databao-context-engine 0.6.1.dev1__tar.gz → 0.6.3__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/PKG-INFO +2 -1
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/pyproject.toml +7 -2
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/__init__.py +2 -2
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/build_sources/__init__.py +8 -1
- databao_context_engine-0.6.3/src/databao_context_engine/build_sources/build_runner.py +433 -0
- databao_context_engine-0.6.3/src/databao_context_engine/build_sources/build_service.py +212 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/build_sources/build_wiring.py +54 -21
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/build_sources/plugin_execution.py +0 -7
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/build_sources/types.py +7 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/cli/commands.py +1 -15
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/databao_context_domain_manager.py +40 -7
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/databao_context_engine.py +1 -0
- databao_context_engine-0.6.3/src/databao_context_engine/datasources/config_wizard.py +178 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/datasources/datasource_context.py +49 -11
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/introspection/property_extract.py +2 -5
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/descriptions/ollama.py +10 -1
- databao_context_engine-0.6.3/src/databao_context_engine/llm/descriptions/provider.py +45 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/service.py +0 -29
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/pluginlib/build_plugin.py +17 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/pluginlib/config.py +1 -1
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/athena/athena_introspector.py +23 -12
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/base_db_plugin.py +9 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/base_introspector.py +59 -9
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/bigquery/bigquery_introspector.py +12 -1
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/clickhouse/clickhouse_introspector.py +18 -1
- databao_context_engine-0.6.3/src/databao_context_engine/plugins/databases/context_enricher.py +156 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/databases_types.py +53 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/duckdb/duckdb_introspector.py +20 -2
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/introspection_model_builder.py +1 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/mssql/mssql_introspector.py +13 -4
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/mysql/mysql_introspector.py +27 -6
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/postgresql/postgresql_introspector.py +19 -4
- databao_context_engine-0.6.3/src/databao_context_engine/plugins/databases/sampling_scope.py +99 -0
- databao_context_engine-0.6.3/src/databao_context_engine/plugins/databases/sampling_scope_matcher.py +117 -0
- databao_context_engine-0.6.3/src/databao_context_engine/plugins/databases/snowflake/snowflake_introspector.py +640 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/sqlite/sqlite_introspector.py +9 -2
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/plugin_loader.py +4 -0
- databao_context_engine-0.6.3/src/databao_context_engine/progress/progress.py +137 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/project/init_project.py +14 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/project/layout.py +5 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/search_context/chunk_search_repository.py +60 -25
- databao_context_engine-0.6.3/src/databao_context_engine/search_context/search_runner.py +36 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/search_context/search_service.py +7 -7
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/search_context/search_wiring.py +11 -1
- databao_context_engine-0.6.3/src/databao_context_engine/services/chunk_embedding_service.py +98 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/services/factories.py +3 -6
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/services/models.py +0 -1
- databao_context_engine-0.6.3/src/databao_context_engine/services/persistence_service.py +161 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/storage/migrate.py +42 -3
- databao_context_engine-0.6.3/src/databao_context_engine/storage/migrations/V03__add_indexed_datasource_table.py +12 -0
- databao_context_engine-0.6.3/src/databao_context_engine/storage/migrations/V03__add_indexed_datasource_table.sql +32 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/storage/models.py +10 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/storage/repositories/chunk_repository.py +52 -7
- databao_context_engine-0.6.3/src/databao_context_engine/storage/repositories/datasource_context_repository.py +108 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/storage/repositories/embedding_repository.py +21 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/storage/repositories/factories.py +5 -0
- databao_context_engine-0.6.1.dev1/src/databao_context_engine/build_sources/build_runner.py +0 -222
- databao_context_engine-0.6.1.dev1/src/databao_context_engine/build_sources/build_service.py +0 -104
- databao_context_engine-0.6.1.dev1/src/databao_context_engine/datasources/config_wizard.py +0 -103
- databao_context_engine-0.6.1.dev1/src/databao_context_engine/llm/descriptions/provider.py +0 -10
- databao_context_engine-0.6.1.dev1/src/databao_context_engine/plugins/databases/snowflake/snowflake_introspector.py +0 -327
- databao_context_engine-0.6.1.dev1/src/databao_context_engine/services/chunk_embedding_service.py +0 -205
- databao_context_engine-0.6.1.dev1/src/databao_context_engine/services/persistence_service.py +0 -104
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/LICENSE.md +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/README.md +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/build_sources/export_results.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/cli/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/cli/datasources.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/cli/info.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/config/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/config/log_config.yaml +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/config/logging.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/datasources/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/datasources/check_config.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/datasources/datasource_discovery.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/datasources/execute_sql_query.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/datasources/sql_read_only.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/datasources/types.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/event_journal/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/event_journal/writer.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/generate_configs_schemas.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/init_domain.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/introspection/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/api.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/config.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/descriptions/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/embeddings/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/embeddings/ollama.