aiecs 1.0.1__py3-none-any.whl → 1.7.6__py3-none-any.whl
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.
Potentially problematic release.
This version of aiecs might be problematic. Click here for more details.
- aiecs/__init__.py +13 -16
- aiecs/__main__.py +7 -7
- aiecs/aiecs_client.py +269 -75
- aiecs/application/executors/operation_executor.py +79 -54
- aiecs/application/knowledge_graph/__init__.py +7 -0
- aiecs/application/knowledge_graph/builder/__init__.py +37 -0
- aiecs/application/knowledge_graph/builder/data_quality.py +302 -0
- aiecs/application/knowledge_graph/builder/data_reshaping.py +293 -0
- aiecs/application/knowledge_graph/builder/document_builder.py +369 -0
- aiecs/application/knowledge_graph/builder/graph_builder.py +490 -0
- aiecs/application/knowledge_graph/builder/import_optimizer.py +396 -0
- aiecs/application/knowledge_graph/builder/schema_inference.py +462 -0
- aiecs/application/knowledge_graph/builder/schema_mapping.py +563 -0
- aiecs/application/knowledge_graph/builder/structured_pipeline.py +1384 -0
- aiecs/application/knowledge_graph/builder/text_chunker.py +317 -0
- aiecs/application/knowledge_graph/extractors/__init__.py +27 -0
- aiecs/application/knowledge_graph/extractors/base.py +98 -0
- aiecs/application/knowledge_graph/extractors/llm_entity_extractor.py +422 -0
- aiecs/application/knowledge_graph/extractors/llm_relation_extractor.py +347 -0
- aiecs/application/knowledge_graph/extractors/ner_entity_extractor.py +241 -0
- aiecs/application/knowledge_graph/fusion/__init__.py +78 -0
- aiecs/application/knowledge_graph/fusion/ab_testing.py +395 -0
- aiecs/application/knowledge_graph/fusion/abbreviation_expander.py +327 -0
- aiecs/application/knowledge_graph/fusion/alias_index.py +597 -0
- aiecs/application/knowledge_graph/fusion/alias_matcher.py +384 -0
- aiecs/application/knowledge_graph/fusion/cache_coordinator.py +343 -0
- aiecs/application/knowledge_graph/fusion/entity_deduplicator.py +433 -0
- aiecs/application/knowledge_graph/fusion/entity_linker.py +511 -0
- aiecs/application/knowledge_graph/fusion/evaluation_dataset.py +240 -0
- aiecs/application/knowledge_graph/fusion/knowledge_fusion.py +632 -0
- aiecs/application/knowledge_graph/fusion/matching_config.py +489 -0
- aiecs/application/knowledge_graph/fusion/name_normalizer.py +352 -0
- aiecs/application/knowledge_graph/fusion/relation_deduplicator.py +183 -0
- aiecs/application/knowledge_graph/fusion/semantic_name_matcher.py +464 -0
- aiecs/application/knowledge_graph/fusion/similarity_pipeline.py +534 -0
- aiecs/application/knowledge_graph/pattern_matching/__init__.py +21 -0
- aiecs/application/knowledge_graph/pattern_matching/pattern_matcher.py +342 -0
- aiecs/application/knowledge_graph/pattern_matching/query_executor.py +366 -0
- aiecs/application/knowledge_graph/profiling/__init__.py +12 -0
- aiecs/application/knowledge_graph/profiling/query_plan_visualizer.py +195 -0
- aiecs/application/knowledge_graph/profiling/query_profiler.py +223 -0
- aiecs/application/knowledge_graph/reasoning/__init__.py +27 -0
- aiecs/application/knowledge_graph/reasoning/evidence_synthesis.py +341 -0
- aiecs/application/knowledge_graph/reasoning/inference_engine.py +500 -0
- aiecs/application/knowledge_graph/reasoning/logic_form_parser.py +163 -0
- aiecs/application/knowledge_graph/reasoning/logic_parser/__init__.py +79 -0
- aiecs/application/knowledge_graph/reasoning/logic_parser/ast_builder.py +513 -0
- aiecs/application/knowledge_graph/reasoning/logic_parser/ast_nodes.py +913 -0
- aiecs/application/knowledge_graph/reasoning/logic_parser/ast_validator.py +866 -0
- aiecs/application/knowledge_graph/reasoning/logic_parser/error_handler.py +475 -0
- aiecs/application/knowledge_graph/reasoning/logic_parser/parser.py +396 -0
- aiecs/application/knowledge_graph/reasoning/logic_parser/query_context.py +208 -0
- aiecs/application/knowledge_graph/reasoning/logic_query_integration.py +170 -0
- aiecs/application/knowledge_graph/reasoning/query_planner.py +855 -0
- aiecs/application/knowledge_graph/reasoning/reasoning_engine.py +518 -0
- aiecs/application/knowledge_graph/retrieval/__init__.py +27 -0
- aiecs/application/knowledge_graph/retrieval/query_intent_classifier.py +211 -0
- aiecs/application/knowledge_graph/retrieval/retrieval_strategies.py +592 -0
- aiecs/application/knowledge_graph/retrieval/strategy_types.py +23 -0
- aiecs/application/knowledge_graph/search/__init__.py +59 -0
- aiecs/application/knowledge_graph/search/hybrid_search.py +457 -0
- aiecs/application/knowledge_graph/search/reranker.py +293 -0
- aiecs/application/knowledge_graph/search/reranker_strategies.py +535 -0
- aiecs/application/knowledge_graph/search/text_similarity.py +392 -0
- aiecs/application/knowledge_graph/traversal/__init__.py +15 -0
- aiecs/application/knowledge_graph/traversal/enhanced_traversal.py +305 -0
- aiecs/application/knowledge_graph/traversal/path_scorer.py +271 -0
- aiecs/application/knowledge_graph/validators/__init__.py +13 -0
- aiecs/application/knowledge_graph/validators/relation_validator.py +239 -0
- aiecs/application/knowledge_graph/visualization/__init__.py +11 -0
- aiecs/application/knowledge_graph/visualization/graph_visualizer.py +313 -0
- aiecs/common/__init__.py +9 -0
- aiecs/common/knowledge_graph/__init__.py +17 -0
- aiecs/common/knowledge_graph/runnable.py +471 -0
- aiecs/config/__init__.py +20 -5
- aiecs/config/config.py +762 -31
- aiecs/config/graph_config.py +131 -0
- aiecs/config/tool_config.py +399 -0
- aiecs/core/__init__.py +29 -13
- aiecs/core/interface/__init__.py +2 -2
- aiecs/core/interface/execution_interface.py +22 -22
- aiecs/core/interface/storage_interface.py +37 -88
- aiecs/core/registry/__init__.py +31 -0
- aiecs/core/registry/service_registry.py +92 -0
- aiecs/domain/__init__.py +270 -1
- aiecs/domain/agent/__init__.py +191 -0
- aiecs/domain/agent/base_agent.py +3870 -0
- aiecs/domain/agent/exceptions.py +99 -0
- aiecs/domain/agent/graph_aware_mixin.py +569 -0
- aiecs/domain/agent/hybrid_agent.py +1435 -0
- aiecs/domain/agent/integration/__init__.py +29 -0
- aiecs/domain/agent/integration/context_compressor.py +216 -0
- aiecs/domain/agent/integration/context_engine_adapter.py +587 -0
- aiecs/domain/agent/integration/protocols.py +281 -0
- aiecs/domain/agent/integration/retry_policy.py +218 -0
- aiecs/domain/agent/integration/role_config.py +213 -0
- aiecs/domain/agent/knowledge_aware_agent.py +1892 -0
- aiecs/domain/agent/lifecycle.py +291 -0
- aiecs/domain/agent/llm_agent.py +692 -0
- aiecs/domain/agent/memory/__init__.py +12 -0
- aiecs/domain/agent/memory/conversation.py +1124 -0
- aiecs/domain/agent/migration/__init__.py +14 -0
- aiecs/domain/agent/migration/conversion.py +163 -0
- aiecs/domain/agent/migration/legacy_wrapper.py +86 -0
- aiecs/domain/agent/models.py +884 -0
- aiecs/domain/agent/observability.py +479 -0
- aiecs/domain/agent/persistence.py +449 -0
- aiecs/domain/agent/prompts/__init__.py +29 -0
- aiecs/domain/agent/prompts/builder.py +159 -0
- aiecs/domain/agent/prompts/formatters.py +187 -0
- aiecs/domain/agent/prompts/template.py +255 -0
- aiecs/domain/agent/registry.py +253 -0
- aiecs/domain/agent/tool_agent.py +444 -0
- aiecs/domain/agent/tools/__init__.py +15 -0
- aiecs/domain/agent/tools/schema_generator.py +364 -0
- aiecs/domain/community/__init__.py +155 -0
- aiecs/domain/community/agent_adapter.py +469 -0
- aiecs/domain/community/analytics.py +432 -0
- aiecs/domain/community/collaborative_workflow.py +648 -0
- aiecs/domain/community/communication_hub.py +634 -0
- aiecs/domain/community/community_builder.py +320 -0
- aiecs/domain/community/community_integration.py +796 -0
- aiecs/domain/community/community_manager.py +803 -0
- aiecs/domain/community/decision_engine.py +849 -0
- aiecs/domain/community/exceptions.py +231 -0
- aiecs/domain/community/models/__init__.py +33 -0
- aiecs/domain/community/models/community_models.py +234 -0
- aiecs/domain/community/resource_manager.py +461 -0
- aiecs/domain/community/shared_context_manager.py +589 -0
- aiecs/domain/context/__init__.py +40 -10
- aiecs/domain/context/context_engine.py +1910 -0
- aiecs/domain/context/conversation_models.py +87 -53
- aiecs/domain/context/graph_memory.py +582 -0
- aiecs/domain/execution/model.py +12 -4
- aiecs/domain/knowledge_graph/__init__.py +19 -0
- aiecs/domain/knowledge_graph/models/__init__.py +52 -0
- aiecs/domain/knowledge_graph/models/entity.py +148 -0
- aiecs/domain/knowledge_graph/models/evidence.py +178 -0
- aiecs/domain/knowledge_graph/models/inference_rule.py +184 -0
- aiecs/domain/knowledge_graph/models/path.py +171 -0
- aiecs/domain/knowledge_graph/models/path_pattern.py +171 -0
- aiecs/domain/knowledge_graph/models/query.py +261 -0
- aiecs/domain/knowledge_graph/models/query_plan.py +181 -0
- aiecs/domain/knowledge_graph/models/relation.py +202 -0
- aiecs/domain/knowledge_graph/schema/__init__.py +23 -0
- aiecs/domain/knowledge_graph/schema/entity_type.py +131 -0
- aiecs/domain/knowledge_graph/schema/graph_schema.py +253 -0
- aiecs/domain/knowledge_graph/schema/property_schema.py +143 -0
- aiecs/domain/knowledge_graph/schema/relation_type.py +163 -0
- aiecs/domain/knowledge_graph/schema/schema_manager.py +691 -0
- aiecs/domain/knowledge_graph/schema/type_enums.py +209 -0
- aiecs/domain/task/dsl_processor.py +172 -56
- aiecs/domain/task/model.py +20 -8
- aiecs/domain/task/task_context.py +27 -24
