gptutil's Introduction

GPT utility

Command utility for creating your own AI assistant

Installation

pip install gptutil

Usage

Ask ChatGPT questions in a pipeline:

export OPENAI_API_KEY="OpenAI API Key"

git clone git clone https://github.com/openai/evals/
cp evals/evals/registry/data/test_fuzzy_match/samples.jsonl .
cat samples.jsonl | gpt-ask 'Translate this.'
cat samples.jsonl | gpt-ask 'Translate this.' |jq |less
cat samples.jsonl | gpt-ask 'Translate this.' | gpt-ask 'Use jq to extract all "content" values with "role" equal to "user".'

Debug commands interactively:

gpt-interact -n simple_chat

gpt-interact -n simple_chat -t gptutil/example/assistant.yaml

You can also customize your own assistant by modifying this file.

Command	Description
@use AssistantName	Switches to a different assistant.
@history	Displays chat history.
@reset	Clears the input and chat history for the assistant.
@params	Show set assistant paramaters
! (e.g. !ls -l, !bash)	Executes a command in the middle of a question and displays the result.

Assistant	Description
simple_chat	Normal chat.
command_debug	Displays solutions by executing commands and displaying error messages.
pentest	Explains penetration testing tools and procedures step by step.

Demo

Asking ChatGPT questions in a pipeline

Debugging commands interactively

gptutil's People

Contributors

Stargazers

Watchers

gptutil's Issues

Fix to be able to split and process huge files by token size limit even when huge files are input

Currently, standard input exceeding the token size cannot be processed.

Traceback (most recent call last):
  File "/home/tatsui/.virtualenvs/poc/bin/gpt-ask", line 33, in <module>
    sys.exit(load_entry_point('gptutil', 'console_scripts', 'gpt-ask')())
  File "/home/tatsui/.virtualenvs/poc/lib/python3.10/site-packages/click/core.py", line 1130, in __call__
    return self.main(*args, **kwargs)
  File "/home/tatsui/.virtualenvs/poc/lib/python3.10/site-packages/click/core.py", line 1055, in main
    rv = self.invoke(ctx)
  File "/home/tatsui/.virtualenvs/poc/lib/python3.10/site-packages/click/core.py", line 1404, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/home/tatsui/.virtualenvs/poc/lib/python3.10/site-packages/click/core.py", line 760, in invoke
    return __callback(*args, **kwargs)
  File "/home/tatsui/gptutil/gptutil/ask.py", line 42, in main
    for resp in openai.ChatCompletion.create(
  File "/home/tatsui/.virtualenvs/poc/lib/python3.10/site-packages/openai/api_resources/chat_completion.py", line 25, in create
    return super().create(*args, **kwargs)
  File "/home/tatsui/.virtualenvs/poc/lib/python3.10/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 153, in create
    response, _, api_key = requestor.request(
  File "/home/tatsui/.virtualenvs/poc/lib/python3.10/site-packages/openai/api_requestor.py", line 226, in request
    resp, got_stream = self._interpret_response(result, stream)
  File "/home/tatsui/.virtualenvs/poc/lib/python3.10/site-packages/openai/api_requestor.py", line 619, in _interpret_response
    self._interpret_response_line(
  File "/home/tatsui/.virtualenvs/poc/lib/python3.10/site-packages/openai/api_requestor.py", line 682, in _interpret_response_line
    raise self.handle_error_response(
openai.error.InvalidRequestError: This model's maximum context length is 4097 tokens. However, your messages resulted in 18450 tokens. Please reduce the length of the messages.

Recommend Projects