirname(__file__)
-    file_path = os.path.join(current_dir, file_name)
-    with open(file_path, "r") as f:
-        st.markdown(f"<style>{f.read()}</style>", unsafe_allow_html=True)
 
-load_css("CSS/style.css")
+# prompt = ChatPromptTemplate.from_template(
+#     """
+#     Answer the questions based on the provided context only.
+#     Please provide the most accurate response based on the question. Try to answer in detail in 1500 words
+#     <context>
+#     {context}
+#     <context>
+#     Questions: {input}
+#     """
+# )
 
+# input_method = st.sidebar.selectbox("Choose a method" , ["Choose input method...","Interact with Doc", "Get Ques from Doc"])
 
 
-#setting up LLM
-llm = ChatGroq(
-    api_key=GROQ_API_KEY,
-    model_name="Llama3-8b-8192"
-)
 
+# st.sidebar.title("Upload your pdf")
 
-prompt = ChatPromptTemplate.from_template(
-    """
-    Answer the questions based on the provided context only.
-    Please provide the most accurate response based on the question. Try to answer in detail in 1500 words
-    <context>
-    {context}
-    <context>
-    Questions: {input}
-    """
-)
+# main_placeholder = st.empty()
+# # #Document upload
+# # uploaded_file = st.sidebar.file_uploader("_____________________________________", type="pdf", accept_multiple_files=True)
+# # st.sidebar.write("Press Submit to process:")
 
-input_method = st.sidebar.selectbox("Choose a method" , ["Choose input method...","Interact with Doc", "Get Ques from Doc"])
 
 
+# # process = st.sidebar.button("Submit")
 
-st.sidebar.title("Upload your pdf")
+# uploaded_files = st.sidebar.file_uploader("Upload your PDFs", type="pdf", accept_multiple_files=True)
 
-main_placeholder = st.empty()
-# #Document upload
-# uploaded_file = st.sidebar.file_uploader("_____________________________________", type="pdf", accept_multiple_files=True)
-# st.sidebar.write("Press Submit to process:")
 
+# process = st.sidebar.button("Submit")
+# # Document processing
 
+# if process:
+#     if uploaded_files:
+#         for uploaded_file in uploaded_files:
+#             file_path = f"/tmp/{uploaded_file.name}"
+#             with open(file_path, "wb") as f:
+#                 f.write(uploaded_file.getbuffer())
+#             st.write(f"Processing file: {file_path}")
+#             st.success(f"{uploaded_file.name} uploaded successfully!")
+#             process_pdf(file_path)
+#     else:
+#         st.warning("Please upload at least one PDF file.")
 
-# process = st.sidebar.button("Submit")
 
-uploaded_files = st.sidebar.file_uploader("Upload your PDFs", type="pdf", accept_multiple_files=True)
 
 
-process = st.sidebar.button("Submit")
-# Document processing
+# #Document processing to convert it into vectors
+# # if process:
+# #     if uploaded_file:
+# #         # Process the uploaded PDF file
+# #         process_pdf(uploaded_file)
+# #     else:
+# #         st.warning("Please upload a PDF file.")
 
-if process:
-    if uploaded_files:
-        for uploaded_file in uploaded_files:
-            file_path = f"/tmp/{uploaded_file.name}"
-            with open(file_path, "wb") as f:
-                f.write(uploaded_file.getbuffer())
-            st.write(f"Processing file: {file_path}")
-            st.success(f"{uploaded_file.name} uploaded successfully!")
-            process_pdf(file_path)
-    else:
-        st.warning("Please upload at least one PDF file.")
+# # Document processing
+# # if process:
+# #     if uploaded_file:
+# #         # Save to /tmp/ before processing
+# #         file_path = f"/tmp/{uploaded_file.name}"
+# #         with open(file_path, "wb") as f:
+# #             f.write(uploaded_file.getbuffer())
+        
+# #         # Call your existing logic with the saved path
+# #         process_pdf(file_path)
+# #     else:
+# #         st.warning("Please upload a PDF file.")
 
