rokstrnisa / robogpt Goto Github PK

A simple and extensible program that helps you run GPT-4 model autonomously.

License: MIT License

Python 100.00%

robogpt's Introduction

RoboGPT: A simple autonomous GPT-4 runner

RoboGPT is a simple and extensible program that helps you run GPT-4 model autonomously. It is designed to be easy to understand, so that anyone can use it and extend it.

The program was inspired by some of my earlier work and Auto-GPT.

License: This project is released under the MIT License.

Simple Demo

Features

🤖 Simple and easy to understand codebase.
🔧 Extensible design for easy contributions.
🔄 Continuous mode for ongoing interaction.
🔈 Speech support (optional) for a more engaging user experience.

Planned:

💫 Generic parsing and encapsulated action definitions.
⚙️ Plug-in system for easy extensibility.

Requirements

Python 3.10 or later.
OpenAI API key with access to gpt-4 model. At the time of writing, you need to join a waitlist, and OpenAI will give you access when capacity is available.
ElevenLabs key (optional for speech).

Setup

Install pipenv.
Clone this repo and change directory to it.
Run pipenv shell to enter the Python virtual environment and pipenv install to install the dependencies.
Rename .env.template to .env and fill in your OPENAI_API_KEY, and optionally ELEVEN_LABS_API_KEY (for speech).

Usage

Run python robogpt/main.py to start the program.

Continuous Mode

The program does not run in continuous mode by default. To run it in continuous mode, simply use the command-line flag --continuous.

Speech

On macOS, run pip install PyObjC to install the required dependency for speech.

To enable speech, use the command-line flag --speech.

Sponsor

If you like this project, consider supporting its further development - become a supporter!

Current Sponsors:

🥉 Martin Köppelmann

Contributing

Contributions to RoboGPT are very welcome! If you'd like to contribute, please follow these guidelines:

Submit issues for bugs or feature requests.
Create pull requests for proposed changes or new features. Make sure your changes are well-documented and follow the project's code style.
Join the community (see below) and participate in discussions to help shape the project's future.

Community

Join RoboGPT Discord server to get help, discuss ideas and collaborate.

To stay up-to-date, follow @RokStrnisa.

robogpt's People

Contributors

Stargazers

Watchers

robogpt's Issues

Incorrect API key provided: your-ope*******-key.

I'm new to Python and pipenv but no matter what I do the script can't seem to see the .env file with my api keys. Renamed the .env.template file to .env, eventually tried copying it to the environment folder that was created, no luck.

Thanks!

James

No API Key Provided

I am getting this error below though i have set my API key within the .env file?

Traceback (most recent call last):
File "/Users/jasonliao/RoboGPT/robogpt/main.py", line 123, in
main()
File "/Users/jasonliao/RoboGPT/robogpt/main.py", line 95, in main
assistant_response = gpt.chat(user_directions, GENERAL_DIRECTIONS_PREFIX, new_plan, message_history)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/jasonliao/RoboGPT/robogpt/gpt.py", line 42, in chat
assistant_response = send_message(messages, available_response_tokens)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/jasonliao/RoboGPT/robogpt/gpt.py", line 63, in send_message
response = openai.ChatCompletion.create(model=MODEL, messages=messages, max_tokens=max_response_tokens)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/api_resources/chat_completion.py", line 25, in create
return super().create(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 149, in create
) = cls.__prepare_create_request(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/api_resources/abstract/engine_api_resource.py", line 106, in __prepare_create_request
requestor = api_requestor.APIRequestor(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/api_requestor.py", line 130, in init
self.api_key = key or util.default_api_key()
^^^^^^^^^^^^^^^^^^^^^^
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/openai/util.py", line 186, in default_api_key
raise openai.error.AuthenticationError(
openai.error.AuthenticationError: No API key provided. You can set your API key in code using 'openai.api_key = ', or you can set the environment variable OPENAI_API_KEY=). If your API key is stored in a file, you can point the openai module at it with 'openai.api_key_path = '. You can generate API keys in the OpenAI web interface. See https://onboard.openai.com for details, or email [email protected] if you have any questions.

Why not using langchain?

For me the actions are similar or the same than Tools on langchain. Should not be easier with langchain?. Im just curious. Thanks.

No googlesearch module

I've followed the instructions from the readme, run main.py and get the following error:

\Robo-GPT\robo-gpt\action_runner.py", line 9, in
from googlesearch import search
ModuleNotFoundError: No module named 'googlesearch'

What have I missed?