Update app.py

app.py

@@ -1,5 +1,4 @@
-from gpt_index import GPTSimpleVectorIndex
-from langchain import OpenAI
+from llama_index import GPTSimpleVectorIndex
 import gradio as gr
 from gradio import Interface, Textbox
 import sys
@@ -17,8 +16,7 @@ DATASET_REPO_URL = "https://huggingface.co/datasets/peterpull/MediatorBot"
 DATA_FILENAME = "data.txt"
 INDEX_FILENAME = "index2.json"
 
-
-# we need a write access token.
+# we need a HF access token - read I think suffices becuase we are cloning the distant repo to local space repo.
 HF_TOKEN = os.environ.get("HF_TOKEN")
 print("HF TOKEN is none?", HF_TOKEN is None)
 print("HF hub ver", huggingface_hub.__version__)
@@ -53,21 +51,18 @@ def store_message(chatinput: str, chatresponse: str):
             file.write(f"{datetime.now()},{chatinput},{chatresponse}\n")
             print(f"Wrote to datafile: {datetime.now()},{chatinput},{chatresponse}\n")
         
-        #trial - take out if fails to write to local directory
-        with open('backup.txt', "a") as file:
-            file.write(f"{datetime.now()},{chatinput},{chatresponse}\n")
-            print(f"Wrote to datafile: {datetime.now()},{chatinput},{chatresponse}\n")
-
+    #need to find a way to push back to dataset repo
+            
     return generate_text()
 
 def get_index(index_file_path):
     if os.path.exists(index_file_path):
+        #print 500 characters of json header
         print_header_json_file(index_file_path)
         index_size = os.path.getsize(index_file_path)
         print(f"Size of {index_file_path}: {index_size} bytes") #let me know how big json file is.
-        #debug - needs to be index_file_path
-        return GPTSimpleVectorIndex.load_from_disk('./index/indexsmall.json'
-        )
+        #debug - this is where an error is occuring
+        return GPTSimpleVectorIndex.load_from_disk(index_file_path)
     else:
         print(f"Error: '{index_file_path}' does not exist.")
         sys.exit()
@@ -83,7 +78,7 @@ index = get_index(INDEX_FILE)
 # passes the prompt to the chatbot
 def chatbot(input_text, mentioned_person='Mediator John Haynes', confidence_threshold=0.5):
     prompt = f"You are {mentioned_person}. Answer this: {input_text}. Reply from the contextual data or say you don't know. To finish, ask an insightful question."
-    response = index.query(prompt, response_mode="default", verbose=True)
+    response = index.query(prompt, response_mode="compact")
 
     store_message(input_text,response)