Update agent.py

agent.py

@@ -29,7 +29,7 @@ import json
 from langchain_core.documents import Document
 from langchain_community.vectorstores import FAISS
 from langchain.vectorstores import FAISS
-from langchain.embeddings import BERTEmbeddings
+#from langchain.embeddings import BERTEmbeddings
 from langchain_community.embeddings import HuggingFaceEmbeddings
 
 from youtube_transcript_api import YouTubeTranscriptApi
@@ -343,37 +343,6 @@ for name in enabled_tool_names:
     tools.append(tool_map[name])
 
     
-
-# -------------------------------
-# Set up BERT Embeddings 
-# -------------------------------
-
-# -----------------------------
-# Define Custom BERT Embedding Model
-# -----------------------------
-import torch
-import torch.nn.functional as F
-from transformers import BertTokenizer, BertModel
-
-class BERTEmbeddings:
-    def __init__(self, model_name='bert-base-uncased'):
-        self.tokenizer = BertTokenizer.from_pretrained(model_name)
-        self.model = BertModel.from_pretrained(model_name)
-        self.model.eval()  # Set to evaluation mode
-
-    def embed_documents(self, texts):
-        inputs = self.tokenizer(texts, return_tensors='pt', padding=True, truncation=True)
-        with torch.no_grad():
-            outputs = self.model(**inputs)
-        embeddings = outputs.last_hidden_state.mean(dim=1)
-        embeddings = F.normalize(embeddings, p=2, dim=1)  # Normalize for cosine similarity
-        return embeddings.cpu().numpy()
-
-    def embed_query(self, text):
-        return self.embed_documents([text])[0]
-
-
-
 # -----------------------------
 # Create FAISS Vector Store
 # -----------------------------