embedding_studio
Embedding Studio is a framework which allows you transform your Vector Database into a feature-rich Search Engine.
파일 탐색기
최종 버전 다운로드 (.zip)- embedding_studio_chart.png
- clickstream_client.py.md
- clickstream_internal.py.md
- delete.py.md
- fine_tuning.py.md
- ping.py.md
- query_parsing.py.md
- similarity_search.py.md
- suggesting.py.md
- upsert.py.md
- delete.py.md
- inference_deployment_tasks.py.md
- reindex.py.md
- upsert.py.md
- vectordb.py.md
- mocked_fine_tuning.py.md
- clickstream_client.py.md
- clickstream_internal.py.md
- delete.py.md
- fine_tuning.py.md
- ping.py.md
- query_parsing.py.md
- similarity_search.py.md
- suggesting.py.md
- upsert.py.md
- delete.py.md
- inference_deployment_tasks.py.md
- reindex.py.md
- upsert.py.md
- vectordb.py.md
- mocked_fine_tuning.py.md
- internal_api.py.md
- mocked_api.py.md
- converter.py.md
- query_retriever.py.md
- search_event.py.md
- text_query_retriever.py.md
- plugin.py.md
- clickstream.py.md
- crud_base.py.md
- mongo_dao.py.md
- clickstream.py.md
- model_stage_tasks.py.md
- model_transfer_tasks.py.md
- gcp_image_loader.py.md
- gcp_json_loader.py.md
- gcp_loader.py.md
- gcp_text_loader.py.md
- s3_image_loader.py.md
- s3_json_loader.py.md
- s3_loader.py.md
- s3_text_loader.py.md
- bucket_file_meta.py.md
- pgsql_image_loader.py.md
- pgsql_jsonb_loader.py.md
- pgsql_loader.py.md
- pgsql_multi_text_column_loader.py.md
- pgsql_text_loader.py.md
- query_generator.py.md
- sql_item_meta.py.md
- aggregated_data_loader.py.md
- data_loader.py.md
- item_meta.py.md
- mongo.py.md
- cases.py.md
- misspellings.py.md
- augmentation_interface.py.md
- augmentation_with_random_selection.py.md
- clickstream_augmentation_applier.py.md
- compose.py.md
- items_set_augmentation_applier.py.md
- paired_fine_tuning_inputs.py.md
- train_test_splitter.py.md
- items_set.py.md
- manager.py.md
- dict_items_preprocessor.py.md
- image_items_preprocessor.py.md
- preprocessor.py.md
- text_items_preprocessor.py.md
- line_from_dict.py.md
- transforms.py.md
- center_padded.py.md
- clip_original.py.md
- transforms.py.md
- dummy.py.md
- transforms.py.md
- max_aggregator.py.md
- mean_aggregator.py.md
- min_aggregator.py.md
- ranks_aggregator.py.md
- event_confidences.py.md
- extractor.py.md
- fine_tuning_features.py.md
- fine_tuning_input.py.md
- torch_based_adjuster.py.md
- vectors_adjuster.py.md
- clip.py.md
- bert.py.md
- e5.py.md
- client.py.md
- prob_margin_ranking_loss.py.md
- distance_shift.py.md
- clip.py.md
- bert.py.md
- e5.py.md
- average_pool.py.md
- differentiable_extreme.py.md
- differentiable_mean.py.md
- pooler_output.py.md
- soft_indicator.py.md
- interface.py.md
- dist_based_selector.py.md
- prob_dist_based_selector.py.md
- selector.py.md
- vectors_based_selector.py.md
- tokenized_grouped_splitter.py.md
- dataset_splitter.py.md
- embeddings_finetuner.py.md
- mlflow_minio_backend.py.md
- mlflow_with_aws_s3_backend.py.md
- mlflow_with_azure_blob_backend.py.md
- mlflow_with_dbfs_backend.py.md
- mlflow_with_gcp_backend.py.md
- mlflow_with_local_backend.py.md
- experiments_tracker.py.md
- finetuning_iteration.py.md
- finetuning_params.py.md
- metrics_accumulator.py.md
- mlflow_client_wrapper.py.md
- generate_model_file.py.md
- types_mapping.py.md
- jit_trace_manager.py.md
- manager.py.md
- model_storage_info.py.md
- pytorch_manager.py.md
- plugin.py.md
- reindex.py.md
- suggesting.py.md
- utils.py.md
- complex_redis_suggester.py.md
- phrases_manager.py.md
- suggester.py.md
- abstract_suggester.py.md
- abtract_phrase_manager.py.md
- tokenizer.py.md
- env_vars.py.md
- conftest.py.md
- test_fine_tuning.py.md
- test_ping.py.md
- misspellers.py.md
- datetime_utils.py.md