- aiecs/infrastructure/__init__.py +0 -2
- aiecs/infrastructure/graph_storage/__init__.py +11 -0
- aiecs/infrastructure/graph_storage/base.py +837 -0
- aiecs/infrastructure/graph_storage/batch_operations.py +458 -0
- aiecs/infrastructure/graph_storage/cache.py +424 -0
- aiecs/infrastructure/graph_storage/distributed.py +223 -0
- aiecs/infrastructure/graph_storage/error_handling.py +380 -0
- aiecs/infrastructure/graph_storage/graceful_degradation.py +294 -0
- aiecs/infrastructure/graph_storage/health_checks.py +378 -0
- aiecs/infrastructure/graph_storage/in_memory.py +1197 -0
- aiecs/infrastructure/graph_storage/index_optimization.py +446 -0
- aiecs/infrastructure/graph_storage/lazy_loading.py +431 -0
- aiecs/infrastructure/graph_storage/metrics.py +344 -0
- aiecs/infrastructure/graph_storage/migration.py +400 -0
- aiecs/infrastructure/graph_storage/pagination.py +483 -0
- aiecs/infrastructure/graph_storage/performance_monitoring.py +456 -0
- aiecs/infrastructure/graph_storage/postgres.py +1563 -0
- aiecs/infrastructure/graph_storage/property_storage.py +353 -0
- aiecs/infrastructure/graph_storage/protocols.py +76 -0
- aiecs/infrastructure/graph_storage/query_optimizer.py +642 -0
- aiecs/infrastructure/graph_storage/schema_cache.py +290 -0
- aiecs/infrastructure/graph_storage/sqlite.py +1373 -0
- aiecs/infrastructure/graph_storage/streaming.py +487 -0
- aiecs/infrastructure/graph_storage/tenant.py +412 -0
- aiecs/infrastructure/messaging/celery_task_manager.py +92 -54
- aiecs/infrastructure/messaging/websocket_manager.py +51 -35
- aiecs/infrastructure/monitoring/__init__.py +22 -0
- aiecs/infrastructure/monitoring/executor_metrics.py +45 -11
- aiecs/infrastructure/monitoring/global_metrics_manager.py +212 -0
- aiecs/infrastructure/monitoring/structured_logger.py +3 -7
- aiecs/infrastructure/monitoring/tracing_manager.py +63 -35
- aiecs/infrastructure/persistence/__init__.py +14 -1
- aiecs/infrastructure/persistence/context_engine_client.py +184 -0
- aiecs/infrastructure/persistence/database_manager.py +67 -43
- aiecs/infrastructure/persistence/file_storage.py +180 -103
- aiecs/infrastructure/persistence/redis_client.py +74 -21
- aiecs/llm/__init__.py +73 -25
- aiecs/llm/callbacks/__init__.py +11 -0
- aiecs/llm/{custom_callbacks.py → callbacks/custom_callbacks.py} +26 -19
- aiecs/llm/client_factory.py +224 -36
- aiecs/llm/client_resolver.py +155 -0
- aiecs/llm/clients/__init__.py +38 -0
- aiecs/llm/clients/base_client.py +324 -0
- aiecs/llm/clients/google_function_calling_mixin.py +457 -0
- aiecs/llm/clients/googleai_client.py +241 -0
- aiecs/llm/clients/openai_client.py +158 -0
- aiecs/llm/clients/openai_compatible_mixin.py +367 -0
- aiecs/llm/clients/vertex_client.py +897 -0
- aiecs/llm/clients/xai_client.py +201 -0
- aiecs/llm/config/__init__.py +51 -0
- aiecs/llm/config/config_loader.py +272 -0
- aiecs/llm/config/config_validator.py +206 -0
- aiecs/llm/config/model_config.py +143 -0
- aiecs/llm/protocols.py +149 -0
- aiecs/llm/utils/__init__.py +10 -0
- aiecs/llm/utils/validate_config.py +89 -0
- aiecs/main.py +140 -121
- aiecs/scripts/aid/VERSION_MANAGEMENT.md +138 -0
- aiecs/scripts/aid/__init__.py +19 -0
- aiecs/scripts/aid/module_checker.py +499 -0
- aiecs/scripts/aid/version_manager.py +235 -0
- aiecs/scripts/{DEPENDENCY_SYSTEM_SUMMARY.md → dependance_check/DEPENDENCY_SYSTEM_SUMMARY.md} +1 -0
- aiecs/scripts/{README_DEPENDENCY_CHECKER.md → dependance_check/README_DEPENDENCY_CHECKER.md} +1 -0
- aiecs/scripts/dependance_check/__init__.py +15 -0
- aiecs/scripts/dependance_check/dependency_checker.py +1835 -0
- aiecs/scripts/{dependency_fixer.py → dependance_check/dependency_fixer.py} +192 -90
- aiecs/scripts/{download_nlp_data.py → dependance_check/download_nlp_data.py} +203 -71
- aiecs/scripts/dependance_patch/__init__.py +7 -0
- aiecs/scripts/dependance_patch/fix_weasel/__init__.py +11 -0
- aiecs/scripts/{fix_weasel_validator.py → dependance_patch/fix_weasel/fix_weasel_validator.py} +21 -14
- aiecs/scripts/{patch_weasel_library.sh → dependance_patch/fix_weasel/patch_weasel_library.sh} +1 -1
- aiecs/scripts/knowledge_graph/__init__.py +3 -0
- aiecs/scripts/knowledge_graph/run_threshold_experiments.py +212 -0
- aiecs/scripts/migrations/multi_tenancy/README.md +142 -0
- aiecs/scripts/tools_develop/README.md +671 -0
- aiecs/scripts/tools_develop/README_CONFIG_CHECKER.md +273 -0
- aiecs/scripts/tools_develop/TOOLS_CONFIG_GUIDE.md +1287 -0
- aiecs/scripts/tools_develop/TOOL_AUTO_DISCOVERY.md +234 -0
- aiecs/scripts/tools_develop/__init__.py +21 -0
- aiecs/scripts/tools_develop/check_all_tools_config.py +548 -0
- aiecs/scripts/tools_develop/check_type_annotations.py +257 -0
- aiecs/scripts/tools_develop/pre-commit-schema-coverage.sh +66 -0
- aiecs/scripts/tools_develop/schema_coverage.py +511 -0
- aiecs/scripts/tools_develop/validate_tool_schemas.py +475 -0
- aiecs/scripts/tools_develop/verify_executor_config_fix.py +98 -0
- aiecs/scripts/tools_develop/verify_tools.py +352 -0
- aiecs/tasks/__init__.py +0 -1
- aiecs/tasks/worker.py +115 -47
- aiecs/tools/__init__.py +194 -72
- aiecs/tools/apisource/__init__.py +99 -0
- aiecs/tools/apisource/intelligence/__init__.py +19 -0
- aiecs/tools/apisource/intelligence/data_fusion.py +632 -0
- aiecs/tools/apisource/intelligence/query_analyzer.py +417 -0
- aiecs/tools/apisource/intelligence/search_enhancer.py +385 -0
- aiecs/tools/apisource/monitoring/__init__.py +9 -0
- aiecs/tools/apisource/monitoring/metrics.py +330 -0
- aiecs/tools/apisource/providers/__init__.py +112 -0
- aiecs/tools/apisource/providers/base.py +671 -0
- aiecs/tools/apisource/providers/census.py +397 -0
- aiecs/tools/apisource/providers/fred.py +535 -0
- aiecs/tools/apisource/providers/newsapi.py +409 -0
- aiecs/tools/apisource/providers/worldbank.py +352 -0
- aiecs/tools/apisource/reliability/__init__.py +12 -0
- aiecs/tools/apisource/reliability/error_handler.py +363 -0
- aiecs/tools/apisource/reliability/fallback_strategy.py +376 -0
- aiecs/tools/apisource/tool.py +832 -0
- aiecs/tools/apisource/utils/__init__.py +9 -0
- aiecs/tools/apisource/utils/validators.py +334 -0
- aiecs/tools/base_tool.py +415 -21
- aiecs/tools/docs/__init__.py +121 -0
- aiecs/tools/docs/ai_document_orchestrator.py +607 -0
- aiecs/tools/docs/ai_document_writer_orchestrator.py +2350 -0
- aiecs/tools/docs/content_insertion_tool.py +1320 -0
- aiecs/tools/docs/document_creator_tool.py +1323 -0
- aiecs/tools/docs/document_layout_tool.py +1160 -0
- aiecs/tools/docs/document_parser_tool.py +1011 -0
- aiecs/tools/docs/document_writer_tool.py +1829 -0
- aiecs/tools/knowledge_graph/__init__.py +17 -0
- aiecs/tools/knowledge_graph/graph_reasoning_tool.py +807 -0
- aiecs/tools/knowledge_graph/graph_search_tool.py +944 -0
- aiecs/tools/knowledge_graph/kg_builder_tool.py +524 -0
- aiecs/tools/langchain_adapter.py +300 -138
- aiecs/tools/schema_generator.py +455 -0
- aiecs/tools/search_tool/__init__.py +100 -0
- aiecs/tools/search_tool/analyzers.py +581 -0
- aiecs/tools/search_tool/cache.py +264 -0
- aiecs/tools/search_tool/constants.py +128 -0
- aiecs/tools/search_tool/context.py +224 -0
- aiecs/tools/search_tool/core.py +778 -0
- aiecs/tools/search_tool/deduplicator.py +119 -0
- aiecs/tools/search_tool/error_handler.py +242 -0
- aiecs/tools/search_tool/metrics.py +343 -0
- aiecs/tools/search_tool/rate_limiter.py +172 -0
- aiecs/tools/search_tool/schemas.py +275 -0
- aiecs/tools/statistics/__init__.py +80 -0
- aiecs/tools/statistics/ai_data_analysis_orchestrator.py +646 -0
- aiecs/tools/statistics/ai_insight_generator_tool.py +508 -0
- aiecs/tools/statistics/ai_report_orchestrator_tool.py +684 -0
- aiecs/tools/statistics/data_loader_tool.py +555 -0
- aiecs/tools/statistics/data_profiler_tool.py +638 -0
- aiecs/tools/statistics/data_transformer_tool.py +580 -0
- aiecs/tools/statistics/data_visualizer_tool.py +498 -0
- aiecs/tools/statistics/model_trainer_tool.py +507 -0
- aiecs/tools/statistics/statistical_analyzer_tool.py +472 -0
- aiecs/tools/task_tools/__init__.py +49 -36
- aiecs/tools/task_tools/chart_tool.py +200 -184
- aiecs/tools/task_tools/classfire_tool.py +268 -267
- aiecs/tools/task_tools/image_tool.py +175 -131
- aiecs/tools/task_tools/office_tool.py +226 -146
- aiecs/tools/task_tools/pandas_tool.py +477 -121
- aiecs/tools/task_tools/report_tool.py +390 -142
- aiecs/tools/task_tools/research_tool.py +149 -79
- aiecs/tools/task_tools/scraper_tool.py +339 -145
- aiecs/tools/task_tools/stats_tool.py +448 -209
- aiecs/tools/temp_file_manager.py +26 -24
- aiecs/tools/tool_executor/__init__.py +18 -16
- aiecs/tools/tool_executor/tool_executor.py +364 -52
- aiecs/utils/LLM_output_structor.py +74 -48
- aiecs/utils/__init__.py +14 -3
- aiecs/utils/base_callback.py +0 -3
- aiecs/utils/cache_provider.py +696 -0
- aiecs/utils/execution_utils.py +50 -31
- aiecs/utils/prompt_loader.py +1 -0
- aiecs/utils/token_usage_repository.py +37 -11
- aiecs/ws/socket_server.py +14 -4
- {aiecs-1.0.1.dist-info → aiecs-1.7.6.dist-info}/METADATA +52 -15
- aiecs-1.7.6.dist-info/RECORD +337 -0
- aiecs-1.7.6.dist-info/entry_points.txt +13 -0
- aiecs/config/registry.py +0 -19
- aiecs/domain/context/content_engine.py +0 -982
- aiecs/llm/base_client.py +0 -99
- aiecs/llm/openai_client.py +0 -125
- aiecs/llm/vertex_client.py +0 -186
- aiecs/llm/xai_client.py +0 -184
- aiecs/scripts/dependency_checker.py +0 -857
