Skip to content

RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.

Fix: The picture and audio chunkers in the knowledge base display unnecessary configuration options. (#19911)

balibabu6ae5ac6e5295
diff --git a/internal/ingestion/pipeline/template/ingestion_pipeline_audio.json b/internal/ingestion/pipeline/template/ingestion_pipeline_audio.json
index ba7871c3ad..34c5a9febe 100644
--- a/internal/ingestion/pipeline/template/ingestion_pipeline_audio.json
+++ b/internal/ingestion/pipeline/template/ingestion_pipeline_audio.json
@@ -26,7 +26,7 @@
},
"Parser:SongsFillAir": {
"downstream": [
- "TokenChunker:BlueSkiesLaugh"
+ "OneChunker:BlueSkiesLaugh"
],
"obj": {
"component_name": "Parser",
@@ -78,7 +78,7 @@
"File"
]
},
- "TokenChunker:BlueSkiesLaugh": {
+ "OneChunker:BlueSkiesLaugh": {
"downstream": [
"Extractor:AutoExtractDefault"
],
@@ -117,7 +117,7 @@
},
"Extractor:AutoExtractDefault": {
"upstream": [
- "TokenChunker:BlueSkiesLaugh"
+ "OneChunker:BlueSkiesLaugh"
],
"downstream": [
"Tokenizer:KindEyesWatch"
@@ -161,15 +161,15 @@
"targetHandle": "end"
},
{
- "id": "xy-edge__Parser:SongsFillAirstart-TokenChunker:BlueSkiesLaughend",
+ "id": "xy-edge__Parser:SongsFillAirstart-OneChunker:BlueSkiesLaughend",
"source": "Parser:SongsFillAir",
"sourceHandle": "start",
- "target": "TokenChunker:BlueSkiesLaugh",
+ "target": "OneChunker:BlueSkiesLaugh",
"targetHandle": "end"
},
{
- "id": "xy-edge__TokenChunker:BlueSkiesLaughstart-Extractor:AutoExtractDefaultend",
- "source": "TokenChunker:BlueSkiesLaugh",
+ "id": "xy-edge__OneChunker:BlueSkiesLaughstart-Extractor:AutoExtractDefaultend",
+ "source": "OneChunker:BlueSkiesLaugh",
"sourceHandle": "start",
"target": "Extractor:AutoExtractDefault",
"targetHandle": "end"
@@ -263,7 +263,7 @@
"label": "OneChunker",
"name": "OneChunker_audio"
},
- "id": "TokenChunker:BlueSkiesLaugh",
+ "id": "OneChunker:BlueSkiesLaugh",
"measured": {
"height": 74,
"width": 200
diff --git a/internal/ingestion/pipeline/template/ingestion_pipeline_picture.json b/internal/ingestion/pipeline/template/ingestion_pipeline_picture.json
index 8441fd5951..1d407ad58a 100644
--- a/internal/ingestion/pipeline/template/ingestion_pipeline_picture.json
+++ b/internal/ingestion/pipeline/template/ingestion_pipeline_picture.json
@@ -26,7 +26,7 @@
},
"Parser:ViewsCaptureLight": {
"downstream": [
- "TokenChunker:BrightColorsGlow"
+ "OneChunker:BrightColorsGlow"
],
"obj": {
"component_name": "Parser",
@@ -92,7 +92,7 @@
"File"
]
},
- "TokenChunker:BrightColorsGlow": {
+ "OneChunker:BrightColorsGlow": {
"downstream": [
"Extractor:AutoExtractDefault"
],
@@ -131,7 +131,7 @@
},
"Extractor:AutoExtractDefault": {
"upstream": [
- "TokenChunker:BrightColorsGlow"
+ "OneChunker:BrightColorsGlow"
],
"downstream": [
"Tokenizer:SharpLensFocus"
@@ -175,15 +175,15 @@
"targetHandle": "end"
},
{
- "id": "xy-edge__Parser:ViewsCaptureLightstart-TokenChunker:BrightColorsGlowend",
