Update app.py

app.py

@@ -1,10 +1,10 @@
 #for learning
 import os
-#import openai
+import openai
 import gradio as gr
 
-#openai.api_key =  os.environ.get('O_APIKey')
-HF_Token = os.environ.get('HF_Token')
+openai.api_key =  os.environ.get('O_APIKey')
+#HF_Token = os.environ.get('HF_Token')
 Data_Read =  os.environ.get('Data_Reader')
 ChurnData =  os.environ.get('Churn_Data')
 ChurnData2 =  os.environ.get('Churn_Data2')
@@ -12,47 +12,6 @@ ChurnData2 =  os.environ.get('Churn_Data2')
 #read data
 from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, SummaryIndex, download_loader
 
-#new
-from huggingface_hub import login
-import json
-login(token=HF_Token)
-
-repo_id = "microsoft/Phi-3-mini-4k-instruct"
-
-llm_client = inferenceClient(
-    model = repo_id,
-    timeout = 120,
-)
-
-def reply(inference_client: InferenceClient, prompt: str):
-    response = inference_client.post(
-        json={
-            "inputs":prompt,
-            "parameters":{"max_new_tokens":200},
-            "tasks":"text-generation",
-        },
-    )
-    answer = json.loads(response.decode())[0]["generated_text"]
-    return answer
-    
-#from llama_index.llms.ollama import Ollama
-#from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-#from llama_index.core import Settings
-
-#Settings.llm = Ollama(model="distilbert", request_timeout=120.0)
-#Settings.embed_model = HuggingFaceEmbedding(
-#    model_name="distilbert/distilgpt2"
-    ##model_name="meta-llama/Llama-2-7b-chat-hf"
-#)
-
-#from transformers import pipeline
-#pipe = pipeline("text-generation", model="distilbert/distilgpt2")
-#from transformers import AutoTokenizer, AutoModelForCausalLM
-#tokenizer = AutoTokenizer.from_pretrained("distilbert/distilgpt2")
-#model = AutoModelForCausalLM.from_pretrained("distilbert/distilgpt2")
-
-#new
-
 DataReader = download_loader(Data_Read)
 loader = DataReader()
 
@@ -69,9 +28,9 @@ documents = documents + documents2
 index = VectorStoreIndex.from_documents(documents)
 query_engine = index.as_query_engine()
 
-#def reply(message, history):
-#  answer = str(query_engine.query(message))
-#  return answer
+def reply(message, history):
+  answer = str(query_engine.query(message))
+  return answer
 
 Conversing = gr.ChatInterface(reply, chatbot=gr.Chatbot(height="70vh"), retry_btn=None,theme=gr.themes.Monochrome(),
                               title = 'BT Accor Q&A', undo_btn = None, clear_btn = None, css='footer {visibility: hidden}').launch()