- dramatiq_middlewares.py.md
- dramatiq_task_handler.py.md
- gpu_monitoring.py.md
- initializer_actions.py.md
- mlflow_utils.py.md
- model_download.py.md
- plugin_utils.py.md
- redis_utils.py.md
- retry.py.md
- string_utils.py.md
- tasks.py.md
- advanced_similarity.py.md
- simple_similarity.py.md
- where_combinations.py.md
- collection.py.md
- db_model.py.md
- optimization.py.md
- query_to_sql.py.md
- vectordb.py.md
- collection.py.md
- collection_base.py.md
- collection_info_cache.py.md
- vectordb.py.md
- finetune_embedding.py.md
- finetune_embedding_one_param.py.md
- mocked_worker.py.md
- prepare_data.py.md
- worker.py.md
- handle_improvement.py.md
- worker.py.md
- deletion.py.md
- deployment.py.md
- file_locks.py.md
- init_model_repo.py.md
- prepare_for_triton.py.md
- worker.py.md
- delete.py.md
- reindex.py.md
- reindex_subtask.py.md
- upsert.py.md
- deployment.py.md
- reindex.py.md
- upsert.py.md
- upsertion_stages.py.md
- worker.py.md
- click.svg
- clock_realtime.svg
- continous_improvement.png
- cost_safe.svg
- customer_centric.svg
- data_model.svg
- data_unstructured.svg
- docker.svg
- dynamic_content.svg
- embedding_studio_chart.png
- embedding_studio_logo.svg
- embedding_studio_product.png
- fine-tuning.svg
- github.svg
- legal-firm.png
- logo.svg
- logo2.svg
- logo3.svg
- logo4.svg
- logo5.svg
- logo6.svg
- logo7.svg
- logo8.svg
- logo9.svg
- loop.svg
- mlflow.png
- mlflow_main.png
- online-store.png
- plugin.svg
- python_logo.svg
- rich_content.svg
- search.svg
- semantic-search.svg
- similarity-search.png
- structured-unstructured-queries.png
- structured-unstructured.png
- train_loss.png
- home.html
- main.html
- semantic_search_engine.md
- semi_unstructured_search.md
- similarity_search.md
- extra.css
- categories_data_flow.md
- clickstream.md
- items_data_flow.md
- management_api.md
- collect_clickstream.md
- configuring.md
- data_flow.md
- fine_tuning_tracking.md
- overview.md
- architecture_overview.md
- configurations.md
- core_concepts.md
- docker_quickstart.md
- introduction.md
- model_lifecycle.md
- configuring.md
- overview.md
- how_to_construct.md
- overview.md
- usage_for_postgresql.md
- data_sources_integration.md
- implement_your_own.md
- understanding_plugin_system.md
- custom_selector.md
- overview.md
- configuring_redis.md
- managing_via_api.md
- overview.md
- configuring.md
- integration.md
- managing.md
- ideal_scenarios.md
- legal_firm.md
- online_store.md
- optimal_moments.md
- challenges.md
- index.md
- overview.md
- __init__.py
- clickstream_client.py
- clickstream_internal.py
- delete.py
- fine_tuning.py
- ping.py
- query_parsing.py
- similarity_search.py
- suggesting.py
- upsert.py
- __init__.py
- delete.py
- inference_deployment_tasks.py
- reindex.py
- upsert.py
- vectordb.py
- __init__.py
- delete.py
- inference_deployment_tasks.py
- reindex.py
- task.py
- upsert.py
- vectrordb.py
- __init__.py
- mocked_fine_tuning.py
- __init__.py
- clickstream_client.py
- clickstream_internal.py
- delete.py
- fine_tuning.py
- payload_filter.py
- query_parsing.py
- similarity_search.py
- sorting_options.py
- suggesting.py
- task.py
- upsert.py
- __init__.py
- api.py
- internal_api.py
- mocked_api.py
- __init__.py
- __init__.py
- converter.py
- __init__.py
- input_with_items.py
- query_item.py
- query_retriever.py
- search_event.py
- text_query_item.py
- text_query_retriever.py
- __init__.py
- app_context.py
- __init__.py
- config.py
- plugin.py
- __init__.py
- clickstream.py
- crud_base.py
- mongo_dao.py
- __init__.py
- clickstream.py
- deletion_tasks.py
- fine_tuning.py
- improvement_sessions.py
- inference_deployment_tasks.py
- model_stage_tasks.py
- model_transfer_tasks.py
- reindex_locks.py
