Added files

Chatbot.py

@@ -0,0 +1,75 @@
+from dotenv import load_dotenv
+import streamlit as st
+from utils._admin_util import invoke_rag, get_ticket_category
+import os
+
+# Initialize categories in session state
+if "categories" not in st.session_state:
+    st.session_state.categories = {
+        "HR Support": [],
+        "IT Support": [],
+        "Transportation Support": [],
+        "Other": []
+    }
+
+def main():
+    load_dotenv()
+    
+    # Page configuration
+    st.set_page_config(
+        page_title="Intelligent Customer Support Agent",
+        page_icon="🤖",
+        layout="wide"
+    )
+
+    # Sidebar for API key
+    with st.sidebar:
+        #openai_api_key = st.text_input("OpenAI API Key", type="password")
+        st.markdown("---")
+        st.markdown("""
+        ### About
+        This is an AI-powered customer support agent that can answer questions or raise support ticket about the company policies and procedures:
+        - HR policies
+        - IT policies
+        - Transportation policies
+        - Other policies
+        """)
+        
+    # Set OpenAI API key
+    openai_api_key = os.getenv("OPENAI_API_KEY")
+    if not openai_api_key:
+        st.error("OpenAI API key not found! Please check your .env file.")
+        st.stop()
+
+    # Main chat interface
+    st.title("🤖 Intelligent Customer Support Agent")
+    st.caption("Your 24/7 AI Customer Service Representative")
+
+
+    st.header("Automatic Ticket Classification Tool")
+    #Capture user input
+    st.write("We are here to help you, please ask your question:")
+    prompt = st.text_input("🔍")
+
+    if prompt:
+        if "vector_store" not in st.session_state:
+            st.error("Please load the document data first!")
+            st.stop()
+        
+        response = invoke_rag(st.session_state.vector_store, prompt)
+        st.write(response)
+
+        #Button to create a ticket with respective department
+        button = st.button("Submit ticket?")
+        
+        if button:
+            category = get_ticket_category(prompt)
+            st.session_state.categories[category].append(prompt)
+            st.success("Ticket submitted successfully!")
+            # Display category (optional)
+            st.write(f"Category: {category}")
+        
+
+if __name__ == '__main__':
+    main()
+

Dockerfile

@@ -0,0 +1,23 @@
+# MIKE DEAN ADAPTATION OF THE CHAINLIT DOCKERFILE USING UV
+# December 31, 2024
+# Get a distribution that has uv already installed
+FROM ghcr.io/astral-sh/uv:python3.13-bookworm-slim
+# Add user - this is the user that will run the app
+# If you do not set user, the app will run as root (undesirable)
+RUN useradd -m -u 1000 user
+USER user
+# Set the home directory and path
+ENV HOME=/home/user \
+PATH=/home/user/.local/bin:$PATH
+# NEW ENV STATEMENT
+ENV UVICORN_WS_PROTOCOL=websockets
+# Set the working directory
+WORKDIR $HOME/app
+# Copy the app to the container
+COPY --chown=user . $HOME/app
+# Install the dependencies
+RUN uv sync --frozen
+# Expose the port
+EXPOSE 7860
+# Run the app
+CMD ["uv", "run", "-m", "streamlit", "run", "Chatbot.py", "--server.address", "0.0.0.0", "--server.port", "7860"]

pages/Load_Documents.py

@@ -0,0 +1,86 @@
+import os
+import openai
+from utils._admin_util import create_embeddings, create_vector_store, read_pdf_data, split_data
+import streamlit as st
+from dotenv import load_dotenv
+
+def validate_api_key(api_key):
+    """Test if the API key is valid"""
+    try:
+       # Make a small test request to OpenAI
+        client = openai.OpenAI(api_key=api_key)
+        client.embeddings.create(input="test", model="text-embedding-ada-002")
+        return True
+    except openai.AuthenticationError:
+        st.error("❌ Invalid API key")
+        return False
+    except openai.PermissionDeniedError:
+        st.error("❌ Permission denied. Please check your API key's permissions")
+        return False
+    except Exception as e:
+        st.error(f"❌ API key validation error: {str(e)}")
+        return False
+
+def main():
+    load_dotenv()
+    
+    # Add detailed API key verification
+    api_key = os.getenv("OPENAI_API_KEY")
+    if not api_key:
+        st.error("❌ OpenAI API key not found! Please ensure it's set in the environment variables.")
+        st.info("To set up your API key:")
+        st.code("1. Go to Hugging Face Space settings\n2. Add OPENAI_API_KEY in Repository Secrets")
+        st.stop()
+    
+    # Validate the API key
+    # if not validate_api_key(api_key):
+    #     st.stop()
+    
+    #print("API KEY :",api_key)
+
+    st.set_page_config(page_title="Dump PDFs to QDrant - Vector Store")
+    st.title("Please upload your files...📁 ")
+    try:
+        # Upload multiple PDF files
+        uploaded_files = st.file_uploader("Upload PDF files", type=["pdf"], accept_multiple_files=True)
+
+        if uploaded_files:
+        
+            with st.spinner('Processing PDF files...'):
+                all_chunks = []
+                
+                # Process each PDF file
+                for pdf in uploaded_files:
+                  
+                    st.write(f"Processing: {pdf.name}")
+                    
+                    # Extract text from PDF
+                    text = read_pdf_data(pdf)
+                    st.write(f"👉 Reading {pdf.name} done")
+
+                    # Create chunks for this PDF
+                    chunks = split_data(text)
+                    all_chunks.extend(chunks)
+                    st.write(f"👉 Splitting {pdf.name} into chunks done")
+                    
+                if not all_chunks:
+                    st.error("❌ No valid chunks were created from the PDFs")
+                    st.stop()
+
+                st.write("Creating embeddings...")
+                embeddings = create_embeddings()
+                st.write("👉 Creating embeddings instance done")
+        
+                # Create vector store with all chunks
+                vector_store = create_vector_store(embeddings, all_chunks)
+                st.session_state.vector_store = vector_store
+            
+                st.success(f"✅ Successfully processed {len(uploaded_files)} files and pushed embeddings to Qdrant")
+                st.write(f"Total chunks created: {len(all_chunks)}")
+
+    except Exception as e:
+            st.error(f"❌ An unexpected error occurred: {str(e)}")
+            
+            
+if __name__ == '__main__':
+    main()

