Update app.py

app.py

@@ -1,6 +1,6 @@
-from llama_index import GPTSimpleVectorIndex
+from gpt_index import GPTSimpleVectorIndex
+from langchain import OpenAI
 import gradio as gr
-from gradio import Interface, Textbox
 import sys
 import os
 import datetime
@@ -11,34 +11,27 @@ import csv
 
 os.environ["OPENAI_API_KEY"] = os.environ['SECRET_CODE']
 
-# Best practice is to use a persistent dataset 
+# Need to write to persistent dataset because cannot store temp data on spaces
 DATASET_REPO_URL = "https://huggingface.co/datasets/peterpull/MediatorBot"
 DATA_FILENAME = "data.txt"
-INDEX_FILENAME = "index2.json"
+DATA_FILE = os.path.join("data", DATA_FILENAME)
 
-# we need a HF access token - read I think suffices becuase we are cloning the distant repo to local space repo.
+# I am guessing we need a write access token.
 HF_TOKEN = os.environ.get("HF_TOKEN")
 print("HF TOKEN is none?", HF_TOKEN is None)
 print("HF hub ver", huggingface_hub.__version__)
 
-#Clones the distant repo to the local repo
 repo = Repository(
-    local_dir='data', 
+    local_dir="data", 
     clone_from=DATASET_REPO_URL, 
     use_auth_token=HF_TOKEN)
 
-DATA_FILEP = os.path.join("data", DATA_FILENAME)
-INDEX_FILE = os.path.join("data", INDEX_FILENAME)
-
-print(f"Repo local_dir: {repo.local_dir}")
-print(f"Repo files: {os.listdir(repo.local_dir)}")
-print (f"Index file:{INDEX_FILENAME}")
 
 def generate_text() -> str:
     with open(DATA_FILE) as file:
         text = ""
         for line in file:
-            row_parts = line.strip().split(",")
+            row_parts = line.strip().split(";")
             if len(row_parts) != 3:
                 continue
             user, chatbot, time = row_parts
@@ -49,35 +42,21 @@ def store_message(chatinput: str, chatresponse: str):
     if chatinput and chatresponse:
         with open(DATA_FILE, "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()
 
+    return generate_text()
+            
+#gets the index file which is the context data
 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 - 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()
 
-def print_header_json_file(filepath):
-    with open(filepath, 'r') as f:
-        file_contents = f.read()
-        print ("JSON FILE HEADER:")
-        print(file_contents[:500]) # print only the first 500 characters
-
-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."
+def chatbot(input_text, mentioned_person='Mediator John Haynes'):
+    index = get_index('./index/indexsmall.json')
+    prompt = f"You are {mentioned_person}: {input_text}\n\n At the end of your answer  ask a provocative question."
     response = index.query(prompt, response_mode="compact")
 
     store_message(input_text,response)
@@ -86,14 +65,11 @@ def chatbot(input_text, mentioned_person='Mediator John Haynes', confidence_thre
     return response.response
 
 
-with open('about.txt', 'r') as file:
-    about = file.read()
 
-iface = Interface(
-    fn=chatbot,
-    inputs=Textbox("Enter your question"),
-    outputs="text",
-    title="AI Chatbot trained on J. Haynes mediation material, v0.5",
-    description=about)
-                                         
-iface.launch()
+iface = gr.Interface(fn=chatbot, 
+                     inputs=gr.inputs.Textbox("Enter your question"), 
+                     outputs="text",
+                     title="AI Chatbot trained on J. Haynes mediation material, v0.1",
+                     description="test")
+iface.launch()
+