├── .cursor └── rules │ └── python.mdc ├── .dockerignore ├── .envrc.example ├── .gcloudignore ├── .github └── workflows │ ├── lint.yaml │ ├── test-amazon-product-search.yaml │ └── test-indexing.yaml ├── .gitignore ├── Makefile ├── README.md ├── cloudbuild.yaml ├── gcloud └── .gitignore ├── notebooks └── .gitignore ├── poetry.lock ├── pyproject.toml ├── search_engines └── elasticsearch │ ├── Dockerfile │ └── compose.yaml └── src ├── amazon-product-search ├── README.md ├── data │ ├── .gitignore │ └── includes │ │ ├── synonyms_jp_fine_tuned_sbert.csv │ │ ├── synonyms_jp_sbert.csv │ │ ├── synonyms_us_all_minilm.csv │ │ └── synonyms_us_mpnet.csv ├── elasticsearch │ └── schemas │ │ ├── products_jp.json │ │ └── products_us.json ├── models │ └── .gitignore ├── poetry.lock ├── pyproject.toml ├── src │ └── amazon_product_search │ │ ├── __init__.py │ │ ├── cache.py │ │ ├── constants.py │ │ ├── es │ │ ├── es_client.py │ │ └── templates │ │ │ ├── lexical.j2 │ │ │ ├── match_all.j2 │ │ │ ├── rescore.j2 │ │ │ ├── semantic.j2 │ │ │ └── template_loader.py │ │ ├── metrics.py │ │ ├── modules │ │ ├── colbert.py │ │ └── splade.py │ │ ├── nlp │ │ ├── normalizer.py │ │ └── tokenizers │ │ │ ├── __init__.py │ │ │ ├── english_tokenizer.py │ │ │ ├── japanese_tokenizer.py │ │ │ └── tokenizer.py │ │ ├── parallel.py │ │ ├── reranking │ │ └── reranker.py │ │ ├── retrieval │ │ ├── core │ │ │ ├── __init__.py │ │ │ ├── protocols.py │ │ │ └── types.py │ │ ├── engines │ │ │ ├── __init__.py │ │ │ ├── base.py │ │ │ ├── lexical.py │ │ │ └── semantic.py │ │ ├── factory.py │ │ ├── fusion │ │ │ ├── __init__.py │ │ │ └── base.py │ │ ├── importance_estimator.py │ │ ├── keyword_generator.py │ │ ├── pipeline.py │ │ ├── processors │ │ │ ├── __init__.py │ │ │ ├── base.py │ │ │ ├── reranking.py │ │ │ └── semantic.py │ │ ├── query_vector_cache.py │ │ ├── rank_fusion.py │ │ ├── resources │ │ │ ├── __init__.py │ │ │ └── manager.py │ │ ├── response.py │ │ ├── retriever.py │ │ ├── score_normalizer.py │ │ └── weighting_strategy.py │ │ ├── synonyms │ │ ├── filters │ │ │ ├── similarity_filter.py │ │ │ └── utils.py │ │ ├── generator.py │ │ └── synonym_dict.py │ │ └── timestamp.py ├── tasks │ ├── __init__.py │ └── synonyms_tasks.py └── tests │ ├── __init__.py │ └── unit │ ├── es │ └── test_es_client.py │ ├── nlp │ ├── test_importance.py │ ├── test_japanese_tokenizer.py │ └── test_normalizer.py │ ├── reranking │ └── test_reranker.py │ ├── retrieval │ ├── test_core_types.py │ ├── test_engines.py │ ├── test_factory.py │ ├── test_pipeline.py │ ├── test_processors.py │ ├── test_rank_fusion.py │ ├── test_response.py │ └── test_score_normalizer.py │ ├── synonyms │ ├── filters │ │ ├── test_similarity_filter.py │ │ └── test_utils.py │ ├── test_generator.py │ └── test_synonym_dict.py │ ├── test_cache.py │ └── test_metrics.py ├── data-source ├── Makefile ├── README.md ├── data │ └── .gitignore ├── poetry.lock ├── pyproject.toml ├── src │ └── data_source │ │ ├── __init__.py │ │ └── loader.py └── tests │ └── __init__.py ├── demo ├── .streamlit │ └── config.toml ├── Makefile ├── README.md ├── poetry.lock ├── pyproject.toml └── src │ └── demo │ ├── apps │ ├── eda │ │ ├── pages │ │ │ └── 1_📊_Relevance_Judgements.py │ │ └── 📊_Product_Catalogue.py │ ├── es │ │ ├── pages │ │ │ ├── 1_🔍_Sparse_vs_Dense.py │ │ │ └── 2_🔍_Reranking.py │ │ ├── search_ui.py │ │ └── 🔍_Retrieval.py │ └── features │ │ ├── pages │ │ └── 1_🤖_Tokenization.py │ │ └── 🤖_AutoTokenizer.py │ ├── page_config.py │ └── utils.py ├── dense-retrieval ├── README.md ├── poetry.lock ├── pyproject.toml └── src │ └── dense_retrieval │ ├── __init__.py │ ├── encoders │ ├── __init__.py │ ├── bi_encoder.py │ ├── modules │ │ ├── losses.py │ │ └── pooler.py │ ├── sbert_encoder.py │ └── text_encoder.py │ ├── retrievers │ ├── __init__.py │ ├── ann_index.py │ ├── multi_vector_retriever.py │ ├── retriever.py │ └── single_vector_retriever.py │ └── training │ ├── data_module.py │ └── trainer.py ├── indexing ├── Dockerfile ├── Makefile ├── README.md ├── conf │ ├── config.yaml │ ├── dest │ │ ├── bq.yaml │ │ ├── es.yaml │ │ └── stdout.yaml │ └── runner │ │ ├── dataflow.yaml │ │ └── direct.yaml ├── poetry.lock ├── pyproject.toml ├── src │ └── indexing │ │ ├── __main__.py │ │ ├── cli.py │ │ ├── io │ │ └── elasticsearch_io.py │ │ ├── options.py │ │ ├── pipelines │ │ ├── base.py │ │ ├── doc_pipeline.py │ │ ├── feed_pipeline.py │ │ ├── pipelien_types.py │ │ └── query_pipeline.py │ │ └── transforms │ │ ├── add_image_url.py │ │ ├── analyze_doc.py │ │ ├── encode_product.py │ │ └── filters.py └── tests │ ├── __init__.py │ ├── conftest.py │ ├── integration │ ├── es_docker.py │ └── test_pipeline.py │ └── unit │ ├── io │ └── test_elasticsearch_io.py │ └── transforms │ ├── test_add_image_url.py │ ├── test_encode_product.py │ └── test_filters.py ├── model-serving ├── Dockerfile ├── Makefile ├── README.md ├── compose.yaml ├── conf │ ├── config.yaml │ └── export_params │ │ └── cl-nagoya │ │ └── ruri-small-v2.yaml ├── model_repository │ ├── embedder_onnx │ │ ├── 1 │ │ │ └── .gitkeep │ │ └── config.pbtxt │ ├── embedder_pt │ │ ├── 1 │ │ │ └── .gitkeep │ │ └── config.pbtxt │ ├── ensemble │ │ ├── 1 │ │ │ └── .gitkeep │ │ └── config.pbtxt │ └── tokenizer │ │ ├── 1 │ │ └── model.py │ │ └── config.pbtxt ├── models │ └── .gitignore ├── poetry.lock ├── pyproject.toml ├── requirements.txt ├── src │ └── model_serving │ │ ├── __init__.py │ │ ├── cli.py │ │ ├── export │ │ ├── exporters.py │ │ └── utils.py │ │ └── modules │ │ └── sentence_transformer_wrapper.py └── tests │ ├── __init__.py │ └── model_serving │ └── onnx │ └── test_utils.py └── training ├── Dockerfile ├── Makefile ├── README.md ├── conf ├── compile_parameters │ └── default.yaml ├── config.yaml └── runtime_parameters │ ├── dummy.yaml │ ├── fine-tune-cl.yaml │ └── fine-tune-mlm.yaml ├── poetry.lock ├── pyproject.toml ├── src ├── pipeline │ ├── __main__.py │ ├── cli.py │ ├── components │ │ ├── dummy.py │ │ └── fine_tuning.py │ └── pipelines.py └── training │ ├── __main__.py │ ├── callbacks │ └── metric_logger.py │ ├── data_modules │ └── product_mlm_data_module.py │ ├── datasets │ └── tokenized_sentences_dataset.py │ ├── modules │ └── mlm_fine_tuner.py │ └── runners │ ├── fine_tuning_cl.py │ └── fine_tuning_mlm.py └── templates └── .gitignore /.cursor/rules/python.mdc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/.cursor/rules/python.mdc -------------------------------------------------------------------------------- /.dockerignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/.dockerignore -------------------------------------------------------------------------------- /.envrc.example: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/.envrc.example -------------------------------------------------------------------------------- /.gcloudignore: -------------------------------------------------------------------------------- 1 | #!include:.dockerignore 2 | -------------------------------------------------------------------------------- /.github/workflows/lint.