- aiecs/scripts/quick_dependency_check.py +0 -269
- aiecs/tools/task_tools/search_api.py +0 -7
- aiecs-1.0.1.dist-info/RECORD +0 -90
- aiecs-1.0.1.dist-info/entry_points.txt +0 -7
- /aiecs/scripts/{setup_nlp_data.sh → dependance_check/setup_nlp_data.sh} +0 -0
- /aiecs/scripts/{README_WEASEL_PATCH.md → dependance_patch/fix_weasel/README_WEASEL_PATCH.md} +0 -0
- /aiecs/scripts/{fix_weasel_validator.sh → dependance_patch/fix_weasel/fix_weasel_validator.sh} +0 -0
- /aiecs/scripts/{run_weasel_patch.sh → dependance_patch/fix_weasel/run_weasel_patch.sh} +0 -0
- {aiecs-1.0.1.dist-info → aiecs-1.7.6.dist-info}/WHEEL +0 -0
- {aiecs-1.0.1.dist-info → aiecs-1.7.6.dist-info}/licenses/LICENSE +0 -0
- {aiecs-1.0.1.dist-info → aiecs-1.7.6.dist-info}/top_level.txt +0 -0
|
@@ -0,0 +1,1287 @@
|
|
|
1
|
+
# AIECS 工具配置指南
|
|
2
|
+
|
|
3
|
+
本文档列出了所有工具的配置参数,方便开发者快速配置和使用。
|
|
4
|
+
|
|
5
|
+
生成时间: check_all_tools_config.py
|
|
6
|
+
|
|
7
|
+
## 目录
|
|
8
|
+
|
|
9
|
+
1. [AIDataAnalysisOrchestrator](#aidataanalysisorchestrator)
|
|
10
|
+
2. [AIDocumentOrchestrator](#aidocumentorchestrator)
|
|
11
|
+
3. [AIDocumentWriterOrchestrator](#aidocumentwriterorchestrator)
|
|
12
|
+
4. [AIInsightGeneratorTool](#aiinsightgeneratortool)
|
|
13
|
+
5. [AIReportOrchestratorTool](#aireportorchestratortool)
|
|
14
|
+
6. [APISourceTool](#apisourcetool)
|
|
15
|
+
7. [ChartTool](#charttool)
|
|
16
|
+
8. [ClassifierTool](#classifiertool)
|
|
17
|
+
9. [ContentInsertionTool](#contentinsertiontool)
|
|
18
|
+
10. [DataLoaderTool](#dataloadertool)
|
|
19
|
+
11. [DataProfilerTool](#dataprofilertool)
|
|
20
|
+
12. [DataTransformerTool](#datatransformertool)
|
|
21
|
+
13. [DataVisualizerTool](#datavisualizertool)
|
|
22
|
+
14. [DocumentCreatorTool](#documentcreatortool)
|
|
23
|
+
15. [DocumentLayoutTool](#documentlayouttool)
|
|
24
|
+
16. [DocumentParserTool](#documentparsertool)
|
|
25
|
+
17. [DocumentWriterTool](#documentwritertool)
|
|
26
|
+
18. [GraphReasoningTool](#graphreasoningtool)
|
|
27
|
+
19. [GraphSearchTool](#graphsearchtool)
|
|
28
|
+
20. [ImageTool](#imagetool)
|
|
29
|
+
21. [KnowledgeGraphBuilderTool](#knowledgegraphbuildertool)
|
|
30
|
+
22. [ModelTrainerTool](#modeltrainertool)
|
|
31
|
+
23. [OfficeTool](#officetool)
|
|
32
|
+
24. [PandasTool](#pandastool)
|
|
33
|
+
25. [ReportTool](#reporttool)
|
|
34
|
+
26. [ResearchTool](#researchtool)
|
|
35
|
+
27. [ScraperTool](#scrapertool)
|
|
36
|
+
28. [StatisticalAnalyzerTool](#statisticalanalyzertool)
|
|
37
|
+
29. [StatsTool](#statstool)
|
|
38
|
+
|
|
39
|
+
---
|
|
40
|
+
|
|
41
|
+
## AIDataAnalysisOrchestrator
|
|
42
|
+
|
|
43
|
+
**配置字段数**: 6 (必需: 6, 可选: 0)
|
|
44
|
+
|
|
45
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
46
|
+
|--------|------|------|--------|------|
|
|
47
|
+
| `Example` | AI_DATA_ORCHESTRATOR_DEFAULT_MODE -> default_mode | ✅ | `-` | - |
|
|
48
|
+
| `default_ai_provider` | str | ✅ | `"openai"` | Default AI provider to use |
|
|
49
|
+
| `default_mode` | str | ✅ | `"exploratory"` | Default analysis mode to use |
|
|
50
|
+
| `enable_auto_workflow` | bool | ✅ | `-` | - |
|
|
51
|
+
| `enable_caching` | bool | ✅ | `True` | Whether to enable result caching |
|
|
52
|
+
| `max_iterations` | int | ✅ | `10` | Maximum number of analysis iterations |
|
|
53
|
+
|
|
54
|
+
### 配置示例
|
|
55
|
+
|
|
56
|
+
```python
|
|
57
|
+
aidataanalysisorchestrator_config = {
|
|
58
|
+
'Example': "your_Example",
|
|
59
|
+
'default_ai_provider': "openai", # Default AI provider to use
|
|
60
|
+
'default_mode': "exploratory", # Default analysis mode to use
|
|
61
|
+
'enable_auto_workflow': False,
|
|
62
|
+
'enable_caching': True, # Whether to enable result caching
|
|
63
|
+
'max_iterations': 10, # Maximum number of analysis iterations
|
|
64
|
+
}
|
|
65
|
+
```
|
|
66
|
+
|
|
67
|
+
### 环境变量映射
|
|
68
|
+
|
|
69
|
+
```bash
|
|
70
|
+
export AIDATAANALYSIS_ORCHESTRATOR_EXAMPLE=<value>
|
|
71
|
+
export AIDATAANALYSIS_ORCHESTRATOR_DEFAULT_AI_PROVIDER=<value>
|
|
72
|
+
export AIDATAANALYSIS_ORCHESTRATOR_DEFAULT_MODE=<value>
|
|
73
|
+
export AIDATAANALYSIS_ORCHESTRATOR_ENABLE_AUTO_WORKFLOW=<value>
|
|
74
|
+
export AIDATAANALYSIS_ORCHESTRATOR_ENABLE_CACHING=<value>
|
|
75
|
+
export AIDATAANALYSIS_ORCHESTRATOR_MAX_ITERATIONS=<value>
|
|
76
|
+
```
|
|
77
|
+
|
|
78
|
+
---
|
|
79
|
+
|
|
80
|
+
## AIDocumentOrchestrator
|
|
81
|
+
|
|
82
|
+
**配置字段数**: 7 (必需: 7, 可选: 0)
|
|
83
|
+
|
|
84
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
85
|
+
|--------|------|------|--------|------|
|
|
86
|
+
| `Example` | AI_DOC_ORCHESTRATOR_DEFAULT_AI_PROVIDER -> default_ai_provider | ✅ | `-` | - |
|
|
87
|
+
| `default_ai_provider` | str | ✅ | `"openai"` | Default AI provider to use |
|
|
88
|
+
| `default_temperature` | float | ✅ | `0.1` | Default temperature for AI model |
|
|
89
|
+
| `max_chunk_size` | int | ✅ | `4000` | Maximum chunk size for AI processing |
|
|
90
|
+
| `max_concurrent_requests` | int | ✅ | `5` | Maximum concurrent AI requests |
|
|
91
|
+
| `max_tokens` | int | ✅ | `2000` | Maximum tokens for AI response |
|
|
92
|
+
| `timeout` | int | ✅ | `60` | Timeout in seconds for AI operations |
|
|
93
|
+
|
|
94
|
+
### 配置示例
|
|
95
|
+
|
|
96
|
+
```python
|
|
97
|
+
aidocumentorchestrator_config = {
|
|
98
|
+
'Example': "your_Example",
|
|
99
|
+
'default_ai_provider': "openai", # Default AI provider to use
|
|
100
|
+
'default_temperature': 0.1, # Default temperature for AI model
|
|
101
|
+
'max_chunk_size': 4000, # Maximum chunk size for AI processing
|
|
102
|
+
'max_concurrent_requests': 5, # Maximum concurrent AI requests
|
|
103
|
+
'max_tokens': 2000, # Maximum tokens for AI response
|
|
104
|
+
'timeout': 60, # Timeout in seconds for AI operations
|
|
105
|
+
}
|
|
106
|
+
```
|
|
107
|
+
|
|
108
|
+
### 环境变量映射
|
|
109
|
+
|
|
110
|
+
```bash
|
|
111
|
+
export AIDOCUMENT_ORCHESTRATOR_EXAMPLE=<value>
|
|
112
|
+
export AIDOCUMENT_ORCHESTRATOR_DEFAULT_AI_PROVIDER=<value>
|
|
113
|
+
export AIDOCUMENT_ORCHESTRATOR_DEFAULT_TEMPERATURE=<value>
|
|
114
|
+
export AIDOCUMENT_ORCHESTRATOR_MAX_CHUNK_SIZE=<value>
|
|
115
|
+
export AIDOCUMENT_ORCHESTRATOR_MAX_CONCURRENT_REQUESTS=<value>
|
|
116
|
+
export AIDOCUMENT_ORCHESTRATOR_MAX_TOKENS=<value>
|
|
117
|
+
export AIDOCUMENT_ORCHESTRATOR_TIMEOUT=<value>
|
|
118
|
+
```
|
|
119
|
+
|
|
120
|
+
---
|
|
121
|
+
|
|
122
|
+
## AIDocumentWriterOrchestrator
|
|
123
|
+
|
|
124
|
+
**配置字段数**: 10 (必需: 10, 可选: 0)
|
|
125
|
+
|
|
126
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
127
|
+
|--------|------|------|--------|------|
|
|
128
|
+
| `auto_backup_on_ai_write` | bool | ✅ | `-` | - |
|
|
129
|
+
| `default_ai_provider` | str | ✅ | `"openai"` | Default AI provider to use |
|
|
130
|
+
| `default_temperature` | float | ✅ | `0.3` | Default temperature for AI model |
|
|
131
|
+
| `enable_content_review` | bool | ✅ | `True` | Whether to enable content review |
|
|
132
|
+
| `enable_draft_mode` | bool | ✅ | `True` | Whether to enable draft mode |
|
|
133
|
+
| `max_concurrent_writes` | int | ✅ | `5` | Maximum concurrent write operations |
|
|
134
|
+
| `max_content_length` | int | ✅ | `-` | - |
|
|
135
|
+
| `max_tokens` | int | ✅ | `4000` | Maximum tokens for AI response |
|
|
136
|
+
| `temp_dir` | str | ✅ | `-` | - |
|
|
137
|
+
| `timeout` | int | ✅ | `60` | Timeout in seconds for AI operations |
|
|
138
|
+
|
|
139
|
+
### 配置示例
|
|
140
|
+
|
|
141
|
+
```python
|
|
142
|
+
aidocumentwriterorchestrator_config = {
|
|
143
|
+
'auto_backup_on_ai_write': False,
|
|
144
|
+
'default_ai_provider': "openai", # Default AI provider to use
|
|
145
|
+
'default_temperature': 0.3, # Default temperature for AI model
|
|
146
|
+
'enable_content_review': True, # Whether to enable content review
|
|
147
|
+
'enable_draft_mode': True, # Whether to enable draft mode
|
|
148
|
+
'max_concurrent_writes': 5, # Maximum concurrent write operations
|
|
149
|
+
'max_content_length': 0,
|
|
150
|
+
'max_tokens': 4000, # Maximum tokens for AI response
|
|
151
|
+
'temp_dir': "your_temp_dir",
|
|
152
|
+
'timeout': 60, # Timeout in seconds for AI operations
|
|
153
|
+
}
|
|
154
|
+
```
|
|
155
|
+
|
|
156
|
+
### 环境变量映射
|
|
157
|
+
|
|
158
|
+
```bash
|
|
159
|
+
export AIDOCUMENTWRITER_ORCHESTRATOR_AUTO_BACKUP_ON_AI_WRITE=<value>
|
|
160
|
+
export AIDOCUMENTWRITER_ORCHESTRATOR_DEFAULT_AI_PROVIDER=<value>
|
|
161
|
+
export AIDOCUMENTWRITER_ORCHESTRATOR_DEFAULT_TEMPERATURE=<value>
|
|
162
|
+
export AIDOCUMENTWRITER_ORCHESTRATOR_ENABLE_CONTENT_REVIEW=<value>
|
|
163
|
+
export AIDOCUMENTWRITER_ORCHESTRATOR_ENABLE_DRAFT_MODE=<value>
|
|
164
|
+
export AIDOCUMENTWRITER_ORCHESTRATOR_MAX_CONCURRENT_WRITES=<value>
|
|
165
|
+
export AIDOCUMENTWRITER_ORCHESTRATOR_MAX_CONTENT_LENGTH=<value>
|
|
166
|
+
export AIDOCUMENTWRITER_ORCHESTRATOR_MAX_TOKENS=<value>
|
|
167
|
+
export AIDOCUMENTWRITER_ORCHESTRATOR_TEMP_DIR=<value>
|
|
168
|
+
export AIDOCUMENTWRITER_ORCHESTRATOR_TIMEOUT=<value>
|
|
169
|
+
```
|
|
170
|
+
|
|
171
|
+
---
|
|
172
|
+
|
|
173
|
+
## AIInsightGeneratorTool
|
|
174
|
+
|
|
175
|
+
**配置字段数**: 5 (必需: 5, 可选: 0)
|
|
176
|
+
|
|
177
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
178
|
+
|--------|------|------|--------|------|
|
|
179
|
+
| `Example` | AI_INSIGHT_GENERATOR_MIN_CONFIDENCE -> min_confidence | ✅ | `-` | - |
|
|
180
|
+
| `anomaly_std_threshold` | float | ✅ | `-` | - |
|
|
181
|
+
