Add forgetting long-term history

app.py

@@ -1,4 +1,5 @@
 import openai
+import tiktoken
 import json
 import os
 
@@ -9,10 +10,10 @@ def ask(question, history):
     try:
         response = openai.ChatCompletion.create(
             model="gpt-3.5-turbo",
-            messages=[
+            messages=forget_long_term([
                 {"role":"user" if i%2==0 else "assistant", "content":content}
                 for i,content in enumerate(history)
-            ]
+            ])
         )["choices"][0]["message"]["content"]
         while response.startswith("\n"):
             response = response[1:]
@@ -25,6 +26,30 @@ def ask(question, history):
     return history
 
 
+def forget_long_term(messages, max_num_tokens=4000):
+    def num_tokens_from_messages(messages, model="gpt-3.5-turbo"):
+        """Returns the number of tokens used by a list of messages."""
+        try:
+            encoding = tiktoken.encoding_for_model(model)
+        except KeyError:
+            encoding = tiktoken.get_encoding("cl100k_base")
+        if model == "gpt-3.5-turbo":  # note: future models may deviate from this
+            num_tokens = 0
+            for message in messages:
+                num_tokens += 4  # every message follows <im_start>{role/name}\n{content}<im_end>\n
+                for key, value in message.items():
+                    num_tokens += len(encoding.encode(value))
+                    if key == "name":  # if there's a name, the role is omitted
+                        num_tokens += -1  # role is always required and always 1 token
+            num_tokens += 2  # every reply is primed with <im_start>assistant
+            return num_tokens
+        else:
+            raise NotImplementedError(f"""num_tokens_from_messages() is not presently implemented for model {model}.
+    See https://github.com/openai/openai-python/blob/main/chatml.md for information on how messages are converted to tokens.""")
+    while num_tokens_from_messages(messages)>max_num_tokens:
+        messages = messages[1:]
+    return messages
+
 
 import gradio as gr
 

requirements.txt

@@ -1 +1,2 @@
-openai==0.27.0
+openai==0.27.0
+tiktoken==0.3.0