Update app.py

app.py

@@ -7,12 +7,23 @@
 import os
 import openai
 import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
 openai.organization = "org-orRhfBkKOfOuNACbjPyWKbUt"
 openai.api_key = "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"
 
-def chat(text):
+def predict(input, history=[]):
 
+    new_user_input_ids = tokenizer.encode(input + tokenizer.eos_token, return_tensors='pt')
+    
+    # tokenize the new input sentence
+    new_user_input_ids = tokenizer.encode(input + tokenizer.eos_token, return_tensors='pt')
+
+    # append the new user input tokens to the chat history
+    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
+
+    # generate a response 
     response = openai.Completion.create(
     model="davinci:ft-placeholder:ai-dhd-2022-12-07-10-09-37",
     prompt= input,
@@ -20,10 +31,15 @@ def chat(text):
     max_tokens=608,
     top_p=1,
     frequency_penalty=0,
-    presence_penalty=0)
-
-    xyz = response[Completion]
-    return xyz
-
-demo = gr.Interface(chat, "text", "text")
-demo.launch(share=True, auth=("username", "password")).launch(debug = True)
+    presence_penalty=0).tolist()
+
+    history = response[Completion]
+    
+    # convert the tokens to text, and then split the responses into lines
+    response = tokenizer.decode(history[0]).split("<|endoftext|>")
+    response = [(response[i], response[i+1]) for i in range(0, len(response)-1, 2)]  # convert to tuples of list
+    return response, history
+
+gr.Interface(fn=predict,
+             inputs=["text", "state"],
+             outputs=["chatbot", "state"]).launch()