Upload 5 files

app.py

@@ -0,0 +1,240 @@
+# First, here's the integrated Streamlit interface with RAG implementation:
+
+import streamlit as st
+import requests
+import json
+import time
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_community.embeddings import OllamaEmbeddings
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import Chroma
+from langchain.prompts import ChatPromptTemplate, PromptTemplate
+from langchain_core.output_parsers import StrOutputParser
+from langchain_community.chat_models import ChatOllama
+from langchain_core.runnables import RunnablePassthrough
+from langchain.retrievers.multi_query import MultiQueryRetriever
+import logging
+import os
+from datetime import datetime
+from PIL import Image
+
+
+# Configure logging
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
+    handlers=[
+        logging.FileHandler('ai_buddy_streamlit.log'),
+        logging.StreamHandler()
+    ]
+)
+logger = logging.getLogger(__name__)
+
+# Configuration
+class Config:
+    LOCAL_PATH = "AI-BUDDY.pdf"  # Adjust path as needed
+    PERSIST_DIRECTORY = "rag_data"
+    COLLECTION_NAME = "local-rags"
+    CHUNK_SIZE = 500
+    CHUNK_OVERLAP = 200
+    LOCAL_MODEL = "llama3.2"
+
+# Initialize RAG Components
+@st.cache_resource
+def initialize_rag():
+    try:
+        embeddings = OllamaEmbeddings(model="nomic-embed-text", show_progress=True)
+        
+        # Initialize or load vector store
+        if os.path.exists(Config.PERSIST_DIRECTORY) and os.listdir(Config.PERSIST_DIRECTORY):
+            vector_db = Chroma(
+                persist_directory=Config.PERSIST_DIRECTORY,
+                embedding_function=embeddings,
+                collection_name=Config.COLLECTION_NAME
+            )
+        else:
+            loader = PyPDFLoader(Config.LOCAL_PATH)
+            data = loader.load()
+            text_splitter = RecursiveCharacterTextSplitter(
+                chunk_size=Config.CHUNK_SIZE,
+                chunk_overlap=Config.CHUNK_OVERLAP
+            )
+            chunks = text_splitter.split_documents(data)
+            
+            vector_db = Chroma.from_documents(
+                documents=chunks,
+                embedding=embeddings,
+                persist_directory=Config.PERSIST_DIRECTORY,
+                collection_name=Config.COLLECTION_NAME
+            )
+        
+        # Initialize LLM and prompts
+        llm = ChatOllama(model=Config.LOCAL_MODEL, streaming=True)
+        
+        query_prompt = PromptTemplate(
+            input_variables=["question"],
+            template="""You are AI Buddy, an AI assistant and counsellor. Generate diverse versions of the user's 
+            question to retrieve comprehensive information about your capabilities and relevant details. Focus on:
+            1. Core question intent
+            2. Related capabilities
+            3. Specific services mentioned
+            4. Similar use cases
+            5. Contextual information
+
+            Original question: {question}
+            
+            Generate three distinct questions that capture different aspects of the query."""
+        )
+        
+        response_prompt = ChatPromptTemplate.from_template("""You are AI Buddy, an AI assistant and counsellor for the AI Buddy platform.
+            Respond in first person as AI Buddy, using "I" and "me". Always maintain this persona.
+
+            Context: {context}
+            Question: {question}
+
+            Guidelines for response:
+            1. Only answer based on the provided context
+            2. For course/bootcamp inquiries, only suggest from our official list
+            3. Verify names and services exist in the context before mentioning them
+            4. Be clear and direct in your responses
+            5. Provide a simple and short answers only which is required to answer the question""")
+        
+        # Initialize retriever
+        retriever = MultiQueryRetriever.from_llm(
+            retriever=vector_db.as_retriever(search_kwargs={"k": 3}),
+            llm=llm,
+            prompt=query_prompt,
+        )
+        
+        # Define the chain
+        chain = (
+            {"context": retriever, "question": RunnablePassthrough()}
+            | response_prompt
+            | llm
+            | StrOutputParser()
+        )
+        
+        return chain
+    
+    except Exception as e:
+        logger.error(f"Error initializing RAG components: {str(e)}")
+        st.error("Failed to initialize AI components. Please check the logs.")
+        return None
+
+# Streamlit interface setup
