Update pages/🤖 Medical Question Answering.py

pages/🤖 Medical Question Answering.py

@@ -1,194 +1,198 @@
-import streamlit as st
-import google.generativeai as genai
-from dotenv import load_dotenv
-import os
-import PIL
-from PyPDF2 import PdfReader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_google_genai import GoogleGenerativeAIEmbeddings
-from langchain_community.vectorstores import FAISS
-from langchain_google_genai import ChatGoogleGenerativeAI
-from langchain.chains.question_answering import load_qa_chain
-from langchain.prompts import PromptTemplate
-
-load_dotenv()
-os.getenv("langchain_google_genai")
-os.environ['GOOGLE_API_KEY'] = 'AIzaSyA5cVv6I1HxH68CTiPGalPQHymtunvDxVY'
-genai.configure(api_key="AIzaSyA5cVv6I1HxH68CTiPGalPQHymtunvDxVY")
-# Function to extract text from PDF files
-
-import os
-os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE'
-
-def get_pdf_text(pdf_docs):
-    text = ""
-    for pdf in pdf_docs:
-        pdf_reader = PdfReader(pdf)
-        for page in pdf_reader.pages:
-            text += page.extract_text()
-    return text
-
-# Function to split text into chunks
-def get_text_chunks(text):
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
-    chunks = text_splitter.split_text(text)
-    return chunks
-
-# Function to create a vector store from text chunks
-def get_vector_store(text_chunks):
-    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
-    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
-    vector_store.save_local("faiss_index")
-
-# Function to get the conversational chain
-if "text_chunks" not in st.session_state:
-    st.session_state.text_chunks = None
-
-if "vector_store" not in st.session_state:
-    st.session_state.vector_store = None
-
-if "document_messages" not in st.session_state:
-    st.session_state.document_messages = []
-
-
-def get_conversational_chain():
-    prompt_template = """
-    Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
-    provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n
-    Context:\n {context}?\n
-    Question: \n{question}\n
-
-    Answer:
-    """
-    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.1)
-    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
-    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
-    return chain
-
-# Function to handle user input
-# Function to handle user input
-def user_input(user_question):
-    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
-    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
-    docs = new_db.similarity_search(user_question)
-    chain = get_conversational_chain()
-    response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
-
-    return response["output_text"]  # Return the answer as a string
-
-
-
-# Streamlit UI setup
-st.markdown("<h1 style='text-align: center;'>Chào mừng tới Medical Question Answering 🎈</h1>", unsafe_allow_html=True)
-
-
-with st.expander("Instructions"):
-    st.markdown("Truyền vào một câu hỏi liên quan đến y tế, chúng tôi sẽ giải đáp cho bạn.")
-    st.markdown("Bạn có thể hỏi các câu liên quan đến triệu chứng, nguyên nhân và một số phương pháp điều trị.")
-
-
-
-
-
-with st.sidebar:
-    mode = st.selectbox("Chọn chức năng", ["Question with Images", "Question with Documents"])
-    if mode == "Question with Images":
-        uploaded_files = st.file_uploader("Choose medical images...", type=["jpg", "jpeg", "png", "dicom"], accept_multiple_files=True)
-    elif mode == "Question with Documents":
-        folder_path = "medicalDocuments"
-        if st.session_state.text_chunks is None:
-            pdf_docs = [os.path.join(folder_path, f) for f in os.listdir(folder_path) if f.endswith(".pdf")]
-            raw_text = get_pdf_text(pdf_docs)
-            st.session_state.text_chunks = get_text_chunks(raw_text)
-            st.session_state.vector_store = get_vector_store(st.session_state.text_chunks)
-
-# Initialize session state
-if "messages" not in st.session_state:
-    st.session_state.messages = []
-
-if "image_messages" not in st.session_state:
-    st.session_state.image_messages = []
-
-if "max_messages" not in st.session_state:
-    st.session_state.max_messages = 1000
-
-# Handle "Question with Images" mode
-col_1, col_2, col_3 = st.columns([8, 1, 8])
-if mode == "Question with Images" and uploaded_files:
-    with col_1:
-        image = PIL.Image.open(uploaded_files[0])
-        st.image(image, caption="Uploaded Image", use_column_width=True)
-    with col_3:
-        # Display past messages for Question with Images
-        for message in st.session_state.image_messages:
-            with st.chat_message(message["role"]):
-                st.markdown(message["content"])
-
-        if prompt := st.chat_input("Ask a question about the image..."):
-            st.session_state.image_messages.append({"role": "user", "content": prompt})
-            with st.chat_message("user"):
-                st.markdown(prompt)
-            model = genai.GenerativeModel('gemini-1.5-flash')
-            with st.chat_message("assistant"):
-                try:
-                    response = model.generate_content([prompt, image])
-                    st.session_state.image_messages.append({"role": "assistant", "content": response.text})
-                    st.markdown(response.text)
-                except Exception as e:
-                    st.session_state.max_messages = len(st.session_state.image_messages)
-                    st.session_state.image_messages.append(