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/embeddings/provider.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/errors.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/factory.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/install.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/prompts/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/prompts/ollama.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/prompts/provider.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/llm/runtime.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/main.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/mcp/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/mcp/mcp_runner.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/mcp/mcp_server.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/perf/core.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/pluginlib/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/pluginlib/plugin_utils.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/pluginlib/sql/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/pluginlib/sql/sql_types.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/athena/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/athena/athena_db_plugin.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/athena/config_file.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/bigquery/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/bigquery/bigquery_db_plugin.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/bigquery/config_file.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/clickhouse/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/clickhouse/clickhouse_db_plugin.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/clickhouse/config_file.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/database_chunker.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/duckdb/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/duckdb/config_file.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/duckdb/duckdb_db_plugin.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/introspection_scope.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/introspection_scope_matcher.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/mssql/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/mssql/config_file.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/mssql/mssql_db_plugin.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/mysql/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/mysql/config_file.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/mysql/mysql_db_plugin.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/postgresql/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/postgresql/config_file.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/postgresql/postgresql_db_plugin.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/snowflake/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/snowflake/config_file.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/snowflake/snowflake_db_plugin.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/sqlite/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/sqlite/config_file.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/databases/sqlite/sqlite_db_plugin.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/dbt/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/dbt/context_filtering.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/dbt/dbt_chunker.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/dbt/dbt_context_extractor.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/dbt/dbt_plugin.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/dbt/types.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/dbt/types_artifacts.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/duckdb_tools.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/files/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/files/docling_chunker.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/files/pdf_plugin.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/files/unstructured_files_plugin.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/resources/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/resources/parquet_chunker.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/resources/parquet_introspector.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/resources/parquet_plugin.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/plugins/resources/types.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/project/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/project/info.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/project/project_config.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/project/resources/examples/src/databases/example_postgres.yaml +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/project/resources/examples/src/files/documentation.md +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/project/resources/examples/src/files/notes.txt +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/py.typed +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/search_context/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/serialization/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/serialization/yaml.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/services/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/services/embedding_shard_resolver.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/services/table_name_policy.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/storage/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/storage/connection.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/storage/exceptions/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/storage/exceptions/exceptions.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/storage/migrations/V01__init.sql +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/storage/migrations/V02__add_keyword_index_text.sql +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/storage/repositories/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/storage/repositories/embedding_model_registry_repository.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/storage/transaction.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/system/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/system/properties.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/templating/__init__.py +0 -0
- {databao_context_engine-0.6.1.dev1 → databao_context_engine-0.6.3}/src/databao_context_engine/templating/renderer.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: databao-context-engine
|
|
3
|
-
Version: 0.6.
|
|
3
|
+
Version: 0.6.3
|
|
4
4
|
Summary: Semantic context for your LLMs — generated automatically
|
|
5
5
|
License-Expression: Apache-2.0 AND LicenseRef-Additional-Terms
|
|
6
6
|
License-File: LICENSE.md
|
|
@@ -13,6 +13,7 @@ Requires-Dist: pydantic>=2.12.4
|
|
|
13
13
|
Requires-Dist: jinja2>=3.1.6
|
|
14
14
|
Requires-Dist: sqlparse>=0.5.5
|
|
15
15
|
Requires-Dist: pyarrow>=19.0.1
|
|
16
|
+
Requires-Dist: xxhash>=3.6.0
|
|
16
17
|
Requires-Dist: pyathena>=3.25.0 ; extra == 'athena'
|
|
17
18
|
Requires-Dist: google-cloud-bigquery>=3.40.1 ; extra == 'bigquery'
|
|
18
19
|
Requires-Dist: clickhouse-connect>=0.10.0 ; extra == 'clickhouse'
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[project]
|
|
2
2
|
name = "databao-context-engine"
|
|
3
|
-
version = "0.6.
