Create app.py

app.py

@@ -0,0 +1,64 @@
+import streamlit as st
+import pdfplumber
+from langchain import PromptTemplate, LLMChain
+from langchain.chat_models import HuggingFaceHub
+from langchain.chains import ConversationalRetrievalChain
+from langchain.vectorstores import Chroma
+from langchain.document_loaders import TextLoader
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.memory import ConversationBufferMemory
+from transformers import AutoTokenizer, AutoModelForQuestionAnswering
+
+# โหลดโมเดล ThaiBERT จาก Hugging Face
+tokenizer = AutoTokenizer.from_pretrained("airesearch/wangchanberta-base-att-spm-uncased")
+model = AutoModelForQuestionAnswering.from_pretrained("airesearch/wangchanberta-base-att-spm-uncased")
+
+# ฟังก์ชันสำหรับอ่านเนื้อหาจาก PDF
+def extract_text_from_pdf(pdf_file):
+    with pdfplumber.open(pdf_file) as pdf:
+        text = ""
+        for page in pdf.pages:
+            text += page.extract_text()
+    return text
+
+# ฟังก์ชันสำหรับการตอบคำถามด้วย ThaiBERT
+def answer_question(question, context):
+    inputs = tokenizer.encode_plus(question, context, return_tensors="pt")
+    answer_start_scores, answer_end_scores = model(**inputs)
+    answer_start = torch.argmax(answer_start_scores)
+    answer_end = torch.argmax(answer_end_scores) + 1
+    answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(inputs['input_ids'][0][answer_start:answer_end]))
+    return answer
+
+# ตั้งค่าอินเตอร์เฟสของหน้าเว็บด้วย Streamlit
+st.title("ThaiBERT PDF QA System")
+uploaded_file = st.file_uploader("Upload a PDF", type="pdf")
+
+if uploaded_file:
+    # อ่านเนื้อหาจาก PDF
+    pdf_text = extract_text_from_pdf(uploaded_file)
+
+    # สร้าง chain สำหรับถามตอบ
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+    docs = text_splitter.create_documents([pdf_text])
+
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/paraphrase-xlm-r-multilingual-v1")
+    vector_store = Chroma.from_documents(documents=docs, embedding=embeddings)
+
+    retriever = vector_store.as_retriever()
+    memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+
+    qa_chain = ConversationalRetrievalChain(
+        retriever=retriever,
+        llm=HuggingFaceHub(repo_id="airesearch/wangchanberta-base-att-spm-uncased", model_kwargs={"temperature": 0}),
+        memory=memory
+    )
+
+    # หน้าต่างสำหรับใส่คำถาม
+    user_question = st.text_input("Ask a question about the PDF content")
+
+    if user_question:
+        response = qa_chain.run(user_question)
+        st.write("Answer:", response)
+