+ "id": "xy-edge__Parser:ViewsCaptureLightstart-OneChunker:BrightColorsGlowend",
"source": "Parser:ViewsCaptureLight",
"sourceHandle": "start",
- "target": "TokenChunker:BrightColorsGlow",
+ "target": "OneChunker:BrightColorsGlow",
"targetHandle": "end"
},
{
- "id": "xy-edge__TokenChunker:BrightColorsGlowstart-Extractor:AutoExtractDefaultend",
- "source": "TokenChunker:BrightColorsGlow",
+ "id": "xy-edge__OneChunker:BrightColorsGlowstart-Extractor:AutoExtractDefaultend",
+ "source": "OneChunker:BrightColorsGlow",
"sourceHandle": "start",
"target": "Extractor:AutoExtractDefault",
"targetHandle": "end"
@@ -285,7 +285,7 @@
"label": "OneChunker",
"name": "OneChunker_picture"
},
- "id": "TokenChunker:BrightColorsGlow",
+ "id": "OneChunker:BrightColorsGlow",
"measured": {
"height": 74,
"width": 200
diff --git a/internal/ingestion/task/pipeline_executor_defaults_test.go b/internal/ingestion/task/pipeline_executor_defaults_test.go
index 82cc5529a2..3de32bb4b4 100644
--- a/internal/ingestion/task/pipeline_executor_defaults_test.go
+++ b/internal/ingestion/task/pipeline_executor_defaults_test.go
@@ -38,7 +38,7 @@ import (
// Comparison is done per-component (see assertComponentsMatch), so the JSON
// serialization order inside each entry is irrelevant.
var builtinComponentParamsGolden = map[string]string{
- "audio": "{\"File\": {}, \"Parser:SongsFillAir\": {\"audio\": {\"output_format\": \"text\", \"preprocess\": [\"main_content\"], \"suffix\": [\"aac\", \"aiff\", \"ape\", \"au\", \"da\", \"flac\", \"midi\", \"mp3\", \"ogg\", \"oggvorbis\", \"realaudio\", \"vqf\", \"wav\", \"wave\", \"wma\"]}}, \"TokenChunker:BlueSkiesLaugh\": {}, \"Tokenizer:KindEyesWatch\": {\"fields\": \"text\", \"filename_embd_weight\": 0.1, \"search_method\": [\"embedding\", \"full_text\"]}, \"Extractor:AutoExtractDefault\": {\"llm_id\": \"\", \"keywords\": {\"top_n\": 0}, \"questions\": {\"top_n\": 0}, \"tags\": {\"top_n\": 0, \"tag_file_id\": \"\"}, \"summary\": {\"enabled\": false}, \"metadata\": {\"enabled\": false, \"metadata\": [], \"built_in_metadata\": []}}}",
+ "audio": "{\"File\": {}, \"Parser:SongsFillAir\": {\"audio\": {\"output_format\": \"text\", \"preprocess\": [\"main_content\"], \"suffix\": [\"aac\", \"aiff\", \"ape\", \"au\", \"da\", \"flac\", \"midi\", \"mp3\", \"ogg\", \"oggvorbis\", \"realaudio\", \"vqf\", \"wav\", \"wave\", \"wma\"]}}, \"OneChunker:BlueSkiesLaugh\": {}, \"Tokenizer:KindEyesWatch\": {\"fields\": \"text\", \"filename_embd_weight\": 0.1, \"search_method\": [\"embedding\", \"full_text\"]}, \"Extractor:AutoExtractDefault\": {\"llm_id\": \"\", \"keywords\": {\"top_n\": 0}, \"questions\": {\"top_n\": 0}, \"tags\": {\"top_n\": 0, \"tag_file_id\": \"\"}, \"summary\": {\"enabled\": false}, \"metadata\": {\"enabled\": false, \"metadata\": [], \"built_in_metadata\": []}}}",