|
|
3
|
+
version = "0.6.3"
|
|
4
4
|
description = "Semantic context for your LLMs — generated automatically"
|
|
5
5
|
readme = "README.md"
|
|
6
6
|
requires-python = ">=3.11"
|
|
@@ -15,7 +15,8 @@ dependencies = [
|
|
|
15
15
|
"pydantic>=2.12.4",
|
|
16
16
|
"jinja2>=3.1.6",
|
|
17
17
|
"sqlparse>=0.5.5",
|
|
18
|
-
"pyarrow>=19.0.1"
|
|
18
|
+
"pyarrow>=19.0.1",
|
|
19
|
+
"xxhash>=3.6.0",
|
|
19
20
|
]
|
|
20
21
|
default-optional-dependency-keys = [
|
|
21
22
|
"mysql",
|
|
@@ -68,6 +69,10 @@ dev = [
|
|
|
68
69
|
"types-pymysql>=1.1.0.20250916",
|
|
69
70
|
"pytest-mock>=3.15.1",
|
|
70
71
|
"asyncpg-stubs>=0.31.1",
|
|
72
|
+
"streamlit>=1.54.0",
|
|
73
|
+
"pandas>=2.3.3",
|
|
74
|
+
"pandas-stubs>=3.0.0.260204",
|
|
75
|
+
"time-machine>=3.2.0",
|
|
71
76
|
]
|
|
72
77
|
|
|
73
78
|
[project.scripts]
|
|
@@ -2,6 +2,7 @@ from databao_context_engine.build_sources.types import (
|
|
|
2
2
|
BuildDatasourceResult,
|
|
3
3
|
DatasourceResult,
|
|
4
4
|
DatasourceStatus,
|
|
5
|
+
EnrichContextResult,
|
|
5
6
|
IndexDatasourceResult,
|
|
6
7
|
)
|
|
7
8
|
from databao_context_engine.databao_context_domain_manager import DatabaoContextDomainManager
|
|
@@ -71,7 +72,6 @@ from databao_context_engine.project.info import (
|
|
|
71
72
|
)
|
|
72
73
|
from databao_context_engine.project.init_project import InitDomainError, InitErrorReason
|
|
73
74
|
from databao_context_engine.search_context.search_service import ContextSearchMode
|
|
74
|
-
from databao_context_engine.services.chunk_embedding_service import ChunkEmbeddingMode
|
|
75
75
|
|
|
76
76
|
__all__ = [
|
|
77
77
|
"DatabaoContextEngine",
|
|
@@ -83,7 +83,6 @@ __all__ = [
|
|
|
83
83
|
"DatabaoContextDomainManager",
|
|
84
84
|
"UserInputCallback",
|
|
85
85
|
"Choice",
|
|
86
|
-
"ChunkEmbeddingMode",
|
|
87
86
|
"ContextSearchMode",
|
|
88
87
|
"DatasourceConnectionStatus",
|
|
89
88
|
"DatasourceType",
|
|
@@ -108,6 +107,7 @@ __all__ = [
|
|
|
108
107
|
"BuildDatasourceResult",
|
|
109
108
|
"DatasourceResult",
|
|
110
109
|
"DatasourceStatus",
|
|
110
|
+
"EnrichContextResult",
|
|
111
111
|
"IndexDatasourceResult",
|
|
112
112
|
"CheckDatasourceConnectionResult",
|
|
113
113
|
"AthenaConfigFile",
|
|
@@ -1,8 +1,13 @@
|
|
|
1
|
-
from databao_context_engine.build_sources.build_wiring import
|
|
1
|
+
from databao_context_engine.build_sources.build_wiring import (
|
|
2
|
+
build_all_datasources,
|
|
3
|
+
enrich_built_contexts,
|
|
4
|
+
index_built_contexts,
|
|
5
|
+
)
|
|
2
6
|
from databao_context_engine.build_sources.types import (
|
|
3
7
|
BuildDatasourceResult,
|
|
4
8
|
DatasourceResult,
|
|
5
9
|
DatasourceStatus,
|
|
10
|
+
EnrichContextResult,
|
|
6
11
|
IndexDatasourceResult,
|
|
7
12
|
)
|
|
8
13
|
|
|
@@ -13,4 +18,6 @@ __all__ = [
|
|
|
13
18
|
"BuildDatasourceResult",
|
|
14
19
|
"index_built_contexts",
|
|
15
20
|
"IndexDatasourceResult",
|
|
21
|
+
"enrich_built_contexts",
|
|
22
|
+
"EnrichContextResult",
|
|
16
23
|
]
|
|
@@ -0,0 +1,433 @@
|
|
|
1
|
+
import logging
|
|
2
|
+
from datetime import datetime
|
|
3
|
+
|
|
4
|
+
