Update app.py

app.py

@@ -3,7 +3,6 @@ import pdfplumber
 from transformers import AutoTokenizer, AutoModelForQuestionAnswering
 import torch
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.vectorstores import Chroma
 from langchain.chains import ConversationalRetrievalChain
 from langchain.memory import ConversationBufferMemory
@@ -41,8 +40,13 @@ if uploaded_file:
     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)
+    # สร้าง embeddings โดยใช้ transformers
+    model_name = "sentence-transformers/paraphrase-xlm-r-multilingual-v1"
+    embedding_model = AutoModel.from_pretrained(model_name)
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+    # ปรับแต่ง Chroma กับ embeddings ของคุณ
+    vector_store = Chroma.from_documents(documents=docs, embedding=embedding_model)
 
     retriever = vector_store.as_retriever()
     memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)