Update app.py

app.py

@@ -1,6 +1,6 @@
 from gpt_index import GPTSimpleVectorIndex
-from langchain import OpenAI
 import gradio as gr
+from gradio import Interface, Textbox
 import sys
 import os
 import datetime
@@ -11,27 +11,34 @@ import csv
 
 os.environ["OPENAI_API_KEY"] = os.environ['SECRET_CODE']
 
-# Need to write to persistent dataset because cannot store temp data on spaces
+# Best practice is to use a persistent dataset 
 DATASET_REPO_URL = "https://huggingface.co/datasets/peterpull/MediatorBot"
 DATA_FILENAME = "data.txt"
-DATA_FILE = os.path.join("data", DATA_FILENAME)
+INDEX_FILENAME = "index2.json"
 
-# I am guessing 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__)
 
+#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
@@ -42,21 +49,35 @@ 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")
-
-    return generate_text()
+            print(f"Wrote to datafile: {datetime.now()},{chatinput},{chatresponse}\n")
+        
+    #need to find a way to push back to dataset repo
             
-#gets the index file which is the context data
+    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 - 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'):
-    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."
+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="compact")
 
     store_message(input_text,response)
@@ -65,11 +86,14 @@ def chatbot(input_text, mentioned_person='Mediator John Haynes'):
     return response.response
 
 
+with open('about.txt', 'r') as file:
+    about = file.read()
 
-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()
-
+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()