Files
goodbuddy/docs/features/knowledge-base/external-knowledge-probe-2026-09-10-strict.json
T
mesalogo 4483c92b57 fix: distinguish external knowledge probe failures from empty results
Validate Dify and RAGFlow outcomes, normalize FastGPT URLs, and report response envelopes, score structures and actual rerank state. Align integration documentation with official APIs and archive 33 redacted read-only requests with strict HTTPS verification.

Validation: 43 focused tests, typecheck and lint passed. Full test runs exceeded 60s and 240s without a summary; this limitation is recorded in the feature progress document.
2026-09-10 22:19:30 +08:00

829 lines
20 KiB
JSON

{
"schemaVersion": 1,
"probedAt": "2026-09-10T14:02:51.600Z",
"mode": "basic-read-only",
"queryCharacters": 3,
"privacy": "No credentials, origins, IDs, names, queries, or content are included.",
"providers": [
{
"provider": "dify",
"profile": "0.x",
"detectedVersion": "0.15.8",
"transport": {
"protocol": "https:",
"tlsVerificationDisabled": false
},
"catalog": {
"success": true,
"count": 3,
"total": 3,
"itemKeys": [
"app_count",
"created_at",
"created_by",
"data_source_type",
"description",
"doc_form",
"document_count",
"embedding_available",
"embedding_model",
"embedding_model_provider",
"external_knowledge_info",
"external_retrieval_model",
"id",
"indexing_technique",
"name",
"permission",
"provider",
"retrieval_model_dict",
"tags",
"updated_at",
"updated_by",
"word_count"
],
"retrievalModelKeys": [
"reranking_enable",
"reranking_mode",
"reranking_model",
"score_threshold",
"score_threshold_enabled",
"search_method",
"top_k",
"weights"
],
"indexingTechniques": [
"high_quality"
],
"metadataSchemaCount": 0,
"multimodalCount": 0,
"pipelineConfiguredCount": 0,
"summaryIndexConfiguredCount": 0
},
"detail": {
"success": false,
"failure": "http-error",
"keys": [
"code",
"message",
"status"
]
},
"retrievals": [
{
"mode": "dataset-defaults",
"success": true,
"count": 0,
"itemKeys": [],
"segmentKeys": [],
"documentKeys": [],
"childChunkKeys": [],
"fileKeys": [],
"contentPresent": false,
"childContentPresent": false,
"summaryPresent": false
}
],
"features": {
"datasetDefaults": true,
"detailSupported": false,
"retrievalOverrideObserved": true,
"retrievalOverrideProbed": false,
"nonEmptyResultObserved": false
},
"operations": [
{
"name": "catalog",
"method": "GET",
"path": "/v1/datasets",
"status": 200,
"durationMs": 1255,
"responseKeys": [
"data",
"has_more",
"limit",
"page",
"total"
]
},
{
"name": "detail",
"method": "GET",
"path": "/v1/datasets/{id}",
"status": 405,
"durationMs": 105,
"responseKeys": [
"code",
"message",
"status"
]
},
{
"name": "retrieve-defaults",
"method": "POST",
"path": "/v1/datasets/{id}/retrieve",
"status": 200,
"durationMs": 582,
"responseKeys": [
"query",
"records"
]
}
]
},
{
"provider": "dify",
"profile": "1.x",
"detectedVersion": "1.17.0",
"transport": {
"protocol": "https:",
"tlsVerificationDisabled": false
},
"catalog": {
"success": true,
"count": 1,
"total": 1,
"itemKeys": [
"app_count",
"author_name",
"built_in_field_enabled",
"chunk_structure",
"created_at",
"created_by",
"data_source_type",
"description",
"doc_form",
"doc_metadata",
"document_count",
"embedding_available",
"embedding_model",
"embedding_model_provider",
"enable_api",