pages/Pending_tickets.py

@@ -0,0 +1,29 @@
+import streamlit as st
+ 
+st.title('Departments')
+ 
+# Create tabs
+tab_titles = ['HR Support', 'IT Support', 'Transportation Support', 'Other']
+tabs = st.tabs(tab_titles)
+ 
+# Add content to each tab...
+with tabs[0]:
+    st.header('HR Support tickets')
+    for ticket in st.session_state.categories["HR Support"]:
+        st.write(str( st.session_state.categories["HR Support"].index(ticket)+1)+" : "+ticket)
+    
+with tabs[1]:
+    st.header('IT Support tickets')
+    for ticket in st.session_state.categories['IT Support']:
+        st.write(str(st.session_state.categories['IT Support'].index(ticket)+1)+" : "+ticket)
+ 
+with tabs[2]:
+    st.header('Transportation Support tickets')
+    for ticket in st.session_state.categories['Transportation Support']:
+        st.write(str(st.session_state.categories['Transportation Support'].index(ticket)+1)+" : "+ticket)
+    
+with tabs[3]:
+    st.header('Other tickets')
+    for ticket in st.session_state.categories['Other']:
+        st.write(str(st.session_state.categories['Other'].index(ticket)+1)+" : "+ticket)
+

pyproject.toml

@@ -0,0 +1,24 @@
+[project]
+name = "midterm"
+version = "0.1.0"
+description = "intelligent customer support chat"
+readme = "README.md"
+requires-python = ">=3.12"
+dependencies = [
+    "pydantic==2.10.1",
+    "langchain-core==0.3.31",
+    "langchain==0.3.15",
+    "langchain-community==0.3.15",
+    "langchain-openai==0.3.1",
+    "langchain-qdrant==0.2.0",
+    "qdrant-client==1.13.2",
+    "tiktoken>=0.8.0",
+    "pymupdf==1.25.2",
+    "langgraph>=0.2.67",
+    "langsmith>=0.3.1",
+    "openai>=1.58.1",
+    "cohere>=5.13.11",
+    "lxml>=5.3.0",
+    "streamlit>=1.29.0",
+    "websockets"
+]

requirements.txt

@@ -0,0 +1,17 @@
+langchain==0.1.13
+streamlit==1.29.0
+openai==1.14.2
+tiktoken>=0.6.0
+python-dotenv==1.0.1
+pinecone-client==3.2.0
+pypdf==4.0.1
+joblib==1.3.2
+pandas==2.2.0
+scikit-learn==1.4.0
+sentence-transformers==2.5.1
+langchain-openai==0.1.0
+PyPDF2
+pymupdf
+langchain-core>=0.1.0
+qdrant-client>=1.7.0
+langchain-qdrant>=0.1.0