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/.github/workflows/lint.yaml -------------------------------------------------------------------------------- /.github/workflows/test-amazon-product-search.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/.github/workflows/test-amazon-product-search.yaml -------------------------------------------------------------------------------- /.github/workflows/test-indexing.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/.github/workflows/test-indexing.yaml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/.gitignore -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/Makefile -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/README.md -------------------------------------------------------------------------------- /cloudbuild.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/cloudbuild.yaml -------------------------------------------------------------------------------- /gcloud/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/gcloud/.gitignore -------------------------------------------------------------------------------- /notebooks/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/notebooks/.gitignore -------------------------------------------------------------------------------- /poetry.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/poetry.lock -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/pyproject.toml -------------------------------------------------------------------------------- /search_engines/elasticsearch/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/search_engines/elasticsearch/Dockerfile -------------------------------------------------------------------------------- /search_engines/elasticsearch/compose.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/search_engines/elasticsearch/compose.yaml -------------------------------------------------------------------------------- /src/amazon-product-search/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/README.md -------------------------------------------------------------------------------- /src/amazon-product-search/data/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/data/.gitignore -------------------------------------------------------------------------------- /src/amazon-product-search/data/includes/synonyms_jp_fine_tuned_sbert.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/data/includes/synonyms_jp_fine_tuned_sbert.csv -------------------------------------------------------------------------------- /src/amazon-product-search/data/includes/synonyms_jp_sbert.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/data/includes/synonyms_jp_sbert.csv -------------------------------------------------------------------------------- /src/amazon-product-search/data/includes/synonyms_us_all_minilm.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/data/includes/synonyms_us_all_minilm.csv -------------------------------------------------------------------------------- /src/amazon-product-search/data/includes/synonyms_us_mpnet.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/data/includes/synonyms_us_mpnet.csv -------------------------------------------------------------------------------- /src/amazon-product-search/elasticsearch/schemas/products_jp.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/elasticsearch/schemas/products_jp.json -------------------------------------------------------------------------------- /src/amazon-product-search/elasticsearch/schemas/products_us.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/elasticsearch/schemas/products_us.json -------------------------------------------------------------------------------- /src/amazon-product-search/models/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/models/.gitignore -------------------------------------------------------------------------------- /src/amazon-product-search/poetry.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/poetry.lock -------------------------------------------------------------------------------- /src/amazon-product-search/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/pyproject.toml -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/__init__.py: -------------------------------------------------------------------------------- 1 | __version__ = "0.1.0" 2 | -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/cache.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/cache.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/constants.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/es/es_client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/es/es_client.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/es/templates/lexical.j2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/es/templates/lexical.j2 -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/es/templates/match_all.j2: -------------------------------------------------------------------------------- 1 | { 2 | "match_all": {} 3 | } 4 | -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/es/templates/rescore.j2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/es/templates/rescore.j2 -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/es/templates/semantic.j2: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/es/templates/semantic.j2 -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/es/templates/template_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/es/templates/template_loader.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/metrics.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/modules/colbert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/modules/colbert.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/modules/splade.