Update app.py

app.py

@@ -6,6 +6,8 @@ from hazm import *
 import docx
 from transformers import AutoTokenizer, AutoModel
 from langchain.llms import OpenAI
+from langchain.chat_models import ChatOpenAI
+
 
 # بارگذاری مدل‌ها و توکنایزر
 tokenizer = AutoTokenizer.from_pretrained("HooshvareLab/bert-fa-base-uncased")
@@ -13,7 +15,7 @@ model = AutoModel.from_pretrained("HooshvareLab/bert-fa-base-uncased")
 
 @st.cache
 def get_embedding(text):
-    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+        inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
     with torch.no_grad():
         outputs = model(**inputs)
     embeddings = outputs.last_hidden_state.mean(dim=1)