app.py

import os
import zipfile
import streamlit as st
from langchain_community.document_loaders import DirectoryLoader, TextLoader
from langchain_community.vectorstores import FAISS
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter

# Step 1: Extract ZIP
def extract_zip(zip_path, extract_to):
    if os.path.exists(zip_path) and not os.path.exists(extract_to):
        with zipfile.ZipFile(zip_path, 'r') as zip_ref:
            zip_ref.extractall(extract_to)
        st.success("Knowledge Base extracted successfully!")

# Step 2: Auto-detect folder that contains .md files
def find_md_folder(base_path):
    for root, dirs, files in os.walk(base_path):
        if any(file.endswith(".md") for file in files):
            return root
    return None

# Step 3: Load and embed knowledge base
@st.cache_resource
def load_knowledge_base(folder_path):
    loader = DirectoryLoader(folder_path, glob="*.md", loader_cls=TextLoader)
    docs = loader.load()
    if not docs:
        st.error("No documents found in the knowledge base folder.")
        return None

    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
    split_docs = splitter.split_documents(docs)
    if not split_docs:
        st.error("Failed to split documents.")
        return None

    model_name = "sentence-transformers/paraphrase-MiniLM-L6-v2"
    embeddings = HuggingFaceEmbeddings(model_name=model_name)

    try:
        db = FAISS.from_documents(split_docs, embeddings)
        return db
    except Exception as e:
        st.error(f"Error creating FAISS index: {e}")
        return None

# Streamlit UI
st.title("📘 Fitlytic Chatbot")

# Step 4: Extract ZIP if needed
zip_path = "Knowledge_Base.zip"
extract_to = "Knowledge_Base"
extract_zip(zip_path, extract_to)

# Step 5: Find folder containing .md files
md_folder = find_md_folder(extract_to)

# Step 6: Load knowledge base
if md_folder:
    db = load_knowledge_base(md_folder)
else:
    st.error("Could not find any Markdown files in the extracted folder.")
    st.stop()

# Step 7: User interaction
if db:
    query = st.text_input("Ask me anything about Fitlytic:")
    if query:
        results = db.similarity_search(query, k=1)
        if results:
            st.success(results[0].page_content)
        else:
            st.error("!!Sorry, I couldn't find an answer. Try rephrasing it.")
else:
    st.stop()