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/modules/splade.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/nlp/normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/nlp/normalizer.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/nlp/tokenizers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/nlp/tokenizers/__init__.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/nlp/tokenizers/english_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/nlp/tokenizers/english_tokenizer.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/nlp/tokenizers/japanese_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/nlp/tokenizers/japanese_tokenizer.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/nlp/tokenizers/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/nlp/tokenizers/tokenizer.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/parallel.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/reranking/reranker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/reranking/reranker.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/core/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/core/protocols.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/core/protocols.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/core/types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/core/types.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/engines/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/engines/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/engines/base.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/engines/lexical.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/engines/lexical.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/engines/semantic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/engines/semantic.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/factory.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/fusion/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/fusion/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/fusion/base.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/importance_estimator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/importance_estimator.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/keyword_generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/keyword_generator.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/pipeline.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/processors/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/processors/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/processors/base.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/processors/reranking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/processors/reranking.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/processors/semantic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/processors/semantic.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/query_vector_cache.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/query_vector_cache.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/rank_fusion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/rank_fusion.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/resources/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/resources/manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/resources/manager.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/response.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/response.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/retriever.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/retriever.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/score_normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/score_normalizer.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/retrieval/weighting_strategy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/retrieval/weighting_strategy.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/synonyms/filters/similarity_filter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/synonyms/filters/similarity_filter.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/synonyms/filters/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/synonyms/filters/utils.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/synonyms/generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/synonyms/generator.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/synonyms/synonym_dict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/synonyms/synonym_dict.py -------------------------------------------------------------------------------- /src/amazon-product-search/src/amazon_product_search/timestamp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/src/amazon_product_search/timestamp.py -------------------------------------------------------------------------------- /src/amazon-product-search/tasks/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tasks/__init__.py -------------------------------------------------------------------------------- /src/amazon-product-search/tasks/synonyms_tasks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tasks/synonyms_tasks.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/es/test_es_client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/es/test_es_client.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/nlp/test_importance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/nlp/test_importance.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/nlp/test_japanese_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/nlp/test_japanese_tokenizer.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/nlp/test_normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/nlp/test_normalizer.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/reranking/test_reranker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/reranking/test_reranker.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/retrieval/test_core_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/retrieval/test_core_types.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/retrieval/test_engines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/retrieval/test_engines.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/retrieval/test_factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/retrieval/test_factory.