Delete app.py

app.py

@@ -1,316 +0,0 @@
-import streamlit as st
-from langchain_core.prompts import ChatPromptTemplate
-from langchain_openai import AzureChatOpenAI
-from langchain.chains import create_retrieval_chain
-from langchain.chains.combine_documents import create_stuff_documents_chain
-from langchain_community.vectorstores import FAISS
-from langchain_text_splitters import RecursiveCharacterTextSplitter
-from langchain_openai import OpenAIEmbeddings
-import pandas as pd
-import io
-import time
-
-from langchain.document_loaders import UnstructuredFileLoader
-from typing import List, Dict, Tuple
-from langchain_openai import AzureChatOpenAI,AzureOpenAIEmbeddings
-from langchain.vectorstores import FAISS
-from langchain.text_splitter import CharacterTextSplitter
-
-class PDFExtract:
-    def __init__(self):
-      pass
-
-    def _extract_text_from_pdfs(self, file_paths: List[str]) -> List[str]:
-        """Extract text content from PDF files.
-        Args:
-            file_paths (List[str]): List of file paths.
-        Returns:
-            List[str]: Extracted text from the PDFs.
-        """
-        docs = []
-        loaders = [UnstructuredFileLoader(file_obj, strategy="fast") for file_obj in file_paths]
-        for loader in loaders:
-            docs.extend(loader.load())
-        return docs
-
-    def _split_text_into_chunks(self, text: str) -> List[str]:
-        """Split text into smaller chunks.
-        Args:
-            text (str): Input text to be split.
-        Returns:
-            List[str]: List of smaller text chunks.
-        """
-        text_splitter = CharacterTextSplitter(separator="\n", chunk_size=2000, chunk_overlap=0, length_function=len)
-
-        chunks = text_splitter.split_documents(text)
-
-        return chunks
-
-    def _create_vector_store_from_text_chunks(self, text_chunks: List[str]) -> FAISS:
-        """Create a vector store from text chunks.
-        Args:
-            text_chunks (List[str]): List of text chunks.
-        Returns:
-            FAISS: Vector store created from the text chunks.
-        """
-        embeddings = AzureOpenAIEmbeddings(
-                        azure_deployment="text-embedding-3-large",
-                    )
-
-        return FAISS.from_documents(documents=text_chunks, embedding=embeddings)
-
-    def main(self,file_paths: List[str]):
-      text = self._extract_text_from_pdfs(file_paths)
-      text_chunks = self._split_text_into_chunks(text)
-      vector_store = self._create_vector_store_from_text_chunks(text_chunks)
-      return vector_store
-# Set page configuration
-st.set_page_config(page_title="GASB Decision Flow", layout="wide")
-
-# Custom CSS for better UI
-st.markdown("""
-<style>
-    .uploadfile-container {
-        display: flex;
-        justify-content: center;
-        margin-bottom: 20px;
-    }
-    .chat-container {
-        margin-top: 20px;
-    }
-    .stApp {
-        max-width: 1200px;
-        margin: 0 auto;
-    }
-    .loader {
-        border: 8px solid #f3f3f3;
-        border-top: 8px solid #3498db;
-        border-radius: 50%;
-        width: 50px;
-        height: 50px;
-        animation: spin 1s linear infinite;
-        margin: 20px auto;
-    }
-    @keyframes spin {
-        0% { transform: rotate(0deg); }
-        100% { transform: rotate(360deg); }
-    }
-    
-    /* Hide scrollbars but keep scrolling functionality */
-    ::-webkit-scrollbar {
-        width: 0px;
-        height: 0px;
-        background: transparent;
-    }
-    
-    * {
-        -ms-overflow-style: none;
-        scrollbar-width: none;
-    }
-    
-    div[data-testid="stVerticalBlock"] {
-        overflow-x: hidden;
-    }
-    
-    .element-container, .stTextInput, .stButton {
-        overflow: visible !important;
-    }
-    
-    /* Custom chat message styling */
-    .user-message-container {
-        display: flex;
-        justify-content: flex-end;
-        margin-bottom: 10px;
-    }
-    .st-emotion-cache-janbn0
-    {
-      margin-left: 3in;
-    }
-    .user-message {
-        background-color: #2b7dfa;
-        color: white;
-        border-radius: 18px 18px 0 18px;
-        padding: 10px 15px;
-        max-width: 70%;
-        text-align: right;
-    }
-    
-    .assistant-message-container {
-        display: flex;
-        justify-content: flex-start;
-        margin-bottom: 10px;
-    }
-    
-    .assistant-message {
-        background-color: #f1f1f1;
-        color: #333;
-        border-radius: 18px 18px 18px 0;
-        padding: 10px 15px;
-        max-width: 70%;
-    }
-</style>
-""", unsafe_allow_html=True)
-
-# Title and description
-st.title("22nd Century")
-st.markdown("Upload your document and ask questions to determine GASB compliance")
-
-# Initialize session state for chat history
-if 'messages' not in st.session_state:
-    st.session_state.messages = []
-
-if 'db' not in st.session_state:
-    st.session_state.db = None
-
-if 'file_processed' not in st.session_state:
-    st.session_state.file_processed = False
-
-# Function to process the uploaded file
-def process_file(uploaded_file):
-    with st.spinner("Processing document..."):
-        # Read file content
-        if uploaded_file.type == "application/pdf":
-            pdfextract = PDFExtract()
-            db = pdfextract.main([uploaded_file.name])
-        
-        return db
-
-# Center the file uploader
-st.markdown('<div class="uploadfile-container">', unsafe_allow_html=True)
-uploaded_file = st.file_uploader("Upload your contract document (PDF, Word, or Text)", type=["pdf", "docx", "txt"])
-st.markdown('</div>', unsafe_allow_html=True)
-
-# Process the file when uploaded
-if uploaded_file and not st.session_state.file_processed:
-    db = process_file(uploaded_file)
-    if db:
-        st.session_state.db = db
-        st.session_state.file_processed = True
-        st.success(f"Document '{uploaded_file.name}' processed successfully!")
