aljaz/Auto-GPT
1
0
Fork 0
mirror of https://github.com/aljazceru/Auto-GPT.git synced 2025-12-17 22:14:28 +01:00
Code Issues Packages Projects Releases Wiki Activity

Implements handling of OpenAI rate limit error.

Browse Source
This commit is contained in:
Torantulino
2023-04-01 01:30:13 +01:00
parent 4100961745
commit ffeb1aca73
1 changed files with 38 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

70
scripts/chat.py
View File

@@ -1,3 +1,4 @@
import time
import openai
import keys
@@ -18,42 +19,47 @@ def create_chat_message(role, content):
return {"role": role, "content": content}
def chat_with_ai(prompt, user_input, full_message_history, permanent_memory, token_limit, debug = False):
"""
Interact with the OpenAI API, sending the prompt, user input, message history, and permanent memory.
while True:
try:
"""
Interact with the OpenAI API, sending the prompt, user input, message history, and permanent memory.
Args:
prompt (str): The prompt explaining the rules to the AI.
user_input (str): The input from the user.
full_message_history (list): The list of all messages sent between the user and the AI.
permanent_memory (list): The list of items in the AI's permanent memory.
token_limit (int): The maximum number of tokens allowed in the API call.
Args:
prompt (str): The prompt explaining the rules to the AI.
user_input (str): The input from the user.
full_message_history (list): The list of all messages sent between the user and the AI.
permanent_memory (list): The list of items in the AI's permanent memory.
token_limit (int): The maximum number of tokens allowed in the API call.
Returns:
str: The AI's response.
"""
current_context = [create_chat_message("system", prompt), create_chat_message("system", f"Permanent memory: {permanent_memory}")]
current_context.extend(full_message_history[-(token_limit - len(prompt) - len(permanent_memory) - 10):])
current_context.extend([create_chat_message("user", user_input)])
Returns:
str: The AI's response.
"""
current_context = [create_chat_message("system", prompt), create_chat_message("system", f"Permanent memory: {permanent_memory}")]
current_context.extend(full_message_history[-(token_limit - len(prompt) - len(permanent_memory) - 10):])
current_context.extend([create_chat_message("user", user_input)])
# Debug print the current context
if debug:
print("------------ CONTEXT SENT TO AI ---------------")
for message in current_context:
# Skip printing the prompt
if message["role"] == "system" and message["content"] == prompt:
continue
print(f"{message['role'].capitalize()}: {message['content']}")
print("----------- END OF CONTEXT ----------------")
# Debug print the current context
if debug:
print("------------ CONTEXT SENT TO AI ---------------")
for message in current_context:
# Skip printing the prompt
if message["role"] == "system" and message["content"] == prompt:
continue
print(f"{message['role'].capitalize()}: {message['content']}")
print("----------- END OF CONTEXT ----------------")
response = openai.ChatCompletion.create(
model="gpt-4",
messages=current_context,
)
response = openai.ChatCompletion.create(
model="gpt-4",
messages=current_context,
)
assistant_reply = response.choices[0].message["content"]
assistant_reply = response.choices[0].message["content"]
# Update full message history
full_message_history.append(create_chat_message("user", user_input))
full_message_history.append(create_chat_message("assistant", assistant_reply))
# Update full message history
full_message_history.append(create_chat_message("user", user_input))
full_message_history.append(create_chat_message("assistant", assistant_reply))
return assistant_reply
return assistant_reply
except openai.RateLimitError:
print("Error: ", "API Rate Limit Reached. Waiting 60 seconds...")
time.sleep(60)