"external_knowledge_info",
"external_retrieval_model",
"icon_info",
"id",
"indexing_technique",
"is_multimodal",
"is_published",
"maintainer",
"name",
"permission",
"pipeline_id",
"provider",
"retrieval_model_dict",
"runtime_mode",
"summary_index_setting",
"tags",
"total_available_documents",
"total_documents",
"updated_at",
"updated_by",
"word_count"
],
"retrievalModelKeys": [
"reranking_enable",
"reranking_mode",
"reranking_model",
"score_threshold",
"score_threshold_enabled",
"search_method",
"top_k",
"weights"
],
"indexingTechniques": [
"high_quality"
],
"metadataSchemaCount": 0,
"multimodalCount": 0,
"pipelineConfiguredCount": 0,
"summaryIndexConfiguredCount": 1
},
"detail": {
"success": true,
"keys": [
"app_count",
"author_name",
"built_in_field_enabled",
"chunk_structure",
"created_at",
"created_by",
"data_source_type",
"description",
"doc_form",
"doc_metadata",
"document_count",
"embedding_available",
"embedding_model",
"embedding_model_provider",
"enable_api",
"external_knowledge_info",
"external_retrieval_model",
"icon_info",
"id",
"indexing_technique",
"is_multimodal",
"is_published",
"maintainer",
"name",
"permission",
"pipeline_id",
"provider",
"retrieval_model_dict",
"runtime_mode",
"summary_index_setting",
"tags",
"total_available_documents",
"total_documents",
"updated_at",
"updated_by",
"word_count"
]
},
"retrievals": [
{
"mode": "dataset-defaults",
"success": true,
"count": 3,
"itemKeys": [
"child_chunks",
"files",
"score",
"segment",
"summary",
"tsne_position"
],
"segmentKeys": [
"answer",
"completed_at",
"content",
"created_at",
"created_by",
"disabled_at",
"disabled_by",
"document",
"document_id",
"enabled",
"error",
"hit_count",
"id",
"index_node_hash",
"index_node_id",
"indexing_at",
"keywords",
"position",
"sign_content",
"status",
"stopped_at",
"tokens",
"word_count"
],
"documentKeys": [
"data_source_type",
"doc_metadata",
"doc_type",
"id",
"name"
],
"childChunkKeys": [],
"fileKeys": [],
"contentPresent": true,
"childContentPresent": false,
"summaryPresent": false,
"scoreRange": {
"minimum": 0.5038624,
"maximum": 0.6006959
}
}
],
"features": {
"datasetDefaults": true,
"detailSupported": true,
"retrievalOverrideObserved": true,
"retrievalOverrideProbed": false,
"nonEmptyResultObserved": true
},
"operations": [
{
"name": "catalog",
"method": "GET",
"path": "/v1/datasets",
"status": 200,
"durationMs": 2261,
"responseKeys": [
"data",
"has_more",
"limit",
"page",
"total"
]
},
{
"name": "detail",
"method": "GET",
"path": "/v1/datasets/{id}",
"status": 200,
"durationMs": 1680,
"responseKeys": [
"app_count",
"author_name",
"built_in_field_enabled",
"chunk_structure",
"created_at",
"created_by",
"data_source_type",
"description",
"doc_form",
"doc_metadata",
"document_count",
"embedding_available",
"embedding_model",
"embedding_model_provider",
"enable_api",
"external_knowledge_info",
"external_retrieval_model",
"icon_info",
"id",
"indexing_technique",
"is_multimodal",
"is_published",
"maintainer",
"name",
"permission",
"pipeline_id",
"provider",
"retrieval_model_dict",
"runtime_mode",
"summary_index_setting",
"tags",
"total_available_documents",
"total_documents",
"updated_at",
"updated_by",
"word_count"
]
},
{
"name": "retrieve-defaults",
"method": "POST",
"path": "/v1/datasets/{id}/retrieve",