| `correlation_threshold` | float | ✅ | `-` | - |
|
|
182
|
+
| `enable_reasoning` | bool | ✅ | `-` | - |
|
|
183
|
+
| `min_confidence` | float | ✅ | `-` | - |
|
|
184
|
+
|
|
185
|
+
### 配置示例
|
|
186
|
+
|
|
187
|
+
```python
|
|
188
|
+
aiinsightgeneratortool_config = {
|
|
189
|
+
'Example': None,
|
|
190
|
+
'anomaly_std_threshold': 0.0,
|
|
191
|
+
'correlation_threshold': 0.0,
|
|
192
|
+
'enable_reasoning': False,
|
|
193
|
+
'min_confidence': 0.0,
|
|
194
|
+
}
|
|
195
|
+
```
|
|
196
|
+
|
|
197
|
+
### 环境变量映射
|
|
198
|
+
|
|
199
|
+
```bash
|
|
200
|
+
export AIINSIGHTGENERATOR_TOOL_EXAMPLE=<value>
|
|
201
|
+
export AIINSIGHTGENERATOR_TOOL_ANOMALY_STD_THRESHOLD=<value>
|
|
202
|
+
export AIINSIGHTGENERATOR_TOOL_CORRELATION_THRESHOLD=<value>
|
|
203
|
+
export AIINSIGHTGENERATOR_TOOL_ENABLE_REASONING=<value>
|
|
204
|
+
export AIINSIGHTGENERATOR_TOOL_MIN_CONFIDENCE=<value>
|
|
205
|
+
```
|
|
206
|
+
|
|
207
|
+
---
|
|
208
|
+
|
|
209
|
+
## AIReportOrchestratorTool
|
|
210
|
+
|
|
211
|
+
**配置字段数**: 7 (必需: 7, 可选: 0)
|
|
212
|
+
|
|
213
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
214
|
+
|--------|------|------|--------|------|
|
|
215
|
+
| `Example` | AI_REPORT_ORCHESTRATOR_DEFAULT_REPORT_TYPE -> default_report_type | ✅ | `-` | - |
|
|
216
|
+
| `default_format` | str | ✅ | `"markdown"` | Default report output format |
|
|
217
|
+
| `default_report_type` | str | ✅ | `-` | - |
|
|
218
|
+
| `include_code` | bool | ✅ | `-` | - |
|
|
219
|
+
| `include_visualizations` | bool | ✅ | `-` | - |
|
|
220
|
+
| `max_insights_per_report` | int | ✅ | `-` | - |
|
|
221
|
+
| `output_directory` | str | ✅ | `-` | - |
|
|
222
|
+
|
|
223
|
+
### 配置示例
|
|
224
|
+
|
|
225
|
+
```python
|
|
226
|
+
aireportorchestratortool_config = {
|
|
227
|
+
'Example': "your_Example",
|
|
228
|
+
'default_format': "markdown", # Default report output format
|
|
229
|
+
'default_report_type': "your_default_report_type",
|
|
230
|
+
'include_code': False,
|
|
231
|
+
'include_visualizations': False,
|
|
232
|
+
'max_insights_per_report': 0,
|
|
233
|
+
'output_directory': "your_output_directory",
|
|
234
|
+
}
|
|
235
|
+
```
|
|
236
|
+
|
|
237
|
+
### 环境变量映射
|
|
238
|
+
|
|
239
|
+
```bash
|
|
240
|
+
export AIREPORT_ORCHESTRATOR_TOOL_EXAMPLE=<value>
|
|
241
|
+
export AIREPORT_ORCHESTRATOR_TOOL_DEFAULT_FORMAT=<value>
|
|
242
|
+
export AIREPORT_ORCHESTRATOR_TOOL_DEFAULT_REPORT_TYPE=<value>
|
|
243
|
+
export AIREPORT_ORCHESTRATOR_TOOL_INCLUDE_CODE=<value>
|
|
244
|
+
export AIREPORT_ORCHESTRATOR_TOOL_INCLUDE_VISUALIZATIONS=<value>
|
|
245
|
+
export AIREPORT_ORCHESTRATOR_TOOL_MAX_INSIGHTS_PER_REPORT=<value>
|
|
246
|
+
export AIREPORT_ORCHESTRATOR_TOOL_OUTPUT_DIRECTORY=<value>
|
|
247
|
+
```
|
|
248
|
+
|
|
249
|
+
---
|
|
250
|
+
|
|
251
|
+
## APISourceTool
|
|
252
|
+
|
|
253
|
+
**配置字段数**: 11 (必需: 11, 可选: 0)
|
|
254
|
+
|
|
255
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
256
|
+
|--------|------|------|--------|------|
|
|
257
|
+
| `Example` | APISOURCE_TOOL_FRED_API_KEY -> fred_api_key | ✅ | `-` | - |
|
|
258
|
+
| `cache_ttl` | int | ✅ | `-` | - |
|
|
259
|
+
| `census_api_key` | Optional[str] | ✅ | `None` | API key for US Census Bureau |
|
|
260
|
+
| `default_timeout` | int | ✅ | `-` | - |
|
|
261
|
+
| `enable_data_fusion` | bool | ✅ | `-` | - |
|
|
262
|
+
| `enable_fallback` | bool | ✅ | `-` | - |
|
|
263
|
+
| `enable_query_enhancement` | bool | ✅ | `-` | - |
|
|
264
|
+
| `enable_rate_limiting` | bool | ✅ | `-` | - |
|
|
265
|
+
| `fred_api_key` | Optional[str] | ✅ | `-` | - |
|
|
266
|
+
| `max_retries` | int | ✅ | `-` | - |
|
|
267
|
+
| `newsapi_api_key` | Optional[str] | ✅ | `None` | API key for News API |
|
|
268
|
+
|
|
269
|
+
### 配置示例
|
|
270
|
+
|
|
271
|
+
```python
|
|
272
|
+
apisourcetool_config = {
|
|
273
|
+
'Example': None,
|
|
274
|
+
'cache_ttl': 0,
|
|
275
|
+
'census_api_key': None, # API key for US Census Bureau
|
|
276
|
+
'default_timeout': 0,
|
|
277
|
+
'enable_data_fusion': False,
|
|
278
|
+
'enable_fallback': False,
|
|
279
|
+
'enable_query_enhancement': False,
|
|
280
|
+
'enable_rate_limiting': False,
|
|
281
|
+
'fred_api_key': "your_fred_api_key",
|
|
282
|
+
'max_retries': 0,
|
|
283
|
+
'newsapi_api_key': None, # API key for News API
|
|
284
|
+
}
|
|
285
|
+
```
|
|
286
|
+
|
|
287
|
+
### 环境变量映射
|
|
288
|
+
|
|
289
|
+
```bash
|
|
290
|
+
export APISOURCE_TOOL_EXAMPLE=<value>
|
|
291
|
+
export APISOURCE_TOOL_CACHE_TTL=<value>
|
|
292
|
+
export APISOURCE_TOOL_CENSUS_API_KEY=<value>
|
|
293
|
+
export APISOURCE_TOOL_DEFAULT_TIMEOUT=<value>
|
|
294
|
+
export APISOURCE_TOOL_ENABLE_DATA_FUSION=<value>
|
|
295
|
+
export APISOURCE_TOOL_ENABLE_FALLBACK=<value>
|
|
296
|
+
export APISOURCE_TOOL_ENABLE_QUERY_ENHANCEMENT=<value>
|
|
297
|
+
export APISOURCE_TOOL_ENABLE_RATE_LIMITING=<value>
|
|
298
|
+
export APISOURCE_TOOL_FRED_API_KEY=<value>
|
|
299
|
+
export APISOURCE_TOOL_MAX_RETRIES=<value>
|
|
300
|
+
export APISOURCE_TOOL_NEWSAPI_API_KEY=<value>
|
|
301
|
+
```
|
|
302
|
+
|
|
303
|
+
---
|
|
304
|
+
|
|
305
|
+
## ChartTool
|
|
306
|
+
|
|
307
|
+
**配置字段数**: 5 (必需: 5, 可选: 0)
|
|
308
|
+
|
|
309
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
310
|
+
|--------|------|------|--------|------|
|
|
311
|
+
| `Example` | CHART_TOOL_EXPORT_DIR -> export_dir | ✅ | `-` | - |
|
|
312
|
+
| `allowed_extensions` | List[str] | ✅ | `-` | - |
|
|
313
|
+
| `export_dir` | str | ✅ | `-` | - |
|
|
314
|
+
| `plot_dpi` | int | ✅ | `100` | DPI for plot exports |
|
|
315
|
+
| `plot_figsize` | Tuple[int, int] | ✅ | `-` | - |
|
|
316
|
+
|
|
317
|
+
### 配置示例
|
|
318
|
+
|
|
319
|
+
```python
|
|
320
|
+
charttool_config = {
|
|
321
|
+
'Example': None,
|
|
322
|
+
'allowed_extensions': "your_allowed_extensions",
|
|
323
|
+
'export_dir': "your_export_dir",
|
|
324
|
+
'plot_dpi': 100, # DPI for plot exports
|
|
325
|
+
'plot_figsize': 0,
|
|
326
|
+
}
|
|
327
|
+
```
|
|
328
|
+
|
|
329
|
+
### 环境变量映射
|
|
330
|
+
|
|
331
|
+
```bash
|
|
332
|
+
export CHART_TOOL_EXAMPLE=<value>
|
|
333
|
+
export CHART_TOOL_ALLOWED_EXTENSIONS=<value>
|
|
334
|
+
export CHART_TOOL_EXPORT_DIR=<value>
|
|
335
|
+
export CHART_TOOL_PLOT_DPI=<value>
|
|
336
|
+
export CHART_TOOL_PLOT_FIGSIZE=<value>
|
|
337
|
+
```
|
|
338
|
+
|
|
339
|
+
---
|
|
340
|
+
|
|
341
|
+
## ClassifierTool
|
|
342
|
+
|
|
343
|
+
**配置字段数**: 12 (必需: 12, 可选: 0)
|
|
344
|
+
|
|
345
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
346
|
+
|--------|------|------|--------|------|
|
|
347
|
+
| `Example` | CLASSIFIER_TOOL_MAX_WORKERS -> max_workers | ✅ | `-` | - |
|
|
348
|
+
| `allowed_models` | List[str] | ✅ | `-` | - |
|
|
349
|
+
| `max_text_length` | int | ✅ | `10_000` | Maximum text length in characters |
|
|
350
|
+
| `max_workers` | int | ✅ | `-` | - |
|
|
351
|
+
| `pipeline_cache_size` | int | ✅ | `10` | Maximum number of pipeline cache entries |
|
|
352
|
+
| `pipeline_cache_ttl` | int | ✅ | `-` | - |
|
|
353
|
+
| `rate_limit_enabled` | bool | ✅ | `True` | Enable rate limiting |
|
|
354
|
+
| `rate_limit_requests` | int | ✅ | `100` | Maximum requests per window |
|
|
355
|
+
| `rate_limit_window` | int | ✅ | `60` | Rate limit window in seconds |
|
|
356
|
+
| `spacy_model_en` | str | ✅ | `"en_core_web_sm"` | spaCy model for English |
|
|
357
|
+
| `spacy_model_zh` | str | ✅ | `"zh_core_web_sm"` | spaCy model for Chinese |
|
|
358
|
+
| `use_rake_for_english` | bool | ✅ | `True` | Use RAKE for English phrase extraction |
|
|
359
|
+
|
|
360
|
+
### 配置示例
|
|
361
|
+
|
|
362
|
+
```python
|
|
363
|
+
classifiertool_config = {
|
|
364
|
+
'Example': None,
|
|
365
|
+
'allowed_models': "your_allowed_models",
|
|
366
|
+
'max_text_length': 10_000, # Maximum text length in characters
|
|
367
|
+
'max_workers': 0,
|
|
368
|
+
'pipeline_cache_size': 10, # Maximum number of pipeline cache entries
|
|
369
|
+
'pipeline_cache_ttl': 0,
|
|
370
|
+
'rate_limit_enabled': True, # Enable rate limiting
|
|
371
|
+
'rate_limit_requests': 100, # Maximum requests per window
|
|
372
|
+
'rate_limit_window': 60, # Rate limit window in seconds
|
|
373
|
+
'spacy_model_en': "en_core_web_sm", # spaCy model for English
|
|
374
|
+
'spacy_model_zh': "zh_core_web_sm", # spaCy model for Chinese
|
|
375
|
+
'use_rake_for_english': True, # Use RAKE for English phrase extraction
|
|
376
|
+
}
|
|
377
|
+
```
|
|
378
|
+
|
|
379
|
+
### 环境变量映射
|
|
380
|
+
|
|
381
|
+
```bash
|
|
382
|
+
export CLASSIFIER_TOOL_EXAMPLE=<value>
|
|
383
|
+
export CLASSIFIER_TOOL_ALLOWED_MODELS=<value>
|
|
384
|
+
export CLASSIFIER_TOOL_MAX_TEXT_LENGTH=<value>
|
|
385
|
+
export CLASSIFIER_TOOL_MAX_WORKERS=<value>
|
|
386
|
+
export CLASSIFIER_TOOL_PIPELINE_CACHE_SIZE=<value>
|
|
387
|
+
export CLASSIFIER_TOOL_PIPELINE_CACHE_TTL=<value>
|
|
388
|
+
export CLASSIFIER_TOOL_RATE_LIMIT_ENABLED=<value>
|
|
389
|
+
export CLASSIFIER_TOOL_RATE_LIMIT_REQUESTS=<value>
|
|
390
|
+
export CLASSIFIER_TOOL_RATE_LIMIT_WINDOW=<value>
|
|
391
|
+
export CLASSIFIER_TOOL_SPACY_MODEL_EN=<value>
|
|
392
|
+
export CLASSIFIER_TOOL_SPACY_MODEL_ZH=<value>
|
|
393
|
+
export CLASSIFIER_TOOL_USE_RAKE_FOR_ENGLISH=<value>
|
|
394
|
+
```
|
|
395
|
+
|
|
396
|
+
---
|
|
397
|
+
|
|
398
|
+
## ContentInsertionTool
|
|
399
|
+
|
|
400
|
+
**配置字段数**: 8 (必需: 8, 可选: 0)
|
|
401
|
+
|
|
402
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
403
|
+
|--------|------|------|--------|------|
