mock

api/question_answering/qa_model.py

@@ -13,6 +13,7 @@ from langchain.llms import HuggingFacePipeline
 from langchain.llms.base import LLM
 from langchain.embeddings import HuggingFaceEmbeddings, HuggingFaceHubEmbeddings, HuggingFaceInstructEmbeddings
 from langchain.vectorstores import FAISS
+from mocks import MockLocalBinaryModel
 
 from api.logger import logger
 from api.question_answering.response import Response
@@ -182,7 +183,7 @@ class QAModel():
             )
         else:
             logger.info('using transformers pipeline model')
-            self.llm_model = TransformersPipelineModel(
+            self.llm_model = MockLocalBinaryModel(
                 model_id=llm_model_id
             )