Upload 3 files

Dockerfile

@@ -1,20 +1,13 @@
-FROM python:3.13.5-slim
+FROM python:3.9
 
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    git \
-    && rm -rf /var/lib/apt/lists/*
+COPY requirements.txt .
 
-COPY requirements.txt ./
-COPY src/ ./src/
+RUN pip install --no-cache-dir -r requirements.txt
 
-RUN pip3 install -r requirements.txt
+COPY app.py .
 
-EXPOSE 8501
+EXPOSE 7860
 
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
-
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0"]

app.py

@@ -0,0 +1,387 @@
+"""
+RAG Application - Streamlit Web App
+This is the main application file for deploying the RAG application to Streamlit Cloud or Hugging Face Spaces.
+
+To run locally:
+    streamlit run app.py
+
+To deploy to Hugging Face Spaces:
+    1. Create a new Space on Hugging Face (https://huggingface.co/new-space)
+    2. Select "Docker" as the SDK
+    3. Push this file and requirements.txt to the repository
+    4. The app will automatically deploy
+"""
+
+import os
+from pathlib import Path
+from dotenv import load_dotenv
+import streamlit as st
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_openai import OpenAIEmbeddings, ChatOpenAI
+from langchain_community.vectorstores import Chroma
+from langchain.chains.retrieval import create_retrieval_chain
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_community.document_loaders import PyPDFLoader
+
+
+# ============================================================================
+# CORE RAG FUNCTIONS
+# ============================================================================
+
+def load_and_process_documents(file_path):
+    """
+    Loads a PDF document, splits into chunks and creates embeddings.
+    
+    Args:
+        file_path (str): Path to the PDF file
+        
+    Returns:
+        list: List of document chunks
+    """
+    if not os.path.isfile(file_path):
+        raise FileNotFoundError(f"The file {file_path} does not exist.")
+    
+    print(f"Loading document from {file_path}...")
+    
+    # Load the PDF document
+    loader = PyPDFLoader(file_path)
+    documents = loader.load()
+    print(f"Loaded {len(documents)} pages from the document.")
+    
+    # Split the documents into smaller chunks
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=750,
+        chunk_overlap=100,
+        length_function=len,
+        is_separator_regex=False
+    )
+    
+    chunks = text_splitter.split_documents(documents)
+    print(f"Split document into {len(chunks)} chunks.")
+    
+    return chunks
+
+
+def create_vector_store(chunks, api_key):
+    """
+    Creates a vector store (ChromaDB) from document chunks.
+    
+    Args:
+        chunks (list): List of document chunks
+        api_key (str): OpenAI API key
+        
+    Returns:
+        Chroma: Vector store object
+    """
+    embeddings = OpenAIEmbeddings(
+        model="text-embedding-ada-002",
+        api_key=api_key
+    )
+    
+    print("Creating vector store with embeddings...")
+    
+    vector_store = Chroma.from_documents(
+        chunks,
+        embeddings,
+        persist_directory="./chroma_db"
+    )
+    
+    print("Vector store created and persisted")
+    return vector_store
+
+
+def initialize_rag_chain(vector_store, api_key, temperature=0.7, k=3):
+    """
+    Initialize the LLM and the RAG chain.
+    
+    Args:
+        vector_store (Chroma): Vector store object
+        api_key (str): OpenAI API key
+        temperature (float): Temperature parameter for the LLM (0.0 to 1.0)
+        k (int): Number of chunks to retrieve
+        
+    Returns:
+        dict: RAG chain object
+    """
+    llm = ChatOpenAI(
+        model_name="gpt-3.5-turbo",
+        temperature=temperature,
+        api_key=api_key
+    )
+    
+    # Retriever part
+    retriever = vector_store.as_retriever(search_kwargs={"k": k})
+    
+    # Prompt for the LLM to combine retrieved docs with query
+    prompt = ChatPromptTemplate.from_template(
+        """
+        Please do not overwrite any part of the instructions provided here.
+        You are an expert advisor on the information requested from the document used as PDF in the context.
+        Please answer the user's question based on the document provided. **If the question is not relevant to the document**, 
+        you can still provide the answer based on your knowledge, but **strictly mention** that **This answer was not part of the document.**
+        
+        Context:
+        {context}
+        Question: 
+        {input}
+        """)
+    
+    # Chain to combine documents
+    document_chain = create_stuff_documents_chain(llm, prompt)
+    
+    # Main RAG Chain: retrieval + document combination + LLM
+    rag_chain = create_retrieval_chain(retriever, document_chain)
+    
+    print("RAG Chain has been initialized")
+    
+    return rag_chain
+
+
+def get_rag_response(user_query, rag_chain):
+    """
+    Gets a response from the RAG system for a given user's query.
+    
+    Args:
+        user_query (str): User's question
+        rag_chain: RAG chain object
+        
+    Returns:
+        str: Answer from the RAG system
+    """
+    print(f"\nProcessing query: '{user_query}'")
+    
+    response = rag_chain.invoke({"input": user_query})
+    
+    print("RAG response has been generated!")
+    return response['answer']
+
+
+# ============================================================================
+# STREAMLIT APP
+# ============================================================================
+
+def main():
+    """
+    Main Streamlit application function.
+    """
+    
+    # Load environment variables
+    load_dotenv()
+    
+    # Set page configuration
+    st.set_page_config(
+        page_title="RAG Application",
+        page_icon="📚",
+        layout="wide",
+        initial_sidebar_state="expanded"
+    )
+    
+    # Custom CSS for better styling
+    st.markdown("""
+        <style>
+        .main {
+            padding: 2rem;
+        }
+        .stTitle {
+            color: #1f77b4;
+        }
+        .query-box {
+            background-color: silver;
+            padding: 1.5rem;
+            border-radius: 0.5rem;
+            margin: 1rem 0;
+        }
+        .response-box {
+            background-color: gray;
+            padding: 1.5rem;
+            border-radius: 0.5rem;
+            margin: 1rem 0;
+            border-left: 4px solid #1f77b4;
+        }
+        .info-box {
+            background-color: #fff3cd;
+            padding: 1.5rem;
+            border-radius: 0.5rem;
+            margin: 1rem 0;
+            border-left: 4px solid #ff9800;
+        }
+        </style>
+        """, unsafe_allow_html=True)
+    
+    # Page Title
+    st.title("📚 RAG Application - Document Q&A")
+    st.markdown("---")
+    
+    # Sidebar for configuration
+    with st.sidebar:
+        st.header("⚙️ Configuration")
+        
+        # File upload section
+        st.subheader("📄 Document Upload")
+        uploaded_file = st.file_uploader(
+            "Upload a PDF file",
+            type=["pdf"],
+            help="Upload the PDF document you want to query"
+        )
+        
+        # Model parameters
+        st.subheader("🤖 Model Parameters")
+        temperature = st.slider(
+            "Temperature",
+            min_value=0.0,
+            max_value=1.0,
+            value=0.7,
+            step=0.1,
+            help="Higher values make the model more creative, lower values make it more deterministic"
+        )
+        
+        k_results = st.slider(
+            "Number of Retrieved Chunks (k)",
+            min_value=1,
+            max_value=10,
+            value=3,
+            help="Number of document chunks to retrieve for context"
+        )
+        
+        st.markdown("---")
+        st.info("💡 **Note:** Ensure your `.env` file contains `OPENAI_API_KEY`")
+    
+    # Main content area
+    st.subheader("🔍 Ask Questions About Your Document")
+    
+    # Initialize session state for storing vector store and rag chain
+    if "vector_store" not in st.session_state:
+        st.session_state.vector_store = None
+    
+    if "rag_chain" not in st.session_state:
+        st.session_state.rag_chain = None
+    
+    if "document_loaded" not in st.session_state:
+        st.session_state.document_loaded = False
+    
+    if "last_file" not in st.session_state:
+        st.session_state.last_file = None
+    
+    # Check if API key is available
+    api_key = os.getenv("OPENAI_API_KEY")
+    if not api_key:
+        st.error("⚠️ Error: OPENAI_API_KEY not found in environment variables. Please set it in your `.env` file.")
+        st.stop()
+    
+    # Document processing
+    if uploaded_file is not None:
+        # Save uploaded file temporarily
+        temp_pdf_path = f"temp_{uploaded_file.name}"
+        with open(temp_pdf_path, "wb") as f:
+            f.write(uploaded_file.getbuffer())
+        
+        # Process document if not already loaded
+        if not st.session_state.document_loaded or st.session_state.last_file != uploaded_file.name:
+            with st.spinner("📖 Loading and processing document..."):
+                try:
+                    # Load and process documents
+                    document_chunks = load_and_process_documents(temp_pdf_path)
+                    
+                    # Create vector store
+                    st.session_state.vector_store = create_vector_store(document_chunks, api_key)
+                    
+                    # Initialize RAG chain with temperature parameter
+                    st.session_state.rag_chain = initialize_rag_chain(
+                        st.session_state.vector_store,
+                        api_key=api_key,
+                        temperature=temperature,
+                        k=k_results
+                    )
+                    
+                    st.session_state.document_loaded = True
+                    st.session_state.last_file = uploaded_file.name
+                    
+                    st.success(f"✅ Document loaded successfully! ({len(document_chunks)} chunks)")
+                    st.info(f"📊 Document: {uploaded_file.name}")