"book": "{\"File\": {}, \"Parser:HipSignsRhyme\": {\"doc\": {\"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"doc\"]}, \"docx\": {\"flatten_media_to_text\": false, \"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"docx\"], \"vlm\": {}}, \"html\": {\"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"htm\", \"html\"]}, \"pdf\": {\"flatten_media_to_text\": false, \"output_format\": \"json\", \"parse_method\": \"DeepDOC\", \"preprocess\": [\"main_content\"], \"remove_toc\": true, \"suffix\": [\"pdf\"], \"vlm\": {}}, \"text&code\": {\"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"txt\"]}}, \"TitleChunker:GrumpyGarlicsBake\": {\"hierarchy\": 5, \"include_heading_content\": true, \"levels\": [[\"^#[^#]\", \"^##[^#]\", \"^###[^#]\", \"^####[^#]\"], [\"第[零一二三四五六七八九十百0-9]+(分?编|部分)\", \"第[零一二三四五六七八九十百0-9]+章\", \"第[零一二三四五六七八九十百0-9]+节\", \"第[零一二三四五六七八九十百0-9]+条\", \"[\\\\((][零一二三四五六七八九十百]+[\\\\))]\"], [\"第[0-9]+章\", \"第[0-9]+节\", \"[0-9]{1,2}[\\\\. 、]\", \"[0-9]{1,2}\\\\.[0-9]{1,2}($|[^a-zA-Z/%~.-])\", \"[0-9]{1,2}\\\\.[0-9]{1,2}\\\\.[0-9]{1,2}\"], [\"第[零一二三四五六七八九十百0-9]+章\", \"第[零一二三四五六七八九十百0-9]+节\", \"[零一二三四五六七八九十百]+[ 、]\", \"[\\\\((][零一二三四五六七八九十百]+[\\\\))]\", \"[\\\\((][0-9]{,2}[\\\\))]\"], [\"PART (ONE|TWO|THREE|FOUR|FIVE|SIX|SEVEN|EIGHT|NINE|TEN)\", \"Chapter (I+V?|VI*|XI|IX|X)\", \"Section [0-9]+\", \"Article [0-9]+\"]], \"method\": \"hierarchy\"}, \"Tokenizer:HotDonutsRing\": {\"fields\": \"text\", \"filename_embd_weight\": 0.1, \"search_method\": [\"embedding\", \"full_text\"]}, \"Extractor:AutoExtractDefault\": {\"llm_id\": \"\", \"keywords\": {\"top_n\": 0}, \"questions\": {\"top_n\": 0}, \"tags\": {\"top_n\": 0, \"tag_file_id\": \"\"}, \"summary\": {\"enabled\": false}, \"metadata\": {\"enabled\": false, \"metadata\": [], \"built_in_metadata\": []}}}",
"email": "{\"File\": {}, \"Parser:BirdsFlutterHigh\": {\"email\": {\"fields\": [\"from\", \"to\", \"cc\", \"bcc\", \"date\", \"subject\", \"body\", \"attachments\"], \"output_format\": \"text\", \"preprocess\": [\"main_content\"], \"suffix\": [\"eml\"]}}, \"TokenChunker:WarmBreadSmells\": {\"children_delimiters\": [], \"chunk_token_size\": 512, \"delimiter_mode\": \"delimiter\", \"delimiters\": [\"\\n\", \"!\", \"?\", \"。\", \";\", \"!\", \"?\"], \"image_context_size\": 0, \"overlapped_percent\": 0, \"table_context_size\": 0}, \"Tokenizer:NiceWordsSpoken\": {\"fields\": \"text\", \"filename_embd_weight\": 0.1, \"search_method\": [\"embedding\", \"full_text\"]}, \"Extractor:AutoExtractDefault\": {\"llm_id\": \"\", \"keywords\": {\"top_n\": 0}, \"questions\": {\"top_n\": 0}, \"tags\": {\"top_n\": 0, \"tag_file_id\": \"\"}, \"summary\": {\"enabled\": false}, \"metadata\": {\"enabled\": false, \"metadata\": [], \"built_in_metadata\": []}}}",