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/retrieval/test_pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/retrieval/test_pipeline.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/retrieval/test_processors.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/retrieval/test_processors.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/retrieval/test_rank_fusion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/retrieval/test_rank_fusion.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/retrieval/test_response.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/retrieval/test_response.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/retrieval/test_score_normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/retrieval/test_score_normalizer.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/synonyms/filters/test_similarity_filter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/synonyms/filters/test_similarity_filter.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/synonyms/filters/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/synonyms/filters/test_utils.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/synonyms/test_generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/synonyms/test_generator.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/synonyms/test_synonym_dict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/synonyms/test_synonym_dict.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/test_cache.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/test_cache.py -------------------------------------------------------------------------------- /src/amazon-product-search/tests/unit/test_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/amazon-product-search/tests/unit/test_metrics.py -------------------------------------------------------------------------------- /src/data-source/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/data-source/Makefile -------------------------------------------------------------------------------- /src/data-source/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/data-source/README.md -------------------------------------------------------------------------------- /src/data-source/data/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/data-source/data/.gitignore -------------------------------------------------------------------------------- /src/data-source/poetry.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/data-source/poetry.lock -------------------------------------------------------------------------------- /src/data-source/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/data-source/pyproject.toml -------------------------------------------------------------------------------- /src/data-source/src/data_source/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/data-source/src/data_source/__init__.py -------------------------------------------------------------------------------- /src/data-source/src/data_source/loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/data-source/src/data_source/loader.py -------------------------------------------------------------------------------- /src/data-source/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/demo/.streamlit/config.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/demo/.streamlit/config.toml -------------------------------------------------------------------------------- /src/demo/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/demo/Makefile -------------------------------------------------------------------------------- /src/demo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/demo/README.md -------------------------------------------------------------------------------- /src/demo/poetry.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/demo/poetry.lock -------------------------------------------------------------------------------- /src/demo/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/demo/pyproject.toml -------------------------------------------------------------------------------- /src/demo/src/demo/apps/eda/pages/1_📊_Relevance_Judgements.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/demo/src/demo/apps/eda/pages/1_📊_Relevance_Judgements.py -------------------------------------------------------------------------------- /src/demo/src/demo/apps/eda/📊_Product_Catalogue.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/demo/src/demo/apps/eda/📊_Product_Catalogue.py -------------------------------------------------------------------------------- /src/demo/src/demo/apps/es/pages/1_🔍_Sparse_vs_Dense.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/demo/src/demo/apps/es/pages/1_🔍_Sparse_vs_Dense.py -------------------------------------------------------------------------------- /src/demo/src/demo/apps/es/pages/2_🔍_Reranking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/demo/src/demo/apps/es/pages/2_🔍_Reranking.py -------------------------------------------------------------------------------- /src/demo/src/demo/apps/es/search_ui.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/demo/src/demo/apps/es/search_ui.py -------------------------------------------------------------------------------- /src/demo/src/demo/apps/es/🔍_Retrieval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/demo/src/demo/apps/es/🔍_Retrieval.py -------------------------------------------------------------------------------- /src/demo/src/demo/apps/features/pages/1_🤖_Tokenization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/demo/src/demo/apps/features/pages/1_🤖_Tokenization.py -------------------------------------------------------------------------------- /src/demo/src/demo/apps/features/🤖_AutoTokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/demo/src/demo/apps/features/🤖_AutoTokenizer.py -------------------------------------------------------------------------------- /src/demo/src/demo/page_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/demo/src/demo/page_config.py -------------------------------------------------------------------------------- /src/demo/src/demo/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/demo/src/demo/utils.py -------------------------------------------------------------------------------- /src/dense-retrieval/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/README.md -------------------------------------------------------------------------------- /src/dense-retrieval/poetry.