Update app.py

app.py

@@ -4,7 +4,7 @@ import streamlit as st
 import cv2
 from streamlit_drawable_canvas import st_canvas
 import torch
-torch.classes.__path__ = []
+import numpy as np
 from diffusers import AutoPipelineForInpainting
 import numpy as np
 from langchain.text_splitter import RecursiveCharacterTextSplitter
@@ -34,7 +34,7 @@ from streamlit_pdf_viewer import pdf_viewer
 
 
 
-dictionary=st.session_state
+
 def consume_llm_api(prompt):
     """
     Sends a prompt to the LLM API and processes the streamed response.
@@ -205,7 +205,7 @@ def d4_to_3d(image):
     return np.array(formatted_array)
     
 st.set_page_config(layout="wide")
-
+dictionary=st.session_state
 # st.write(str(os.getcwd()))
 screen_width = streamlit_js_eval(label="screen.width",js_expressions='screen.width')
 screen_height = streamlit_js_eval(label="screen.height",js_expressions='screen.height')
@@ -543,7 +543,7 @@ with st.spinner('Wait for it...'):
                             text_splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=100)
                             chunks = text_splitter.split_documents(data)
 
-                            dictionary['text_embeddings'][str(data)]={str(chunk.page_content):model.encode(str(chunk.page_content)) for chunk in chunks}
+                            dictionary['text_embeddings'][str(data)]={str(chunk.page_content):np.array(model.encode(str(chunk.page_content))) for chunk in chunks}
 
                             embeddings = [dictionary['text_embeddings'][str(data)][i] for i in dictionary['text_embeddings'][str(data)]]
                             vector_store = []