Fixed

app.py

@@ -10,6 +10,7 @@ Original file is located at
 
 
 # Import Libraries
+import os
 from langchain_community.vectorstores import Chroma
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain.llms import HuggingFacePipeline
@@ -20,6 +21,9 @@ from langchain.text_splitter import CharacterTextSplitter
 from langchain.schema import Document
 from transformers import BitsAndBytesConfig
 
+
+login(token=os.getenv("HF_TOKEN"))
+
 # ByteCode Data (as context)
 bytecode_info = """
 You are a ByteCode helpful GenZ AI assistant. Be concise, friendly, and practical.
@@ -130,7 +134,9 @@ model_name = "google/gemma-2b-it"
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
     device_map="auto",
-    quantization_config=quant_config
+    quantization_config=quant_config,
+    token=os.getenv("HF_TOKEN")
+
 )
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)

requirements.txt

@@ -1,8 +1,10 @@
-gradio
+transformers
+huggingface_hub
 langchain
 langchain-community
-transformers
+langchain-huggingface
+sentence-transformers
 bitsandbytes
 accelerate
 chromadb
-sentence-transformers
+gradio