Update app.py

app.py

@@ -1,130 +1,239 @@
-import gradio as gr
 import streamlit as st
+import langchain
+from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.embeddings.openai import OpenAIEmbeddings
-from langchain.text_splitter import CharacterTextSplitter
 from langchain.vectorstores import Chroma
-from langchain.chains import ConversationalRetrievalChain
-from langchain.chat_models import ChatOpenAI
-from langchain.document_loaders import PyPDFLoader
-import os
-import fitz
-from PIL import Image
+from langchain import OpenAI, VectorDBQA
+from langchain.chains import RetrievalQAWithSourcesChain
+import PyPDF2
+
+api_key = os.environ["OPENAI_API_KEY"]
+
+#This function will go through pdf and extract and return list of page texts.
+def read_and_textify(files):
+    text_list = []
+    sources_list = []
+    for file in files:
+        pdfReader = PyPDF2.PdfReader(file)
+        #print("Page Number:", len(pdfReader.pages))
+        for i in range(len(pdfReader.pages)):
+          pageObj = pdfReader.pages[i]
+          text = pageObj.extract_text()
+          pageObj.clear()
+          text_list.append(text)
+          sources_list.append(file.name + "_page_"+str(i))
+    return [text_list,sources_list]
+  
+st.set_page_config(layout="centered", page_title="Multidoc_QnA")
+st.header("Multidoc_QnA")
+st.write("---")
+  
+#file uploader
+uploaded_files = st.file_uploader("Upload documents",accept_multiple_files=True, type=["txt","pdf"])
+st.write("---")
+
+if uploaded_files is None:
+  st.info(f"""Upload files to analyse""")
+elif uploaded_files:
+  st.write(str(len(uploaded_files)) + " document(s) loaded..")
+  
+  textify_output = read_and_textify(uploaded_files)
+  
+  documents = textify_output[0]
+  sources = textify_output[1]
+  
+  #extract embeddings
+  embeddings = OpenAIEmbeddings(openai_api_key = api_key)
+  #vstore with metadata. Here we will store page numbers.
+  vStore = Chroma.from_texts(documents, embeddings, metadatas=[{"source": s} for s in sources])
+  #deciding model
+  model_name = "gpt-3.5-turbo"
+  # model_name = "gpt-4"
+
+  retriever = vStore.as_retriever()
+  retriever.search_kwargs = {'k':2}
+
+  #initiate model
+  llm = OpenAI(model_name=model_name, openai_api_key = api_key, streaming=True)
+  model = RetrievalQAWithSourcesChain.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever)
+  
+  st.header("Ask your data")
+  user_q = st.text_area("Enter your questions here")
+  
+  if st.button("Get Response"):
+    try:
+      with st.spinner("Model is working on it..."):
+        result = model({"question":user_q}, return_only_outputs=True)
+        st.subheader('Your response:')
+        st.write(result['answer'])
+        st.subheader('Source pages:')
+        st.write(result['sources'])
+    except Exception as e:
+      st.error(f"An error occurred: {e}")
+      st.error('Oops, the GPT response resulted in an error :( Please try again with a different question.')
+      
+        
+    
+  
+  
+  
+  
+  
+  
+  
+  
+  
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+# import gradio as gr
+# import streamlit as st
+# from langchain.embeddings.openai import OpenAIEmbeddings
+# from langchain.text_splitter import CharacterTextSplitter
+# from langchain.vectorstores import Chroma
+# from langchain.chains import ConversationalRetrievalChain
+# from langchain.chat_models import ChatOpenAI
+# from langchain.document_loaders import PyPDFLoader
+# import os
+# import fitz
+# from PIL import Image
 
 
-# Global variables
-COUNT, N = 0, 0
-chat_history = []
-chain = None  # Initialize chain as None
+# # Global variables
+# COUNT, N = 0, 0
+# chat_history = []
+# chain = None  # Initialize chain as None
 
-# Function to set the OpenAI API key
+# # Function to set the OpenAI API key
 
-api_key = os.environ['OPENAI_API_KEY']
+# api_key = os.environ['OPENAI_API_KEY']
 
-st.write(api_key)
+# st.write(api_key)
 
