Update app.py

app.py

@@ -19,7 +19,7 @@ from transformers import pipeline
 import os
 import transformers
 import torch
-from langchain_community.llms import LlamaCpp
+# from langchain_community.llms import LlamaCpp
 # from langchain_retrieval import BaseRetrieverChain
 # from dotenv import load_dotenv
 
@@ -140,19 +140,19 @@ def get_response(user_input):
     #     task="text2text-generation",
     #     # model_kwargs={"temperature": 0.2},
     # )
-    # llm = HuggingFacePipeline.from_model_id(
-    #     model_id="google-t5/t5-small",
-    #     task="text2text-generation",
-    #     # model_kwargs={"temperature": 0.2},
-    # )
+    llm = HuggingFacePipeline.from_model_id(
+        model_id="google-t5/t5-small",
+        task="text2text-generation",
+        # model_kwargs={"temperature": 0.2},
+    )
     # llm = pipeline(task="conversational", model="facebook/blenderbot-400M-distill")
-    llm = LlamaCpp(
-    model_path="TheBloke/OpenOrca-Platypus2-13B-GGUF",
-    temperature=0.75,
-    max_tokens=2000,
-    top_p=1,
-    # callback_manager=callback_manager,
-    verbose=True,  # Verbose is required to pass to the callback manager
+    # llm = LlamaCpp(
+    # model_path="TheBloke/OpenOrca-Platypus2-13B-GGUF",
+    # temperature=0.75,
+    # max_tokens=2000,
+    # top_p=1,
+    # # callback_manager=callback_manager,
+    # verbose=True,  # Verbose is required to pass to the callback manager
 )
 
     # llm = HuggingFacePipeline.from_model_id(