-
-# GASB decision flow logic
-if st.session_state.file_processed:
-    # Setup langchain components
-    retriever = st.session_state.db.as_retriever()
-    llm = AzureChatOpenAI(model='gpt-4o', temperature=0, max_tokens=3000)
-    
-    system_prompt = (
-        "Use the given context to answer the question. Answer yes or no with justify the answer detailed. "
-        "If you don't know the answer, say you don't know. "
-        "Use three sentence maximum and keep the answer concise. "
-        """'GASB Do Not Apply' sentence include in the output for the following Questions Otherwise don't include:
-        Does the contract involve the use of software or capital assets? if answer is 'no' include 'GASB 87/96 Do Not Apply' in the answer.
-        Is the software an insignificant component to any fixed asset in the agreement? if answer is 'yes' include 'GASB 96 Do Not Apply' in the answer.
-        Is this a software that you are procuring? if answer is 'no' include 'GASB 96 Do Not Apply' in the answer.
-        Is it a perpetual license/agreement? if answer is 'yes' or 'no' include 'GASB 96 Do Not Apply' in the answer.
-
-        Lease Queries:{lease_queries} if 'yes' for all questions include 'GASB 87 Do Not Apply' in the answer.
-        Does the lease explicitly transfer ownership? if answer is 'no' include 'GASB 87 Do Not Apply' in the answer.
-
-        Must Return the Reason Why you answer yes or no.
-        """
-        "Context: {context}"
-    )
-    
-    prompt = ChatPromptTemplate.from_messages(
-        [
-            ("system", system_prompt),
-            ("human", "{input}"),
-        ]
-    )
-    
-    question_answer_chain = create_stuff_documents_chain(llm, prompt)
-    chain = create_retrieval_chain(retriever, question_answer_chain)
-    
-    # Define flows
-    initial_flow = ["Does the contract involve the use of software or capital assets?", "Does this contract include software?"]
-    
-    software_flow = [
-        "Is the software an insignificant component to any fixed asset in the agreement?",
-        "Is this a software that you are procuring?",
-        "Is it a perpetual license/agreement?"
-    ]
-    
-    lease_flow = [
-        "Is this a lease of an intangible asset?",
-        "Is this a lease for supply contracts?",
-        "Is this a lease of inventory?",
-        "Does the lease explicitly transfer ownership?"
-    ]
-    
-    # Chat container
-    st.markdown('<div class="chat-container">', unsafe_allow_html=True)
-    st.subheader("GASB Decision Flow Chat")
-    
-    # Display chat messages
-    for message in st.session_state.messages:
-        with st.chat_message(message["role"]):
-            st.write(message["content"])
-    
-    # Function to run the GASB decision flow
-    def run_gasb_flow():
-        with st.spinner("Running initial questions..."):
-            execute = True
-            
-            for question in initial_flow:
-                # Add user question to chat
-                st.session_state.messages.append({"role": "user", "content": question})
-                with st.chat_message("user"):
-                    st.write(question)
-                
-                # Get AI response
-                with st.spinner("Thinking..."):
-                    response = chain.invoke({"input": question, 'lease_queries': lease_flow})
-                    answer = response['answer']
-                
-                # Add AI response to chat
-                st.session_state.messages.append({"role": "assistant", "content": answer})
-                with st.chat_message("assistant"):
-                    st.write(answer)
-                
-                if "GASB" in answer:
-                    st.info("Flow stopped due to GASB answer.")
-                    execute = False
-                    break
-                
-                time.sleep(1)  # Small delay for better UX
-            
-            if execute:
-                if "software" in answer.lower():
-                    selected_flow = software_flow
-                    st.info("Continuing with software flow...")
-                else:
-                    selected_flow = lease_flow
-                    st.info("Continuing with lease flow...")
-                
-                for question in selected_flow:
-                    # Add user question to chat
-                    st.session_state.messages.append({"role": "user", "content": question})
-                    with st.chat_message("user"):
-                        st.write(question)
-                    
-                    # Get AI response
-                    with st.spinner("Thinking..."):
-                        response = chain.invoke({"input": question, 'lease_queries': lease_flow})
-                        answer = response['answer']
-                    
-                    # Add AI response to chat
-                    st.session_state.messages.append({"role": "assistant", "content": answer})
-                    with st.chat_message("assistant"):
-                        st.write(answer)
-                    
-                    if "GASB" in answer:
-                        st.info("Flow stopped due to GASB answer.")
-                        break
-                    
-                    time.sleep(2)  # Small delay for better UX
-    
-    # Custom question input
-    if st.session_state.file_processed and 'custom_mode' not in st.session_state:
-        if st.button("Start GASB Decision Flow"):
-            run_gasb_flow()
-            st.session_state.custom_mode = True
-    
-    st.markdown('</div>', unsafe_allow_html=True)
-else:
-    st.info("Please upload a document to start the GASB decision flow")