.dockerignore
.dvcignore
.env.example
.gitignore
.mypy.ini
.readthedocs.yml
AUTHORS.md
CONTRIBUTING.md
COPYING
COPYING.LESSER
README.md
docker-compose.yml
pyproject.toml
requirements-data_and_models.txt
requirements-dev.txt
requirements.txt
setup.py
tox.ini
.dvc/.gitignore
.dvc/config
.dvc/plots/confusion.json
.dvc/plots/default.json
.dvc/plots/scatter.json
.dvc/plots/smooth.json
.github/PULL_REQUEST_TEMPLATE.md
.github/ISSUE_TEMPLATE/bug-report.md
.github/ISSUE_TEMPLATE/documentation.md
.github/ISSUE_TEMPLATE/feature-request.md
.github/ISSUE_TEMPLATE/other-questions-help.md
.github/workflows/run-tests.yml
benchmarks/conftest.py
benchmarks/test_benchmark_insert.py
benchmarks/test_benchmark_servers.py
data_and_models/annotations/README.md
data_and_models/annotations/ner/.gitignore
data_and_models/annotations/ner/README.md
data_and_models/annotations/ner/analyze.py
data_and_models/annotations/ner/annotations10_EmmanuelleLogette_2020-08-28_raw1_raw5_10EntityTypes.jsonl.dvc
data_and_models/annotations/ner/annotations11_CharlotteLorin_2020-08-28_raw1_10EntityTypes.jsonl.dvc
data_and_models/annotations/ner/annotations12_EmmanuelleLogette_2020-08-28_raw7_10EntityTypes.jsonl.dvc
data_and_models/annotations/ner/annotations13_CharlotteLorin_2020-09-02_raw7_10EntityTypes.jsonl.dvc
data_and_models/annotations/ner/annotations14_EmmanuelleLogette_2020-09-02_raw8_CellCompartmentDrugOrgan.jsonl.dvc
data_and_models/annotations/ner/annotations15_EmmanuelleLogette_2020-09-22_raw9_Pathway.jsonl.dvc
data_and_models/annotations/ner/annotations1_EmmanuelleLogette_2020-06-19_raw1_8FirstLabels.jsonl.dvc
data_and_models/annotations/ner/annotations2_CharlotteLorin_2020-06-19_8FirstLabels.jsonl.dvc
data_and_models/annotations/ner/annotations3_EmmanuelleLogette_2020-07-06_raw1_8FirstLabels.jsonl.dvc
data_and_models/annotations/ner/annotations4_CharlotteLorin_2020-07-02_raw1_8FirstLabels.jsonl.dvc
data_and_models/annotations/ner/annotations5_EmmanuelleLogette_2020-06-30_raw2_Disease.jsonl.dvc
data_and_models/annotations/ner/annotations6_EmmanuelleLogette_2020-07-07_raw4_TaxonChebi.jsonl.dvc
data_and_models/annotations/ner/annotations7_EmmanuelleLogette_2020-07-06_raw1_9EntityTypes.jsonl.dvc
data_and_models/annotations/ner/annotations8_EmmanuelleLogette_2020-07-08_raw5_9EntityTypes.jsonl.dvc
data_and_models/annotations/ner/annotations9_EmmanuelleLogette_2020-07-08_raw6_CelltypeProtein.jsonl.dvc
data_and_models/annotations/ner/rule_based_patterns.jsonl.dvc
data_and_models/annotations/ner/patterns/.gitignore
data_and_models/annotations/ner/patterns/README.md
data_and_models/annotations/ner/patterns/pathway_patterns.jsonl.dvc
data_and_models/annotations/ner/patterns/patterns.jsonl.dvc
data_and_models/annotations/sentence_embedding/.gitignore
data_and_models/annotations/sentence_embedding/README.md
data_and_models/annotations/sentence_embedding/cord19_v47_sentences_pre.txt.dvc
data_and_models/annotations/sentence_embedding/sentence_similarity_cord19.csv.dvc
data_and_models/metrics/ner/cell_compartment.json
data_and_models/metrics/ner/cell_type.json
data_and_models/metrics/ner/chemical.json
data_and_models/metrics/ner/disease.json
data_and_models/metrics/ner/drug.json
data_and_models/metrics/ner/organ.json
data_and_models/metrics/ner/organism.json
data_and_models/metrics/ner/pathway.json
data_and_models/metrics/ner/protein.json
data_and_models/metrics/ner/interrater/cell_compartment.json
data_and_models/metrics/ner/interrater/cell_type.json
data_and_models/metrics/ner/interrater/chemical.json
data_and_models/metrics/ner/interrater/condition.json