 
 
+        
+# if input_method == "Choose input method...":
+#     st.title(f"Welcome You all!")
+#     st.title("Choose an option in the sidebar")
+#     st.title("Now, let's get started!") 
+    
+        
+# #If User wants to interact with the document
+# elif input_method == "Interact with Doc":
+#     st.title(f"let's Interact with pdf's")
 
-#Document processing to convert it into vectors
-# if process:
-#     if uploaded_file:
-#         # Process the uploaded PDF file
-#         process_pdf(uploaded_file)
-#     else:
-#         st.warning("Please upload a PDF file.")
+#     prompt1 = st.text_input("______", placeholder="Enter your Question")
 
-# Document processing
-# if process:
-#     if uploaded_file:
-#         # Save to /tmp/ before processing
-#         file_path = f"/tmp/{uploaded_file.name}"
-#         with open(file_path, "wb") as f:
-#             f.write(uploaded_file.getbuffer())
-        
-#         # Call your existing logic with the saved path
-#         process_pdf(file_path)
-#     else:
-#         st.warning("Please upload a PDF file.")
 
+#     # Generate response if question is entered
+#     if prompt1 and "vectors" in st.session_state:
+#         document_chain = create_stuff_documents_chain(llm, prompt)
+#         retriever = st.session_state.vectors.as_retriever()
+#         retrieval_chain = create_retrieval_chain(retriever, document_chain)
+        
+        
+#         response = retrieval_chain.invoke({'input': prompt1})
+
+#         # st.write(response['answer'])
+        
+#         #Get the respose in the card
+#         st.markdown(
+#         f"""
+#         <div class="card">
+#             <div class="response">{response['answer']}</div>
+#         </div>
+#         """,
+#         unsafe_allow_html=True,
+#     )
+        
+        
+        
+# #When User wants to get questions from the doc based on certain topic
+# elif input_method == "Get Ques from Doc":
+#     st.title(f"Let's Get Ques from Document")
+    
+#     prompt2 = """Based on the topic of {topic}, 
+#                 kindly provide a comprehensive list of all possible questions that could arise. 
+#                 For each question, provide detailed and explanatory answers in atleast 1000 words detail based on the context,
+#                 ensuring that the responses are as informative as possible.
+#                 make sure you strictly follow the {topic}"""
+#     topic = st.text_input("Enter a topic", placeholder="What is your topic")
+    
+#     # Generate response if question is entered
+#     if topic and "vectors" in st.session_state:
+#         document_chain = create_stuff_documents_chain(llm, prompt)
+#         retriever = st.session_state.vectors.as_retriever()
+#         retrieval_chain = create_retrieval_chain(retriever, document_chain)
+        
+        
+#         response = retrieval_chain.invoke({'input': prompt2})
+        
+#         #Get the respose in the card
+#         st.markdown(
+#         f"""
+#         <div class="card">
+#             <div class="response">{response['answer']}</div>
+#         </div>
+#         """,
+#         unsafe_allow_html=True,
+#     )
 
 
+import streamlit as st
+import os
+from PDFprocess_sample import process_pdf_from_path
+from langchain_core.runnables import Runnable
+from langchain.chains import RetrievalQA
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain_community.chat_models import ChatGoogleGenerativeAI
+from langchain.chains.retrieval_qa.base import create_retrieval_chain
+
+# Set up the page
+st.set_page_config(page_title="Chat with your PDF", layout="wide")
+
+# CSS Styling
+with open("src/CSS/style.css") as f:
+    st.markdown(f"<style>{f.read()}</style>", unsafe_allow_html=True)
+
+st.markdown("<h1 class='main-heading'>Chat with your PDF using Gemini AI</h1>", unsafe_allow_html=True)
+
+# Sidebar Upload
+st.sidebar.markdown("<h2 style='color: white;'>Upload PDFs</h2>", unsafe_allow_html=True)
+uploaded_files = st.sidebar.file_uploader("Upload your PDFs", type="pdf", accept_multiple_files=True)
+
+if uploaded_files:
+    for uploaded_file in uploaded_files:
+        file_path = f"/tmp/{uploaded_file.name}"
+        
+        with open(file_path, "wb") as f:
+            f.write(uploaded_file.getbuffer())
         
