mkdocs.yml

site_name: Embedding Studio
repo_url: https://github.com/EulerSearch/embedding_studio
repo_name: embedding_studio
theme:
  name: material
  palette:
    primary: indigo
  logo: images/logo.svg
  favicon: images/logo.svg
  custom_dir: docs/overrides
  features:
    - navigation.tabs
    - navigation.path
    - navigation.indexes
    - navigation.expand
markdown_extensions:
  - admonition
  - tables
  - pymdownx.details
  - pymdownx.superfences
  - attr_list
  - pymdownx.emoji:
      emoji_index: !!python/name:material.extensions.emoji.twemoji
      emoji_generator: !!python/name:material.extensions.emoji.to_svg
  - toc:
      permalink: true
plugins:
  - minify:
      cache_safe: true
      css_files:
        - stylesheets/extra.css
extra_css:
  - stylesheets/extra.css
nav:
  - Home: index.md
  - Overview: overview.md
  - Challenges & Solutions:
      - Challenges: challenges.md
      - Solutions:
        - Semantic search engines: solutions/semantic_search_engine.md
        - Similarity search: solutions/similarity_search.md
        - Semi-unstructured search engines: solutions/semi_unstructured_search.md
  - Use Cases:
      - When is EmbeddingStudio the Best Fit?:
          - Ideal scenarios 🎯: use_cases/ideal_scenarios.md
          - Optimal Moments 🚀: use_cases/optimal_moments.md
          - Examples 💼:
              - Online-store: use_cases/online_store.md
              - Legal firm: use_cases/legal_firm.md
  - API:
      - Ping: api/api_v1/endpoints/ping.py.md
      - Public:
          - Similarity Search:
              - Methods: api/api_v1/endpoints/similarity_search.py.md
              - About Payload:
                  - Overview: tutorial/payload/overview.md
                  - How to Construct: tutorial/payload/how_to_construct.md
                  - Usage for PostgreSQL: tutorial/payload/usage_for_postgresql.md
          - Query Parsing: api/api_v1/endpoints/query_parsing.py.md
          - Suggesting Service: api/api_v1/endpoints/suggesting.py.md
          - Clickstream:
              - Management: api/api_v1/endpoints/clickstream_client.py.md
              - Usage: api/api_v1/endpoints/clickstream_internal.py.md
          - Fine-Tuning: api/api_v1/endpoints/fine_tuning.py.md
          - Data Management:
              - Upsert: api/api_v1/endpoints/upsert.py.md
              - Delete: api/api_v1/endpoints/delete.py.md
      - Internal:
          - Model Management: api/api_v1/internal_endpoints/inference_deployment_tasks.py.md
          - Vector DB Management: api/api_v1/internal_endpoints/vectordb.py.md
          - Data Management:
              - Upsert: api/api_v1/internal_endpoints/upsert.py.md
              - Delete: api/api_v1/internal_endpoints/delete.py.md
              - Reindex: api/api_v1/internal_endpoints/reindex.py.md
  - Tutorials:
      - Getting Started: tutorial/getting_started/introduction.md
      - Basic:
          - Core Concepts: tutorial/getting_started/core_concepts.md
          - Architecture Overview: tutorial/getting_started/architecture_overview.md
          - Model Lifecycle: tutorial/getting_started/model_lifecycle.md
          - Configurations: tutorial/getting_started/configurations.md
          - Docker Quickstart: tutorial/getting_started/docker_quickstart.md
      - Advanced:
          - Data Management:
              - Clickstream: tutorial/data_management/clickstream.md
              - Items: tutorial/data_management/items_data_flow.md
              - Categories: tutorial/data_management/categories_data_flow.md
              - API: tutorial/data_management/management_api.md
          - About Vector DB:
              - Integration: tutorial/vectordb/integration.md
              - Configuring: tutorial/vectordb/configuring.md
              - Managing: tutorial/vectordb/managing.md
          - Suggestions:
              - Overview: tutorial/suggestings/overview.md
              - Management API: tutorial/suggestings/managing_via_api.md
              - Configuring Redis: tutorial/suggestings/configuring_redis.md
          - Query Parsing:
              - Overview: tutorial/query_parsing/overview.md
              - Customizing Selector: tutorial/query_parsing/custom_selector.md
          - Vector Improvement & Personalization:
              - Overview: tutorial/improvement/overview.md
              - Configuring: tutorial/improvement/configuring.md
      - Plugins:
          - About Plugin System: tutorial/plugins/understanding_plugin_system.md
          - Data Sources Integration: tutorial/plugins/data_sources_integration.md
          - How to Implement: tutorial/plugins/implement_your_own.md
  - Documentation:
      - api:
          - api_v1:
              - endpoints:
                  - clickstream_client: embedding_studio/api/api_v1/endpoints/clickstream_client.py.md
                  - clickstream_internal: embedding_studio/api/api_v1/endpoints/clickstream_internal.py.md
                  - delete: embedding_studio/api/api_v1/endpoints/delete.py.md
                  - fine_tuning: embedding_studio/api/api_v1/endpoints/fine_tuning.py.md
                  - ping: embedding_studio/api/api_v1/endpoints/ping.py.md
                  - query_parsing: embedding_studio/api/api_v1/endpoints/query_parsing.py.md
                  - similarity_search: embedding_studio/api/api_v1/endpoints/similarity_search.py.md
                  - suggesting: embedding_studio/api/api_v1/endpoints/suggesting.py.md
                  - upsert: embedding_studio/api/api_v1/endpoints/upsert.py.md
              - internal_api: embedding_studio/api/api_v1/internal_api.py.md
              - internal_endpoints:
                  - delete: embedding_studio/api/api_v1/internal_endpoints/delete.py.md
                  - inference_deployment_tasks: embedding_studio/api/api_v1/internal_endpoints/inference_deployment_tasks.py.md
                  - reindex: embedding_studio/api/api_v1/internal_endpoints/reindex.py.md
                  - upsert: embedding_studio/api/api_v1/internal_endpoints/upsert.py.md
                  - vectordb: embedding_studio/api/api_v1/internal_endpoints/vectordb.py.md
              - mocked_api: embedding_studio/api/api_v1/mocked_api.py.md
              - mocked_endpoints:
                  - mocked_fine_tuning: embedding_studio/api/api_v1/mocked_endpoints/mocked_fine_tuning.py.md
      - clickstream_storage:
          - converters:
              - converter: embedding_studio/clickstream_storage/converters/converter.py.md
          - query_retriever: embedding_studio/clickstream_storage/query_retriever.py.md
          - search_event: embedding_studio/clickstream_storage/search_event.py.md
          - text_query_retriever: embedding_studio/clickstream_storage/text_query_retriever.py.md
      - core:
          - plugin: embedding_studio/core/plugin.py.md
      - data_access:
          - clickstream: embedding_studio/data_access/clickstream.py.md
          - model_stage_tasks: embedding_studio/data_access/model_stage_tasks.py.md
          - model_transfer_tasks: embedding_studio/data_access/model_transfer_tasks.py.md
          - mongo:
              - clickstream: embedding_studio/data_access/mongo/clickstream.py.md
              - crud_base: embedding_studio/data_access/mongo/crud_base.py.md
              - mongo_dao: embedding_studio/data_access/mongo/mongo_dao.py.md
      - data_storage:
          - loaders:
              - aggregated_data_loader: embedding_studio/data_storage/loaders/aggregated_data_loader.py.md
              - cloud_storage:
                  - bucket_file_meta: embedding_studio/data_storage/loaders/cloud_storage/bucket_file_meta.py.md
                  - gcp:
                      - gcp_image_loader: embedding_studio/data_storage/loaders/cloud_storage/gcp/gcp_image_loader.py.md
                      - gcp_json_loader: embedding_studio/data_storage/loaders/cloud_storage/gcp/gcp_json_loader.py.md
                      - gcp_loader: embedding_studio/data_storage/loaders/cloud_storage/gcp/gcp_loader.py.md
                      - gcp_text_loader: embedding_studio/data_storage/loaders/cloud_storage/gcp/gcp_text_loader.py.md
                  - s3:
                      - s3_image_loader: embedding_studio/data_storage/loaders/cloud_storage/s3/s3_image_loader.py.md
                      - s3_json_loader: embedding_studio/data_storage/loaders/cloud_storage/s3/s3_json_loader.py.md
                      - s3_loader: embedding_studio/data_storage/loaders/cloud_storage/s3/s3_loader.py.md
                      - s3_text_loader: embedding_studio/data_storage/loaders/cloud_storage/s3/s3_text_loader.py.md
              - data_loader: embedding_studio/data_storage/loaders/data_loader.py.md
              - item_meta: embedding_studio/data_storage/loaders/item_meta.py.md
              - sql:
                  - pgsql:
                      - pgsql_image_loader: embedding_studio/data_storage/loaders/sql/pgsql/pgsql_image_loader.py.md
                      - pgsql_jsonb_loader: embedding_studio/data_storage/loaders/sql/pgsql/pgsql_jsonb_loader.py.md
                      - pgsql_loader: embedding_studio/data_storage/loaders/sql/pgsql/pgsql_loader.py.md
                      - pgsql_multi_text_column_loader: embedding_studio/data_storage/loaders/sql/pgsql/pgsql_multi_text_column_loader.py.md