data_and_models/metrics/ner/interrater/disease.json
data_and_models/metrics/ner/interrater/drug.json
data_and_models/metrics/ner/interrater/organ.json
data_and_models/metrics/ner/interrater/organism.json
data_and_models/metrics/ner/interrater/pathway.json
data_and_models/metrics/ner/interrater/protein.json
data_and_models/metrics/sentence_embedding/.gitignore
data_and_models/metrics/sentence_embedding/biobert_nli_sts.json
data_and_models/metrics/sentence_embedding/biobert_nli_sts_cord19_v1.json
data_and_models/metrics/sentence_embedding/count.json
data_and_models/metrics/sentence_embedding/sbert.json
data_and_models/metrics/sentence_embedding/sbiobert.json
data_and_models/metrics/sentence_embedding/tf_idf.json
data_and_models/models/language_modeling/.gitignore
data_and_models/models/language_modeling/biobert_cord19_v1.dvc
data_and_models/models/ner/.gitignore
data_and_models/models/ner_er/.gitignore
data_and_models/models/sentence_embedding/.gitignore
data_and_models/models/sentence_embedding/biobert_nli_sts_cord19_v1.dvc
data_and_models/pipelines/README.md
data_and_models/pipelines/ner/Dockerfile
data_and_models/pipelines/ner/add_er.py
data_and_models/pipelines/ner/clean.py
data_and_models/pipelines/ner/config.cfg
data_and_models/pipelines/ner/dvc.lock
data_and_models/pipelines/ner/dvc.yaml
data_and_models/pipelines/ner/eval.py
data_and_models/pipelines/ner/interrater.py
data_and_models/pipelines/ner/params.yaml
data_and_models/pipelines/ner/preprocess.py
data_and_models/pipelines/ner/transformers_vs_spacy/requirements.txt
data_and_models/pipelines/ner/transformers_vs_spacy/spacy/.gitignore
data_and_models/pipelines/ner/transformers_vs_spacy/spacy/compare_tokens.py
data_and_models/pipelines/ner/transformers_vs_spacy/spacy/eval.py
data_and_models/pipelines/ner/transformers_vs_spacy/spacy/eval.sh
data_and_models/pipelines/ner/transformers_vs_spacy/transformers/.gitignore
data_and_models/pipelines/ner/transformers_vs_spacy/transformers/0_prepare_data.sh
data_and_models/pipelines/ner/transformers_vs_spacy/transformers/1_run_transformers_ner.py
data_and_models/pipelines/ner/transformers_vs_spacy/transformers/1_run_transformers_ner.sh
data_and_models/pipelines/ner/transformers_vs_spacy/transformers/2_eval_pred.py
data_and_models/pipelines/ner/transformers_vs_spacy/transformers/2_eval_pred.sh
data_and_models/pipelines/ner/transformers_vs_spacy/transformers/3_compare_tokens.py
data_and_models/pipelines/ner/transformers_vs_spacy/transformers/create_pickle.py
data_and_models/pipelines/ner/transformers_vs_spacy/transformers/francesco_script.py
data_and_models/pipelines/ner/transformers_vs_spacy/transformers/our_bert_classifier.py
data_and_models/pipelines/relation_extraction/README.md
data_and_models/pipelines/relation_extraction/convert_chemprot_fmt.py
data_and_models/pipelines/sentence_embedding/Dockerfile
data_and_models/pipelines/sentence_embedding/dvc.lock
data_and_models/pipelines/sentence_embedding/dvc.yaml
data_and_models/pipelines/sentence_embedding/eval.py
data_and_models/pipelines/sentence_embedding/params.yaml
data_and_models/pipelines/sentence_embedding/train.py
data_and_models/pipelines/sentence_embedding/scripts/.gitignore
data_and_models/pipelines/sentence_embedding/scripts/README.md
data_and_models/pipelines/sentence_embedding/scripts/biosses_sentences.txt.dvc
data_and_models/pipelines/sentence_embedding/scripts/build.sh
data_and_models/pipelines/sentence_embedding/scripts/fine_tune.py
data_and_models/pipelines/sentence_embedding/scripts/sentences-filtered_11-527-877.txt.dvc
