Update app.py

app.py

@@ -19,13 +19,17 @@ import chainlit as cl
 from langchain import hub
 from langchain.chains import LLMChain, APIChain
 from langchain_core.prompts import PromptTemplate
+from langchain.memory.buffer import ConversationBufferMemory
+
 from langchain_community.llms import HuggingFaceHub
+from langchain_huggingface import HuggingFacePipeline
 from langchain_huggingface import HuggingFaceEndpoint
-from langchain.memory.buffer import ConversationBufferMemory
+from langchain_core.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 
-logging.basicConfig(level=logging.DEBUG)
+#logging.basicConfig(level=logging.DEBUG)
 
-HUGGINGFACEHUB_API_TOKEN = os.environ.get("HUGGINGFACEHUB_API_TOKEN")
+
+#HF_INFERENCE_ENDPOINT = 
 #BOOKING_ID = re.compile(r'\b[A-Z]{6}\d{6}\b')
 BOOKING_KEYWORDS = [
     "booking",
@@ -91,14 +95,27 @@ api_response_prompt = PromptTemplate(
 @cl.on_chat_start
 def setup_multiple_chains():
     
-    llm = HuggingFaceHub(
+    llm = HuggingFaceEndpoint(
     repo_id="google/gemma-2-2b-it", #"norallm/normistral-7b-warm-instruct", 
-    huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN, 
-    #max_new_tokens=512,  
-    temperature=0.7,     
-    #task="text-generation"  
+        #endpoint_url="http://localhost:8010/",
+        model="gemma-2-2b-it",
+        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=os.environ.get("HUGGINGFACEHUB_API_TOKEN"),
+        task="text-generation"
     )
 
+   
+    #llm = HuggingFacePipeline.from_model_id(
+    #model_id="normistral-7b-warm-instruct",
+    #task="text-generation",
+    #pipeline_kwargs={"max_new_tokens": 10},
+    #)
+    
     conversation_memory = ConversationBufferMemory(memory_key="chat_history",
                                                    max_len=200,
                                                    return_messages=True,