File size: 3,019 Bytes
5c6086a |
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 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 |
import streamlit as st
from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.chains import RetrievalQA
from langchain_google_genai import ChatGoogleGenerativeAI
import tempfile
import os
from dotenv import load_dotenv
from pydantic import SecretStr
load_dotenv()
GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
# ---------------------------- SETUP ----------------------------
st.title("📄 LangChain RAG Chatbot")
# Session state
if "chat_history" not in st.session_state:
st.session_state.chat_history = []
if "qa_chain" not in st.session_state:
st.session_state.qa_chain = None
# ---------------------------- FILE UPLOAD ----------------------------
st.subheader("Upload your PDF")
pdf_file = st.file_uploader("Upload", type="pdf")
if pdf_file is not None and st.session_state.qa_chain is None:
with st.spinner("🔍 Processing document..."):
# Save file temporarily
with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
tmp_file.write(pdf_file.read())
tmp_path = tmp_file.name
# Load and split PDF
loader = PyPDFLoader(tmp_path)
documents = loader.load_and_split()
splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
chunks = splitter.split_documents(documents)
# Vector store
vectordb = Chroma.from_documents(
chunks, embeddings, persist_directory="./chroma_db"
)
retriever = vectordb.as_retriever()
# QA Chain
llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", api_key=SecretStr(GOOGLE_API_KEY) if GOOGLE_API_KEY else None)
qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever)
# Store in session
st.session_state.qa_chain = qa_chain
st.success("✅ Document processed and indexed!")
# ---------------------------- CHAT ----------------------------
if st.session_state.qa_chain:
st.subheader("💬 Ask a question")
question = st.text_input("You:", key="user_input")
if question:
with st.spinner("🤖 Generating answer..."):
answer = st.session_state.qa_chain.run(question)
st.session_state.chat_history.append({"user": question, "bot": answer})
# Display chat history
for chat in st.session_state.chat_history:
st.markdown(f"🧑 **You:** {chat['user']}")
st.markdown(f"🤖 **Bot:** {chat['bot']}")
# Reset button
if st.button("🔄 Reset Chat"):
st.session_state.chat_history = []
st.session_state.qa_chain = None
st.rerun()
else:
st.info("📂 Please upload a PDF to begin.")
|