"general": "{\"File\": {}, \"Parser:HipSignsRhyme\": {\"doc\": {\"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"doc\"]}, \"docx\": {\"flatten_media_to_text\": false, \"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"docx\"], \"vlm\": {}}, \"html\": {\"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"htm\", \"html\"]}, \"markdown\": {\"flatten_media_to_text\": false, \"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"md\", \"markdown\", \"mdx\"], \"vlm\": {}}, \"pdf\": {\"flatten_media_to_text\": false, \"output_format\": \"json\", \"pages\": [[1, 100000]], \"parse_method\": \"DeepDOC\", \"preprocess\": [\"main_content\"], \"suffix\": [\"pdf\"], \"vlm\": {}}, \"spreadsheet\": {\"flatten_media_to_text\": false, \"output_format\": \"json\", \"parse_method\": \"DeepDOC\", \"preprocess\": [\"main_content\"], \"suffix\": [\"xls\", \"xlsx\", \"csv\"], \"vlm\": {}}, \"text&code\": {\"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"txt\", \"py\", \"js\", \"java\", \"c\", \"cpp\", \"h\", \"php\", \"go\", \"ts\", \"sh\", \"cs\", \"kt\", \"sql\"]}}, \"GeneralChunker:SixApplesFall\": {\"children_delimiters\": [], \"chunk_token_size\": 512, \"delimiters\": [\"\\n\", \"!\", \"?\", \";\", \"。\", \";\", \"!\", \"?\"], \"image_context_size\": 0, \"overlapped_percent\": 0, \"table_context_size\": 0}, \"Tokenizer:LegalReadersDecide\": {\"fields\": \"text\", \"filename_embd_weight\": 0.1, \"search_method\": [\"embedding\", \"full_text\"]}, \"Extractor:AutoExtractDefault\": {\"llm_id\": \"\", \"keywords\": {\"top_n\": 0}, \"questions\": {\"top_n\": 0}, \"tags\": {\"top_n\": 0, \"tag_file_id\": \"\"}, \"summary\": {\"enabled\": false}, \"metadata\": {\"enabled\": false, \"metadata\": [], \"built_in_metadata\": []}}}",
@@ -46,7 +46,7 @@ var builtinComponentParamsGolden = map[string]string{
"manual": "{\"File\": {}, \"Parser:HipSignsRhyme\": {\"doc\": {\"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"doc\"]}, \"docx\": {\"flatten_media_to_text\": false, \"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"docx\"], \"vlm\": {}}, \"pdf\": {\"flatten_media_to_text\": false, \"output_format\": \"json\", \"parse_method\": \"DeepDOC\", \"preprocess\": [\"main_content\"], \"suffix\": [\"pdf\"], \"vlm\": {}}}, \"ManualChunker:NineInsectsFind\": {\"hierarchy\": 0, \"include_heading_content\": false, \"levels\": [[\"^#[^#]\", \"^##[^#]\", \"^###[^#]\", \"^####[^#]\"], [\"第[零一二三四五六七八九十百0-9]+(分?编|部分)\", \"第[零一二三四五六七八九十百0-9]+章\", \"第[零一二三四五六七八九十百0-9]+节\", \"第[零一二三四五六七八九十百0-9]+条\", \"[\\\\((][零一二三四五六七八九十百]+[\\\\))]\"], [\"第[0-9]+章\", \"第[0-9]+节\", \"[0-9]{1,2}[\\\\. 、]\", \"[0-9]{1,2}\\\\.[0-9]{1,2}($|[^a-zA-Z/%~.-])\", \"[0-9]{1,2}\\\\.[0-9]{1,2}\\\\.[0-9]{1,2}\"], [\"第[零一二三四五六七八九十百0-9]+章\", \"第[零一二三四五六七八九十百0-9]+节\", \"[零一二三四五六七八九十百]+[ 、]\", \"[\\\\((][零一二三四五六七八九十百]+[\\\\))]\", \"[\\\\((][0-9]{,2}[\\\\))]\"], [\"PART (ONE|TWO|THREE|FOUR|FIVE|SIX|SEVEN|EIGHT|NINE|TEN)\", \"Chapter (I+V?|VI*|XI|IX|X)\", \"Section [0-9]+\", \"Article [0-9]+\"]], \"method\": \"group\"}, \"Tokenizer:FunnyBalloonsGrin\": {\"fields\": \"text\", \"filename_embd_weight\": 0.1, \"search_method\": [\"embedding\", \"full_text\"]}, \"Extractor:AutoExtractDefault\": {\"llm_id\": \"\", \"keywords\": {\"top_n\": 0}, \"questions\": {\"top_n\": 0}, \"tags\": {\"top_n\": 0, \"tag_file_id\": \"\"}, \"summary\": {\"enabled\": false}, \"metadata\": {\"enabled\": false, \"metadata\": [], \"built_in_metadata\": []}}}",
