alvarosevilla95/autolang

autolang's Issues

Bump to Python 3.9

Running python -m venv .venv on Python 3.8 gives the following stack trace:

Traceback (most recent call last):
  File "/usr/local/Cellar/[email protected]/3.8.16/Frameworks/Python.framework/Versions/3.8/lib/python3.8/runpy.py", line 194, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/usr/local/Cellar/[email protected]/3.8.16/Frameworks/Python.framework/Versions/3.8/lib/python3.8/runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "/Users/skurilyak/dev/autolang/autolang/__main__.py", line 11, in <module>
    from .auto import AutoAgent
  File "/Users/skurilyak/dev/autolang/autolang/auto.py", line 10, in <module>
    from .reviewer import ReviewingChain
  File "/Users/skurilyak/dev/autolang/autolang/reviewer.py", line 34, in <module>
    class ReviewingChain(LLMChain):
  File "/Users/skurilyak/dev/autolang/autolang/reviewer.py", line 40, in ReviewingChain
    def review_tasks(self, this_task_id: int, completed_tasks: List[str], pending_tasks: List[str], context: str) -> deque[Dict]:
TypeError: 'type' object is not subscriptable

I recommend updating README to reflect the requirement of using Python 3.9. For example:

python3.9 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

License

Hello, I would like to try experimenting with this repo. Could you please add a license?

Autolang as a langchain agent?

Hey,
First: I love autolang, it looks neat and feels like the right method to implement autogpt like services for proprietary tasks.
It just took a few minutes to use it with Llamacpp, and surprisingly, it works quite well - see https://github.com/mayflower/autolang.
However, before supporting multiple LLMs directly in autolang it feels better to use autolang within langchain itself, and your file structure seems a bit like you had the same idea.
Would that be something you are planning to do anyway?

abstracting agents and tools into skills

make this work with langchain in a way that abstracts the tools and agent combination into a "Skill" - (eg bookwriter, financial analyser). so if we have a skills framework - then devs can write skills which can then be composed to solve higher level goals and problem statements by using a combination of skills. note: the agent-toolkit in langchain can be extended or used for this abstraction.