                      - pgsql_text_loader: embedding_studio/data_storage/loaders/sql/pgsql/pgsql_text_loader.py.md
                  - query_generator: embedding_studio/data_storage/loaders/sql/query_generator.py.md
                  - sql_item_meta: embedding_studio/data_storage/loaders/sql/sql_item_meta.py.md
      - db:
          - mongo: embedding_studio/db/mongo.py.md
      - embeddings:
          - augmentations:
              - augmentation_interface: embedding_studio/embeddings/augmentations/augmentation_interface.py.md
              - augmentation_with_random_selection: embedding_studio/embeddings/augmentations/augmentation_with_random_selection.py.md
              - clickstream_augmentation_applier: embedding_studio/embeddings/augmentations/clickstream_augmentation_applier.py.md
              - compose: embedding_studio/embeddings/augmentations/compose.py.md
              - items_set_augmentation_applier: embedding_studio/embeddings/augmentations/items_set_augmentation_applier.py.md
              - text:
                  - cases: embedding_studio/embeddings/augmentations/text/cases.py.md
                  - misspellings: embedding_studio/embeddings/augmentations/text/misspellings.py.md
          - data:
              - clickstream:
                  - paired_fine_tuning_inputs: embedding_studio/embeddings/data/clickstream/paired_fine_tuning_inputs.py.md
                  - train_test_splitter: embedding_studio/embeddings/data/clickstream/train_test_splitter.py.md
              - items:
                  - items_set: embedding_studio/embeddings/data/items/items_set.py.md
                  - manager: embedding_studio/embeddings/data/items/manager.py.md
              - preprocessors:
                  - dict_items_preprocessor: embedding_studio/embeddings/data/preprocessors/dict_items_preprocessor.py.md
                  - image_items_preprocessor: embedding_studio/embeddings/data/preprocessors/image_items_preprocessor.py.md
                  - preprocessor: embedding_studio/embeddings/data/preprocessors/preprocessor.py.md
                  - text_items_preprocessor: embedding_studio/embeddings/data/preprocessors/text_items_preprocessor.py.md
              - transforms:
                  - dict:
                      - line_from_dict: embedding_studio/embeddings/data/transforms/dict/line_from_dict.py.md
                      - transforms: embedding_studio/embeddings/data/transforms/dict/transforms.py.md
                  - image:
                      - center_padded: embedding_studio/embeddings/data/transforms/image/center_padded.py.md
                      - clip_original: embedding_studio/embeddings/data/transforms/image/clip_original.py.md
                      - transforms: embedding_studio/embeddings/data/transforms/image/transforms.py.md
                  - text:
                      - dummy: embedding_studio/embeddings/data/transforms/text/dummy.py.md
                      - transforms: embedding_studio/embeddings/data/transforms/text/transforms.py.md
          - features:
              - event_confidences: embedding_studio/embeddings/features/event_confidences.py.md
              - extractor: embedding_studio/embeddings/features/extractor.py.md
              - fine_tuning_features: embedding_studio/embeddings/features/fine_tuning_features.py.md
              - fine_tuning_input: embedding_studio/embeddings/features/fine_tuning_input.py.md
              - ranks_aggregators:
                  - max_aggregator: embedding_studio/embeddings/features/ranks_aggregators/max_aggregator.py.md
                  - mean_aggregator: embedding_studio/embeddings/features/ranks_aggregators/mean_aggregator.py.md
                  - min_aggregator: embedding_studio/embeddings/features/ranks_aggregators/min_aggregator.py.md
                  - ranks_aggregator: embedding_studio/embeddings/features/ranks_aggregators/ranks_aggregator.py.md
          - improvement:
              - torch_based_adjuster: embedding_studio/embeddings/improvement/torch_based_adjuster.py.md
              - vectors_adjuster: embedding_studio/embeddings/improvement/vectors_adjuster.py.md
          - inference:
              - triton:
                  - client: embedding_studio/embeddings/inference/triton/client.py.md
                  - text_to_image:
                      - clip: embedding_studio/embeddings/inference/triton/text_to_image/clip.py.md
                  - text_to_text:
                      - bert: embedding_studio/embeddings/inference/triton/text_to_text/bert.py.md
                      - e5: embedding_studio/embeddings/inference/triton/text_to_text/e5.py.md
          - losses:
              - prob_margin_ranking_loss: embedding_studio/embeddings/losses/prob_margin_ranking_loss.py.md