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/poetry.lock -------------------------------------------------------------------------------- /src/dense-retrieval/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/pyproject.toml -------------------------------------------------------------------------------- /src/dense-retrieval/src/dense_retrieval/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/dense-retrieval/src/dense_retrieval/encoders/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/src/dense_retrieval/encoders/__init__.py -------------------------------------------------------------------------------- /src/dense-retrieval/src/dense_retrieval/encoders/bi_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/src/dense_retrieval/encoders/bi_encoder.py -------------------------------------------------------------------------------- /src/dense-retrieval/src/dense_retrieval/encoders/modules/losses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/src/dense_retrieval/encoders/modules/losses.py -------------------------------------------------------------------------------- /src/dense-retrieval/src/dense_retrieval/encoders/modules/pooler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/src/dense_retrieval/encoders/modules/pooler.py -------------------------------------------------------------------------------- /src/dense-retrieval/src/dense_retrieval/encoders/sbert_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/src/dense_retrieval/encoders/sbert_encoder.py -------------------------------------------------------------------------------- /src/dense-retrieval/src/dense_retrieval/encoders/text_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/src/dense_retrieval/encoders/text_encoder.py -------------------------------------------------------------------------------- /src/dense-retrieval/src/dense_retrieval/retrievers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/src/dense_retrieval/retrievers/__init__.py -------------------------------------------------------------------------------- /src/dense-retrieval/src/dense_retrieval/retrievers/ann_index.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/src/dense_retrieval/retrievers/ann_index.py -------------------------------------------------------------------------------- /src/dense-retrieval/src/dense_retrieval/retrievers/multi_vector_retriever.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/src/dense_retrieval/retrievers/multi_vector_retriever.py -------------------------------------------------------------------------------- /src/dense-retrieval/src/dense_retrieval/retrievers/retriever.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/src/dense_retrieval/retrievers/retriever.py -------------------------------------------------------------------------------- /src/dense-retrieval/src/dense_retrieval/retrievers/single_vector_retriever.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/src/dense_retrieval/retrievers/single_vector_retriever.py -------------------------------------------------------------------------------- /src/dense-retrieval/src/dense_retrieval/training/data_module.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/src/dense_retrieval/training/data_module.py -------------------------------------------------------------------------------- /src/dense-retrieval/src/dense_retrieval/training/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/dense-retrieval/src/dense_retrieval/training/trainer.py -------------------------------------------------------------------------------- /src/indexing/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/Dockerfile -------------------------------------------------------------------------------- /src/indexing/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/Makefile -------------------------------------------------------------------------------- /src/indexing/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/README.md -------------------------------------------------------------------------------- /src/indexing/conf/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/conf/config.yaml -------------------------------------------------------------------------------- /src/indexing/conf/dest/bq.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/conf/dest/bq.yaml -------------------------------------------------------------------------------- /src/indexing/conf/dest/es.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/conf/dest/es.yaml -------------------------------------------------------------------------------- /src/indexing/conf/dest/stdout.yaml: -------------------------------------------------------------------------------- 1 | name: stdout -------------------------------------------------------------------------------- /src/indexing/conf/runner/dataflow.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/conf/runner/dataflow.yaml -------------------------------------------------------------------------------- /src/indexing/conf/runner/direct.yaml: -------------------------------------------------------------------------------- 1 | name: DirectRunner 2 | num_workers: 0 -------------------------------------------------------------------------------- /src/indexing/poetry.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/poetry.lock -------------------------------------------------------------------------------- /src/indexing/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/pyproject.toml -------------------------------------------------------------------------------- /src/indexing/src/indexing/__main__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/src/indexing/__main__.py -------------------------------------------------------------------------------- /src/indexing/src/indexing/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/src/indexing/cli.py -------------------------------------------------------------------------------- /src/indexing/src/indexing/io/elasticsearch_io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/src/indexing/io/elasticsearch_io.py -------------------------------------------------------------------------------- /src/indexing/src/indexing/options.