|
|
404
|
+
| `Example` | CONTENT_INSERT_TEMP_DIR -> temp_dir | ✅ | `-` | - |
|
|
405
|
+
| `assets_dir` | str | ✅ | `-` | - |
|
|
406
|
+
| `auto_resize` | bool | ✅ | `-` | - |
|
|
407
|
+
| `default_image_format` | str | ✅ | `-` | - |
|
|
408
|
+
| `max_chart_size` | Tuple[int, int] | ✅ | `-` | - |
|
|
409
|
+
| `max_image_size` | int | ✅ | `10 * 1024 * 1024` | Maximum image size in bytes |
|
|
410
|
+
| `optimize_images` | bool | ✅ | `-` | - |
|
|
411
|
+
| `temp_dir` | str | ✅ | `-` | - |
|
|
412
|
+
|
|
413
|
+
### 配置示例
|
|
414
|
+
|
|
415
|
+
```python
|
|
416
|
+
contentinsertiontool_config = {
|
|
417
|
+
'Example': None,
|
|
418
|
+
'assets_dir': "your_assets_dir",
|
|
419
|
+
'auto_resize': False,
|
|
420
|
+
'default_image_format': "your_default_image_format",
|
|
421
|
+
'max_chart_size': 0,
|
|
422
|
+
'max_image_size': 10 * 1024 * 1024, # Maximum image size in bytes
|
|
423
|
+
'optimize_images': False,
|
|
424
|
+
'temp_dir': "your_temp_dir",
|
|
425
|
+
}
|
|
426
|
+
```
|
|
427
|
+
|
|
428
|
+
### 环境变量映射
|
|
429
|
+
|
|
430
|
+
```bash
|
|
431
|
+
export CONTENTINSERTION_TOOL_EXAMPLE=<value>
|
|
432
|
+
export CONTENTINSERTION_TOOL_ASSETS_DIR=<value>
|
|
433
|
+
export CONTENTINSERTION_TOOL_AUTO_RESIZE=<value>
|
|
434
|
+
export CONTENTINSERTION_TOOL_DEFAULT_IMAGE_FORMAT=<value>
|
|
435
|
+
export CONTENTINSERTION_TOOL_MAX_CHART_SIZE=<value>
|
|
436
|
+
export CONTENTINSERTION_TOOL_MAX_IMAGE_SIZE=<value>
|
|
437
|
+
export CONTENTINSERTION_TOOL_OPTIMIZE_IMAGES=<value>
|
|
438
|
+
export CONTENTINSERTION_TOOL_TEMP_DIR=<value>
|
|
439
|
+
```
|
|
440
|
+
|
|
441
|
+
---
|
|
442
|
+
|
|
443
|
+
## DataLoaderTool
|
|
444
|
+
|
|
445
|
+
**配置字段数**: 7 (必需: 7, 可选: 0)
|
|
446
|
+
|
|
447
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
448
|
+
|--------|------|------|--------|------|
|
|
449
|
+
| `Example` | DATA_LOADER_MAX_FILE_SIZE_MB -> max_file_size_mb | ✅ | `-` | - |
|
|
450
|
+
| `default_chunk_size` | int | ✅ | `10000` | Default chunk size for chunked loading |
|
|
451
|
+
| `default_encoding` | str | ✅ | `-` | - |
|
|
452
|
+
| `enable_quality_validation` | bool | ✅ | `-` | - |
|
|
453
|
+
| `enable_schema_inference` | bool | ✅ | `-` | - |
|
|
454
|
+
| `max_file_size_mb` | int | ✅ | `500` | Maximum file size in megabytes |
|
|
455
|
+
| `max_memory_usage_mb` | int | ✅ | `2000` | Maximum memory usage in megabytes |
|
|
456
|
+
|
|
457
|
+
### 配置示例
|
|
458
|
+
|
|
459
|
+
```python
|
|
460
|
+
dataloadertool_config = {
|
|
461
|
+
'Example': None,
|
|
462
|
+
'default_chunk_size': 10000, # Default chunk size for chunked loading
|
|
463
|
+
'default_encoding': "your_default_encoding",
|
|
464
|
+
'enable_quality_validation': False,
|
|
465
|
+
'enable_schema_inference': False,
|
|
466
|
+
'max_file_size_mb': 500, # Maximum file size in megabytes
|
|
467
|
+
'max_memory_usage_mb': 2000, # Maximum memory usage in megabytes
|
|
468
|
+
}
|
|
469
|
+
```
|
|
470
|
+
|
|
471
|
+
### 环境变量映射
|
|
472
|
+
|
|
473
|
+
```bash
|
|
474
|
+
export DATALOADER_TOOL_EXAMPLE=<value>
|
|
475
|
+
export DATALOADER_TOOL_DEFAULT_CHUNK_SIZE=<value>
|
|
476
|
+
export DATALOADER_TOOL_DEFAULT_ENCODING=<value>
|
|
477
|
+
export DATALOADER_TOOL_ENABLE_QUALITY_VALIDATION=<value>
|
|
478
|
+
export DATALOADER_TOOL_ENABLE_SCHEMA_INFERENCE=<value>
|
|
479
|
+
export DATALOADER_TOOL_MAX_FILE_SIZE_MB=<value>
|
|
480
|
+
export DATALOADER_TOOL_MAX_MEMORY_USAGE_MB=<value>
|
|
481
|
+
```
|
|
482
|
+
|
|
483
|
+
---
|
|
484
|
+
|
|
485
|
+
## DataProfilerTool
|
|
486
|
+
|
|
487
|
+
**配置字段数**: 7 (必需: 7, 可选: 0)
|
|
488
|
+
|
|
489
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
490
|
+
|--------|------|------|--------|------|
|
|
491
|
+
| `Example` | DATA_PROFILER_DEFAULT_PROFILE_LEVEL -> default_profile_level | ✅ | `-` | - |
|
|
492
|
+
| `correlation_threshold` | float | ✅ | `-` | - |
|
|
493
|
+
| `default_profile_level` | str | ✅ | `"standard"` | Default profiling depth level |
|
|
494
|
+
| `enable_visualizations` | bool | ✅ | `-` | - |
|
|
495
|
+
| `max_unique_values_categorical` | int | ✅ | `-` | - |
|
|
496
|
+
| `missing_threshold` | float | ✅ | `-` | - |
|
|
497
|
+
| `outlier_std_threshold` | float | ✅ | `-` | - |
|
|
498
|
+
|
|
499
|
+
### 配置示例
|
|
500
|
+
|
|
501
|
+
```python
|
|
502
|
+
dataprofilertool_config = {
|
|
503
|
+
'Example': None,
|
|
504
|
+
'correlation_threshold': 0.0,
|
|
505
|
+
'default_profile_level': "standard", # Default profiling depth level
|
|
506
|
+
'enable_visualizations': False,
|
|
507
|
+
'max_unique_values_categorical': 0,
|
|
508
|
+
'missing_threshold': 0.0,
|
|
509
|
+
'outlier_std_threshold': 0.0,
|
|
510
|
+
}
|
|
511
|
+
```
|
|
512
|
+
|
|
513
|
+
### 环境变量映射
|
|
514
|
+
|
|
515
|
+
```bash
|
|
516
|
+
export DATAPROFILER_TOOL_EXAMPLE=<value>
|
|
517
|
+
export DATAPROFILER_TOOL_CORRELATION_THRESHOLD=<value>
|
|
518
|
+
export DATAPROFILER_TOOL_DEFAULT_PROFILE_LEVEL=<value>
|
|
519
|
+
export DATAPROFILER_TOOL_ENABLE_VISUALIZATIONS=<value>
|
|
520
|
+
export DATAPROFILER_TOOL_MAX_UNIQUE_VALUES_CATEGORICAL=<value>
|
|
521
|
+
export DATAPROFILER_TOOL_MISSING_THRESHOLD=<value>
|
|
522
|
+
export DATAPROFILER_TOOL_OUTLIER_STD_THRESHOLD=<value>
|
|
523
|
+
```
|
|
524
|
+
|
|
525
|
+
---
|
|
526
|
+
|
|
527
|
+
## DataTransformerTool
|
|
528
|
+
|
|
529
|
+
**配置字段数**: 5 (必需: 5, 可选: 0)
|
|
530
|
+
|
|
531
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
532
|
+
|--------|------|------|--------|------|
|
|
533
|
+
| `Example` | DATA_TRANSFORMER_OUTLIER_STD_THRESHOLD -> outlier_std_threshold | ✅ | `-` | - |
|
|
534
|
+
| `default_missing_strategy` | str | ✅ | `-` | - |
|
|
535
|
+
| `enable_pipeline_caching` | bool | ✅ | `-` | - |
|
|
536
|
+
| `max_one_hot_categories` | int | ✅ | `-` | - |
|
|
537
|
+
| `outlier_std_threshold` | float | ✅ | `-` | - |
|
|
538
|
+
|
|
539
|
+
### 配置示例
|
|
540
|
+
|
|
541
|
+
```python
|
|
542
|
+
datatransformertool_config = {
|
|
543
|
+
'Example': None,
|
|
544
|
+
'default_missing_strategy': "your_default_missing_strategy",
|
|
545
|
+
'enable_pipeline_caching': False,
|
|
546
|
+
'max_one_hot_categories': 0,
|
|
547
|
+
'outlier_std_threshold': 0.0,
|
|
548
|
+
}
|
|
549
|
+
```
|
|
550
|
+
|
|
551
|
+
### 环境变量映射
|
|
552
|
+
|
|
553
|
+
```bash
|
|
554
|
+
export DATATRANSFORMER_TOOL_EXAMPLE=<value>
|
|
555
|
+
export DATATRANSFORMER_TOOL_DEFAULT_MISSING_STRATEGY=<value>
|
|
556
|
+
export DATATRANSFORMER_TOOL_ENABLE_PIPELINE_CACHING=<value>
|
|
557
|
+
export DATATRANSFORMER_TOOL_MAX_ONE_HOT_CATEGORIES=<value>
|
|
558
|
+
export DATATRANSFORMER_TOOL_OUTLIER_STD_THRESHOLD=<value>
|
|
559
|
+
```
|
|
560
|
+
|
|
561
|
+
---
|
|
562
|
+
|
|
563
|
+
## DataVisualizerTool
|
|
564
|
+
|
|
565
|
+
**配置字段数**: 6 (必需: 6, 可选: 0)
|
|
566
|
+
|
|
567
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
568
|
+
|--------|------|------|--------|------|
|
|
569
|
+
| `Example` | DATA_VISUALIZER_DEFAULT_STYLE -> default_style | ✅ | `-` | - |
|
|
570
|
+
| `default_dpi` | int | ✅ | `100` | Default DPI for image exports |
|
|
571
|
+
| `default_figsize` | List[int] | ✅ | `-` | - |
|
|
572
|
+
| `default_output_dir` | str | ✅ | `-` | - |
|
|
573
|
+
| `default_style` | str | ✅ | `"static"` | Default visualization style |
|
|
574
|
+
| `enable_auto_recommendation` | bool | ✅ | `-` | - |
|
|
575
|
+
|
|
576
|
+
### 配置示例
|
|
577
|
+
|
|
578
|
+
```python
|
|
579
|
+
datavisualizertool_config = {
|
|
580
|
+
'Example': None,
|
|
581
|
+
'default_dpi': 100, # Default DPI for image exports
|
|
582
|
+
'default_figsize': 0,
|
|
583
|
+
'default_output_dir': "your_default_output_dir",
|
|
584
|
+
'default_style': "static", # Default visualization style
|
|
585
|
+
'enable_auto_recommendation': False,
|
|
586
|
+
}
|
|
587
|
+
```
|
|
588
|
+
|
|
589
|
+
### 环境变量映射
|
|
590
|
+
|
|
591
|
+
```bash
|
|
592
|
+
export DATAVISUALIZER_TOOL_EXAMPLE=<value>
|
|
593
|
+
export DATAVISUALIZER_TOOL_DEFAULT_DPI=<value>
|
|
594
|
+
export DATAVISUALIZER_TOOL_DEFAULT_FIGSIZE=<value>
|
|
595
|
+
export DATAVISUALIZER_TOOL_DEFAULT_OUTPUT_DIR=<value>
|
|
596
|
+
export DATAVISUALIZER_TOOL_DEFAULT_STYLE=<value>
|
|
597
|
+
export DATAVISUALIZER_TOOL_ENABLE_AUTO_RECOMMENDATION=<value>
|
|
598
|
+
```
|
|
599
|
+
|
|
600
|
+
---
|
|
601
|
+
|
|
602
|
+
## DocumentCreatorTool
|
|
603
|
+
|
|
604
|
+
**配置字段数**: 8 (必需: 8, 可选: 0)
|
|
605
|
+
|
|
606
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
607
|
+
|--------|------|------|--------|------|
|
|
608
|
+
| `Example` | DOC_CREATOR_TEMPLATES_DIR -> templates_dir | ✅ | `-` | - |
|
|
609
|
+
| `auto_backup` | bool | ✅ | `-` | - |
|
|
610
|
+
| `default_format` | str | ✅ | `"markdown"` | Default output format |
|
|
611
|
+
| `default_style` | str | ✅ | `"default"` | Default style preset |
|
|
612
|
+
| `generate_toc` | bool | ✅ | `-` | - |
|
|
613
|
+
| `include_metadata` | bool | ✅ | `-` | - |
|
|
614
|
+
| `output_dir` | str | ✅ | `-` | - |
|
|
615
|
+
| `templates_dir` | str | ✅ | `-` | - |
|
|
616
|
+
|
|
617
|
+
### 配置示例
|
|
618
|
+
|
|
619
|
+
```python
|
|
620
|
+
documentcreatortool_config = {
|
|
621
|
+
'Example': None,
|
|
622
|
+
'auto_backup': False,
|
|
623
|
+
'default_format': "markdown", # Default output format
|
|
624
|
+
'default_style': "default", # Default style preset
|
|
625
|
+
'generate_toc': False,
|
|
626
|
+
'include_metadata': False,
|
|
627
|
+
'output_dir': "your_output_dir",