"one": "{\"File\": {}, \"Parser:HipSignsRhyme\": {\"doc\": {\"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"doc\"]}, \"docx\": {\"flatten_media_to_text\": false, \"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"docx\"], \"vlm\": {}}, \"html\": {\"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"htm\", \"html\"]}, \"markdown\": {\"flatten_media_to_text\": false, \"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"md\", \"markdown\", \"mdx\"], \"vlm\": {}}, \"pdf\": {\"flatten_media_to_text\": false, \"output_format\": \"json\", \"parse_method\": \"DeepDOC\", \"preprocess\": [\"main_content\"], \"suffix\": [\"pdf\"], \"vlm\": {}}, \"spreadsheet\": {\"flatten_media_to_text\": false, \"output_format\": \"html\", \"parse_method\": \"DeepDOC\", \"preprocess\": [\"main_content\"], \"suffix\": [\"xls\", \"xlsx\"], \"vlm\": {}}, \"text&code\": {\"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"txt\"]}}, \"OneChunker:DryDrinksVisit\": {}, \"Tokenizer:FrankWeeksListen\": {\"fields\": \"text\", \"filename_embd_weight\": 0.1, \"search_method\": [\"embedding\", \"full_text\"]}, \"Extractor:AutoExtractDefault\": {\"llm_id\": \"\", \"keywords\": {\"top_n\": 0}, \"questions\": {\"top_n\": 0}, \"tags\": {\"top_n\": 0, \"tag_file_id\": \"\"}, \"summary\": {\"enabled\": false}, \"metadata\": {\"enabled\": false, \"metadata\": [], \"built_in_metadata\": []}}}",
"paper": "{\"File\": {}, \"Parser:HipSignsRhyme\": {\"pdf\": {\"enable_multi_column\": true, \"flatten_media_to_text\": false, \"output_format\": \"json\", \"parse_method\": \"DeepDOC\", \"preprocess\": [\"main_content\"], \"suffix\": [\"pdf\"], \"vlm\": {}}}, \"TitleChunker:SparklySchoolsTravel\": {\"hierarchy\": 0, \"include_heading_content\": false, \"levels\": [[\"^#[^#]\", \"^##[^#]\", \"^###[^#]\", \"^####[^#]\"], [\"第[零一二三四五六七八九十百0-9]+(分?编|部分)\", \"第[零一二三四五六七八九十百0-9]+章\", \"第[零一二三四五六七八九十百0-9]+节\", \"第[零一二三四五六七八九十百0-9]+条\", \"[\\\\((][零一二三四五六七八九十百]+[\\\\))]\"], [\"第[0-9]+章\", \"第[0-9]+节\", \"[0-9]{1,2}[\\\\. 、]\", \"[0-9]{1,2}\\\\.[0-9]{1,2}($|[^a-zA-Z/%~.-])\", \"[0-9]{1,2}\\\\.[0-9]{1,2}\\\\.[0-9]{1,2}\"], [\"第[零一二三四五六七八九十百0-9]+章\", \"第[零一二三四五六七八九十百0-9]+节\", \"[零一二三四五六七八九十百]+[ 、]\", \"[\\\\((][零一二三四五六七八九十百]+[\\\\))]\", \"[\\\\((][0-9]{,2}[\\\\))]\"], [\"PART (ONE|TWO|THREE|FOUR|FIVE|SIX|SEVEN|EIGHT|NINE|TEN)\", \"Chapter (I+V?|VI*|XI|IX|X)\", \"Section [0-9]+\", \"Article [0-9]+\"]], \"method\": \"group\"}, \"Tokenizer:GreatCarsWash\": {\"fields\": \"text\", \"filename_embd_weight\": 0.1, \"search_method\": [\"embedding\", \"full_text\"]}, \"Extractor:AutoExtractDefault\": {\"llm_id\": \"\", \"keywords\": {\"top_n\": 0}, \"questions\": {\"top_n\": 0}, \"tags\": {\"top_n\": 0, \"tag_file_id\": \"\"}, \"summary\": {\"enabled\": false}, \"metadata\": {\"enabled\": false, \"metadata\": [], \"built_in_metadata\": []}}}",