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/src/indexing/options.py -------------------------------------------------------------------------------- /src/indexing/src/indexing/pipelines/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/src/indexing/pipelines/base.py -------------------------------------------------------------------------------- /src/indexing/src/indexing/pipelines/doc_pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/src/indexing/pipelines/doc_pipeline.py -------------------------------------------------------------------------------- /src/indexing/src/indexing/pipelines/feed_pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/src/indexing/pipelines/feed_pipeline.py -------------------------------------------------------------------------------- /src/indexing/src/indexing/pipelines/pipelien_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/src/indexing/pipelines/pipelien_types.py -------------------------------------------------------------------------------- /src/indexing/src/indexing/pipelines/query_pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/src/indexing/pipelines/query_pipeline.py -------------------------------------------------------------------------------- /src/indexing/src/indexing/transforms/add_image_url.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/src/indexing/transforms/add_image_url.py -------------------------------------------------------------------------------- /src/indexing/src/indexing/transforms/analyze_doc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/src/indexing/transforms/analyze_doc.py -------------------------------------------------------------------------------- /src/indexing/src/indexing/transforms/encode_product.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/src/indexing/transforms/encode_product.py -------------------------------------------------------------------------------- /src/indexing/src/indexing/transforms/filters.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/src/indexing/transforms/filters.py -------------------------------------------------------------------------------- /src/indexing/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/indexing/tests/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/tests/conftest.py -------------------------------------------------------------------------------- /src/indexing/tests/integration/es_docker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/tests/integration/es_docker.py -------------------------------------------------------------------------------- /src/indexing/tests/integration/test_pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/tests/integration/test_pipeline.py -------------------------------------------------------------------------------- /src/indexing/tests/unit/io/test_elasticsearch_io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/tests/unit/io/test_elasticsearch_io.py -------------------------------------------------------------------------------- /src/indexing/tests/unit/transforms/test_add_image_url.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/tests/unit/transforms/test_add_image_url.py -------------------------------------------------------------------------------- /src/indexing/tests/unit/transforms/test_encode_product.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/tests/unit/transforms/test_encode_product.py -------------------------------------------------------------------------------- /src/indexing/tests/unit/transforms/test_filters.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/indexing/tests/unit/transforms/test_filters.py -------------------------------------------------------------------------------- /src/model-serving/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/Dockerfile -------------------------------------------------------------------------------- /src/model-serving/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/Makefile -------------------------------------------------------------------------------- /src/model-serving/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/README.md -------------------------------------------------------------------------------- /src/model-serving/compose.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/compose.yaml -------------------------------------------------------------------------------- /src/model-serving/conf/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/conf/config.yaml -------------------------------------------------------------------------------- /src/model-serving/conf/export_params/cl-nagoya/ruri-small-v2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/conf/export_params/cl-nagoya/ruri-small-v2.yaml -------------------------------------------------------------------------------- /src/model-serving/model_repository/embedder_onnx/1/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/model-serving/model_repository/embedder_onnx/config.pbtxt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/model_repository/embedder_onnx/config.pbtxt -------------------------------------------------------------------------------- /src/model-serving/model_repository/embedder_pt/1/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/model-serving/model_repository/embedder_pt/config.pbtxt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/model_repository/embedder_pt/config.pbtxt -------------------------------------------------------------------------------- /src/model-serving/model_repository/ensemble/1/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/model-serving/model_repository/ensemble/config.pbtxt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/model_repository/ensemble/config.pbtxt -------------------------------------------------------------------------------- /src/model-serving/model_repository/tokenizer/1/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/model_repository/tokenizer/1/model.py -------------------------------------------------------------------------------- /src/model-serving/model_repository/tokenizer/config.pbtxt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/model_repository/tokenizer/config.pbtxt -------------------------------------------------------------------------------- /src/model-serving/models/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/models/.gitignore -------------------------------------------------------------------------------- /src/model-serving/poetry.