+        st.sidebar.success(f"{uploaded_file.name} uploaded successfully!")
+        st.write(f"Processing file: {uploaded_file.name}")
+        
+        process_pdf_from_path(file_path)
+
+# Select input method
+input_method = st.sidebar.selectbox("Choose input method...", ["Choose input method...", "Interact with Doc", "Get Ques from Doc"])
+
+# Initialize LLM
+llm = ChatGoogleGenerativeAI(model="gemini-pro")
+
 if input_method == "Choose input method...":
-    st.title(f"Welcome You all!")
-    st.title("Choose an option in the sidebar")
-    st.title("Now, let's get started!") 
+    st.title("Welcome You all!")
+    st.subheader("Choose an option in the sidebar")
+    st.write("Now, let's get started!") 
     
-        
-#If User wants to interact with the document
 elif input_method == "Interact with Doc":
-    st.title(f"let's Interact with pdf's")
+    st.title("Let's Interact with the PDF")
 
-    prompt1 = st.text_input("______", placeholder="Enter your Question")
+    prompt1 = st.text_input("Ask a question", placeholder="Enter your Question")
 
-
-    # Generate response if question is entered
     if prompt1 and "vectors" in st.session_state:
-        document_chain = create_stuff_documents_chain(llm, prompt)
+        document_chain = create_stuff_documents_chain(llm, prompt="Answer the question based on the document.")
         retriever = st.session_state.vectors.as_retriever()
         retrieval_chain = create_retrieval_chain(retriever, document_chain)
         
-        
         response = retrieval_chain.invoke({'input': prompt1})
 
-        # st.write(response['answer'])
-        
-        #Get the respose in the card
         st.markdown(
-        f"""
-        <div class="card">
-            <div class="response">{response['answer']}</div>
-        </div>
-        """,
-        unsafe_allow_html=True,
-    )
-        
-        
-        
-#When User wants to get questions from the doc based on certain topic
+            f"""
+            <div class="card">
+                <div class="response">{response['answer']}</div>
+            </div>
+            """,
+            unsafe_allow_html=True,
+        )
+
 elif input_method == "Get Ques from Doc":
-    st.title(f"Let's Get Ques from Document")
-    
-    prompt2 = """Based on the topic of {topic}, 
-                kindly provide a comprehensive list of all possible questions that could arise. 
-                For each question, provide detailed and explanatory answers in atleast 1000 words detail based on the context,
-                ensuring that the responses are as informative as possible.
-                make sure you strictly follow the {topic}"""
-    topic = st.text_input("Enter a topic", placeholder="What is your topic")
-    
-    # Generate response if question is entered
+    st.title("Let's Generate Questions from the Document")
+
+    topic = st.text_input("Enter a topic", placeholder="What is your topic?")
+
     if topic and "vectors" in st.session_state:
-        document_chain = create_stuff_documents_chain(llm, prompt)
+        prompt2 = f"""
+        Based on the topic of {topic}, 
+        kindly provide a comprehensive list of all possible questions that could arise. 
+        For each question, provide detailed and explanatory answers in at least 1000 words,
+        ensuring that the responses are as informative as possible.
+        Make sure you strictly follow the topic of {topic}.
+        """
+
+        document_chain = create_stuff_documents_chain(llm, prompt="Generate questions and answers based on the topic and document.")
         retriever = st.session_state.vectors.as_retriever()
         retrieval_chain = create_retrieval_chain(retriever, document_chain)
         
-        
         response = retrieval_chain.invoke({'input': prompt2})
-        
-        #Get the respose in the card
+
         st.markdown(
-        f"""
-        <div class="card">
-            <div class="response">{response['answer']}</div>
-        </div>
-        """,
-        unsafe_allow_html=True,
-    )
+            f"""
+            <div class="card">
+                <div class="response">{response['answer']}</div>
+            </div>
+            """,
+            unsafe_allow_html=True,
+        )
+