utils/_admin_util.py

@@ -0,0 +1,188 @@
+import os
+import tiktoken
+import PyPDF2
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_openai.embeddings import OpenAIEmbeddings
+from langchain_qdrant import QdrantVectorStore
+from qdrant_client import QdrantClient
+from qdrant_client.http.models import Distance, VectorParams
+from langchain_core.runnables import RunnablePassthrough
+from langchain_core.output_parsers import StrOutputParser
+from langchain_openai import ChatOpenAI
+from langchain_core.prompts import ChatPromptTemplate
+import streamlit as st
+
+
+
+HUMAN_TEMPLATE = """
+#CONTEXT:
+{context}
+
+QUERY:
+{query}
+
+Use the provide context to answer the provided user query. Only use the provided context to answer the query. If you do not know the answer, or it's not contained in the provided context response with "I don't know"
+"""
+
+# Define the system prompt for categorization
+CATEGORY_PROMPT = """You are a ticket categorization system. Categorize the following query into exactly one of these categories:
+    - HR Support: For queries about employment, benefits, leaves, workplace policies, etc.
+    - IT Support: For queries about software, hardware, network, system access, etc.
+    - Transportation Support: For queries about company transport, parking, vehicle maintenance, etc.
+    - Other: For queries that do not fit into the above categories.
+    Respond with ONLY the category name, nothing else.
+    
+    Query: {query}
+    """
+
+def check_api_key():
+    """Verify that the API key is set and valid"""
+    api_key = os.getenv("OPENAI_API_KEY")
+    if not api_key:
+        raise ValueError("OpenAI API key not found in environment variables")
+    return api_key
+
+#Read PDF data
+def read_pdf_data(pdf_file):
+    try:
+        pdf_reader = PyPDF2.PdfReader(pdf_file)
+        text = ""
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+        if not text.strip():
+            raise ValueError("No text extracted from PDF")
+        return text
+    except Exception as e:
+        raise Exception(f"Error reading PDF: {str(e)}")
+
+def tiktoken_len(text):
+    try:
+        tokens = tiktoken.encoding_for_model("gpt-4").encode(text)
+        return len(tokens)
+    except Exception as e:
+        raise Exception(f"Error in token calculation: {str(e)}")
+
+#Split data into chunks
+def split_data(text):
+    try:
+        text_splitter = RecursiveCharacterTextSplitter(
+            chunk_size=500,  # Increased for better context
+            chunk_overlap=50,  # Added overlap for better continuity
+            length_function=tiktoken_len,
+            separators=["\n\n", "\n", " ", ""]
+        )   
+        chunks = text_splitter.split_text(text)
+        if not chunks:
+            raise ValueError("Text splitting produced no chunks")
+        return chunks
+    except Exception as e:
+        raise Exception(f"Error splitting text: {str(e)}")
+
+#Create embeddings instance
+
+def create_embeddings():
+    try:
+        api_key = check_api_key()
+        embedding_model = OpenAIEmbeddings(
+            model="text-embedding-3-small",
+            openai_api_key=api_key
+        )
+        return embedding_model
+    except Exception as e:
+        raise Exception(f"Error creating embeddings model: {str(e)}")
+
+
+# Create a vector database using Qdrant
+def create_vector_store(embedding_model, chunks):
+    try:
+        embedding_dim = 1536
+        client = QdrantClient(":memory:")  # Consider using persistent storage for production
+        
+        # Create collection with error handling
+        try:
+            client.create_collection(
+                collection_name="lcel_doc_v2",
+                vectors_config=VectorParams(size=embedding_dim, distance=Distance.COSINE),
+            )
+        except Exception as e:
+            raise Exception(f"Error creating Qdrant collection: {str(e)}")
+
+        vector_store = QdrantVectorStore(
+            client=client,
+            collection_name="lcel_doc_v2",
+            embedding=embedding_model,
+        )
+        
+        # Add texts with progress tracking
+        try:
+            _ = vector_store.add_texts(texts=chunks)
+        except Exception as e:
+            raise Exception(f"Error adding texts to vector store: {str(e)}")
+            
+        return vector_store
+    except Exception as e:
+        raise Exception(f"Error in vector store creation: {str(e)}")
+
+# create RAG
+def create_rag(vector_store):
+    try:
+        api_key = check_api_key()
+        openai_chat_model = ChatOpenAI(
+            model="gpt-3.5-turbo",
+            openai_api_key=api_key,
+            temperature=0.7
+        )
+        
+        chat_prompt = ChatPromptTemplate.from_messages([
+            ("system", "You are a helpful assistant that answers questions based on the provided context."),
+            ("human", HUMAN_TEMPLATE)
+        ])
+        
+        retriever = vector_store.as_retriever(search_kwargs={"k": 3})
+        
+        simple_rag = (
+            {"context": retriever, "query": RunnablePassthrough()}
+            | chat_prompt
+            | openai_chat_model
+            | StrOutputParser() 
+        ) 
+        
+        return simple_rag
+    except Exception as e:
+        raise Exception(f"Error creating RAG chain: {str(e)}")
+
+# Invoke RAG
+def invoke_rag(vector_store, query):
+    try:
+        rag_chain = create_rag(vector_store)
+        response = rag_chain.invoke(query)
+        return response
+    except Exception as e:
+        raise Exception(f"Error invoking RAG chain: {str(e)}")
+
+
+def get_ticket_category(query):
+    try:
+        api_key = check_api_key()
+        client = ChatOpenAI(
+            model="gpt-3.5-turbo",
+            openai_api_key=api_key,
+            temperature=0
+        )
+        
+        prompt = ChatPromptTemplate.from_messages([
+            ("system", CATEGORY_PROMPT)
+        ])
+        
+        chain = prompt | client | StrOutputParser()
+        category = chain.invoke({"query": query})
+        
+        category = category.strip()
+        valid_categories = ["HR Support", "IT Support", "Transportation Support", "Other"]
+        
+        return category if category in valid_categories else "Other"
+    except Exception as e:
+        st.error(f"Error in category classification: {str(e)}")
+        return "Other"  # Fallback category
+
+