|
|
628
|
+
'templates_dir': "your_templates_dir",
|
|
629
|
+
}
|
|
630
|
+
```
|
|
631
|
+
|
|
632
|
+
### 环境变量映射
|
|
633
|
+
|
|
634
|
+
```bash
|
|
635
|
+
export DOCUMENTCREATOR_TOOL_EXAMPLE=<value>
|
|
636
|
+
export DOCUMENTCREATOR_TOOL_AUTO_BACKUP=<value>
|
|
637
|
+
export DOCUMENTCREATOR_TOOL_DEFAULT_FORMAT=<value>
|
|
638
|
+
export DOCUMENTCREATOR_TOOL_DEFAULT_STYLE=<value>
|
|
639
|
+
export DOCUMENTCREATOR_TOOL_GENERATE_TOC=<value>
|
|
640
|
+
export DOCUMENTCREATOR_TOOL_INCLUDE_METADATA=<value>
|
|
641
|
+
export DOCUMENTCREATOR_TOOL_OUTPUT_DIR=<value>
|
|
642
|
+
export DOCUMENTCREATOR_TOOL_TEMPLATES_DIR=<value>
|
|
643
|
+
```
|
|
644
|
+
|
|
645
|
+
---
|
|
646
|
+
|
|
647
|
+
## DocumentLayoutTool
|
|
648
|
+
|
|
649
|
+
**配置字段数**: 7 (必需: 7, 可选: 0)
|
|
650
|
+
|
|
651
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
652
|
+
|--------|------|------|--------|------|
|
|
653
|
+
| `Example` | DOC_LAYOUT_TEMP_DIR -> temp_dir | ✅ | `-` | - |
|
|
654
|
+
| `auto_adjust_layout` | bool | ✅ | `-` | - |
|
|
655
|
+
| `default_margins` | Dict[str, float] | ✅ | `-` | - |
|
|
656
|
+
| `default_orientation` | str | ✅ | `"portrait"` | Default page orientation |
|
|
657
|
+
| `default_page_size` | str | ✅ | `"a4"` | Default page size |
|
|
658
|
+
| `preserve_formatting` | bool | ✅ | `-` | - |
|
|
659
|
+
| `temp_dir` | str | ✅ | `-` | - |
|
|
660
|
+
|
|
661
|
+
### 配置示例
|
|
662
|
+
|
|
663
|
+
```python
|
|
664
|
+
documentlayouttool_config = {
|
|
665
|
+
'Example': None,
|
|
666
|
+
'auto_adjust_layout': False,
|
|
667
|
+
'default_margins': "your_default_margins",
|
|
668
|
+
'default_orientation': "portrait", # Default page orientation
|
|
669
|
+
'default_page_size': "a4", # Default page size
|
|
670
|
+
'preserve_formatting': False,
|
|
671
|
+
'temp_dir': "your_temp_dir",
|
|
672
|
+
}
|
|
673
|
+
```
|
|
674
|
+
|
|
675
|
+
### 环境变量映射
|
|
676
|
+
|
|
677
|
+
```bash
|
|
678
|
+
export DOCUMENTLAYOUT_TOOL_EXAMPLE=<value>
|
|
679
|
+
export DOCUMENTLAYOUT_TOOL_AUTO_ADJUST_LAYOUT=<value>
|
|
680
|
+
export DOCUMENTLAYOUT_TOOL_DEFAULT_MARGINS=<value>
|
|
681
|
+
export DOCUMENTLAYOUT_TOOL_DEFAULT_ORIENTATION=<value>
|
|
682
|
+
export DOCUMENTLAYOUT_TOOL_DEFAULT_PAGE_SIZE=<value>
|
|
683
|
+
export DOCUMENTLAYOUT_TOOL_PRESERVE_FORMATTING=<value>
|
|
684
|
+
export DOCUMENTLAYOUT_TOOL_TEMP_DIR=<value>
|
|
685
|
+
```
|
|
686
|
+
|
|
687
|
+
---
|
|
688
|
+
|
|
689
|
+
## DocumentParserTool
|
|
690
|
+
|
|
691
|
+
**配置字段数**: 10 (必需: 10, 可选: 0)
|
|
692
|
+
|
|
693
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
694
|
+
|--------|------|------|--------|------|
|
|
695
|
+
| `Example` | DOC_PARSER_TIMEOUT -> timeout | ✅ | `-` | - |
|
|
696
|
+
| `default_encoding` | str | ✅ | `"utf-8"` | Default encoding for text files |
|
|
697
|
+
| `enable_cloud_storage` | bool | ✅ | `-` | - |
|
|
698
|
+
| `gcs_bucket_name` | str | ✅ | `-` | - |
|
|
699
|
+
| `gcs_project_id` | Optional[str] | ✅ | `None` | Google Cloud Storage project ID |
|
|
700
|
+
| `max_file_size` | int | ✅ | `50 * 1024 * 1024` | Maximum file size in bytes |
|
|
701
|
+
| `max_pages` | int | ✅ | `-` | - |
|
|
702
|
+
| `temp_dir` | str | ✅ | `-` | - |
|
|
703
|
+
| `timeout` | int | ✅ | `30` | Timeout for HTTP requests in seconds |
|
|
704
|
+
| `user_agent` | str | ✅ | `-` | - |
|
|
705
|
+
|
|
706
|
+
### 配置示例
|
|
707
|
+
|
|
708
|
+
```python
|
|
709
|
+
documentparsertool_config = {
|
|
710
|
+
'Example': None,
|
|
711
|
+
'default_encoding': "utf-8", # Default encoding for text files
|
|
712
|
+
'enable_cloud_storage': False,
|
|
713
|
+
'gcs_bucket_name': "your_gcs_bucket_name",
|
|
714
|
+
'gcs_project_id': None, # Google Cloud Storage project ID
|
|
715
|
+
'max_file_size': 50 * 1024 * 1024, # Maximum file size in bytes
|
|
716
|
+
'max_pages': 0,
|
|
717
|
+
'temp_dir': "your_temp_dir",
|
|
718
|
+
'timeout': 30, # Timeout for HTTP requests in seconds
|
|
719
|
+
'user_agent': "your_user_agent",
|
|
720
|
+
}
|
|
721
|
+
```
|
|
722
|
+
|
|
723
|
+
### 环境变量映射
|
|
724
|
+
|
|
725
|
+
```bash
|
|
726
|
+
export DOCUMENTPARSER_TOOL_EXAMPLE=<value>
|
|
727
|
+
export DOCUMENTPARSER_TOOL_DEFAULT_ENCODING=<value>
|
|
728
|
+
export DOCUMENTPARSER_TOOL_ENABLE_CLOUD_STORAGE=<value>
|
|
729
|
+
export DOCUMENTPARSER_TOOL_GCS_BUCKET_NAME=<value>
|
|
730
|
+
export DOCUMENTPARSER_TOOL_GCS_PROJECT_ID=<value>
|
|
731
|
+
export DOCUMENTPARSER_TOOL_MAX_FILE_SIZE=<value>
|
|
732
|
+
export DOCUMENTPARSER_TOOL_MAX_PAGES=<value>
|
|
733
|
+
export DOCUMENTPARSER_TOOL_TEMP_DIR=<value>
|
|
734
|
+
export DOCUMENTPARSER_TOOL_TIMEOUT=<value>
|
|
735
|
+
export DOCUMENTPARSER_TOOL_USER_AGENT=<value>
|
|
736
|
+
```
|
|
737
|
+
|
|
738
|
+
---
|
|
739
|
+
|
|
740
|
+
## DocumentWriterTool
|
|
741
|
+
|
|
742
|
+
**配置字段数**: 22 (必需: 22, 可选: 0)
|
|
743
|
+
|
|
744
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
745
|
+
|--------|------|------|--------|------|
|
|
746
|
+
| `Example` | DOC_WRITER_GCS_PROJECT_ID -> gcs_project_id | ✅ | `-` | - |
|
|
747
|
+
| `atomic_write` | bool | ✅ | `True` | Whether to use atomic write operations |
|
|
748
|
+
| `atomic_writes` | bool | ✅ | `True` | Whether to use atomic write operations |
|
|
749
|
+
| `auto_backup` | bool | ✅ | `-` | - |
|
|
750
|
+
| `backup_dir` | str | ✅ | `-` | - |
|
|
751
|
+
| `default_encoding` | str | ✅ | `"utf-8"` | Default text encoding for documents |
|
|
752
|
+
| `default_format` | str | ✅ | `"md"` | Default document format |
|
|
753
|
+
| `enable_backup` | bool | ✅ | `-` | - |
|
|
754
|
+
| `enable_cloud_storage` | bool | ✅ | `-` | - |
|
|
755
|
+
| `enable_content_validation` | bool | ✅ | `True` | Whether to enable content validation |
|
|
756
|
+
| `enable_security_scan` | bool | ✅ | `True` | Whether to enable security scanning |
|
|
757
|
+
| `enable_versioning` | bool | ✅ | `True` | Whether to enable document versioning |
|
|
758
|
+
| `gcs_bucket_name` | str | ✅ | `-` | - |
|
|
759
|
+
| `gcs_project_id` | Optional[str] | ✅ | `None` | Google Cloud Storage project ID |
|
|
760
|
+
| `max_backup_versions` | int | ✅ | `10` | Maximum number of backup versions to keep |
|
|
761
|
+
| `max_file_size` | int | ✅ | `100 * 1024 * 1024` | Maximum file size in bytes |
|
|
762
|
+
| `output_dir` | Optional[str] | ✅ | `None` | Default output directory for documents |
|
|
763
|
+
| `security_scan` | bool | ✅ | `True` | Whether to enable security scanning |
|
|
764
|
+
| `temp_dir` | str | ✅ | `-` | - |
|
|
765
|
+
| `timeout_seconds` | int | ✅ | `60` | Operation timeout in seconds |
|
|
766
|
+
| `validation_level` | str | ✅ | `"basic"` | Content validation level |
|
|
767
|
+
| `version_control` | bool | ✅ | `True` | Whether to enable version control |
|
|
768
|
+
|
|
769
|
+
### 配置示例
|
|
770
|
+
|
|
771
|
+
```python
|
|
772
|
+
documentwritertool_config = {
|
|
773
|
+
'Example': None,
|
|
774
|
+
'atomic_write': True, # Whether to use atomic write operations
|
|
775
|
+
'atomic_writes': True, # Whether to use atomic write operations
|
|
776
|
+
'auto_backup': False,
|
|
777
|
+
'backup_dir': "your_backup_dir",
|
|
778
|
+
'default_encoding': "utf-8", # Default text encoding for documents
|
|
779
|
+
'default_format': "md", # Default document format
|
|
780
|
+
'enable_backup': False,
|
|
781
|
+
'enable_cloud_storage': False,
|
|
782
|
+
'enable_content_validation': True, # Whether to enable content validation
|
|
783
|
+
'enable_security_scan': True, # Whether to enable security scanning
|
|
784
|
+
'enable_versioning': True, # Whether to enable document versioning
|
|
785
|
+
'gcs_bucket_name': "your_gcs_bucket_name",
|
|
786
|
+
'gcs_project_id': None, # Google Cloud Storage project ID
|
|
787
|
+
'max_backup_versions': 10, # Maximum number of backup versions to keep
|
|
788
|
+
'max_file_size': 100 * 1024 * 1024, # Maximum file size in bytes
|
|
789
|
+
'output_dir': None, # Default output directory for documents
|
|
790
|
+
'security_scan': True, # Whether to enable security scanning
|
|
791
|
+
'temp_dir': "your_temp_dir",
|
|
792
|
+
'timeout_seconds': 60, # Operation timeout in seconds
|
|
793
|
+
'validation_level': "basic", # Content validation level
|
|
794
|
+
'version_control': True, # Whether to enable version control
|
|
795
|
+
}
|
|
796
|
+
```
|
|
797
|
+
|
|
798
|
+
### 环境变量映射
|
|
799
|
+
|
|
800
|
+
```bash
|
|
801
|
+
export DOCUMENTWRITER_TOOL_EXAMPLE=<value>
|
|
802
|
+
export DOCUMENTWRITER_TOOL_ATOMIC_WRITE=<value>
|
|
803
|
+
export DOCUMENTWRITER_TOOL_ATOMIC_WRITES=<value>
|
|
804
|
+
export DOCUMENTWRITER_TOOL_AUTO_BACKUP=<value>
|
|
805
|
+
export DOCUMENTWRITER_TOOL_BACKUP_DIR=<value>
|
|
806
|
+
export DOCUMENTWRITER_TOOL_DEFAULT_ENCODING=<value>
|
|
807
|
+
export DOCUMENTWRITER_TOOL_DEFAULT_FORMAT=<value>
|
|
808
|
+
export DOCUMENTWRITER_TOOL_ENABLE_BACKUP=<value>
|
|
809
|
+
export DOCUMENTWRITER_TOOL_ENABLE_CLOUD_STORAGE=<value>
|
|
810
|
+
export DOCUMENTWRITER_TOOL_ENABLE_CONTENT_VALIDATION=<value>
|
|
811
|
+
export DOCUMENTWRITER_TOOL_ENABLE_SECURITY_SCAN=<value>
|
|
812
|
+
export DOCUMENTWRITER_TOOL_ENABLE_VERSIONING=<value>
|
|
813
|
+
export DOCUMENTWRITER_TOOL_GCS_BUCKET_NAME=<value>
|
|
814
|
+
export DOCUMENTWRITER_TOOL_GCS_PROJECT_ID=<value>
|
|
815
|
+
export DOCUMENTWRITER_TOOL_MAX_BACKUP_VERSIONS=<value>
|
|
816
|
+
export DOCUMENTWRITER_TOOL_MAX_FILE_SIZE=<value>
|
|
817
|
+
export DOCUMENTWRITER_TOOL_OUTPUT_DIR=<value>
