Update app.py

app.py

@@ -21,6 +21,8 @@ from langchain.chains import LLMChain, APIChain
 from langchain_core.prompts import PromptTemplate
 from langchain.memory.buffer import ConversationBufferMemory
 
+from langchain_openai import OpenAI
+
 from langchain_community.llms import HuggingFaceHub
 from langchain_huggingface import HuggingFacePipeline
 from langchain_huggingface import HuggingFaceEndpoint
@@ -94,22 +96,25 @@ api_response_prompt = PromptTemplate(
 
 @cl.on_chat_start
 def setup_multiple_chains():
+
+    llm = OpenAI(model='gpt-3.5-turbo-instruct',
+             temperature=0.7)
     
-    llm = HuggingFaceEndpoint(
+    #llm = HuggingFaceEndpoint(
         #repo_id="google/gemma-2-2b", #"norallm/normistral-7b-warm-instruct", 
         #endpoint_url="http://localhost:8010/",
-        model="google/gemma-2-2b",
-        max_new_tokens=512,
-        top_k=10,
-        top_p=0.95,
-        typical_p=0.95,
-        temperature=0.7,
-        repetition_penalty=1.03,
-        huggingfacehub_api_token=HUGGINGFACE_API_TOKEN,
-        task="text-generation"
-    )
+    
+        #model="google/gemma-2-2b",
+        #max_new_tokens=512,
+        #top_k=10,
+        #top_p=0.95,
+        #typical_p=0.95,
+        #temperature=0.7,
+        #repetition_penalty=1.03,
+        #huggingfacehub_api_token=HUGGINGFACE_API_TOKEN,
+        #task="text-generation"
+    #)
 
-   
     #llm = HuggingFacePipeline.from_model_id(
     #model_id="normistral-7b-warm-instruct",
     #task="text-generation",