data_and_models/pipelines/sentence_embedding/scripts/train.py
data_and_models/raw_sentences/.gitignore
data_and_models/raw_sentences/README.md
data_and_models/raw_sentences/raw1_2020-06-10_cord19_TestSet.jsonl.dvc
data_and_models/raw_sentences/raw2_2020-06-29_cord19_Disease.jsonl.dvc
data_and_models/raw_sentences/raw3_2020-06-30_cord19_Disease.jsonl.dvc
data_and_models/raw_sentences/raw4_2020-07-02_cord19_ChemicalOrganism.jsonl.dvc
data_and_models/raw_sentences/raw5_2020-07-08_cord19_Drug_TestSet.jsonl.dvc
data_and_models/raw_sentences/raw6_2020-07-08_cord19_CelltypeProtein.jsonl.dvc
data_and_models/raw_sentences/raw7_2020-09-01_cord19v35_CellCompartment.jsonl.dvc
data_and_models/raw_sentences/raw8_2020-09-02_cord19v35_CellCompartmentDrugOrgan.jsonl.dvc
data_and_models/raw_sentences/raw9_2020-09-02_cord19v35_Pathway.jsonl.dvc
docker/base.Dockerfile
docker/corenlp.Dockerfile
docker/embedding.Dockerfile
docker/grobid_quantities.Dockerfile
docker/mining.Dockerfile
docker/mining.sh
docker/mining_cache.Dockerfile
docker/mining_cache.sh
docker/mysql.Dockerfile
docker/search.Dockerfile
docker/utils.sh
docs/Makefile
docs/conf.py
docs/index.rst
docs/_static/.keep
docs/source/_substitutions.rst
docs/source/entrypoint.rst
docs/source/example.rst
docs/source/faq.rst
docs/source/instructions.rst
docs/source/server.rst
docs/source/whatsnew.rst
docs/source/api/bluesearch.database.cord_19.rst
docs/source/api/bluesearch.database.mining_cache.rst
docs/source/api/bluesearch.database.rst
docs/source/api/bluesearch.embedding_models.rst
docs/source/api/bluesearch.mining.attribute.rst
docs/source/api/bluesearch.mining.entity.rst
docs/source/api/bluesearch.mining.eval.rst
docs/source/api/bluesearch.mining.pipeline.rst
docs/source/api/bluesearch.mining.relation.rst
docs/source/api/bluesearch.mining.rst
docs/source/api/bluesearch.rst
docs/source/api/bluesearch.search.rst
docs/source/api/bluesearch.server.embedding_server.rst
docs/source/api/bluesearch.server.invalid_usage_exception.rst
docs/source/api/bluesearch.server.mining_server.rst
docs/source/api/bluesearch.server.rst
docs/source/api/bluesearch.server.search_server.rst
docs/source/api/bluesearch.sql.rst
docs/source/api/bluesearch.utils.rst
docs/source/api/bluesearch.version.rst
docs/source/api/bluesearch.widgets.article_saver.rst
docs/source/api/bluesearch.widgets.mining_schema.rst
docs/source/api/bluesearch.widgets.mining_widget.rst
docs/source/api/bluesearch.widgets.rst
docs/source/api/bluesearch.widgets.search_widget.rst
docs/source/logo/BlueBrainSearch_banner.jpg
notebooks/STS_evaluation.ipynb
notebooks/demo_attribute_extraction.ipynb
screenshots/mining_widget_articles.png
screenshots/mining_widget_text.png
screenshots/search_widget.png
src/bluesearch/__init__.py
src/bluesearch/embedding_models.py
src/bluesearch/py.typed
src/bluesearch/search.py
src/bluesearch/sql.py
src/bluesearch/utils.py
src/bluesearch/version.py
src/bluesearch.egg-info/PKG-INFO
src/bluesearch.egg-info/SOURCES.txt
src/bluesearch.egg-info/dependency_links.txt
src/bluesearch.egg-info/entry_points.txt
src/bluesearch.egg-info/not-zip-safe
src/bluesearch.egg-info/requires.txt
src/bluesearch.egg-info/top_level.txt
src/bluesearch/_css/__init__.py
src/bluesearch/_css/style.py
src/bluesearch/_css/stylesheet.css
src/bluesearch/database/__init__.py
src/bluesearch/database/article.py
src/bluesearch/database/cord_19.py
src/bluesearch/database/mining_cache.py
src/bluesearch/entrypoint/__init__.py
src/bluesearch/entrypoint/_helper.py
src/bluesearch/entrypoint/compute_embeddings.py
src/bluesearch/entrypoint/create_database.py