from pydantic import TypeAdapter
|
|
5
|
+
|
|
6
|
+
import databao_context_engine.perf.core as perf
|
|
7
|
+
from databao_context_engine.build_sources.build_service import BuildService
|
|
8
|
+
from databao_context_engine.build_sources.export_results import (
|
|
9
|
+
delete_all_results_file,
|
|
10
|
+
export_build_result,
|
|
11
|
+
)
|
|
12
|
+
from databao_context_engine.build_sources.types import (
|
|
13
|
+
BuildDatasourceResult,
|
|
14
|
+
DatasourceStatus,
|
|
15
|
+
EnrichContextResult,
|
|
16
|
+
IndexDatasourceResult,
|
|
17
|
+
)
|
|
18
|
+
from databao_context_engine.datasources.datasource_context import (
|
|
19
|
+
DatasourceContext,
|
|
20
|
+
hash_context_file,
|
|
21
|
+
read_datasource_type_from_context,
|
|
22
|
+
)
|
|
23
|
+
from databao_context_engine.datasources.datasource_discovery import discover_datasources, prepare_source
|
|
24
|
+
from databao_context_engine.datasources.types import PreparedConfig, PreparedDatasource
|
|
25
|
+
from databao_context_engine.pluginlib.build_plugin import DatasourceType
|
|
26
|
+
from databao_context_engine.plugins.plugin_loader import DatabaoContextPluginLoader
|
|
27
|
+
from databao_context_engine.progress.progress import ProgressCallback, ProgressEmitter, ProgressStep
|
|
28
|
+
from databao_context_engine.project.layout import ProjectLayout
|
|
29
|
+
|
|
30
|
+
logger = logging.getLogger(__name__)
|
|
31
|
+
|
|
32
|
+
|
|
33
|
+
def _build_step_plan(*, should_index: bool, should_enrich_context: bool) -> tuple[ProgressStep, ...]:
|
|
34
|
+
steps: list[ProgressStep] = []
|
|
35
|
+
|
|
36
|
+
steps.extend(BuildService.build_context_step_plan())
|
|
37
|
+
|
|
38
|
+
if should_enrich_context:
|
|
39
|
+
steps.extend(BuildService.enrich_context_step_plan())
|
|
40
|
+
|
|
41
|
+
if should_index:
|
|
42
|
+
steps.extend(BuildService.index_step_plan())
|
|
43
|
+
|
|
44
|
+
return tuple(steps)
|
|
45
|
+
|
|
46
|
+
|
|
47
|
+
@perf.perf_run(
|
|
48
|
+
operation="build",
|
|
49
|
+
attrs=lambda *, should_index, should_enrich_context, **_: {
|
|
50
|
+
"should_index": should_index,
|
|
51
|
+
"should_enrich_context": should_enrich_context,
|
|
52
|
+
},
|
|
53
|
+
)
|
|
54
|
+
@perf.perf_span("build.total")
|
|
55
|
+
def build(
|
|
56
|
+
*,
|
|
57
|
+
project_layout: ProjectLayout,
|
|
58
|
+
plugin_loader: DatabaoContextPluginLoader,
|
|
59
|
+
build_service: BuildService,
|
|
60
|
+
should_index: bool,
|
|
61
|
+
should_enrich_context: bool,
|
|
62
|
+
progress: ProgressCallback | None = None,
|
|
63
|
+
) -> list[BuildDatasourceResult]:
|
|
64
|
+
"""Build the context for all datasources in the project.
|
|
65
|
+
|
|
66
|
+
Unless you already have access to BuildService, this should not be called directly.
|
|
67
|
+
Instead, internal callers should go through the build_wiring module or directly use DatabaoContextProjectManager.build_context().
|
|
68
|
+
|
|
69
|
+
1) Load available plugins
|
|
70
|
+
2) Discover sources
|
|
71
|
+
3) For each source, call process_source
|
|
72
|
+
|
|
73
|
+
Returns:
|
|
74
|
+
A list of per-datasource build results.
