.flake8
.gitignore
.pre-commit-config.yaml
.readthedocs.yml
LICENSE
MANIFEST.in
Makefile
README.md
mkdocs.yml
pyproject.toml
requirements-dev.txt
requirements.txt
tox.ini
.circleci/config.yml
.github/workflows/pytest.yml
.github/workflows/python-publish.yml
docs/Makefile
docs/make.bat
docs/requirements.txt
docs/source/conf.py
docs/source/index.rst
docs/source/api/conversation.rst
docs/source/api/index.rst
docs/source/api/ir.rst
docs/source/api/text.rst
docs/source/datasets/conversation.rst
docs/source/datasets/embeddings.rst
docs/source/datasets/index.rst
docs/source/datasets/ir.rst
docs/source/datasets/irds.rst
docs/source/datasets/recommendation.rst
docs/source/datasets/text.rst
src/datamaestro_text/__init__.py
src/datamaestro_text/version.py
src/datamaestro_text.egg-info/PKG-INFO
src/datamaestro_text.egg-info/SOURCES.txt
src/datamaestro_text.egg-info/dependency_links.txt
src/datamaestro_text.egg-info/entry_points.txt
src/datamaestro_text.egg-info/requires.txt
src/datamaestro_text.egg-info/top_level.txt
src/datamaestro_text/config/__init__.py
src/datamaestro_text/config/ai/quac.yaml
src/datamaestro_text/config/com/oscar-corpus.py
src/datamaestro_text/config/com/sentiment140.py
src/datamaestro_text/config/com/fastml/goodbooks-10k.yaml
src/datamaestro_text/config/com/github/aagohary/canard.py
src/datamaestro_text/config/com/github/prdwb/orconvqa.py
src/datamaestro_text/config/com/github/soskek/bookcorpus.yaml
src/datamaestro_text/config/com/microsoft/wikiqa.yaml
src/datamaestro_text/config/com/microsoft/msmarco/passage.py
src/datamaestro_text/config/com/smashwords/bookcorpus.py
src/datamaestro_text/config/edu/cornell/nlvr.yaml
src/datamaestro_text/config/edu/stanford/__init__.py
src/datamaestro_text/config/edu/stanford/aclimdb.py
src/datamaestro_text/config/edu/stanford/glove.py
src/datamaestro_text/config/edu/stanford/im2p.yaml
src/datamaestro_text/config/edu/upenn/__init__.py
src/datamaestro_text/config/edu/upenn/ldc/__init__.py
src/datamaestro_text/config/edu/upenn/ldc/aquaint.py
src/datamaestro_text/config/gov/__init__.py
src/datamaestro_text/config/gov/nist/__init__.py
src/datamaestro_text/config/gov/nist/ir/covid.py
src/datamaestro_text/config/gov/nist/trec/__init__.py
src/datamaestro_text/config/gov/nist/trec/adhoc.py
src/datamaestro_text/config/gov/nist/trec/clueweb.yaml
src/datamaestro_text/config/gov/nist/trec/deeplearning.yaml
src/datamaestro_text/config/gov/nist/trec/index.yaml
src/datamaestro_text/config/gov/nist/trec/tipster.py
src/datamaestro_text/config/gov/nist/trec/web.yaml
src/datamaestro_text/config/io/github/rajpurkar/squad.yaml
src/datamaestro_text/config/io/github/thunlp/fewrel.py
src/datamaestro_text/config/io/metamind/research/__init__.py
src/datamaestro_text/config/io/metamind/research/wikitext.py
src/datamaestro_text/config/net/mattmahoney/enwiki.yaml
src/datamaestro_text/config/org/acm/recsys/cb2014.yaml
src/datamaestro_text/config/org/cocodataset/index.yaml
src/datamaestro_text/config/org/grouplens/movielens.py
src/datamaestro_text/config/org/universaldependencies/french.py
src/datamaestro_text/config/uk/ac/ucl/cs/qangaroo.yaml
src/datamaestro_text/data/embeddings.py
src/datamaestro_text/data/recommendation.py
src/datamaestro_text/data/tagging.py
src/datamaestro_text/data/text.py
src/datamaestro_text/data/conversation/__init__.py
src/datamaestro_text/data/conversation/base.py
src/datamaestro_text/data/conversation/canard.py
src/datamaestro_text/data/conversation/orconvqa.py
src/datamaestro_text/data/ir/__init__.py
src/datamaestro_text/data/ir/base.py
src/datamaestro_text/data/ir/cord19.py
src/datamaestro_text/data/ir/csv.py
src/datamaestro_text/data/ir/data.py
src/datamaestro_text/data/ir/formats.py
src/datamaestro_text/data/ir/huggingface.py
src/datamaestro_text/data/ir/stores.py
src/datamaestro_text/data/ir/trec.py
src/datamaestro_text/data/ir/utils.py
src/datamaestro_text/datasets/irds/__init__.py
src/datamaestro_text/datasets/irds/data.py
src/datamaestro_text/datasets/irds/datasets.py
src/datamaestro_text/datasets/irds/helpers.py
src/datamaestro_text/datasets/irds/utils.py
src/datamaestro_text/download/tmdb.py
src/datamaestro_text/interfaces/plaintext.py
src/datamaestro_text/interfaces/trec.py
src/datamaestro_text/test/__init__.py
src/datamaestro_text/test/test_datasets.py
src/datamaestro_text/transforms/__init__.py
src/datamaestro_text/transforms/ir/__init__.py
src/datamaestro_text/utils/__init__.py
src/datamaestro_text/utils/files.py
src/datamaestro_text/utils/iter.py
src/datamaestro_text/utils/randomstream.py
src/datamaestro_text/utils/shuffle.py