"status": 200,
"durationMs": 3814,
"responseKeys": [
"query",
"records"
]
}
]
},
{
"provider": "fastgpt",
"transport": {
"protocol": "https:",
"tlsVerificationDisabled": false
},
"catalog": {
"success": true,
"count": 1,
"envelope": "data-array",
"itemKeys": [
"_id",
"avatar",
"createTime",
"inheritPermission",
"intro",
"name",
"permission",
"private",
"sourceMember",
"tmbId",
"type",
"updateTime",
"vectorModel"
],
"itemTypes": [
"dataset"
]
},
"detail": {
"keys": [
"_id",
"agentModel",
"agentModelId",
"avatar",
"deleteTime",
"inheritPermission",
"intro",
"name",
"parentId",
"permission",
"status",
"teamId",
"tmbId",
"type",
"updateTime",
"vectorModel",
"vectorModelId",
"vlmModel",
"vlmModelId"
],
"vectorModelKeys": [
"avatar",
"charsPointsPrice",
"config",
"isActive",
"isCustom",
"model",
"modelId",
"name",
"provider",
"scope",
"testMode",
"type"
]
},
"retrievals": [
{
"searchMode": "embedding",
"success": true,
"envelope": "data-list",
"count": 8,
"itemKeys": [
"chunkIndex",
"collectionId",
"datasetId",
"id",
"q",
"score",
"sourceId",
"sourceName",
"updateTime"
],
"contentPresent": true,
"scoreTypes": [
"array"
],
"scoreItemKeys": [
"index",
"type",
"value"
],
"scoreValueRange": {
"minimum": 0.27009665966033936,
"maximum": 0.3160914182662964
},
"rerankEnabled": false
},
{
"searchMode": "fullTextRecall",
"success": true,
"envelope": "data-list",
"count": 2,
"itemKeys": [
"chunkIndex",
"collectionId",
"datasetId",
"id",
"q",
"score",
"sourceId",
"sourceName",
"updateTime"
],
"contentPresent": true,
"scoreTypes": [
"array"
],
"scoreItemKeys": [
"index",
"type",
"value"
],
"scoreValueRange": {
"minimum": 0.5047619047619047,
"maximum": 0.505
},
"rerankEnabled": false
},
{
"searchMode": "mixedRecall",
"success": true,
"envelope": "data-list",
"count": 7,
"itemKeys": [
"chunkIndex",
"collectionId",
"datasetId",
"id",
"q",
"score",
"sourceId",
"sourceName",
"updateTime"
],
"contentPresent": true,
"scoreTypes": [
"array"
],
"scoreItemKeys": [
"index",
"type",
"value"
],
"scoreValueRange": {
"minimum": 0.007575757575757576,
"maximum": 0.505
},
"rerankEnabled": false
}
],
"features": {
"searchModes": [
"embedding",
"fullTextRecall",
"mixedRecall"
],
"rerankProbed": false,
"rerankRequestSucceeded": false,
"extensionQueryProbed": false
},
"operations": [
{
"name": "catalog",
"method": "POST",
"path": "/api/core/dataset/list",
"status": 200,
"businessCode": 200,
"durationMs": 1785,
"responseKeys": [
"code",
"data",
"message",
"statusText"
]
},
{
"name": "detail",
"method": "GET",
"path": "/api/core/dataset/detail",
"status": 200,
"businessCode": 200,
"durationMs": 571,
"responseKeys": [
"code",
"data",
"message",
"statusText"
]
},
{
"name": "retrieve-embedding",
"method": "POST",
"path": "/api/core/dataset/searchTest",
"status": 200,
"businessCode": 200,
"durationMs": 1255,
"responseKeys": [
"code",
"data",
"message",
"statusText"
]
},
{
"name": "retrieve-fullTextRecall",
"method": "POST",
"path": "/api/core/dataset/searchTest",
"status": 200,
"businessCode": 200,
"durationMs": 777,
"responseKeys": [
"code",
"data",
"message",
"statusText"
]
},
{
"name": "retrieve-mixedRecall",
"method": "POST",
"path": "/api/core/dataset/searchTest",
"status": 200,
"businessCode": 200,
"durationMs": 2326,
"responseKeys": [
"code",
"data",