|
|
75
|
+
"""
|
|
76
|
+
datasource_ids = discover_datasources(project_layout)
|
|
77
|
+
|
|
78
|
+
emitter = ProgressEmitter(progress)
|
|
79
|
+
|
|
80
|
+
if not datasource_ids:
|
|
81
|
+
logger.info("No sources discovered under %s", project_layout.src_dir)
|
|
82
|
+
emitter.operation_started(operation="build", total=0)
|
|
83
|
+
emitter.operation_finished(operation="build")
|
|
84
|
+
return []
|
|
85
|
+
|
|
86
|
+
emitter.operation_started(operation="build", total=len(datasource_ids))
|
|
87
|
+
|
|
88
|
+
results: list[BuildDatasourceResult] = []
|
|
89
|
+
failed = 0
|
|
90
|
+
skipped = 0
|
|
91
|
+
delete_all_results_file(project_layout)
|
|
92
|
+
for datasource_index, datasource_id in enumerate(datasource_ids, start=1):
|
|
93
|
+
emitter.datasource_started(
|
|
94
|
+
datasource_id=str(datasource_id),
|
|
95
|
+
index=datasource_index,
|
|
96
|
+
total=len(datasource_ids),
|
|
97
|
+
)
|
|
98
|
+
try:
|
|
99
|
+
result = _build_one_datasource(
|
|
100
|
+
project_layout=project_layout,
|
|
101
|
+
plugin_loader=plugin_loader,
|
|
102
|
+
build_service=build_service,
|
|
103
|
+
datasource_id=datasource_id,
|
|
104
|
+
should_index=should_index,
|
|
105
|
+
should_enrich_context=should_enrich_context,
|
|
106
|
+
progress=progress,
|
|
107
|
+
)
|
|
108
|
+
results.append(result)
|
|
109
|
+
if result.status == DatasourceStatus.SKIPPED:
|
|
110
|
+
skipped += 1
|
|
111
|
+
|
|
112
|
+
emitter.datasource_finished(
|
|
113
|
+
datasource_id=str(datasource_id),
|
|
114
|
+
index=datasource_index,
|
|
115
|
+
total=len(datasource_ids),
|
|
116
|
+
status=result.status.value,
|
|
117
|
+
error=result.error,
|
|
118
|
+
)
|
|
119
|
+
except Exception as e:
|
|
120
|
+
logger.debug(str(e), exc_info=True, stack_info=True)
|
|
121
|
+
logger.info(f"Failed to build source at ({datasource_id.relative_path_to_config_file()}): {str(e)}")
|
|
122
|
+
|
|
123
|
+
failed += 1
|
|
124
|
+
results.append(
|
|
125
|
+
BuildDatasourceResult(datasource_id=datasource_id, status=DatasourceStatus.FAILED, error=str(e))
|
|
126
|
+
)
|
|
127
|
+
emitter.datasource_finished(
|
|
128
|
+
datasource_id=str(datasource_id),
|
|
129
|
+
index=datasource_index,
|
|
130
|
+
total=len(datasource_ids),
|
|
131
|
+
status=DatasourceStatus.FAILED.value,
|
|
132
|
+
error=str(e),
|
|
133
|
+
)
|
|
134
|
+
|
|
135
|
+
ok = sum(1 for result in results if result.status == DatasourceStatus.OK)
|
|
136
|
+
logger.debug(
|
|
137
|
+
"Successfully built %d/%d datasources. %s",
|
|
138
|
+
ok,
|
|
139
|
+
len(datasource_ids),
|
|
140
|
+
f"Skipped {skipped}. Failed {failed}." if (skipped or failed) else "",
|
|
141
|
+
)
|
|
142
|
+
|
|
143
|
+
emitter.operation_finished(operation="build")
|
|
144
|
+
return results
|
|
145
|
+
|
|
146
|
+
|
|
147
|
+
@perf.perf_span(
|
|
148
|
+
"datasource.total",
|
|
149
|
+
datasource_id=lambda *, datasource_id, **_: str(datasource_id),
|
|
150
|
+
)
|
|
151
|
+
def _build_one_datasource(
|
|
152
|
+
*,
|
|
153
|
+
project_layout: ProjectLayout,
|
|
154
|
+
plugin_loader: DatabaoContextPluginLoader,
|
|
155
|
+
build_service: BuildService,
|
|
156
|
+
datasource_id,
|
|
157
|
+
should_index: bool,
|
|
158
|
+
should_enrich_context: bool,
|
|
159
|
+
progress: ProgressCallback | None = None,
|
|
160
|
+
) -> BuildDatasourceResult:
|
|
161
|
+
prepared_source = prepare_source(project_layout, datasource_id)
|
|
162
|
+
if not _is_datasource_enabled(prepared_source):
|
|
163
|
+
logger.info(f"Skipping disabled datasource {prepared_source.datasource_id.datasource_path}")
|
|
164
|
+
return BuildDatasourceResult(datasource_id=datasource_id, status=DatasourceStatus.SKIPPED)
|
|
165