- "picture": "{\"File\": {}, \"Parser:ViewsCaptureLight\": {\"image\": {\"output_format\": \"json\", \"parse_method\": \"ocr\", \"preprocess\": [\"main_content\"], \"suffix\": [\"bmp\", \"gif\", \"jpeg\", \"jpg\", \"png\", \"svg\", \"tif\", \"tiff\", \"webp\"]}, \"video\": {\"output_format\": \"text\", \"preprocess\": [\"main_content\"], \"suffix\": [\"3gp\", \"3gpp\", \"avi\", \"flv\", \"mkv\", \"mov\", \"mp4\", \"mpeg\", \"mpg\", \"webm\", \"wmv\"]}}, \"TokenChunker:BrightColorsGlow\": {}, \"Tokenizer:SharpLensFocus\": {\"fields\": \"text\", \"filename_embd_weight\": 0.1, \"search_method\": [\"embedding\", \"full_text\"]}, \"Extractor:AutoExtractDefault\": {\"llm_id\": \"\", \"keywords\": {\"top_n\": 0}, \"questions\": {\"top_n\": 0}, \"tags\": {\"top_n\": 0, \"tag_file_id\": \"\"}, \"summary\": {\"enabled\": false}, \"metadata\": {\"enabled\": false, \"metadata\": [], \"built_in_metadata\": []}}}",
+ "picture": "{\"File\": {}, \"Parser:ViewsCaptureLight\": {\"image\": {\"output_format\": \"json\", \"parse_method\": \"ocr\", \"preprocess\": [\"main_content\"], \"suffix\": [\"bmp\", \"gif\", \"jpeg\", \"jpg\", \"png\", \"svg\", \"tif\", \"tiff\", \"webp\"]}, \"video\": {\"output_format\": \"text\", \"preprocess\": [\"main_content\"], \"suffix\": [\"3gp\", \"3gpp\", \"avi\", \"flv\", \"mkv\", \"mov\", \"mp4\", \"mpeg\", \"mpg\", \"webm\", \"wmv\"]}}, \"OneChunker:BrightColorsGlow\": {}, \"Tokenizer:SharpLensFocus\": {\"fields\": \"text\", \"filename_embd_weight\": 0.1, \"search_method\": [\"embedding\", \"full_text\"]}, \"Extractor:AutoExtractDefault\": {\"llm_id\": \"\", \"keywords\": {\"top_n\": 0}, \"questions\": {\"top_n\": 0}, \"tags\": {\"top_n\": 0, \"tag_file_id\": \"\"}, \"summary\": {\"enabled\": false}, \"metadata\": {\"enabled\": false, \"metadata\": [], \"built_in_metadata\": []}}}",
"presentation": "{\"File\": {}, \"Parser:HipSignsRhyme\": {\"pdf\": {\"flatten_media_to_text\": false, \"output_format\": \"json\", \"parse_method\": \"DeepDOC\", \"preprocess\": [\"main_content\"], \"suffix\": [\"pdf\"], \"vlm\": {}}, \"slides\": {\"output_format\": \"json\", \"parse_method\": \"DeepDOC\", \"preprocess\": [\"main_content\"], \"suffix\": [\"pptx\", \"ppt\"]}}, \"Tokenizer:TallTreesDance\": {\"fields\": \"text\", \"filename_embd_weight\": 0.1, \"search_method\": [\"embedding\", \"full_text\"]}, \"PageChunker:HappyHillsGlow\": {}, \"Extractor:AutoExtractDefault\": {\"llm_id\": \"\", \"keywords\": {\"top_n\": 0}, \"questions\": {\"top_n\": 0}, \"tags\": {\"top_n\": 0, \"tag_file_id\": \"\"}, \"summary\": {\"enabled\": false}, \"metadata\": {\"enabled\": false, \"metadata\": [], \"built_in_metadata\": []}}}",
