“AI Business Assistant (RAG-Powered)”

---

📁 Folder Structure

ai_business_assistant/
│
├── app.py # Streamlit main app
├── build_index.py # Creates the vector database
├── data/
│ └── business.txt # Your business knowledge base
├── faiss_index/ # Auto-created folder (after running build_index.py)
├── requirements.txt # Dependencies
└── README.md # (optional) Info about the project

---

📄 1. requirements.txt

langchain
openai
faiss-cpu
streamlit
pypdf
tiktoken

---

📘 2. data/business.txt

You can write or paste any business content here.
Example:

Artificial Intelligence (AI) is transforming business processes across industries.
Startups in 2025 are focusing on AI-driven marketing, customer personalization, and automation.
Digital transformation strategies now include machine learning-based analytics, predictive insights, and chatbots.
AI can help small businesses optimize their sales and reduce costs through smart automation.

You can later replace or add PDFs with business research reports.

---

⚙️ 3. build_index.py

This file prepares your vector database (FAISS).

from langchain.document_loaders import TextLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import FAISS
import os

Ensure OpenAI API Key is set

os.environ["OPENAI_API_KEY"] = "your_openai_api_key_here"

1️⃣ Load your text file

loader = TextLoader("data/business.txt")
docs = loader.load()

2️⃣ Split into chunks

splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
chunks = splitter.split_documents(docs)

3️⃣ Create embeddings and FAISS index

embeddings = OpenAIEmbeddings()
db = FAISS.from_documents(chunks, embeddings)

4️⃣ Save FAISS index locally

db.save_local("faiss_index")

print("✅ FAISS vector index built and saved successfully!")

Run this first (to create the FAISS index):

python build_index.py

---

💻 4. app.py

This is your Streamlit web app — the front-end interface.

import streamlit as st
from langchain.chains import RetrievalQA
from langchain.llms import OpenAI
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import FAISS
import os

🔑 Set API key

os.environ["OPENAI_API_KEY"] = "your_openai_api_key_here"

🧠 Load FAISS index

embeddings = OpenAIEmbeddings()
db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
retriever = db.as_retriever(search_kwargs={"k": 3})

⚙️ Setup LLM

llm = OpenAI(model_name="gpt-4-turbo", temperature=0.3)
qa = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)

🎨 Streamlit Interface

st.set_page_config(page_title="AI Business Assistant", page_icon="💼")
st.title("💼 AI Business Assistant")
st.markdown("Ask any question about business, startups, or AI trends!")

query = st.text_input("🔍 Enter your question here:")
if st.button("Ask"):
if query.strip():
with st.spinner("Thinking..."):
result = qa.run(query)
st.success(result)
else:
st.warning("Please enter a question.")

---

▶️ 5. Run Your App

1. Install dependencies:

pip install -r requirements.txt

2. Build your FAISS index:

python build_index.py

3. Start the Streamlit app:

streamlit run app.py

4. Open your browser → it will show your AI Business Assistant interface.
   Example URL: http://localhost:8501