[update] deploymeny

requirements.txt

@@ -14,4 +14,5 @@ chromadb==0.5
 starlette==0.37.2
 typer==0.10.0
 sentence-transformers
+ctransformers
 pinecone-client

run.py

@@ -3,7 +3,7 @@ from langchain_core.output_parsers import StrOutputParser
 from langchain_core.runnables import RunnablePassthrough
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain_community.vectorstores import Chroma
-from transformers import AutoModelForCausalLM
+from ctransformers import AutoModelForCausalLM
 
 import os
 os.environ['TRANSFORMERS_CACHE'] = '/code/model/cache/'