|
+
|
|
166
|
+
perf.set_attribute("datasource_type", prepared_source.datasource_type.full_type)
|
|
167
|
+
|
|
168
|
+
logger.info(
|
|
169
|
+
f'Found datasource of type "{prepared_source.datasource_type.full_type}" with name {prepared_source.datasource_id.datasource_path}'
|
|
170
|
+
)
|
|
171
|
+
|
|
172
|
+
plugin = plugin_loader.get_plugin_for_datasource_type(prepared_source.datasource_type)
|
|
173
|
+
if plugin is None:
|
|
174
|
+
logger.warning(
|
|
175
|
+
"No plugin for '%s' (datasource=%s) — skipping.",
|
|
176
|
+
prepared_source.datasource_type.full_type,
|
|
177
|
+
prepared_source.datasource_id.relative_path_to_config_file(),
|
|
178
|
+
)
|
|
179
|
+
return BuildDatasourceResult(datasource_id=datasource_id, status=DatasourceStatus.SKIPPED)
|
|
180
|
+
|
|
181
|
+
ProgressEmitter(progress).datasource_step_plan_set(
|
|
182
|
+
datasource_id=str(datasource_id),
|
|
183
|
+
step_plan=_build_step_plan(
|
|
184
|
+
should_index=should_index,
|
|
185
|
+
should_enrich_context=should_enrich_context,
|
|
186
|
+
),
|
|
187
|
+
)
|
|
188
|
+
|
|
189
|
+
result = build_service.build_context(
|
|
190
|
+
prepared_source=prepared_source,
|
|
191
|
+
plugin=plugin,
|
|
192
|
+
progress=progress,
|
|
193
|
+
)
|
|
194
|
+
|
|
195
|
+
if should_enrich_context:
|
|
196
|
+
result = build_service.enrich_built_context(result, plugin, progress)
|
|
197
|
+
|
|
198
|
+
output_dir = project_layout.output_dir
|
|
199
|
+
context_file_path = export_build_result(output_dir, result)
|
|
200
|
+
|
|
201
|
+
perf.set_attribute("context_size_bytes", context_file_path.stat().st_size)
|
|
202
|
+
|
|
203
|
+
if should_index:
|
|
204
|
+
context_hash = hash_context_file(datasource_id=prepared_source.datasource_id, context_path=context_file_path)
|
|
205
|
+
build_service.index_built_context(
|
|
206
|
+
built_context=result, plugin=plugin, context_hash=context_hash, progress=progress
|
|
207
|
+
)
|
|
208
|
+
|
|
209
|
+
return BuildDatasourceResult(
|
|
210
|
+
datasource_id=datasource_id,
|
|
211
|
+
status=DatasourceStatus.OK,
|
|
212
|
+
datasource_type=DatasourceType(full_type=result.datasource_type),
|
|
213
|
+
context_built_at=datetime.now(),
|
|
214
|
+
context_file_path=context_file_path,
|
|
215
|
+
)
|
|
216
|
+
|
|
217
|
+
|
|
218
|
+
def _is_datasource_enabled(prepared_source: PreparedDatasource) -> bool:
|
|
219
|
+
if isinstance(prepared_source, PreparedConfig):
|
|
220
|
+
enabled_attribute = prepared_source.config.get("enabled", True)
|
|
221
|
+
return TypeAdapter(bool).validate_python(enabled_attribute)
|
|
222
|
+
|
|
223
|
+
return True
|
|
224
|
+
|
|
225
|
+
|
|
226
|
+
@perf.perf_run(
|
|
227
|
+
operation="enrich_context",
|
|
228
|
+
attrs=lambda *, should_index, **_: {
|
|
229
|
+
"should_index": should_index,
|
|
230
|
+
},
|
|
231
|
+
)
|
|
232
|
+
@perf.perf_span("enrich_context.total")
|
|
233
|
+
def run_enrich_context(
|
|
234
|
+
*,
|
|
235
|
+
project_layout: ProjectLayout,
|
|
236
|
+
plugin_loader: DatabaoContextPluginLoader,
|
|
237
|
+
build_service: BuildService,
|
|
238
|
+
contexts: list[DatasourceContext],
|
|
239
|
+
should_index: bool,
|
|
240
|
+
) -> list[EnrichContextResult]:
|
|
241
|
+
results: list[EnrichContextResult] = []
|
|
242
|
+
ok = 0
|
|
243
|
+
skipped = 0
|
|
244
|
+
failed = 0
|
|
245
|
+
|
|
246
|
+
for context in contexts:
|
|
247
|
+
try:
|
|
248
|
+
logger.info(f"Enriching context for datasource {context.datasource_id}")
|
|
249
|
+
|
|
250
|
+
result = _enrich_one_context(
|
|
251
|
+
project_layout=project_layout,
|
|
252
|
+
context=context,
|
|
253
|
+
plugin_loader=plugin_loader,
|
|
254
|
+
build_service=build_service,
