Update app.py

app.py

@@ -13,7 +13,8 @@ import moviepy
 import gradio as gr
 import pandas as pd
 from spacy.cli import download
-
+from transformers import AutoTokenizer, AutoModel
+import torch
 
 class BasicAgent:
     def __init__(self):
@@ -22,11 +23,15 @@ class BasicAgent:
             self.spacy = spacy.load("en_core_web_sm")
         except OSError:
             download("en_core_web_sm")
-        self.spacy = spacy.load("en_core_web_sm")
+            self.spacy = spacy.load("en_core_web_sm")
+    
         self.whisper_model = whisper.load_model("base")
         self.qa_pipeline = pipeline("question-answering", truncation=True, padding=True)
         self.ner_pipeline = pipeline("ner", aggregation_strategy="simple")
-        self.embedding_model = pipeline("feature-extraction", truncation=True)
+    
+        # ✅ FIXED: safer embedding model setup
+        self.embedding_tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
+        self.embedding_model = AutoModel.from_pretrained("bert-base-uncased")
 
     def split_text_into_chunks(self, text, max_length=512):
         """Split text into chunks smaller than `max_length` tokens."""