"qa": "{\"File\": {}, \"Parser:HipSignsRhyme\": {\"docx\": {\"flatten_media_to_text\": false, \"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"docx\"], \"vlm\": {}}, \"markdown\": {\"flatten_media_to_text\": false, \"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"md\", \"markdown\", \"mdx\"], \"vlm\": {}}, \"pdf\": {\"flatten_media_to_text\": false, \"output_format\": \"json\", \"parse_method\": \"DeepDOC\", \"preprocess\": [\"main_content\"], \"suffix\": [\"pdf\"], \"vlm\": {}}, \"spreadsheet\": {\"flatten_media_to_text\": false, \"output_format\": \"html\", \"parse_method\": \"DeepDOC\", \"preprocess\": [\"main_content\"], \"suffix\": [\"xls\", \"xlsx\", \"csv\"], \"vlm\": {}}, \"text&code\": {\"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"txt\"]}}, \"Tokenizer:ColdCloudsDream\": {\"fields\": \"text\", \"filename_embd_weight\": 0.1, \"search_method\": [\"embedding\", \"full_text\"]}, \"QAChunker:TidyCloudsThink\": {}}",
"table": "{\"File\": {}, \"Parser:HipSignsRhyme\": {\"spreadsheet\": {\"flatten_media_to_text\": false, \"output_format\": \"html\", \"parse_method\": \"DeepDOC\", \"preprocess\": [\"main_content\"], \"suffix\": [\"xls\", \"xlsx\", \"csv\"], \"vlm\": {}, \"column_mode\": \"auto\", \"column_roles\": {}, \"column_names\": []}, \"text&code\": {\"output_format\": \"json\", \"preprocess\": [\"main_content\"], \"suffix\": [\"txt\"]}}, \"TableChunker:FastFoxesJump\": {}, \"Tokenizer:DeepLakesShine\": {\"fields\": \"text\", \"filename_embd_weight\": 0.1, \"search_method\": [\"embedding\", \"full_text\"]}}",
diff --git a/web/src/components/pipeline-operator-tabs/pipeline-operator-form.tsx b/web/src/components/pipeline-operator-tabs/pipeline-operator-form.tsx
index a1aa1b7252..423da244a9 100644
--- a/web/src/components/pipeline-operator-tabs/pipeline-operator-form.tsx
+++ b/web/src/components/pipeline-operator-tabs/pipeline-operator-form.tsx
@@ -25,6 +25,7 @@ import TokenizerForm from '@/pages/agent/form/tokenizer-form';
import { getOperatorType } from '@/utils/pipeline-operator';
import { memo, useCallback } from 'react';
import { FieldErrors } from 'react-hook-form';
+import { useTranslation } from 'react-i18next';
type PipelineOperatorFormProps = {
node: RAGFlowNodeType;
@@ -35,12 +36,20 @@ type PipelineOperatorFormProps = {
fixedFileFormats?: boolean;
};
+// Derive the built-in parser name from the chunker node name, e.g.
+// "Table Chunker" -> "Table".
+function getBuiltinParserName(node: RAGFlowNodeType): string {
+ return String(node.data?.name ?? '').replace(/\s*Chunker$/, '');
+}
+
const PipelineOperatorForm = ({
node,
onValuesChange,
externalErrors,
fixedFileFormats,
}: PipelineOperatorFormProps) => {
+ const { t } = useTranslation();
+
const operatorType = getOperatorType(
(node.data as Record<string, any>)?.operatorId || node.data?.label || '',
);
@@ -118,6 +127,19 @@ const PipelineOperatorForm = ({
externalErrors={externalErrors}
/>
);
+ case Operator.TableChunker:
+ case Operator.QAChunker:
+ case Operator.OneChunker:
+ case Operator.PageChunker:
+ // These chunkers have no configurable parameters — the built-in parser
+ // handles chunking internally.
