Updated file

app.py

@@ -1,5 +1,4 @@
 # Importing necessary modules for embeddings and vector database storage.
-from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_chroma import Chroma
 # Importing RunnableLambda for wrapping functions as runnable components.
 from langchain_core.runnables import RunnableLambda
@@ -7,7 +6,8 @@ from langchain_core.prompts import PromptTemplate
 from langchain_core.output_parsers import StrOutputParser                            # to transform the output of an LLM into a more usable format
 from langchain.schema.runnable import RunnableParallel, RunnablePassthrough 
 # importing HuggingFace model abstraction class from langchain
-from langchain_huggingface import HuggingFaceEndpoint
+from langchain.llms import HuggingFaceEndpoint
+from sentence_transformers import SentenceTransformer
 
 import torch
 import gradio
@@ -27,14 +27,9 @@ llm = HuggingFaceEndpoint(
     repetition_penalty=1.03,  # Slightly penalizes repeated tokens to reduce redundancy in responses.
 )
 
-# Initializing the Hugging Face embedding model.
-embedding =  HuggingFaceEmbeddings(
-    model_name="mixedbread-ai/mxbai-embed-large-v1",  # Using a pre-trained embedding model for text vectorization.
+# Load the embedding model
 
-    model_kwargs={'device': "cuda" if torch.cuda.is_available() else "cpu"},  # Configuring the model to use GPU if available.
-
-    encode_kwargs={'normalize_embeddings': False}  # Disabling normalization to preserve the original embedding scale.
-)
+embedding = SentenceTransformer("mixedbread-ai/mxbai-embed-large-v1")
 
 # Creating a Chroma vector database instance.
 vectordb = Chroma(