- reindex_tasks.py
- upsertion_tasks.py
- __init__.py
- exceptions.py
- gcp_image_loader.py
- gcp_json_loader.py
- gcp_loader.py
- gcp_text_loader.py
- item_meta.py
- __init__.py
- exceptions.py
- item_meta.py
- s3_image_loader.py
- s3_json_loader.py
- s3_loader.py
- s3_text_loader.py
- __init__.py
- bucket_file_meta.py
- __init__.py
- item_meta.py
- pgsql_image_loader.py
- pgsql_jsonb_loader.py
- pgsql_loader.py
- pgsql_multi_text_column_loader.py
- pgsql_text_loader.py
- __init__.py
- query_generator.py
- sql_item_meta.py
- __init__.py
- aggregated_data_loader.py
- data_loader.py
- downloaded_item.py
- item_meta.py
- __init__.py
- __init__.py
- common.py
- mongo.py
- postgres.py
- redis.py
- __init__.py
- cases.py
- misspellings.py
- __init__.py
- augmentation_interface.py
- augmentation_with_random_selection.py
- clickstream_augmentation_applier.py
- compose.py
- items_set_augmentation_applier.py
- __init__.py
- improvement_input.py
- paired_fine_tuning_inputs.py
- train_test_splitter.py
- __init__.py
- clip.py
- dict.py
- text.py
- __init__.py
- items_set.py
- manager.py
- __init__.py
- dict_items_preprocessor.py
- image_items_preprocessor.py
- preprocessor.py
- text_items_preprocessor.py
- __init__.py
- line_from_dict.py
- transforms.py
- __init__.py
- center_padded.py
- clip_original.py
- transforms.py
- __init__.py
- dummy.py
- transforms.py
- __init__.py
- __init__.py
- fields_normalizer.py
- normalizers.py
- __init__.py
- ranking_data.py
- __init__.py
- clicks_aggregator.py
- max_aggregator.py
- __init__.py
- max_aggregator.py
- mean_aggregator.py
- min_aggregator.py
- ranks_aggregator.py
- __init__.py
- event_confidences.py
- extractor.py
- fine_tuning_features.py
- fine_tuning_input.py
- __init__.py
- torch_based_adjuster.py
- vectors_adjuster.py
- __init__.py
- clip.py
- __init__.py
- bert.py
- e5.py
- __init__.py
- client.py
- __init__.py
- __init__.py
- prob_cosine_margin_ranking_loss.py
- prob_margin_ranking_loss.py
- ranking_loss_interface.py
- __init__.py
- distance_shift.py
- metric.py
- __init__.py
- clip.py
- image-for-tracing.png
- __init__.py
- bert.py
- e5.py
- test_inputs.py
- __init__.py
- average_pool.py
- differentiable_extreme.py
- differentiable_mean.py
- pooler_output.py
- soft_indicator.py
- __init__.py
- interface.py
- __init__.py
- dist_based_selector.py
- prob_dist_based_selector.py
- selector.py
- vectors_based_selector.py
- __init__.py
- field_combined_splitter.py
- json_splitter.py
- __init__.py
- dummy_sentence_splitter.py
- pattern_splitter.py
- separator_splitter.py
- tokenized_grouped_splitter.py
- __init__.py
- dataset_splitter.py
- item_splitter.py
- no_splitter.py
- __init__.py
- embeddings_finetuner.py
- __init__.py
- __init__.py
- __init__.py
- clip.py
- __init__.py
- mlflow_minio_backend.py
- mlflow_with_aws_s3_backend.py
- mlflow_with_azure_blob_backend.py
- mlflow_with_dbfs_backend.py
- mlflow_with_gcp_backend.py
- mlflow_with_local_backend.py
- __init__.py
- experiments_tracker.py
- finetuning_iteration.py
- finetuning_params.py
- finetuning_settings.py
- metrics_accumulator.py
- mlflow_client_wrapper.py
- status.py
- __init__.py
- generate_model_file.py
- types_mapping.py
- __init__.py
- jit_trace_manager.py
- manager.py
- model_storage_info.py
- pytorch_manager.py
- __init__.py
- __init__.py
- session_batches.py
- session_events.py
- sessions.py
- __init__.py
- collections.py
- models.py
- objects.py
- __init__.py
- models.py
- __init__.py
- models.py
- __init__.py
- delete.py
- fine_tuning.py
- improvement.py
- inference_deployment_tasks.py
- items_handler.py
- plugin.py
- reindex.py
- reindex_lock.py
- suggesting.py
- task.py
- upsert.py
- utils.py