+ return (
+ <div className="p-4 text-sm text-text-secondary">
+ {t('knowledgeConfiguration.noConfigChunkerHint', {
+ name: getBuiltinParserName(node),
+ })}
+ </div>
+ );
default:
return null;
}
diff --git a/web/src/constants/agent.tsx b/web/src/constants/agent.tsx
index c3fb973a83..5152dd5814 100644
--- a/web/src/constants/agent.tsx
+++ b/web/src/constants/agent.tsx
@@ -133,6 +133,10 @@ export enum Operator {
GeneralChunker = 'GeneralChunker',
TokenChunker = 'TokenChunker',
TitleChunker = 'TitleChunker',
+ TableChunker = 'TableChunker',
+ QAChunker = 'QAChunker',
+ OneChunker = 'OneChunker',
+ PageChunker = 'PageChunker',
Extractor = 'Extractor',
Compiler = 'Compiler',
Loop = 'Loop',
diff --git a/web/src/locales/en.ts b/web/src/locales/en.ts
index a18f5c4ab8..1bf3effbbe 100644
--- a/web/src/locales/en.ts
+++ b/web/src/locales/en.ts
@@ -748,6 +748,8 @@ Example: A 1 KB message with 1024-dim embedding uses ~9 KB. The 5 MB default lim
parseType: 'Parse mode',
manualSetup: 'Custom ingestion pipeline',
builtIn: 'Built-in parsing template',
+ noConfigChunkerHint:
+ 'The built-in {{name}} parser handles chunking automatically, so no additional configuration is required.',
titleDescription:
'Update your dataset configuration here, particularly the LLM and prompts.',
name: 'Dataset name',
@@ -3514,6 +3516,14 @@ This process aggregates variables from multiple branches into a single variable
titleChunkerDescription:
'Split documents into sections by title hierarchy. Define heading levels with regex rules, then choose Hierarchy or Group mode to control how chunks are structured.',
titleChunker: 'Title Chunker',
+ oneChunkerDescription:
+ 'No additional configuration is required for this chunker.',
+ qAChunkerDescription:
+ 'No additional configuration is required for this chunker.',
+ tableChunkerDescription:
+ 'No additional configuration is required for this chunker.',
+ pageChunkerDescription:
+ 'No additional configuration is required for this chunker.',
extractor: 'Transformer',
extractorDescription:
'Use an LLM to extract structured insights from document chunks—such as summaries, classifications, etc.',
diff --git a/web/src/locales/zh.ts b/web/src/locales/zh.ts
index c1a771db83..c96cf89002 100644
--- a/web/src/locales/zh.ts
+++ b/web/src/locales/zh.ts
@@ -686,6 +686,8 @@ export default {
parseType: '解析方式',
manualSetup: '自定义Ingestion pipeline',
builtIn: '内置解析模板',
+ noConfigChunkerHint:
+ '内置的 {{name}} 解析器会自动处理分块,因此无需额外配置。',
titleDescription: '在这里更新您的知识库配置,特别是大语言模型和提示词。',
name: '知识库名称',
photo: '知识库图片',
@@ -3060,6 +3062,10 @@ NER:使用 spaCy NER 和基于规则的关键词提取来抽取 Entities 和 R
titleChunkerDescription:
'按标题层级拆分文档。通过正则表达式定义各级标题,再选择层级或分组模式控制切片方式。',
titleChunker: '按标题分块',
+ oneChunkerDescription: '此 Chunker 无需额外配置。',
+ qAChunkerDescription: '此 Chunker 无需额外配置。',
+ tableChunkerDescription: '此 Chunker 无需额外配置。',
+ pageChunkerDescription: '此 Chunker 无需额外配置。',
extractor: '提取器',
extractorDescription:
'使用 LLM 从文档块(例如摘要、分类等)中提取结构化见解。',