quora
: The Quora dataset is composed of question pairs, and the task is to determine if the questions are paraphrases of each other (have the same meaning).wiki
: From DeepLearning.ai Building Applications with Vector Databases Course.!wget -q -O lesson2-wiki.csv.zip "https://www.dropbox.com/scl/fi/yxzmsrv2sgl249zcspeqb/lesson2-wiki.csv.zip?rlkey=paehnoxjl3s5x53d1bedt4pmc&dl=0" !unzip lesson2-wiki.csv.zip
news
: From DeepLearning.ai Building Applications with Vector Databases Course.wget -q --show-progress -O all-the-news-3.zip "https://www.dropbox.com/scl/fi/wruzj2bwyg743d0jzd7ku/all-the-news-3.zip?rlkey=rgwtwpeznbdadpv3f01sznwxa&dl=1" unzip all-the-news-3.zip
ashraq/fashion-product-images-small
: Multimodal data of fashion productsfamily-photos
: From DeepLearning.ai Building Applications with Vector Databases Course.!wget -q --show-progress -O family_photos.zip "https://www.dropbox.com/scl/fi/yg0f2ynbzzd2q4nsweti5/family_photos.zip?rlkey=00oeuiii3jgapz2b1bfj0vzys&dl=0" !unzip -q family_photos.zip
cisco-logs
: From DeepLearning.ai Building Applications with Vector Databases Course.!wget -q --show-progress -O training.tar.zip "https://www.dropbox.com/scl/fi/rihfngx4ju5pzjzjj7u9z/lesson6.tar.zip?rlkey=rct9a9bo8euqgshrk8wiq2orh&dl=1" !tar -xzvf training.tar.zip !tar -xzvf lesson6.tar
DSPy
: For programming - not prompting - LLMsjinja2
: For creating prompt templatespython-dotenv
: For loading .env variablespoetry
: For Python package and dep managementuv
: Package installer written in Rustruff
: Fast Python linter and code formattersentence-transformers
: Pretrained models for text/image embedding models