- __init__.py
- complex_mongo_suggester.py
- full_suggests_pipeline_generator.py
- phrases_manager.py
- pipeline_generator.py
- prefix_suggests_pipeline_generator.py
- simple_suggests_pipeline_generator.py
- suggester.py
- __init__.py
- combined_suggests_pipeline_generator.py
- complex_redis_suggester.py
- most_probable_suggests_pipeline_generator.py
- phrases_manager.py
- prefix_suggests_query_generator.py
- query_generator.py
- simple_suggests_query_generator.py
- suggester.py
- __init__.py
- abstract_suggester.py
- abtract_phrase_manager.py
- tokenizer.py
- __init__.py
- env_vars.py
- __init__.py
- conftest.py
- test_fine_tuning.py
- test_ping.py
- __init__.py
- keyboard_layout.py
- misspellers.py
- __init__.py
- datetime_utils.py
- deployment_utils.py
- dot_object.py
- dramatiq_middlewares.py
- dramatiq_task_handler.py
- gpu_monitoring.py
- initializer_actions.py
- mlflow_utils.py
- model_download.py
- plugin_utils.py
- redis_utils.py
- retry.py
- string_utils.py
- tasks.py
- __init__.py
- advanced_similarity.py
- simple_similarity.py
- where_combinations.py
- __init__.py
- collection.py
- db_model.py
- optimization.py
- query_to_sql.py
- vectordb.py
- __init__.py
- collection.py
- collection_base.py
- collection_info_cache.py
- exceptions.py
- optimization.py
- vectordb.py
- __init__.py
- config.py
- exceptions.py
- retry.py
- __init__.py
- exceptions.py
- finetune_embedding.py
- finetune_embedding_one_param.py
- mocked_worker.py
- prepare_data.py
- worker.py
- worker_exceptions.py
- __init__.py
- handle_improvement.py
- __init__.py
- worker.py
- __init__.py
- deletion.py
- deployment.py
- exceptions.py
- file_locks.py
- init_model_repo.py
- prepare_for_triton.py
- __init__.py
- start_service.sh
- worker.py
- __init__.py
- delete.py
- reindex.py
- reindex_subtask.py
- upsert.py
- __init__.py
- deployment.py
- exceptions.py
- reindex.py
- upsert.py
- upsertion_stages.py
- __init__.py
- worker.py
- __init__.py
- __init__.py
- log_config.yaml
- main.py
- __init__.py
- api_utils.py
- aws_utils.py
- constants.py
- mlflow_utils.py
- __init__.py
- clickstream_emulator.py
- fine_tuning_emulator.py
- iteration_emulator.py
- __init__.py
- __init__.py
- hf_categories_query_generator.py
- hf_datasets_query_generator.py
- hf_models_query_generator.py
- item_meta.py
- __init__.py
- __init__.py
- indexes.py
- __init__.py
- __init__.py
- categories_text_fine_tuning_method.py
- default_fine_tuning_method.py
- dict_text_fine_tuning_method.py
- hugsearch_categories_fine_tuning_method.py
- hugsearch_fine_tuning_method.py
- text_fine_tuning_method.py
- format-imports.sh
- format.sh
- format_all.sh
- generate_mkdocs_for_documentation.py
- lint.sh
- .env
- .gitignore
- docker-compose.local.yml
- docker-compose.yml
- LICENSE
- mkdocs.yml
- pyproject.toml
- README.md
- service.Dockerfile
- setup.py
- worker.fine_tuning.Dockerfile
- worker.improvement_worker.Dockerfile
- worker.inference.Dockerfile
- worker.upsertion_worker.Dockerfile
# 설치 가이드
1. 코드 내려받기
git clone https://github.com/EulerSearch/embedding_studio
깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.
cd embedding_studio
방금 내려받은 프로젝트 폴더 안으로 이동합니다.
2. Docker
쉬움 추천사전 준비물
- Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
- Docker Desktop 컨테이너를 빌드하고 실행하려면 필요합니다. 설치 후 실행해서 백그라운드에 켜두세요.
<a href="#"><img src="https://img.shields.io/badge/docker--compose-2.17.0-blue.svg" alt="Docker Compose Version"></a>
compose 설정 파일에 정의된 서비스들을 대상으로 명령을 실행합니다.
터미널에 docker compose ps 를 입력해 컨테이너들이 Up 상태인지 확인하세요. README에 포트 번호가 적혀있다면 브라우저에서 http://localhost:포트번호 로 접속해보세요.
이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.
// repository documentation
Was this content helpful?
(0 ratings)