+st.set_page_config(page_title="AI-Buddy Assistant", page_icon="AI-Buddy.png", layout="centered")
+
+# Load and resize the image
+img = Image.open("AI Buddy Green Logo.png")
+resized_img = img.resize((400, 150))  # Set width=400px and height=200px
+
+# Display the resized image
+st.image(resized_img, caption="AI-Buddy Assistant")
+
+# Set the title
+# st.title("AI-Buddy Assistant")
+# Custom CSS (keeping your original styling)
+st.markdown("""
+    <style>
+        .sidebar .sidebar-content {
+            font-size: 1.3rem;
+            color: #333333;
+            background-color: #f9f9f9;
+            padding: 20px;
+            border-radius: 10px;
+        }
+        .sidebar .sidebar-content h1 {
+            font-size: 1.8rem;
+            font-weight: bold;
+            color: #ff4b4b;
+            margin-bottom: 15px;
+        }
+        .sidebar .sidebar-content select, .sidebar .sidebar-content textarea, .sidebar .sidebar-content input {
+            border: 2px solid #ff4b4b;
+            padding: 12px;
+            font-size: 1.2rem;
+            margin-bottom: 15px;
+            border-radius: 5px;
+        }
+        .sidebar .sidebar-content button {
+            background-color: #ff4b4b;
+            color: white;
+            font-size: 1.2rem;
+            padding: 10px 20px;
+            border-radius: 5px;
+            border: none;
+            cursor: pointer;
+            transition: background-color 0.3s ease;
+        }
+        .sidebar .sidebar-content button:hover {
+            background-color: #ff6565;
+        }
+        .st-chat-message p {
+            font-size: 1.3rem;
+        }
+    </style>
+""", unsafe_allow_html=True)
+
+# Initialize RAG chain
+chain = initialize_rag()
+
+# Initialize chat history
+if "messages" not in st.session_state:
+    st.session_state.messages = [
+        {"role": "assistant", "content": "Hello! I'm AI-Buddy. How can I assist you today?"}
+    ]
+
+# Sidebar for profession selection (keeping your original implementation)
+st.sidebar.title("Want to know how AI helps in your profession and the role of AI-Buddy?")
+professions = ["Software Engineer", "Data Scientist", "Marketing Specialist", "Financial Analyst", "Teacher", "Doctor", "Project Manager", "Consultant", "Business Analyst", "Other"]
+fields = ["IT", "Healthcare", "Education", "Finance", "Marketing", "Engineering", "Sales", "Human Resources", "Consulting", "Other"]
+
+profession = st.sidebar.selectbox("Choose Your Profession", professions)
+field = st.sidebar.selectbox("Choose Your Field/Domain", fields)
+
+if profession == "Other":
+    profession = st.sidebar.text_input("Please specify your profession")
+if field == "Other":
+    field = st.sidebar.text_input("Please specify your field")
+
+description = st.sidebar.text_area("About you (a short description)", placeholder="Briefly describe your role")
+
+# Submit button for profession info
+if st.sidebar.button("Submit"):
+    prompt = f"My profession is {profession} in the {field} field. Here's a bit about me: {description}. Tell me how AI and AI-Buddy can help me."
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+# Function to display streaming response
+def display_response_streaming(response_iterator):
+    response_placeholder = st.empty()
+    full_response = ""
+    for chunk in response_iterator:
+        full_response += chunk
+        response_placeholder.write(full_response)
+        time.sleep(0.05)
+    return full_response
+
+# Chat interface
+if prompt := st.chat_input("Type your message"):
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+# Display chat history and generate responses
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.write(message["content"])
+
+# Generate new response if last message is from user
+if st.session_state.messages[-1]["role"] == "user":
+    with st.chat_message("assistant"):
+        with st.spinner("Thinking..."):
+            try:
+                # Use RAG chain to generate response
+                response_iterator = chain.stream({"question": st.session_state.messages[-1]["content"]})
+                response = display_response_streaming(response_iterator)
+                st.session_state.messages.append({"role": "assistant", "content": response})
+            except Exception as e:
+                logger.error(f"Error generating response: {str(e)}")
+                st.error("I apologize, but I encountered an error. Please try again or rephrase your question.")
+
+if __name__ == "__main__":
+    logging.info("AI-Buddy Streamlit Interface Started")

requirements.txt

@@ -0,0 +1,9 @@
+streamlit
+requests
+pillow
+langchain
+langchain-community
+chromadb
+pypdf
+ollama
+