refactor: app.py (#26)

- refactor: app.py (b6fa951ce9bcb3b796306b5c90e2b66befa34ffd)


Co-authored-by: Khan <Uzaiir@users.noreply.huggingface.co>

src/app.py

@@ -0,0 +1,131 @@
+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)
+
+load_css('CSS/style.css')
+
+#setting up LLM
+llm = ChatGroq(
+    api_key=GROQ_API_KEY,
+    model_name="Llama3-8b-8192"
+)
+
+
+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"])
+
+
+
+st.sidebar.title("Upload your pdf")
+
+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 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 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")
+
+    prompt1 = st.text_input("______", 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)
+        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,
+    )

src/streamlit_app.py

@@ -1,278 +0,0 @@
-# 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
-
-# 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")
-
-
-
-# #setting up LLM
-# llm = ChatGroq(
-#     api_key=GROQ_API_KEY,
-#     model_name="Llama3-8b-8192"
-# )
-
-
-# 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"])
-
-
-
-# st.sidebar.title("Upload your pdf")
-
-# 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")
-
-# uploaded_files = st.sidebar.file_uploader("Upload your PDFs", type="pdf", accept_multiple_files=True)
-
-
-# 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.")
-
-
-
-
-# #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.")
-
-# # 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")
-
-#     prompt1 = st.text_input("______", 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)
-#         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 os
-import streamlit as st
-from langchain.chains import RetrievalQA
-from langchain_google_genai import ChatGoogleGenerativeAI
-
-from PDFprocess_sample.py import process_pdf_from_path
-from langchain.vectorstores import FAISS
-import faiss
-
-# 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("Welcome You all!")
-    st.subheader("Choose an option in the sidebar")
-    st.write("Now, let's get started!") 
-    
-elif input_method == "Interact with Doc":
-    st.title("Let's Interact with the PDF")
-
-    prompt1 = st.text_input("Ask a question", placeholder="Enter your Question")
-
-    if prompt1 and "vectors" in st.session_state:
-        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.markdown(
-            f"""
-            <div class="card">
-                <div class="response">{response['answer']}</div>
-            </div>
-            """,
-            unsafe_allow_html=True,
-        )
-
-elif input_method == "Get Ques from Doc":
-    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:
-        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})
-
-        st.markdown(
-            f"""
-            <div class="card">
-                <div class="response">{response['answer']}</div>
-            </div>
-            """,
-            unsafe_allow_html=True,
-        )
-