"message",
"statusText"
]
}
]
},
{
"provider": "ragflow",
"transport": {
"protocol": "http:"
},
"catalog": {
"success": true,
"count": 29,
"total": 29,
"itemKeys": [
"artifact_task_finish_at",
"artifact_task_id",
"avatar",
"chunk_count",
"chunk_method",
"create_date",
"create_time",
"created_by",
"description",
"document_count",
"embedding_model",
"graphrag_task_finish_at",
"graphrag_task_id",
"id",
"language",
"mindmap_task_finish_at",
"mindmap_task_id",
"name",
"nickname",
"pagerank",
"parser_config",
"permission",
"pipeline_id",
"raptor_task_finish_at",
"raptor_task_id",
"similarity_threshold",
"skill_task_finish_at",
"skill_task_id",
"status",
"tenant_avatar",
"tenant_embd_id",
"tenant_id",
"token_num",
"update_date",
"update_time",
"vector_similarity_weight"
],
"parserConfigKeys": [
"auto_keywords",
"auto_questions",
"built_in_metadata",
"children_delimiter",
"chunk_token_num",
"compilation_template_group_id",
"delimiter",
"enable_children",
"enable_metadata",
"ext",
"filename_embd_weight",
"graphrag",
"html4excel",
"image_context_size",
"image_table_context_window",
"layout_recognize",
"llm_id",
"metadata",
"mineru_formula_enable",
"mineru_lang",
"mineru_parse_method",
"mineru_table_enable",
"overlapped_percent",
"pages",
"parent_child",
"raptor",
"table_column_mode",
"table_column_names",
"table_column_roles",
"table_context_size",
"tag_kb_ids",
"task_page_size",
"tenant_llm_id",
"toc_extraction",
"topn_tags"
],
"graphConfiguredCount": 18,
"graphCompletedCount": 16,
"knowledgeCompilationConfiguredCount": 0
},
"detail": {
"success": true,
"keys": [
"artifact_task_finish_at",
"artifact_task_id",
"avatar",
"chunk_count",
"chunk_method",
"create_date",
"create_time",
"created_by",
"description",
"document_count",
"embedding_model",
"graphrag_task_finish_at",
"graphrag_task_id",
"id",
"language",
"mindmap_task_finish_at",
"mindmap_task_id",
"name",
"nickname",
"pagerank",
"parser_config",
"permission",
"pipeline_id",
"raptor_task_finish_at",
"raptor_task_id",
"similarity_threshold",
"skill_task_finish_at",
"skill_task_id",
"status",
"tenant_avatar",
"tenant_embd_id",
"tenant_id",
"token_num",
"update_date",
"update_time",
"vector_similarity_weight"
]
},
"retrievals": [
{
"feature": "baseline",
"success": true,
"count": 2,
"itemKeys": [
"content",
"content_ltks",
"dataset_id",
"doc_type_kwd",
"document_id",
"document_keyword",
"id",
"image_id",
"important_keywords",
"mom_id",
"positions",
"row_id",
"similarity",
"tag_kwd",
"term_similarity",
"vector_similarity"
],
"contentPresent": true,
"scoreRange": {
"minimum": 0.18431304078777125,
"maximum": 0.2623782504333604
}
}
],
"features": {
"graphRetrievalProbed": false,
"knowledgeCompilationProbed": false,
"metadataConditionProbed": false
},
"operations": [
{
"name": "catalog",
"method": "GET",
"path": "/api/v1/datasets",
"status": 200,
"businessCode": 0,
"durationMs": 2817,
"responseKeys": [
"code",
"data",
"total_datasets"
]
},
{
"name": "detail",
"method": "GET",
"path": "/api/v1/datasets",
"status": 200,
"businessCode": 0,
"durationMs": 159,
"responseKeys": [
"code",
"data",
"total_datasets"
]
},
{
"name": "retrieve-baseline",
"method": "POST",
"path": "/api/v1/retrieval",
"status": 200,
"businessCode": 0,
"durationMs": 776,
"responseKeys": [
"code",
"data"
]
}
]
}
]
}