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/poetry.lock -------------------------------------------------------------------------------- /src/model-serving/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/pyproject.toml -------------------------------------------------------------------------------- /src/model-serving/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/requirements.txt -------------------------------------------------------------------------------- /src/model-serving/src/model_serving/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/model-serving/src/model_serving/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/src/model_serving/cli.py -------------------------------------------------------------------------------- /src/model-serving/src/model_serving/export/exporters.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/src/model_serving/export/exporters.py -------------------------------------------------------------------------------- /src/model-serving/src/model_serving/export/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/src/model_serving/export/utils.py -------------------------------------------------------------------------------- /src/model-serving/src/model_serving/modules/sentence_transformer_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/src/model_serving/modules/sentence_transformer_wrapper.py -------------------------------------------------------------------------------- /src/model-serving/tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/model-serving/tests/model_serving/onnx/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/model-serving/tests/model_serving/onnx/test_utils.py -------------------------------------------------------------------------------- /src/training/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/Dockerfile -------------------------------------------------------------------------------- /src/training/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/Makefile -------------------------------------------------------------------------------- /src/training/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/README.md -------------------------------------------------------------------------------- /src/training/conf/compile_parameters/default.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/conf/compile_parameters/default.yaml -------------------------------------------------------------------------------- /src/training/conf/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/conf/config.yaml -------------------------------------------------------------------------------- /src/training/conf/runtime_parameters/dummy.yaml: -------------------------------------------------------------------------------- 1 | message: Hello World 2 | -------------------------------------------------------------------------------- /src/training/conf/runtime_parameters/fine-tune-cl.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/conf/runtime_parameters/fine-tune-cl.yaml -------------------------------------------------------------------------------- /src/training/conf/runtime_parameters/fine-tune-mlm.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/conf/runtime_parameters/fine-tune-mlm.yaml -------------------------------------------------------------------------------- /src/training/poetry.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/poetry.lock -------------------------------------------------------------------------------- /src/training/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/pyproject.toml -------------------------------------------------------------------------------- /src/training/src/pipeline/__main__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/src/pipeline/__main__.py -------------------------------------------------------------------------------- /src/training/src/pipeline/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/src/pipeline/cli.py -------------------------------------------------------------------------------- /src/training/src/pipeline/components/dummy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/src/pipeline/components/dummy.py -------------------------------------------------------------------------------- /src/training/src/pipeline/components/fine_tuning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/src/pipeline/components/fine_tuning.py -------------------------------------------------------------------------------- /src/training/src/pipeline/pipelines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/src/pipeline/pipelines.py -------------------------------------------------------------------------------- /src/training/src/training/__main__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/src/training/__main__.py -------------------------------------------------------------------------------- /src/training/src/training/callbacks/metric_logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/src/training/callbacks/metric_logger.py -------------------------------------------------------------------------------- /src/training/src/training/data_modules/product_mlm_data_module.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/src/training/data_modules/product_mlm_data_module.py -------------------------------------------------------------------------------- /src/training/src/training/datasets/tokenized_sentences_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/src/training/datasets/tokenized_sentences_dataset.py -------------------------------------------------------------------------------- /src/training/src/training/modules/mlm_fine_tuner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/src/training/modules/mlm_fine_tuner.py -------------------------------------------------------------------------------- /src/training/src/training/runners/fine_tuning_cl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/src/training/runners/fine_tuning_cl.py -------------------------------------------------------------------------------- /src/training/src/training/runners/fine_tuning_mlm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/src/training/runners/fine_tuning_mlm.py -------------------------------------------------------------------------------- /src/training/templates/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/rejasupotaro/amazon-product-search/HEAD/src/training/templates/.gitignore --------------------------------------------------------------------------------