-                        {"role": "assistant", "content": f"Oops! There was an error: {str(e)}"}
-                    )
-                    st.rerun()
-
-if "document_messages" not in st.session_state:
-    st.session_state.document_messages = []
-
-# Handle "Question with Documents" mode
-if mode == "Question with Documents":
-    # Display past messages for Document-based conversation
-    for message in st.session_state.document_messages:
-        with st.chat_message(message["role"]):
-            st.markdown(message["content"])
-
-    if user_question := st.chat_input("Hỏi câu hỏi từ file PDF"):
-        st.session_state.document_messages.append({"role": "user", "content": user_question})
-        with st.chat_message("user"):
-            st.markdown(user_question)
-
-        # Generate the response
-        with st.chat_message("assistant"):
-            try:
-                response = user_input(user_question)
-                st.session_state.document_messages.append({"role": "assistant", "content": response})
-                st.markdown(response)
-            except Exception as e:
-                st.session_state.document_messages.append(
-                    {"role": "assistant", "content": f"Oops! There was an error: {str(e)}"}
-                )
-                st.rerun()
-
-# Display past messages for non-image-based conversation
-if mode != "Question with Images" and mode != "Question with Documents":
-    for message in st.session_state.messages:
-        with st.chat_message(message["role"]):
-            st.markdown(message["content"])
-
-    if len(st.session_state.messages) < st.session_state.max_messages:
-        if prompt := st.chat_input("Hôm nay bạn như thế nào?"):
-            st.session_state.messages.append({"role": "user", "content": prompt})
-            with st.chat_message("user"):
-                st.markdown(prompt)
-            model = genai.GenerativeModel(model_name="gemini-pro")
-            with st.chat_message("assistant"):
-                try:
-                    prompt_parts = [prompt]
-                    response = model.generate_content(prompt_parts)
-                    st.session_state.messages.append({"role": "assistant", "content": response.text})
-                    st.markdown(response.text)
-                except Exception as e:
-                    st.session_state.max_messages = len(st.session_state.messages)
-                    st.session_state.messages.append(
-                        {"role": "assistant", "content": f"Oops! There was an error: {str(e)}"}
-                    )
-                    st.rerun()
+import streamlit as st
+import google.generativeai as genai
+from dotenv import load_dotenv
+import os
+import PIL
+from PyPDF2 import PdfReader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_google_genai import GoogleGenerativeAIEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain.chains.question_answering import load_qa_chain
+from langchain.prompts import PromptTemplate
+
+load_dotenv()
+os.getenv("langchain_google_genai")
+os.environ['GOOGLE_API_KEY'] = 'AIzaSyA5cVv6I1HxH68CTiPGalPQHymtunvDxVY'
+genai.configure(api_key="AIzaSyA5cVv6I1HxH68CTiPGalPQHymtunvDxVY")
+# Function to extract text from PDF files
+
+import os
+os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE'
+
+def get_pdf_text(pdf_docs):
+    text = ""
+    for pdf in pdf_docs:
+        pdf_reader = PdfReader(pdf)
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+    return text
+
+# Function to split text into chunks
+def get_text_chunks(text):
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
+    chunks = text_splitter.split_text(text)
+    return chunks
+
+# Function to create a vector store from text chunks
+def get_vector_store(text_chunks):
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
+    vector_store.save_local("faiss_index")
+
+# Function to get the conversational chain
+if "text_chunks" not in st.session_state:
+    st.session_state.text_chunks = None
+
+if "vector_store" not in st.session_state:
+    st.session_state.vector_store = None
+
+if "document_messages" not in st.session_state:
+    st.session_state.document_messages = []
+
+
+def get_conversational_chain():
+    prompt_template = """
+    Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
+    provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n
+    Context:\n {context}?\n
+    Question: \n{question}\n
+
+    Answer:
+    """
+    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.1)
+    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
+    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
+    return chain
+
+# Function to handle user input
+# Function to handle user input
+def user_input(user_question):
+    # embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    # new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
+    # docs = new_db.similarity_search(user_question)
+    # chain = get_conversational_chain()
+    # response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
+
+    # return response["output_text"]  # Return the answer as a string
+    chain = get_conversational_chain()
+    response = chain({"input_documents": [], "question": user_question}, return_only_outputs=True)
+    
+    return response["output_text"]
+
+
+
+# Streamlit UI setup
+st.markdown("<h1 style='text-align: center;'>Chào mừng tới Medical Question Answering 🎈</h1>", unsafe_allow_html=True)
+
+
+with st.expander("Instructions"):
+    st.markdown("Truyền vào một câu hỏi liên quan đến y tế, chúng tôi sẽ giải đáp cho bạn.")