|
|
818
|
+
export DOCUMENTWRITER_TOOL_SECURITY_SCAN=<value>
|
|
819
|
+
export DOCUMENTWRITER_TOOL_TEMP_DIR=<value>
|
|
820
|
+
export DOCUMENTWRITER_TOOL_TIMEOUT_SECONDS=<value>
|
|
821
|
+
export DOCUMENTWRITER_TOOL_VALIDATION_LEVEL=<value>
|
|
822
|
+
export DOCUMENTWRITER_TOOL_VERSION_CONTROL=<value>
|
|
823
|
+
```
|
|
824
|
+
|
|
825
|
+
---
|
|
826
|
+
|
|
827
|
+
## GraphReasoningTool
|
|
828
|
+
|
|
829
|
+
**配置字段数**: 5 (必需: 5, 可选: 0)
|
|
830
|
+
|
|
831
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
832
|
+
|--------|------|------|--------|------|
|
|
833
|
+
| `Example` | GRAPH_REASONING_DEFAULT_MAX_HOPS -> default_max_hops | ✅ | `-` | - |
|
|
834
|
+
| `default_confidence_threshold` | float | ✅ | `-` | - |
|
|
835
|
+
| `default_inference_max_steps` | int | ✅ | `-` | - |
|
|
836
|
+
| `default_max_hops` | int | ✅ | `-` | - |
|
|
837
|
+
| `enable_default_rules` | bool | ✅ | `-` | - |
|
|
838
|
+
|
|
839
|
+
### 配置示例
|
|
840
|
+
|
|
841
|
+
```python
|
|
842
|
+
graphreasoningtool_config = {
|
|
843
|
+
'Example': None,
|
|
844
|
+
'default_confidence_threshold': 0.0,
|
|
845
|
+
'default_inference_max_steps': 0,
|
|
846
|
+
'default_max_hops': 0,
|
|
847
|
+
'enable_default_rules': False,
|
|
848
|
+
}
|
|
849
|
+
```
|
|
850
|
+
|
|
851
|
+
### 环境变量映射
|
|
852
|
+
|
|
853
|
+
```bash
|
|
854
|
+
export GRAPHREASONING_TOOL_EXAMPLE=<value>
|
|
855
|
+
export GRAPHREASONING_TOOL_DEFAULT_CONFIDENCE_THRESHOLD=<value>
|
|
856
|
+
export GRAPHREASONING_TOOL_DEFAULT_INFERENCE_MAX_STEPS=<value>
|
|
857
|
+
export GRAPHREASONING_TOOL_DEFAULT_MAX_HOPS=<value>
|
|
858
|
+
export GRAPHREASONING_TOOL_ENABLE_DEFAULT_RULES=<value>
|
|
859
|
+
```
|
|
860
|
+
|
|
861
|
+
---
|
|
862
|
+
|
|
863
|
+
## GraphSearchTool
|
|
864
|
+
|
|
865
|
+
**配置字段数**: 5 (必需: 5, 可选: 0)
|
|
866
|
+
|
|
867
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
868
|
+
|--------|------|------|--------|------|
|
|
869
|
+
| `Example` | GRAPH_SEARCH_CACHE_MAX_SIZE -> cache_max_size | ✅ | `-` | - |
|
|
870
|
+
| `cache_max_size` | int | ✅ | `-` | - |
|
|
871
|
+
| `cache_ttl` | int | ✅ | `-` | - |
|
|
872
|
+
| `default_max_depth` | int | ✅ | `-` | - |
|
|
873
|
+
| `default_max_results` | int | ✅ | `-` | - |
|
|
874
|
+
|
|
875
|
+
### 配置示例
|
|
876
|
+
|
|
877
|
+
```python
|
|
878
|
+
graphsearchtool_config = {
|
|
879
|
+
'Example': None,
|
|
880
|
+
'cache_max_size': 0,
|
|
881
|
+
'cache_ttl': 0,
|
|
882
|
+
'default_max_depth': 0,
|
|
883
|
+
'default_max_results': 0,
|
|
884
|
+
}
|
|
885
|
+
```
|
|
886
|
+
|
|
887
|
+
### 环境变量映射
|
|
888
|
+
|
|
889
|
+
```bash
|
|
890
|
+
export GRAPHSEARCH_TOOL_EXAMPLE=<value>
|
|
891
|
+
export GRAPHSEARCH_TOOL_CACHE_MAX_SIZE=<value>
|
|
892
|
+
export GRAPHSEARCH_TOOL_CACHE_TTL=<value>
|
|
893
|
+
export GRAPHSEARCH_TOOL_DEFAULT_MAX_DEPTH=<value>
|
|
894
|
+
export GRAPHSEARCH_TOOL_DEFAULT_MAX_RESULTS=<value>
|
|
895
|
+
```
|
|
896
|
+
|
|
897
|
+
---
|
|
898
|
+
|
|
899
|
+
## ImageTool
|
|
900
|
+
|
|
901
|
+
**配置字段数**: 4 (必需: 4, 可选: 0)
|
|
902
|
+
|
|
903
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
904
|
+
|--------|------|------|--------|------|
|
|
905
|
+
| `Example` | IMAGE_TOOL_MAX_FILE_SIZE_MB -> max_file_size_mb | ✅ | `-` | - |
|
|
906
|
+
| `allowed_extensions` | List[str] | ✅ | `-` | - |
|
|
907
|
+
| `max_file_size_mb` | int | ✅ | `50` | Maximum file size in megabytes |
|
|
908
|
+
| `tesseract_pool_size` | int | ✅ | `2` | Number of Tesseract processes for OCR |
|
|
909
|
+
|
|
910
|
+
### 配置示例
|
|
911
|
+
|
|
912
|
+
```python
|
|
913
|
+
imagetool_config = {
|
|
914
|
+
'Example': None,
|
|
915
|
+
'allowed_extensions': "your_allowed_extensions",
|
|
916
|
+
'max_file_size_mb': 50, # Maximum file size in megabytes
|
|
917
|
+
'tesseract_pool_size': 2, # Number of Tesseract processes for OCR
|
|
918
|
+
}
|
|
919
|
+
```
|
|
920
|
+
|
|
921
|
+
### 环境变量映射
|
|
922
|
+
|
|
923
|
+
```bash
|
|
924
|
+
export IMAGE_TOOL_EXAMPLE=<value>
|
|
925
|
+
export IMAGE_TOOL_ALLOWED_EXTENSIONS=<value>
|
|
926
|
+
export IMAGE_TOOL_MAX_FILE_SIZE_MB=<value>
|
|
927
|
+
export IMAGE_TOOL_TESSERACT_POOL_SIZE=<value>
|
|
928
|
+
```
|
|
929
|
+
|
|
930
|
+
---
|
|
931
|
+
|
|
932
|
+
## KnowledgeGraphBuilderTool
|
|
933
|
+
|
|
934
|
+
**配置字段数**: 7 (必需: 7, 可选: 0)
|
|
935
|
+
|
|
936
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
937
|
+
|--------|------|------|--------|------|
|
|
938
|
+
| `Example` | KG_BUILDER_CHUNK_SIZE -> chunk_size | ✅ | `-` | - |
|
|
939
|
+
| `batch_size` | int | ✅ | `-` | - |
|
|
940
|
+
| `chunk_size` | int | ✅ | `-` | - |
|
|
941
|
+
| `enable_chunking` | bool | ✅ | `-` | - |
|
|
942
|
+
| `enable_deduplication` | bool | ✅ | `-` | - |
|
|
943
|
+
| `enable_linking` | bool | ✅ | `-` | - |
|
|
944
|
+
| `skip_errors` | bool | ✅ | `-` | - |
|
|
945
|
+
|
|
946
|
+
### 配置示例
|
|
947
|
+
|
|
948
|
+
```python
|
|
949
|
+
knowledgegraphbuildertool_config = {
|
|
950
|
+
'Example': None,
|
|
951
|
+
'batch_size': 0,
|
|
952
|
+
'chunk_size': 0,
|
|
953
|
+
'enable_chunking': False,
|
|
954
|
+
'enable_deduplication': False,
|
|
955
|
+
'enable_linking': False,
|
|
956
|
+
'skip_errors': False,
|
|
957
|
+
}
|
|
958
|
+
```
|
|
959
|
+
|
|
960
|
+
### 环境变量映射
|
|
961
|
+
|
|
962
|
+
```bash
|
|
963
|
+
export KNOWLEDGEGRAPHBUILDER_TOOL_EXAMPLE=<value>
|
|
964
|
+
export KNOWLEDGEGRAPHBUILDER_TOOL_BATCH_SIZE=<value>
|
|
965
|
+
export KNOWLEDGEGRAPHBUILDER_TOOL_CHUNK_SIZE=<value>
|
|
966
|
+
export KNOWLEDGEGRAPHBUILDER_TOOL_ENABLE_CHUNKING=<value>
|
|
967
|
+
export KNOWLEDGEGRAPHBUILDER_TOOL_ENABLE_DEDUPLICATION=<value>
|
|
968
|
+
export KNOWLEDGEGRAPHBUILDER_TOOL_ENABLE_LINKING=<value>
|
|
969
|
+
export KNOWLEDGEGRAPHBUILDER_TOOL_SKIP_ERRORS=<value>
|
|
970
|
+
```
|
|
971
|
+
|
|
972
|
+
---
|
|
973
|
+
|
|
974
|
+
## ModelTrainerTool
|
|
975
|
+
|
|
976
|
+
**配置字段数**: 6 (必需: 6, 可选: 0)
|
|
977
|
+
|
|
978
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
979
|
+
|--------|------|------|--------|------|
|
|
980
|
+
| `Example` | MODEL_TRAINER_TEST_SIZE -> test_size | ✅ | `-` | - |
|
|
981
|
+
| `cv_folds` | int | ✅ | `5` | Number of cross-validation folds |
|
|
982
|
+
| `enable_hyperparameter_tuning` | bool | ✅ | `-` | - |
|
|
983
|
+
| `max_tuning_iterations` | int | ✅ | `-` | - |
|
|
984
|
+
| `random_state` | int | ✅ | `42` | Random state for reproducibility |
|
|
985
|
+
| `test_size` | float | ✅ | `0.2` | Proportion of data to use for testing |
|
|
986
|
+
|
|
987
|
+
### 配置示例
|
|
988
|
+
|
|
989
|
+
```python
|
|
990
|
+
modeltrainertool_config = {
|
|
991
|
+
'Example': None,
|
|
992
|
+
'cv_folds': 5, # Number of cross-validation folds
|
|
993
|
+
'enable_hyperparameter_tuning': False,
|
|
994
|
+
'max_tuning_iterations': 0,
|
|
995
|
+
'random_state': 42, # Random state for reproducibility
|
|
996
|
+
'test_size': 0.2, # Proportion of data to use for testing
|
|
997
|
+
}
|
|
998
|
+
```
|
|
999
|
+
|
|
1000
|
+
### 环境变量映射
|
|
1001
|
+
|
|
1002
|
+
```bash
|
|
1003
|
+
export MODELTRAINER_TOOL_EXAMPLE=<value>
|
|
1004
|
+
export MODELTRAINER_TOOL_CV_FOLDS=<value>
|
|
1005
|
+
export MODELTRAINER_TOOL_ENABLE_HYPERPARAMETER_TUNING=<value>
|
|
1006
|
+
export MODELTRAINER_TOOL_MAX_TUNING_ITERATIONS=<value>
|
|
1007
|
+
export MODELTRAINER_TOOL_RANDOM_STATE=<value>
|
|
1008
|
+
export MODELTRAINER_TOOL_TEST_SIZE=<value>
|
|
1009
|
+
```
|
|
1010
|
+
|
|
1011
|
+
---
|
|
1012
|
+
|
|
1013
|
+
## OfficeTool
|
|
1014
|
+
|
|
1015
|
+
**配置字段数**: 6 (必需: 6, 可选: 0)
|
|
1016
|
+
|
|
1017
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
1018
|
+
|--------|------|------|--------|------|
|
|
1019
|
+
| `Example` | OFFICE_TOOL_MAX_FILE_SIZE_MB -> max_file_size_mb | ✅ | `-` | - |
|
|
1020
|
+
| `allowed_extensions` | List[str] | ✅ | `-` | - |
|
|
1021
|
+
| `default_font` | str | ✅ | `"Arial"` | Default font for documents |
|
|
1022
|
+
| `default_font_size` | int | ✅ | `12` | Default font size in points |
|
|
1023
|
+
| `max_file_size_mb` | int | ✅ | `100` | Maximum file size in megabytes |
|
|
1024
|
+
| `tika_log_path` | str | ✅ | `-` | - |
|
|
1025
|
+
|
|
1026
|
+
### 配置示例
|
|
1027
|
+
|
|
1028
|
+
```python
|
|
1029
|
+
officetool_config = {
|
|
1030
|
+
'Example': None,
|
|
1031
|
+
'allowed_extensions': "your_allowed_extensions",
|
|
1032
|
+
'default_font': "Arial", # Default font for documents
|
|
1033
|
+
'default_font_size': 12, # Default font size in points
|
|
1034
|
+
'max_file_size_mb': 100, # Maximum file size in megabytes
|
|
1035
|
+
'tika_log_path': "your_tika_log_path",
|
|
1036
|
+
}
|
|
1037
|
+
```
|
|
1038
|
+
|
|
1039
|
+
### 环境变量映射
|
|
1040
|
+
|
|
1041
|
+
```bash
|
|
1042
|
+
export OFFICE_TOOL_EXAMPLE=<value>
|
|
1043
|
+
export OFFICE_TOOL_ALLOWED_EXTENSIONS=<value>
|
|
1044
|
+
export OFFICE_TOOL_DEFAULT_FONT=<value>
|
|
1045
|
+
export OFFICE_TOOL_DEFAULT_FONT_SIZE=<value>
|
|
1046
|
+
export OFFICE_TOOL_MAX_FILE_SIZE_MB=<value>
|
|
1047
|
+
export OFFICE_TOOL_TIKA_LOG_PATH=<value>
|
|
1048
|
+
```
|
|
1049
|
+
|
|
1050
|
+
---
|
|
1051
|
+
|
|
1052
|
+
## PandasTool
|
|
1053
|
+
|
|
1054
|
+
**配置字段数**: 7 (必需: 7, 可选: 0)
|
|
1055
|
+
|
|
1056
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
1057
|
+
|--------|------|------|--------|------|
|
|
1058
|
+
| `Example` | PANDAS_TOOL_CSV_DELIMITER -> csv_delimiter | ✅ | `-` | - |
|
|
1059
|
+
| `allowed_file_extensions` | List[str] | ✅ | `-` | - |
