File size: 2,181 Bytes
ff77f23 | 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 |
import streamlit as st
from langchain_community.document_loaders import PyPDFLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_huggingface import HuggingFaceEmbeddings
from langchain.vectorstores import Chroma
from langchain.prompts import ChatPromptTemplate
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_core.runnables import RunnablePassthrough
import tempfile
# --- Streamlit App Title ---
st.title("📄 Medical Education Visual Aid - PDF RAG Chatbot")
# --- File Uploader ---
uploaded_file = st.file_uploader("Upload a PDF document", type=["pdf"])
# Check if a file is uploaded
if uploaded_file:
# Save uploaded file to a temporary path
with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
tmp_file.write(uploaded_file.read())
temp_pdf_path = tmp_file.name
# Load and process the PDF
loader = PyPDFLoader(temp_pdf_path)
pages = loader.load()
splitter = RecursiveCharacterTextSplitter(
chunk_size=100,
chunk_overlap=20
)
split = splitter.split_documents(pages)
# Create embeddings and vector store
hfembedding = HuggingFaceEmbeddings()
db = Chroma.from_documents(documents=split, embedding=hfembedding)
# Prompt template
template_string = """
You are a smart medical assistant. Use the provided context to answer the question.
context: {context}
question: {question}
"""
prompt_template = ChatPromptTemplate.from_template(template_string)
# LLM initialization (replace with your key or env variable)
GOOGLE_API_KEY = "AIzaSyDA1zZ006f4krgUDjhdju_RcwZNwNPOJwI"
llm = ChatGoogleGenerativeAI(model="gemini-1.5-flash-latest", api_key=GOOGLE_API_KEY)
# RAG chain
retriever = db.as_retriever()
chain = (
{"context": retriever, "question": RunnablePassthrough()}
| prompt_template
| llm
)
# User query
query = st.text_input("💬 Ask a question about the uploaded PDF:")
if query:
response = chain.invoke(query)
st.subheader("Answer")
st.write(response.content)
|