Spaces:
Sleeping
Sleeping
File size: 2,025 Bytes
972a93c 210135b 972a93c 210135b 972a93c 210135b 972a93c 210135b 972a93c 210135b 972a93c 210135b 972a93c 210135b 972a93c 210135b 972a93c 210135b 972a93c 210135b 972a93c 210135b 972a93c 210135b 972a93c 210135b 972a93c 210135b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
import streamlit as st
from langchain_community.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.chains import RetrievalQA
from langchain_community.llms import HuggingFaceEndpoint
import os
# --- UI ---
st.set_page_config(page_title="SMEHelpBot", layout="wide")
st.title("🤖 SMEHelpBot – Your AI Assistant for Small Business")
uploaded_file = st.file_uploader("📄 Upload an industry-specific PDF (policy, FAQ, etc.):", type=["pdf"])
user_query = st.text_input("💬 Ask a business-related question:")
# --- Process PDF + RAG ---
if uploaded_file:
with open("temp.pdf", "wb") as f:
f.write(uploaded_file.read())
loader = PyPDFLoader("temp.pdf")
pages = loader.load()
splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
chunks = splitter.split_documents(pages)
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
db = FAISS.from_documents(chunks, embeddings)
retriever = db.as_retriever()
# --- Groq API (LLaMA3 via HuggingFaceEndpoint) ---
os.environ["HUGGINGFACEHUB_API_TOKEN"] = st.secrets.get("HF_TOKEN") or "your_api_token_here"
llm = HuggingFaceEndpoint(
repo_id="meta-llama/Meta-Llama-3-8B-Instruct",
temperature=0.6,
max_new_tokens=512
)
qa_chain = RetrievalQA.from_chain_type(
llm=llm,
retriever=retriever,
return_source_documents=True
)
if user_query:
with st.spinner("Generating response..."):
result = qa_chain({"query": user_query})
st.success(result["result"])
with st.expander("📚 Sources"):
for doc in result["source_documents"]:
st.markdown(f"• Page content: {doc.page_content[:300]}...")
else:
st.info("Upload a PDF and type your question to get started.")
|