|
|
1060
|
+
| `chunk_size` | int | ✅ | `10000` | Chunk size for large file processing |
|
|
1061
|
+
| `csv_delimiter` | str | ✅ | `"` | Delimiter for CSV files |
|
|
1062
|
+
| `default_agg` | Dict[str, str] | ✅ | `-` | - |
|
|
1063
|
+
| `encoding` | str | ✅ | `"utf-8"` | Encoding for file operations |
|
|
1064
|
+
| `max_csv_size` | int | ✅ | `1000000` | Threshold for chunked CSV processing |
|
|
1065
|
+
|
|
1066
|
+
### 配置示例
|
|
1067
|
+
|
|
1068
|
+
```python
|
|
1069
|
+
pandastool_config = {
|
|
1070
|
+
'Example': None,
|
|
1071
|
+
'allowed_file_extensions': "your_allowed_file_extensions",
|
|
1072
|
+
'chunk_size': 10000, # Chunk size for large file processing
|
|
1073
|
+
'csv_delimiter': ", # Delimiter for CSV files
|
|
1074
|
+
'default_agg': "your_default_agg",
|
|
1075
|
+
'encoding': "utf-8", # Encoding for file operations
|
|
1076
|
+
'max_csv_size': 1000000, # Threshold for chunked CSV processing
|
|
1077
|
+
}
|
|
1078
|
+
```
|
|
1079
|
+
|
|
1080
|
+
### 环境变量映射
|
|
1081
|
+
|
|
1082
|
+
```bash
|
|
1083
|
+
export PANDAS_TOOL_EXAMPLE=<value>
|
|
1084
|
+
export PANDAS_TOOL_ALLOWED_FILE_EXTENSIONS=<value>
|
|
1085
|
+
export PANDAS_TOOL_CHUNK_SIZE=<value>
|
|
1086
|
+
export PANDAS_TOOL_CSV_DELIMITER=<value>
|
|
1087
|
+
export PANDAS_TOOL_DEFAULT_AGG=<value>
|
|
1088
|
+
export PANDAS_TOOL_ENCODING=<value>
|
|
1089
|
+
export PANDAS_TOOL_MAX_CSV_SIZE=<value>
|
|
1090
|
+
```
|
|
1091
|
+
|
|
1092
|
+
---
|
|
1093
|
+
|
|
1094
|
+
## ReportTool
|
|
1095
|
+
|
|
1096
|
+
**配置字段数**: 10 (必需: 10, 可选: 0)
|
|
1097
|
+
|
|
1098
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
1099
|
+
|--------|------|------|--------|------|
|
|
1100
|
+
| `Example` | REPORT_TOOL_TEMPLATES_DIR -> templates_dir | ✅ | `-` | - |
|
|
1101
|
+
| `allowed_extensions` | List[str] | ✅ | `-` | - |
|
|
1102
|
+
| `allowed_html_attributes` | Dict[str, List[str]] | ✅ | `-` | - |
|
|
1103
|
+
| `allowed_html_tags` | Set[str] | ✅ | `-` | - |
|
|
1104
|
+
| `default_font` | str | ✅ | `"Arial"` | Default font for documents |
|
|
1105
|
+
| `default_font_size` | int | ✅ | `12` | Default font size in points |
|
|
1106
|
+
| `default_output_dir` | str | ✅ | `-` | - |
|
|
1107
|
+
| `pdf_page_size` | str | ✅ | `"A4"` | Default PDF page size |
|
|
1108
|
+
| `temp_files_max_age` | int | ✅ | `-` | - |
|
|
1109
|
+
| `templates_dir` | str | ✅ | `os.getcwd(` | Directory for Jinja2 templates |
|
|
1110
|
+
|
|
1111
|
+
### 配置示例
|
|
1112
|
+
|
|
1113
|
+
```python
|
|
1114
|
+
reporttool_config = {
|
|
1115
|
+
'Example': None,
|
|
1116
|
+
'allowed_extensions': "your_allowed_extensions",
|
|
1117
|
+
'allowed_html_attributes': "your_allowed_html_attributes",
|
|
1118
|
+
'allowed_html_tags': "your_allowed_html_tags",
|
|
1119
|
+
'default_font': "Arial", # Default font for documents
|
|
1120
|
+
'default_font_size': 12, # Default font size in points
|
|
1121
|
+
'default_output_dir': "your_default_output_dir",
|
|
1122
|
+
'pdf_page_size': "A4", # Default PDF page size
|
|
1123
|
+
'temp_files_max_age': 0,
|
|
1124
|
+
'templates_dir': os.getcwd(, # Directory for Jinja2 templates
|
|
1125
|
+
}
|
|
1126
|
+
```
|
|
1127
|
+
|
|
1128
|
+
### 环境变量映射
|
|
1129
|
+
|
|
1130
|
+
```bash
|
|
1131
|
+
export REPORT_TOOL_EXAMPLE=<value>
|
|
1132
|
+
export REPORT_TOOL_ALLOWED_EXTENSIONS=<value>
|
|
1133
|
+
export REPORT_TOOL_ALLOWED_HTML_ATTRIBUTES=<value>
|
|
1134
|
+
export REPORT_TOOL_ALLOWED_HTML_TAGS=<value>
|
|
1135
|
+
export REPORT_TOOL_DEFAULT_FONT=<value>
|
|
1136
|
+
export REPORT_TOOL_DEFAULT_FONT_SIZE=<value>
|
|
1137
|
+
export REPORT_TOOL_DEFAULT_OUTPUT_DIR=<value>
|
|
1138
|
+
export REPORT_TOOL_PDF_PAGE_SIZE=<value>
|
|
1139
|
+
export REPORT_TOOL_TEMP_FILES_MAX_AGE=<value>
|
|
1140
|
+
export REPORT_TOOL_TEMPLATES_DIR=<value>
|
|
1141
|
+
```
|
|
1142
|
+
|
|
1143
|
+
---
|
|
1144
|
+
|
|
1145
|
+
## ResearchTool
|
|
1146
|
+
|
|
1147
|
+
**配置字段数**: 5 (必需: 5, 可选: 0)
|
|
1148
|
+
|
|
1149
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
1150
|
+
|--------|------|------|--------|------|
|
|
1151
|
+
| `Example` | RESEARCH_TOOL_SPACY_MODEL -> spacy_model | ✅ | `-` | - |
|
|
1152
|
+
| `allowed_spacy_models` | List[str] | ✅ | `-` | - |
|
|
1153
|
+
| `max_text_length` | int | ✅ | `10_000` | Maximum text length for inputs |
|
|
1154
|
+
| `max_workers` | int | ✅ | `-` | - |
|
|
1155
|
+
| `spacy_model` | str | ✅ | `"en_core_web_sm"` | Default spaCy model to use |
|
|
1156
|
+
|
|
1157
|
+
### 配置示例
|
|
1158
|
+
|
|
1159
|
+
```python
|
|
1160
|
+
researchtool_config = {
|
|
1161
|
+
'Example': None,
|
|
1162
|
+
'allowed_spacy_models': "your_allowed_spacy_models",
|
|
1163
|
+
'max_text_length': 10_000, # Maximum text length for inputs
|
|
1164
|
+
'max_workers': 0,
|
|
1165
|
+
'spacy_model': "en_core_web_sm", # Default spaCy model to use
|
|
1166
|
+
}
|
|
1167
|
+
```
|
|
1168
|
+
|
|
1169
|
+
### 环境变量映射
|
|
1170
|
+
|
|
1171
|
+
```bash
|
|
1172
|
+
export RESEARCH_TOOL_EXAMPLE=<value>
|
|
1173
|
+
export RESEARCH_TOOL_ALLOWED_SPACY_MODELS=<value>
|
|
1174
|
+
export RESEARCH_TOOL_MAX_TEXT_LENGTH=<value>
|
|
1175
|
+
export RESEARCH_TOOL_MAX_WORKERS=<value>
|
|
1176
|
+
export RESEARCH_TOOL_SPACY_MODEL=<value>
|
|
1177
|
+
```
|
|
1178
|
+
|
|
1179
|
+
---
|
|
1180
|
+
|
|
1181
|
+
## ScraperTool
|
|
1182
|
+
|
|
1183
|
+
**配置字段数**: 8 (必需: 8, 可选: 0)
|
|
1184
|
+
|
|
1185
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
1186
|
+
|--------|------|------|--------|------|
|
|
1187
|
+
| `Example` | SCRAPER_TOOL_USER_AGENT -> user_agent | ✅ | `-` | - |
|
|
1188
|
+
| `allowed_domains` | List[str] | ✅ | `[]` | Allowed domains for scraping |
|
|
1189
|
+
| `blocked_domains` | List[str] | ✅ | `[]` | Blocked domains for scraping |
|
|
1190
|
+
| `max_content_length` | int | ✅ | `-` | - |
|
|
1191
|
+
| `output_dir` | str | ✅ | `-` | - |
|
|
1192
|
+
| `playwright_available` | bool | ✅ | `-` | - |
|
|
1193
|
+
| `scrapy_command` | str | ✅ | `"scrapy"` | Command to run Scrapy |
|
|
1194
|
+
| `user_agent` | str | ✅ | `-` | - |
|
|
1195
|
+
|
|
1196
|
+
### 配置示例
|
|
1197
|
+
|
|
1198
|
+
```python
|
|
1199
|
+
scrapertool_config = {
|
|
1200
|
+
'Example': None,
|
|
1201
|
+
'allowed_domains': [], # Allowed domains for scraping
|
|
1202
|
+
'blocked_domains': [], # Blocked domains for scraping
|
|
1203
|
+
'max_content_length': 0,
|
|
1204
|
+
'output_dir': "your_output_dir",
|
|
1205
|
+
'playwright_available': False,
|
|
1206
|
+
'scrapy_command': "scrapy", # Command to run Scrapy
|
|
1207
|
+
'user_agent': "your_user_agent",
|
|
1208
|
+
}
|
|
1209
|
+
```
|
|
1210
|
+
|
|
1211
|
+
### 环境变量映射
|
|
1212
|
+
|
|
1213
|
+
```bash
|
|
1214
|
+
export SCRAPER_TOOL_EXAMPLE=<value>
|
|
1215
|
+
export SCRAPER_TOOL_ALLOWED_DOMAINS=<value>
|
|
1216
|
+
export SCRAPER_TOOL_BLOCKED_DOMAINS=<value>
|
|
1217
|
+
export SCRAPER_TOOL_MAX_CONTENT_LENGTH=<value>
|
|
1218
|
+
export SCRAPER_TOOL_OUTPUT_DIR=<value>
|
|
1219
|
+
export SCRAPER_TOOL_PLAYWRIGHT_AVAILABLE=<value>
|
|
1220
|
+
export SCRAPER_TOOL_SCRAPY_COMMAND=<value>
|
|
1221
|
+
export SCRAPER_TOOL_USER_AGENT=<value>
|
|
1222
|
+
```
|
|
1223
|
+
|
|
1224
|
+
---
|
|
1225
|
+
|
|
1226
|
+
## StatisticalAnalyzerTool
|
|
1227
|
+
|
|
1228
|
+
**配置字段数**: 4 (必需: 4, 可选: 0)
|
|
1229
|
+
|
|
1230
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
1231
|
+
|--------|------|------|--------|------|
|
|
1232
|
+
| `Example` | STATISTICAL_ANALYZER_SIGNIFICANCE_LEVEL -> significance_level | ✅ | `-` | - |
|
|
1233
|
+
| `confidence_level` | float | ✅ | `-` | - |
|
|
1234
|
+
| `enable_effect_size` | bool | ✅ | `-` | - |
|
|
1235
|
+
| `significance_level` | float | ✅ | `-` | - |
|
|
1236
|
+
|
|
1237
|
+
### 配置示例
|
|
1238
|
+
|
|
1239
|
+
```python
|
|
1240
|
+
statisticalanalyzertool_config = {
|
|
1241
|
+
'Example': None,
|
|
1242
|
+
'confidence_level': 0.0,
|
|
1243
|
+
'enable_effect_size': False,
|
|
1244
|
+
'significance_level': 0.0,
|
|
1245
|
+
}
|
|
1246
|
+
```
|
|
1247
|
+
|
|
1248
|
+
### 环境变量映射
|
|
1249
|
+
|
|
1250
|
+
```bash
|
|
1251
|
+
export STATISTICALANALYZER_TOOL_EXAMPLE=<value>
|
|
1252
|
+
export STATISTICALANALYZER_TOOL_CONFIDENCE_LEVEL=<value>
|
|
1253
|
+
export STATISTICALANALYZER_TOOL_ENABLE_EFFECT_SIZE=<value>
|
|
1254
|
+
export STATISTICALANALYZER_TOOL_SIGNIFICANCE_LEVEL=<value>
|
|
1255
|
+
```
|
|
1256
|
+
|
|
1257
|
+
---
|
|
1258
|
+
|
|
1259
|
+
## StatsTool
|
|
1260
|
+
|
|
1261
|
+
**配置字段数**: 3 (必需: 3, 可选: 0)
|
|
1262
|
+
|
|
1263
|
+
| 字段名 | 类型 | 必需 | 默认值 | 说明 |
|
|
1264
|
+
|--------|------|------|--------|------|
|
|
1265
|
+
| `Example` | STATS_TOOL_MAX_FILE_SIZE_MB -> max_file_size_mb | ✅ | `-` | - |
|
|
1266
|
+
| `allowed_extensions` | List[str] | ✅ | `-` | - |
|
|
1267
|
+
| `max_file_size_mb` | int | ✅ | `200` | Maximum file size in megabytes |
|
|
1268
|
+
|
|
1269
|
+
### 配置示例
|
|
1270
|
+
|
|
1271
|
+
```python
|
|
1272
|
+
statstool_config = {
|
|
1273
|
+
'Example': None,
|
|
1274
|
+
'allowed_extensions': "your_allowed_extensions",
|
|
1275
|
+
'max_file_size_mb': 200, # Maximum file size in megabytes
|
|
1276
|
+
}
|
|
1277
|
+
```
|
|
1278
|
+
|
|
1279
|
+
### 环境变量映射
|
|
1280
|
+
|
|
1281
|
+
```bash
|
|
1282
|
+
export STATS_TOOL_EXAMPLE=<value>
|
|
1283
|
+
export STATS_TOOL_ALLOWED_EXTENSIONS=<value>
|
|
1284
|
+
export STATS_TOOL_MAX_FILE_SIZE_MB=<value>
|
|
1285
|
+
```
|
|
1286
|
+
|
|
1287
|
+
---
|