+    st.markdown("Bạn có thể hỏi các câu liên quan đến triệu chứng, nguyên nhân và một số phương pháp điều trị.")
+
+
+
+
+
+with st.sidebar:
+    mode = st.selectbox("Chọn chức năng", ["Question with Images", "Question with Documents"])
+    if mode == "Question with Images":
+        uploaded_files = st.file_uploader("Choose medical images...", type=["jpg", "jpeg", "png", "dicom"], accept_multiple_files=True)
+    elif mode == "Question with Documents":
+        folder_path = "medicalDocuments"
+        if st.session_state.text_chunks is None:
+            pdf_docs = [os.path.join(folder_path, f) for f in os.listdir(folder_path) if f.endswith(".pdf")]
+            raw_text = get_pdf_text(pdf_docs)
+            st.session_state.text_chunks = get_text_chunks(raw_text)
+            st.session_state.vector_store = get_vector_store(st.session_state.text_chunks)
+
+# Initialize session state
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+if "image_messages" not in st.session_state:
+    st.session_state.image_messages = []
+
+if "max_messages" not in st.session_state:
+    st.session_state.max_messages = 1000
+
+# Handle "Question with Images" mode
+col_1, col_2, col_3 = st.columns([8, 1, 8])
+if mode == "Question with Images" and uploaded_files:
+    with col_1:
+        image = PIL.Image.open(uploaded_files[0])
+        st.image(image, caption="Uploaded Image", use_column_width=True)
+    with col_3:
+        # Display past messages for Question with Images
+        for message in st.session_state.image_messages:
+            with st.chat_message(message["role"]):
+                st.markdown(message["content"])
+
+        if prompt := st.chat_input("Ask a question about the image..."):
+            st.session_state.image_messages.append({"role": "user", "content": prompt})
+            with st.chat_message("user"):
+                st.markdown(prompt)
+            model = genai.GenerativeModel('gemini-1.5-flash')
+            with st.chat_message("assistant"):
+                try:
+                    response = model.generate_content([prompt, image])
+                    st.session_state.image_messages.append({"role": "assistant", "content": response.text})
+                    st.markdown(response.text)
+                except Exception as e:
+                    st.session_state.max_messages = len(st.session_state.image_messages)
+                    st.session_state.image_messages.append(
+                        {"role": "assistant", "content": f"Oops! There was an error: {str(e)}"}
+                    )
+                    st.rerun()
+
+if "document_messages" not in st.session_state:
+    st.session_state.document_messages = []
+
+# Handle "Question with Documents" mode
+if mode == "Question with Documents":
+    # Display past messages for Document-based conversation
+    for message in st.session_state.document_messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+
+    if user_question := st.chat_input("Hỏi câu hỏi từ file PDF"):
+        st.session_state.document_messages.append({"role": "user", "content": user_question})
+        with st.chat_message("user"):
+            st.markdown(user_question)
+
+        # Generate the response
+        with st.chat_message("assistant"):
+            try:
+                response = user_input(user_question)
+                st.session_state.document_messages.append({"role": "assistant", "content": response})
+                st.markdown(response)
+            except Exception as e:
+                st.session_state.document_messages.append(
+                    {"role": "assistant", "content": f"Oops! There was an error: {str(e)}"}
+                )
+                st.rerun()
+
+# Display past messages for non-image-based conversation
+if mode != "Question with Images" and mode != "Question with Documents":
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+
+    if len(st.session_state.messages) < st.session_state.max_messages:
+        if prompt := st.chat_input("Hôm nay bạn như thế nào?"):
+            st.session_state.messages.append({"role": "user", "content": prompt})
+            with st.chat_message("user"):
+                st.markdown(prompt)
+            model = genai.GenerativeModel(model_name="gemini-pro")
+            with st.chat_message("assistant"):
+                try:
+                    prompt_parts = [prompt]
+                    response = model.generate_content(prompt_parts)
+                    st.session_state.messages.append({"role": "assistant", "content": response.text})
+                    st.markdown(response.text)
+                except Exception as e:
+                    st.session_state.max_messages = len(st.session_state.messages)
+                    st.session_state.messages.append(
+                        {"role": "assistant", "content": f"Oops! There was an error: {str(e)}"}
+                    )
+                    st.rerun()