|
|
255
|
+
should_index=should_index,
|
|
256
|
+
)
|
|
257
|
+
|
|
258
|
+
results.append(result)
|
|
259
|
+
if result.status == DatasourceStatus.OK:
|
|
260
|
+
ok += 1
|
|
261
|
+
elif result.status == DatasourceStatus.SKIPPED:
|
|
262
|
+
skipped += 1
|
|
263
|
+
except Exception as e:
|
|
264
|
+
logger.debug(str(e), exc_info=True, stack_info=True)
|
|
265
|
+
logger.info(f"Failed to enrich context for datasource ({context.datasource_id}): {str(e)}")
|
|
266
|
+
failed += 1
|
|
267
|
+
results.append(
|
|
268
|
+
EnrichContextResult(datasource_id=context.datasource_id, status=DatasourceStatus.FAILED, error=str(e))
|
|
269
|
+
)
|
|
270
|
+
|
|
271
|
+
logger.debug(
|
|
272
|
+
"Successfully indexed %d/%d datasource(s). %s",
|
|
273
|
+
ok,
|
|
274
|
+
len(contexts),
|
|
275
|
+
f"Skipped {skipped}. Failed {failed}." if (skipped or failed) else "",
|
|
276
|
+
)
|
|
277
|
+
|
|
278
|
+
return results
|
|
279
|
+
|
|
280
|
+
|
|
281
|
+
@perf.perf_span(
|
|
282
|
+
"datasource.total",
|
|
283
|
+
datasource_id=lambda *, context, **_: str(context.datasource_id),
|
|
284
|
+
)
|
|
285
|
+
def _enrich_one_context(
|
|
286
|
+
*,
|
|
287
|
+
project_layout: ProjectLayout,
|
|
288
|
+
context: DatasourceContext,
|
|
289
|
+
plugin_loader: DatabaoContextPluginLoader,
|
|
290
|
+
build_service: BuildService,
|
|
291
|
+
should_index: bool,
|
|
292
|
+
) -> EnrichContextResult:
|
|
293
|
+
perf.set_attribute("context_size_bytes", len(context.context.encode("utf-8")))
|
|
294
|
+
|
|
295
|
+
datasource_type = read_datasource_type_from_context(context)
|
|
296
|
+
perf.set_attribute("datasource_type", getattr(datasource_type, "full_type", datasource_type))
|
|
297
|
+
|
|
298
|
+
plugin = plugin_loader.get_plugin_for_datasource_type(datasource_type)
|
|
299
|
+
if plugin is None:
|
|
300
|
+
logger.warning(
|
|
301
|
+
"No plugin for datasource type '%s' — skipping context enrichment for datasource %s.",
|
|
302
|
+
getattr(datasource_type, "full_type", datasource_type),
|
|
303
|
+
context.datasource_id,
|
|
304
|
+
)
|
|
305
|
+
return EnrichContextResult(datasource_id=context.datasource_id, status=DatasourceStatus.SKIPPED)
|
|
306
|
+
|
|
307
|
+
enriched_context = build_service.enrich_datasource_context(context=context, plugin=plugin)
|
|
308
|
+
|
|
309
|
+
output_dir = project_layout.output_dir
|
|
310
|
+
context_file_path = export_build_result(output_dir, enriched_context)
|
|
311
|
+
|
|
312
|
+
if should_index:
|
|
313
|
+
context_hash = hash_context_file(datasource_id=context.datasource_id, context_path=context_file_path)
|
|
314
|
+
build_service.index_built_context(built_context=enriched_context, plugin=plugin, context_hash=context_hash)
|
|
315
|
+
|
|
316
|
+
return EnrichContextResult(
|
|
317
|
+
datasource_id=context.datasource_id,
|
|
318
|
+
status=DatasourceStatus.OK,
|
|
319
|
+
context_file_path=context_file_path,
|
|
320
|
+
)
|
|
321
|
+
|
|
322
|
+
|
|
323
|
+
@perf.perf_run(operation="index")
|
|
324
|
+
@perf.perf_span("index.total")
|
|
325
|
+
def run_indexing(
|
|
326
|
+
*,
|
|
327
|
+
project_layout: ProjectLayout,
|
|
328
|
+
plugin_loader: DatabaoContextPluginLoader,
|
|
329
|
+
build_service: BuildService,
|
|
330
|
+
contexts: list[DatasourceContext],
|
|
331
|
+
progress: ProgressCallback | None = None,
|
|
332
|
+
) -> list[IndexDatasourceResult]:
|
|
333
|
+
"""Index a list of built datasource contexts.
|
|
334
|
+
|
|
335
|
+
1) Load available plugins
|
|
336
|
+
2) Infer datasource type from context file
|
|
337
|
+
3) For each context, call index_built_context
|
|
338
|
+
|
|
339
|
+
Returns:
|
|
340
|
+
A list of per-context indexing results.