src/bluesearch/entrypoint/create_mining_cache.py
src/bluesearch/entrypoint/embedding_server.py
src/bluesearch/entrypoint/mining_server.py
src/bluesearch/entrypoint/search_server.py
src/bluesearch/mining/__init__.py
src/bluesearch/mining/attribute.py
src/bluesearch/mining/entity.py
src/bluesearch/mining/eval.py
src/bluesearch/mining/pipeline.py
src/bluesearch/mining/relation.py
src/bluesearch/server/__init__.py
src/bluesearch/server/embedding_server.py
src/bluesearch/server/invalid_usage_exception.py
src/bluesearch/server/mining_server.py
src/bluesearch/server/search_server.py
src/bluesearch/widgets/__init__.py
src/bluesearch/widgets/article_saver.py
src/bluesearch/widgets/mining_schema.py
src/bluesearch/widgets/mining_widget.py
src/bluesearch/widgets/search_widget.py
tests/conftest.py
tests/test_embedding_models.py
tests/test_fixtures.py
tests/test_search.py
tests/test_sql.py
tests/test_utils.py
tests/data/CORD19_samples/metadata.csv
tests/data/CORD19_samples/biorxiv_medrxiv/biorxiv_medrxiv/pdf_json/9ae476404f7ef1ec1ede965f0b898f31a5bf5a81.json
tests/data/CORD19_samples/biorxiv_medrxiv/biorxiv_medrxiv/pdf_json/b52e0f732cefa36aae4d45ebc13208fba190b5af.json
tests/data/CORD19_samples/comm_use_subset/comm_use_subset/pdf_json/820acf55c4e52411482f6eb44360ffa35288b89a.json
tests/data/CORD19_samples/comm_use_subset/comm_use_subset/pmc_json/PMC5878846.xml.json
tests/data/CORD19_samples/custom_license/custom_license/pdf_json/bd21184623ceed45f1cede4066b540ff330ccb63.json
tests/data/CORD19_samples/custom_license/custom_license/pdf_json/be602928156cf0ace9899c1c8569eb4f4ea4597b.json
tests/data/CORD19_samples/custom_license/custom_license/pmc_json/PMC3396214.xml.json
tests/data/CORD19_samples/custom_license/custom_license/pmc_json/PMC6863268.xml.json
tests/data/CORD19_samples/noncomm_use_subset/noncomm_use_subset/pdf_json/67a52569919632f4bf58782538ff24838ac7f26c.json
tests/data/CORD19_samples/noncomm_use_subset/noncomm_use_subset/pmc_json/PMC3863901.xml.json
tests/data/cord19_v35/metadata.csv
tests/data/cord19_v35/document_parses/pdf_json/16e82ce0e0c8a1b36497afc0d4392b4fe21eb174.json
tests/data/cord19_v35/document_parses/pdf_json/5f267fa1ef3a65e239aa974329e935a4d93dafd2.json
tests/data/cord19_v35/document_parses/pmc_json/PMC7140272.xml.json
tests/data/cord19_v35/document_parses/pmc_json/PMC7186928.xml.json
tests/data/cord19_v35/document_parses/pmc_json/PMC7223769.xml.json
tests/data/mining/eval/iob_punctuation_after.csv
tests/data/mining/eval/iob_punctuation_before.csv
tests/data/mining/eval/ner_iob_sample.csv
tests/data/mining/request/request.csv
tests/test_database/test_article.py
tests/test_database/test_cord_19.py
tests/test_database/test_mining_cache.py
tests/test_entrypoint/__init__.py
tests/test_entrypoint/test__helper.py
tests/test_entrypoint/test_compute_embeddings.py
tests/test_entrypoint/test_create_database.py
tests/test_entrypoint/test_create_mining_cache.py
tests/test_entrypoint/test_embedding_server.py
tests/test_entrypoint/test_entrypoint_installation.py
tests/test_entrypoint/test_mining_server.py
tests/test_entrypoint/test_search_sever.py
tests/test_mining/test_attribute.py
tests/test_mining/test_entity.py
tests/test_mining/test_eval.py
tests/test_mining/test_pipeline.py
tests/test_mining/test_relation.py
tests/test_server/__init__.py
tests/test_server/test_embedding_server.py
tests/test_server/test_mining_server.py
tests/test_server/test_search_server.py
tests/test_widgets/test_article_saver.py
tests/test_widgets/test_mining_schema.py
tests/test_widgets/test_mining_widget.py
tests/test_widgets/test_search_widget.py