Add CLI interface about screenshot-to-code

[Test67766]

okay i will try

[abi]

There isn't but if someone wants to submit a PR, happy to include it.

[abi]

I'd appreciate it if it didn't refactor the code too much (harder to review PR). There is a eval script that does run the generate code functionality in bulk from CLI: https://github.com/abi/screenshot-to-code/blob/main/Evaluation.md

[Test67766]

I have add the STACK var but (i have defined at start an OpenAPi on .env fie):

python3 run_evals.py
Traceback (most recent call last):
File "/home/glande/Desktop/screenshot-to-code/backend/run_evals.py", line 43, in
asyncio.run(main())
File "/usr/lib/python3.11/asyncio/runners.py", line 190, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/asyncio/base_events.py", line 654, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/home//Desktop/screenshot-to-code/backend/run_evals.py", line 31, in main
results = await asyncio.gather(*tasks)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home//Desktop/screenshot-to-code/backend/evals/core.py", line 21, in generate_code_core
if not anthropic_api_key:
^^^^^^^^^^^^^^^^^
NameError: name 'anthropic_api_key' is not defined

[abi]

You probably just need to set that env var