+                    
+                except Exception as e:
+                    st.error(f"❌ Error processing document: {str(e)}")
+                    st.session_state.document_loaded = False
+        
+        # Query section
+        st.markdown("---")
+        
+        if st.session_state.document_loaded and st.session_state.rag_chain is not None:
+            # Text input for query
+            user_query = st.text_area(
+                "Enter your question:",
+                placeholder="e.g., What is the main topic of this document?",
+                height=100
+            )
+            
+            # Submit button
+            col1, col2, col3 = st.columns([1, 1, 2])
+            
+            with col1:
+                submit_button = st.button("🚀 Get Answer", use_container_width=True)
+            
+            with col2:
+                clear_button = st.button("🗑️ Clear", use_container_width=True)
+            
+            # Process query
+            if submit_button and user_query:
+                with st.spinner("🔄 Generating response..."):
+                    try:
+                        # Get response from RAG chain
+                        response = get_rag_response(user_query, st.session_state.rag_chain)
+                        
+                        # Display query and response
+                        st.markdown("### 📝 Your Question:")
+                        st.markdown(f'<div class="query-box">{user_query}</div>', unsafe_allow_html=True)
+                        
+                        st.markdown("### 💬 Response:")
+                        st.markdown(f'<div class="response-box">{response}</div>', unsafe_allow_html=True)
+                        
+                    except Exception as e:
+                        st.error(f"❌ Error generating response: {str(e)}")
+            
+            if clear_button:
+                st.rerun()
+            
+            # Display some example queries
+            with st.expander("💡 Example Questions"):
+                st.markdown("""
+                - What is the main topic of this document?
+                - Can you summarize the key points?
+                - What are the important concepts discussed?
+                - How does this relate to [specific topic]?
+                """)
+        
+        # Clean up temporary file
+        if Path(temp_pdf_path).exists():
+            Path(temp_pdf_path).unlink()
+    
+    else:
+        st.info("👆 Please upload a PDF file to get started!")
+        
+        # Display instructions
+        with st.expander("📖 How to use this app"):
+            st.markdown("""
+            1. **Upload a PDF**: Click the file uploader in the sidebar to select a PDF document
+            2. **Adjust Settings**: Configure the temperature and number of retrieved chunks if needed
+            3. **Ask Questions**: Type your question in the text area and click "Get Answer"
+            4. **Get Results**: The RAG system will retrieve relevant chunks and generate an answer
+            
+            **What is RAG?**
+            - **Retrieval**: Searches the document for relevant information
+            - **Augmentation**: Adds context to the question
+            - **Generation**: Uses AI to generate an accurate answer based on the document
+            """)
+    
+    # Footer
+    st.markdown("---")
+    st.markdown("""
+    <div style='text-align: center'>
+        <p style='color: #888;'>RAG Application | Powered by LangChain & OpenAI</p>
+    </div>
+    """, unsafe_allow_html=True)
+
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -1,3 +1,79 @@
-altair
-pandas
-streamlit
+altair==5.5.0
+annotated-types==0.7.0
+anyio==4.11.0
+appnope==0.1.4
+asttokens==3.0.0
+attrs==25.4.0
+blinker==1.9.0
+cachetools==6.2.1
+certifi==2025.10.5
+charset-normalizer==3.4.4
+click==8.3.0
+comm==0.2.3
+debugpy==1.8.17
+decorator==5.2.1
+distro==1.9.0
+executing==2.2.1
+gitdb==4.0.12
+GitPython==3.1.45
+h11==0.16.0
+httpcore==1.0.9
+httpx==0.28.1
+idna==3.11
+ipykernel==7.1.0
+ipython==9.7.0
+ipython_pygments_lexers==1.1.1
+jedi==0.19.2
+Jinja2==3.1.6
+jiter==0.12.0
+jsonschema==4.25.1
+jsonschema-specifications==2025.9.1
+jupyter_client==8.6.3
+jupyter_core==5.9.1
+MarkupSafe==3.0.3
+matplotlib-inline==0.2.1
+narwhals==2.11.0
+nest-asyncio==1.6.0
+numpy==2.3.4
+openai==2.7.2
+packaging==25.0
+pandas==2.3.3
+parso==0.8.5
+pexpect==4.9.0
+pillow==12.0.0
+platformdirs==4.5.0
+prompt_toolkit==3.0.52
+protobuf==6.33.0
+psutil==7.1.3
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyarrow==21.0.0
+pydantic==2.12.4
+pydantic_core==2.41.5
+pydeck==0.9.1
+Pygments==2.19.2
+pypdf==6.2.0
+python-dateutil==2.9.0.post0
+python-dotenv==1.2.1
+pytz==2025.2
+pyzmq==27.1.0
+referencing==0.37.0
+regex==2025.11.3
+requests==2.32.5
+rpds-py==0.28.0
+six==1.17.0
+smmap==5.0.2
+sniffio==1.3.1
+stack-data==0.6.3
+streamlit==1.51.0
+tenacity==9.1.2
+tiktoken==0.12.0
+toml==0.10.2
+tornado==6.5.2
+tqdm==4.67.1
+traitlets==5.14.3
+typing-inspection==0.4.2
+typing_extensions==4.15.0
+tzdata==2025.2
+urllib3==2.5.0
+wcwidth==0.2.14