Increase token size - Githubissues

garyfeng / Auto-GPT

An experimental open-source attempt to make GPT-4 fully autonomous.

MIT License

0 stars 0 forks source link

Increase token size #7

Open garyfeng opened 1 year ago

garyfeng commented 1 year ago

Duplicates

[X] I have searched the existing issues

Summary 💡

As the user I want to increase the token limit per API call so that I can get longer response from GPT.

Examples 🌈

Making this 8k

Motivation 🔦

Current token is limited to cfg.fast_token_limit which is about 4k. This is hardwired in the current version, main.py

    # Send message to AI, get response
    with Spinner("Thinking... "):
        assistant_reply = chat.chat_with_ai(
            prompt,
            user_input,
            full_message_history,
            memory,
            cfg.fast_token_limit) # TODO: This hardcodes the model to use GPT3.5. Make this an argument