|
|
341
|
+
"""
|
|
342
|
+
emitter = ProgressEmitter(progress)
|
|
343
|
+
emitter.operation_started(operation="index", total=len(contexts))
|
|
344
|
+
|
|
345
|
+
results: list[IndexDatasourceResult] = []
|
|
346
|
+
ok = 0
|
|
347
|
+
skipped = 0
|
|
348
|
+
failed = 0
|
|
349
|
+
|
|
350
|
+
for context_index, context in enumerate(contexts, start=1):
|
|
351
|
+
emitter.datasource_started(
|
|
352
|
+
datasource_id=str(context.datasource_id),
|
|
353
|
+
index=context_index,
|
|
354
|
+
total=len(contexts),
|
|
355
|
+
)
|
|
356
|
+
try:
|
|
357
|
+
logger.info(f"Indexing datasource {context.datasource_id}")
|
|
358
|
+
|
|
359
|
+
result = _index_one_context(
|
|
360
|
+
context=context, plugin_loader=plugin_loader, build_service=build_service, progress=progress
|
|
361
|
+
)
|
|
362
|
+
|
|
363
|
+
results.append(result)
|
|
364
|
+
if result.status == DatasourceStatus.OK:
|
|
365
|
+
ok += 1
|
|
366
|
+
elif result.status == DatasourceStatus.SKIPPED:
|
|
367
|
+
skipped += 1
|
|
368
|
+
|
|
369
|
+
emitter.datasource_finished(
|
|
370
|
+
datasource_id=str(context.datasource_id),
|
|
371
|
+
index=context_index,
|
|
372
|
+
total=len(contexts),
|
|
373
|
+
status=result.status.value,
|
|
374
|
+
error=result.error,
|
|
375
|
+
)
|
|
376
|
+
except Exception as e:
|
|
377
|
+
logger.debug(str(e), exc_info=True, stack_info=True)
|
|
378
|
+
logger.info(f"Failed to build source at ({context.datasource_id}): {str(e)}")
|
|
379
|
+
failed += 1
|
|
380
|
+
results.append(
|
|
381
|
+
IndexDatasourceResult(datasource_id=context.datasource_id, status=DatasourceStatus.FAILED, error=str(e))
|
|
382
|
+
)
|
|
383
|
+
emitter.datasource_finished(
|
|
384
|
+
datasource_id=str(context.datasource_id),
|
|
385
|
+
index=context_index,
|
|
386
|
+
total=len(contexts),
|
|
387
|
+
status=DatasourceStatus.FAILED.value,
|
|
388
|
+
error=str(e),
|
|
389
|
+
)
|
|
390
|
+
|
|
391
|
+
logger.debug(
|
|
392
|
+
"Successfully indexed %d/%d datasource(s). %s",
|
|
393
|
+
ok,
|
|
394
|
+
len(contexts),
|
|
395
|
+
f"Skipped {skipped}. Failed {failed}." if (skipped or failed) else "",
|
|
396
|
+
)
|
|
397
|
+
|
|
398
|
+
emitter.operation_finished(operation="index")
|
|
399
|
+
return results
|
|
400
|
+
|
|
401
|
+
|
|
402
|
+
@perf.perf_span(
|
|
403
|
+
"datasource.total",
|
|
404
|
+
datasource_id=lambda *, context, **_: str(context.datasource_id),
|
|
405
|
+
)
|
|
406
|
+
def _index_one_context(
|
|
407
|
+
*,
|
|
408
|
+
context: DatasourceContext,
|
|
409
|
+
plugin_loader: DatabaoContextPluginLoader,
|
|
410
|
+
build_service: BuildService,
|
|
411
|
+
progress: ProgressCallback | None = None,
|
|
412
|
+
) -> IndexDatasourceResult:
|
|
413
|
+
perf.set_attribute("context_size_bytes", len(context.context.encode("utf-8")))
|
|
414
|
+
|
|
415
|
+
datasource_type = read_datasource_type_from_context(context)
|
|
416
|
+
perf.set_attribute("datasource_type", getattr(datasource_type, "full_type", datasource_type))
|
|
417
|
+
|
|
418
|
+
plugin = plugin_loader.get_plugin_for_datasource_type(datasource_type)
|
|
419
|
+
if plugin is None:
|
|
420
|
+
logger.warning(
|
|
421
|
+
"No plugin for datasource type '%s' — skipping indexing for %s.",
|
|
422
|
+
getattr(datasource_type, "full_type", datasource_type),
|
|
423
|
+
context.datasource_id,
|
|
424
|
+
)
|
|
425
|
+
return IndexDatasourceResult(datasource_id=context.datasource_id, status=DatasourceStatus.SKIPPED)
|
|
426
|
+
|
|
427
|
+
ProgressEmitter(progress).datasource_step_plan_set(
|
|
428
|
+
datasource_id=str(context.datasource_id),
|
|
429
|
+
step_plan=BuildService.index_step_plan(),
|
|
430
|
+
)
|
|
431
|
+
|
|
432
|
+
build_service.index_datasource_context(context=context, plugin=plugin, progress=progress)
|
|
433
|
+
return IndexDatasourceResult(datasource_id=context.datasource_id, status=DatasourceStatus.OK)
|