| import streamlit as st | |
| import joblib | |
| from langchain_community.document_loaders import PyPDFLoader | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| from langchain_community.embeddings import SentenceTransformerEmbeddings | |
| from langchain_community.vectorstores import Chroma | |
| from langchain.chains import RetrievalQAWithSourcesChain | |
| from langchain_openai import ChatOpenAI | |
| from dotenv import load_dotenv | |
| import os | |
| import time | |
| load_dotenv("bookie.env") | |
| api_key=os.getenv("OPENAI_API_KEY") | |
| api_base=os.getenv("OPENAI_API_BASE") | |
| llm=ChatOpenAI(model_name="google/gemma-3n-e2b-it:free",temperature=0.2) | |
| em=joblib.load("bai.joblib") | |
| mp=st.empty() | |
| st.title("Welcome to Bookie 😊😊") | |
| st.sidebar.title("give you book in pdf format(digitally generated) and less than 5mb for faster answers😊😊") | |
| uploaded_file = st.sidebar.file_uploader("Upload a PDF file", type=["pdf"]) | |
| upl=st.sidebar.button("upload") | |
| import tempfile | |
| if upl and uploaded_file: | |
| if uploaded_file.size > 5 * 1024 * 1024: | |
| st.sidebar.error("❌ File too large. Please upload files under 5MB.") | |
| st.stop() | |
| with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file: | |
| tmp_file.write(uploaded_file.read()) | |
| tmp_path = tmp_file.name | |
| mp.text("loading doc") | |
| loader = PyPDFLoader(tmp_path) | |
| docs = loader.load() | |
| st.write(len(docs)) | |
| mp.text("loading split") | |
| tct=RecursiveCharacterTextSplitter.from_tiktoken_encoder(encoding_name="cl100k_base",chunk_size=512, chunk_overlap=16) | |
| doc=tct.split_documents(docs) | |
| st.write(len(doc)) | |
| mp.text("loading vector db") | |
| vb= Chroma.from_documents(doc,em) | |
| r1=vb.as_retriever(search_type="similarity",search_kwargs={"k":4}) | |
| mp.text("loading retriever") | |
| chain=RetrievalQAWithSourcesChain.from_chain_type(llm=llm,chain_type="map_reduce",retriever=r1) | |
| st.session_state.chain=chain | |
| mp.text("loading done") | |
| time.sleep(3) | |
| q=mp.text_input("Ask a question about the document:") | |
| qb=st.button("submit") | |
| if qb: | |
| if "chain" not in st.session_state: | |
| st.warning("⚠️ Please upload a document first.") | |
| st.stop() | |
| else: | |
| with st.spinner("Waiting for it...."): | |
| result=st.session_state.chain({"question":q},return_only_outputs=True) | |
| st.header("Answer") | |
| st.subheader(result["answer"]) | |
| sb=st.button("show sources") | |
| if sb: | |
| sources = result.get("sources", "") | |
| st.subheader("Sources") | |
| for line in sources.split("\n"): | |
| st.write(line) | |