     
-# Function to enable the API key input box
-def enable_api_box():
-    return enable_box
-
-# Function to add text to the chat history
-def add_text(history, text):
-    if not text:
-        raise gr.Error('Enter text')
-    history = history + [(text, '')]
-    return history
-
-# Function to process the PDF file and create a conversation chain
-def process_file(file):
-    global chain
-    if 'OPENAI_API_KEY' not in os.environ:
-        raise gr.Error('Upload your OpenAI API key')
-
-    # Replace with your actual PDF processing logic
-    loader = PyPDFLoader(file.name)
-    documents = loader.load()
-    embeddings = OpenAIEmbeddings()
-    pdfsearch = Chroma.from_documents(documents, embeddings)
-
-    chain = ConversationalRetrievalChain.from_llm(ChatOpenAI(temperature=0.3),
-                                    retriever=pdfsearch.as_retriever(search_kwargs={"k": 1}),
-                                    return_source_documents=True)
-    return chain
-
-# Function to generate a response based on the chat history and query
-def generate_response(history, query, pdf_upload):
-    global COUNT, N, chat_history, chain
-    if not pdf_upload:
-        raise gr.Error(message='Upload a PDF')
-
-    if COUNT == 0:
-        chain = process_file(pdf_upload)
-        COUNT += 1
-
-    # Replace with your LangChain logic to generate a response 
-    result = chain({"question": query, 'chat_history': chat_history}, return_only_outputs=True)  
-    chat_history += [(query, result["answer"])]
-    N = list(result['source_documents'][0])[1][1]['page']  # Adjust as needed
-
-    for char in result['answer']:
-        history[-1][-1] += char  
-    return history, ''  
-
-# Function to render a specific page of a PDF file as an image
-def render_file(file):
-    global N
-    doc = fitz.open(file.name)
-    page = doc[N]
-    pix = page.get_pixmap(matrix=fitz.Matrix(300/72, 300/72)) 
-    image = Image.frombytes('RGB', [pix.width, pix.height], pix.samples)
-    return image
-
-# Function to render initial content from the PDF
-def render_first(pdf_file): 
-    # Replace with logic to process the PDF and generate an initial image
-    image = Image.new('RGB', (600, 400), color = 'white') # Placeholder
-    return image
-
-# Streamlit & Gradio Interface
-
-st.title("PDF-Powered Chatbot") 
-
-with st.container():      
-  gr.Markdown("""     
-  <style>       
-  .image-container { height: 680px; }     
-  </style>     
-  """)    
-
-with gr.Blocks() as demo:
-    pdf_upload1 = gr.UploadButton("📁 Upload PDF 1", file_types=[".pdf"])  # Define pdf_upload1
-
-    # ... (rest of your interface creation)
-
-    txt = gr.Textbox(label="Enter your query", placeholder="Ask a question...")     
-    submit_btn = gr.Button('Submit')
-
-    @submit_btn.click()
-    def on_submit():
-      add_text(chatbot, txt)
-      generate_response(chatbot, txt, pdf_upload1)  # Use pdf_upload1 here
-      render_file(pdf_upload1)  # Use pdf_upload1 here
-
-if __name__ == "__main__":
-    gr.Interface(         
-        fn=generate_response,
-        inputs=[
-            "file",  # Define pdf_upload1
-            "text",  # Define chatbot output
-            "text"   # Define txt
-        ],
-        outputs=[
-            "image",  # Define show_img
-            "text",   # Define chatbot output
-            "text"    # Define txt
-        ],   
-        title="PDF-Powered Chatbot"     
-    ).launch()
+# # Function to enable the API key input box
+# def enable_api_box():
+#     return enable_box
+
+# # Function to add text to the chat history
+# def add_text(history, text):
+#     if not text:
+#         raise gr.Error('Enter text')
+#     history = history + [(text, '')]
+#     return history
+
+# # Function to process the PDF file and create a conversation chain
+# def process_file(file):
+#     global chain
+#     if 'OPENAI_API_KEY' not in os.environ:
+#         raise gr.Error('Upload your OpenAI API key')
+
+#     # Replace with your actual PDF processing logic
+#     loader = PyPDFLoader(file.name)
+#     documents = loader.load()
+#     embeddings = OpenAIEmbeddings()
+#     pdfsearch = Chroma.from_documents(documents, embeddings)
+
+#     chain = ConversationalRetrievalChain.from_llm(ChatOpenAI(temperature=0.3),
+#                                     retriever=pdfsearch.as_retriever(search_kwargs={"k": 1}),
+#                                     return_source_documents=True)
+#     return chain
+
+# # Function to generate a response based on the chat history and query
+# def generate_response(history, query, pdf_upload):
+#     global COUNT, N, chat_history, chain
+#     if not pdf_upload:
+#         raise gr.Error(message='Upload a PDF')
+
+#     if COUNT == 0:
+#         chain = process_file(pdf_upload)
+#         COUNT += 1
+
+#     # Replace with your LangChain logic to generate a response 
+#     result = chain({"question": query, 'chat_history': chat_history}, return_only_outputs=True)  
+#     chat_history += [(query, result["answer"])]
+#     N = list(result['source_documents'][0])[1][1]['page']  # Adjust as needed
+
+#     for char in result['answer']:
+#         history[-1][-1] += char  
+#     return history, ''  
+
+# # Function to render a specific page of a PDF file as an image
+# def render_file(file):
+#     global N
+#     doc = fitz.open(file.name)
+#     page = doc[N]
+#     pix = page.get_pixmap(matrix=fitz.Matrix(300/72, 300/72)) 
+#     image = Image.frombytes('RGB', [pix.width, pix.height], pix.samples)
+#     return image
+
+# # Function to render initial content from the PDF
+# def render_first(pdf_file): 
+#     # Replace with logic to process the PDF and generate an initial image
+#     image = Image.new('RGB', (600, 400), color = 'white') # Placeholder
+#     return image
+
+# # Streamlit & Gradio Interface
+
+# st.title("PDF-Powered Chatbot") 
+
+# with st.container():      
+#   gr.Markdown("""     
+#   <style>       
+#   .image-container { height: 680px; }     
+#   </style>     
+#   """)    
+
+# with gr.Blocks() as demo:
+#     pdf_upload1 = gr.UploadButton("📁 Upload PDF 1", file_types=[".pdf"])  # Define pdf_upload1
+
+#     # ... (rest of your interface creation)
+
+#     txt = gr.Textbox(label="Enter your query", placeholder="Ask a question...")     
+#     submit_btn = gr.Button('Submit')
+
+#     @submit_btn.click()
+#     def on_submit():
+#       add_text(chatbot, txt)
+#       generate_response(chatbot, txt, pdf_upload1)  # Use pdf_upload1 here
+#       render_file(pdf_upload1)  # Use pdf_upload1 here
+
+# if __name__ == "__main__":
+#     gr.Interface(         
+#         fn=generate_response,
+#         inputs=[
+#             "file",  # Define pdf_upload1
+#             "text",  # Define chatbot output
+#             "text"   # Define txt
+#         ],
+#         outputs=[
+#             "image",  # Define show_img
+#             "text",   # Define chatbot output
+#             "text"    # Define txt
+#         ],   
+#         title="PDF-Powered Chatbot"     
+#     ).launch()