from llmcam.ytlive import capture_youtube_live_frame
from llmcam.gpt4v import ask_gpt4v
from llmcam.chat_ui import llmcam_chatbot
llmcam
llm camera project
This file will become your README and also the index of your documentation.
Developer Guide
If you are new to using nbdev
here are some useful pointers to get you started.
Install llmcam in Development mode
# make sure llmcam package is installed in development mode
$ pip install -e .
# make changes under nbs/ directory
# ...
# compile to have changes apply to llmcam
$ nbdev_prepare
Usage
Installation
Install latest from the GitHub repository:
$ pip install git+https://github.com/ninjalabo/llmcam.git
or from conda
$ conda install -c ninjalabo llmcam
or from pypi
$ pip install llmcam
Documentation
Documentation can be found hosted on this GitHub repository’s pages. Additionally you can find package manager specific guidelines on conda and pypi respectively.
How to use
In development mode, navigate to the local repository and install the editable version:
$ cd /path/to/llmcam/repository
$ pip install -e . ['dev']
Start by importing our modules:
= capture_youtube_live_frame()
fn fn
[youtube] Extracting URL: https://www.youtube.com/watch?v=LMZQ7eFhm58
[youtube] LMZQ7eFhm58: Downloading webpage
[youtube] LMZQ7eFhm58: Downloading ios player API JSON
[youtube] LMZQ7eFhm58: Downloading web creator player API JSON
[youtube] LMZQ7eFhm58: Downloading m3u8 information
30.10.2024 21:55:57 Tuomiokirkko
PosixPath('../data/cap_2024.10.30_21:55:57_Tuomiokirkko.jpg')
ask_gpt4v(fn)
{'timestamp': '2024-10-30T21:55:57',
'location': 'Tuomiokirkko',
'dimensions': {'width': 1280, 'height': 720},
'buildings': {'number_of_buildings': 15,
'building_height_range': '2-5 stories'},
'vehicles': {'number_of_vehicles': 0},
'waterbodies': {'visible': False},
'street_lights': {'number_of_street_lights': 25},
'people': {'approximate_number': 0},
'lighting': {'time_of_day': 'night', 'artificial_lighting': 'prominent'},
'visibility': {'clear': True},
'sky': {'visible': True, 'light_conditions': 'night'}}
# Start the application on port 5001
llmcam_chatbot()