          - metrics:
              - distance_shift: embedding_studio/embeddings/metrics/distance_shift.py.md
          - models:
              - interface: embedding_studio/embeddings/models/interface.py.md
              - text_to_image:
                  - clip: embedding_studio/embeddings/models/text_to_image/clip.py.md
              - text_to_text:
                  - bert: embedding_studio/embeddings/models/text_to_text/bert.py.md
                  - e5: embedding_studio/embeddings/models/text_to_text/e5.py.md
              - utils:
                  - average_pool: embedding_studio/embeddings/models/utils/average_pool.py.md
                  - differentiable_extreme: embedding_studio/embeddings/models/utils/differentiable_extreme.py.md
                  - differentiable_mean: embedding_studio/embeddings/models/utils/differentiable_mean.py.md
                  - pooler_output: embedding_studio/embeddings/models/utils/pooler_output.py.md
                  - soft_indicator: embedding_studio/embeddings/models/utils/soft_indicator.py.md
          - selectors:
              - dist_based_selector: embedding_studio/embeddings/selectors/dist_based_selector.py.md
              - prob_dist_based_selector: embedding_studio/embeddings/selectors/prob_dist_based_selector.py.md
              - selector: embedding_studio/embeddings/selectors/selector.py.md
              - vectors_based_selector: embedding_studio/embeddings/selectors/vectors_based_selector.py.md
          - splitters:
              - dataset_splitter: embedding_studio/embeddings/splitters/dataset_splitter.py.md
              - text:
                  - tokenized_grouped_splitter: embedding_studio/embeddings/splitters/text/tokenized_grouped_splitter.py.md
          - training:
              - embeddings_finetuner: embedding_studio/embeddings/training/embeddings_finetuner.py.md
      - experiments:
          - experiments_tracker: embedding_studio/experiments/experiments_tracker.py.md
          - finetuning_iteration: embedding_studio/experiments/finetuning_iteration.py.md
          - finetuning_params: embedding_studio/experiments/finetuning_params.py.md
          - metrics_accumulator: embedding_studio/experiments/metrics_accumulator.py.md
          - mlflow_client_wrapper: embedding_studio/experiments/mlflow_client_wrapper.py.md
          - trackers:
              - mlflow_minio_backend: embedding_studio/experiments/trackers/mlflow_minio_backend.py.md
              - mlflow_with_aws_s3_backend: embedding_studio/experiments/trackers/mlflow_with_aws_s3_backend.py.md
              - mlflow_with_azure_blob_backend: embedding_studio/experiments/trackers/mlflow_with_azure_blob_backend.py.md
              - mlflow_with_dbfs_backend: embedding_studio/experiments/trackers/mlflow_with_dbfs_backend.py.md
              - mlflow_with_gcp_backend: embedding_studio/experiments/trackers/mlflow_with_gcp_backend.py.md
              - mlflow_with_local_backend: embedding_studio/experiments/trackers/mlflow_with_local_backend.py.md
      - inference_management:
          - triton:
              - jit_trace_manager: embedding_studio/inference_management/triton/jit_trace_manager.py.md
              - manager: embedding_studio/inference_management/triton/manager.py.md
              - model_storage_info: embedding_studio/inference_management/triton/model_storage_info.py.md
              - pytorch_manager: embedding_studio/inference_management/triton/pytorch_manager.py.md
              - utils:
                  - generate_model_file: embedding_studio/inference_management/triton/utils/generate_model_file.py.md
                  - types_mapping: embedding_studio/inference_management/triton/utils/types_mapping.py.md
      - models:
          - plugin: embedding_studio/models/plugin.py.md
          - reindex: embedding_studio/models/reindex.py.md
          - suggesting: embedding_studio/models/suggesting.py.md
          - utils: embedding_studio/models/utils.py.md
      - suggesting:
          - abstract_suggester: embedding_studio/suggesting/abstract_suggester.py.md
          - abtract_phrase_manager: embedding_studio/suggesting/abtract_phrase_manager.py.md
          - redis:
              - complex_redis_suggester: embedding_studio/suggesting/redis/complex_redis_suggester.py.md
              - phrases_manager: embedding_studio/suggesting/redis/phrases_manager.py.md
              - suggester: embedding_studio/suggesting/redis/suggester.py.md
          - tokenizer: embedding_studio/suggesting/tokenizer.py.md
      - tests:
          - conftest: embedding_studio/tests/conftest.py.md
          - pytest_plugins:
              - env_vars: embedding_studio/tests/pytest_plugins/env_vars.py.md
          - test_fine_tuning: embedding_studio/tests/test_fine_tuning.py.md
          - test_ping: embedding_studio/tests/test_ping.py.md
      - utils:
          - datetime_utils: embedding_studio/utils/datetime_utils.py.md
          - dramatiq_middlewares: embedding_studio/utils/dramatiq_middlewares.py.md
          - dramatiq_task_handler: embedding_studio/utils/dramatiq_task_handler.py.md
          - gpu_monitoring: embedding_studio/utils/gpu_monitoring.py.md
          - initializer_actions: embedding_studio/utils/initializer_actions.py.md
          - misspelling:
              - misspellers: embedding_studio/utils/misspelling/misspellers.py.md
          - mlflow_utils: embedding_studio/utils/mlflow_utils.py.md
          - model_download: embedding_studio/utils/model_download.py.md
          - plugin_utils: embedding_studio/utils/plugin_utils.py.md
          - redis_utils: embedding_studio/utils/redis_utils.py.md
          - retry: embedding_studio/utils/retry.py.md
          - string_utils: embedding_studio/utils/string_utils.py.md
          - tasks: embedding_studio/utils/tasks.py.md
      - vectordb:
          - collection: embedding_studio/vectordb/collection.py.md
          - collection_base: embedding_studio/vectordb/collection_base.py.md
          - collection_info_cache: embedding_studio/vectordb/collection_info_cache.py.md
          - pgvector:
              - collection: embedding_studio/vectordb/pgvector/collection.py.md
              - db_model: embedding_studio/vectordb/pgvector/db_model.py.md
              - functions:
                  - advanced_similarity: embedding_studio/vectordb/pgvector/functions/advanced_similarity.py.md
                  - simple_similarity: embedding_studio/vectordb/pgvector/functions/simple_similarity.py.md
                  - where_combinations: embedding_studio/vectordb/pgvector/functions/where_combinations.py.md
              - optimization: embedding_studio/vectordb/pgvector/optimization.py.md
              - query_to_sql: embedding_studio/vectordb/pgvector/query_to_sql.py.md
              - vectordb: embedding_studio/vectordb/pgvector/vectordb.py.md
          - vectordb: embedding_studio/vectordb/vectordb.py.md
      - workers:
          - fine_tuning:
              - finetune_embedding: embedding_studio/workers/fine_tuning/finetune_embedding.py.md
              - finetune_embedding_one_param: embedding_studio/workers/fine_tuning/finetune_embedding_one_param.py.md
              - mocked_worker: embedding_studio/workers/fine_tuning/mocked_worker.py.md
              - prepare_data: embedding_studio/workers/fine_tuning/prepare_data.py.md
              - worker: embedding_studio/workers/fine_tuning/worker.py.md
          - improvement:
              - utils:
                  - handle_improvement: embedding_studio/workers/improvement/utils/handle_improvement.py.md
              - worker: embedding_studio/workers/improvement/worker.py.md
          - inference:
              - utils:
                  - deletion: embedding_studio/workers/inference/utils/deletion.py.md
                  - deployment: embedding_studio/workers/inference/utils/deployment.py.md
                  - file_locks: embedding_studio/workers/inference/utils/file_locks.py.md
                  - init_model_repo: embedding_studio/workers/inference/utils/init_model_repo.py.md
                  - prepare_for_triton: embedding_studio/workers/inference/utils/prepare_for_triton.py.md
              - worker: embedding_studio/workers/inference/worker.py.md
          - upsertion:
              - handlers:
                  - delete: embedding_studio/workers/upsertion/handlers/delete.py.md
                  - reindex: embedding_studio/workers/upsertion/handlers/reindex.py.md
                  - reindex_subtask: embedding_studio/workers/upsertion/handlers/reindex_subtask.py.md
                  - upsert: embedding_studio/workers/upsertion/handlers/upsert.py.md
              - utils:
                  - deployment: embedding_studio/workers/upsertion/utils/deployment.py.md
                  - reindex: embedding_studio/workers/upsertion/utils/reindex.py.md
                  - upsert: embedding_studio/workers/upsertion/utils/upsert.py.md
                  - upsertion_stages: embedding_studio/workers/upsertion/utils/upsertion_stages.py.md
              - worker: embedding_studio/workers/upsertion/worker.py.md
extra:
  generator: false
  social:
    - icon: fontawesome/brands/github
      link: https://github.com/EulerSearch/embedding_studio
  analytics:
    provider: google
    property: G-9CJ7KGX34N
copyright: © 2024 EulerSearch. All Rights Reserved.