{ "id": 24, "title": { "en": "Chunk Summary", "de": "Segmentzusammenfassung", "zh": "总结切片" }, "description": { "en": "This template uses an LLM to generate chunk summaries for building text and vector indexes. During retrieval, summaries enhance matching, and the original chunks are returned as results.", "de": "Diese Vorlage nutzt ein LLM zur Generierung von Segmentzusammenfassungen für den Aufbau von Text- und Vektorindizes. Bei der Abfrage verbessern die Zusammenfassungen die Übereinstimmung, während die ursprünglichen Segmente als Ergebnisse zurückgegeben werden.", "zh": "此模板利用大模型生成切片摘要，并据此建立全文索引与向量。检索时以摘要提升匹配效果，最终召回对应的原文切片。" }, "canvas_type": "Ingestion Pipeline", "canvas_category": "dataflow_canvas", "dsl": { "components": { "Extractor:SharpTaxisSay": { "downstream": [ "Tokenizer:ShaggyShrimpsLose" ], "obj": { "component_name": "Extractor", "params": { "field_name": "summary", "frequencyPenaltyEnabled": true, "frequency_penalty": 0.7, "llm_id": "THUDM/GLM-4.1V-9B-Thinking@SILICONFLOW", "maxTokensEnabled": false, "max_tokens": 256, "outputs": { "chunks": { "type": "Array", "value": [] } }, "presencePenaltyEnabled": true, "presence_penalty": 0.4, "prompts": [ { "content": "Text to Summarize:\n{TokenChunker:ModernPetsKneel@chunks}", "role": "user" } ], "sys_prompt": "Act as a precise summarizer. Your task is to create a summary of the provided content that is both concise and faithful to the original.\n\nKey Instructions:\n1. Accuracy: Strictly base the summary on the information given. Do not introduce any new facts, conclusions, or interpretations that are not explicitly stated.\n2. Language: Write the summary in the same language as the source text.\n3. Objectivity: Present the key points without bias, preserving the original intent and tone of the content. Do not editorialize.\n4. Conciseness: Focus on the most important ideas, omitting minor details and fluff.", "temperature": 0.1, "temperatureEnabled": true, "tenant_llm_id": 63, "topPEnabled": true, "top_p": 0.3 } }, "upstream": [ "TokenChunker:ModernPetsKneel" ] }, "File": { "downstream": [ "Parser:HipSignsRhyme" ], "obj": { "component_name": "File", "params": {} }, "upstream": [] }, "Parser:HipSignsRhyme": { "downstream": [ "TokenChunker:ModernPetsKneel" ], "obj": { "component_name": "Parser", "params": { "outputs": { "html": { "type": "string", "value": "" }, "json": { "type": "Array", "value": [] }, "markdown": { "type": "string", "value": "" }, "text": { "type": "string", "value": "" } }, "setups": { "doc": { "output_format": "json", "preprocess": "main_content", "suffix": [ "doc" ] }, "docx": { "flatten_media_to_text": false, "output_format": "json", "preprocess": "main_content", "suffix": [ "docx" ], "vlm": {} }, "email": { "fields": [ "from", "to", "cc", "bcc", "date", "subject", "body", "attachments" ], "output_format": "text", "preprocess": "main_content", "suffix": [ "eml", "msg" ] }, "html": { "output_format": "json", "preprocess": "main_content", "suffix": [ "htm", "html" ] }, "image": { "output_format": "text", "parse_method": "ocr", "preprocess": "main_content", "suffix": [ "jpg", "jpeg", "png", "gif" ], "system_prompt": "" }, "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": {} }, "slides": { "output_format": "json", "parse_method": "DeepDOC", "preprocess": "main_content", "suffix": [ "pptx", "ppt" ] }, "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", "py", "js", "java", "c", "cpp", "h", "php", "go", "ts", "sh", "cs", "kt", "sql" ] } } } }, "upstream": [ "File" ] }, "TokenChunker:ModernPetsKneel": { "downstream": [ "Extractor:SharpTaxisSay" ], "obj": { "component_name": "TokenChunker", "params": { "children_delimiters": [], "chunk_token_size": 512, "delimiter_mode": "token_size", "delimiters": [], "image_context_size": 0, "outputs": { "chunks": { "type": "Array", "value": [] } }, "overlapped_percent": 0, "table_context_size": 0 } }, "upstream": [ "Parser:HipSignsRhyme" ] }, "Tokenizer:ShaggyShrimpsLose": { "downstream": [], "obj": { "component_name": "Tokenizer", "params": { "fields": "text", "filename_embd_weight": 0.1, "outputs": {}, "search_method": [ "embedding", "full_text" ] } }, "upstream": [ "Extractor:SharpTaxisSay" ] } }, "globals": { "sys.history": [] }, "graph": { "edges": [ { "id": "xy-edge__Filestart-Parser:HipSignsRhymeend", "source": "File", "sourceHandle": "start", "target": "Parser:HipSignsRhyme", "targetHandle": "end" }, { "id": "xy-edge__Parser:HipSignsRhymestart-TokenChunker:ModernPetsKneelend", "source": "Parser:HipSignsRhyme", "sourceHandle": "start", "target": "TokenChunker:ModernPetsKneel", "targetHandle": "end" }, { "id": "xy-edge__TokenChunker:ModernPetsKneelstart-Extractor:SharpTaxisSayend", "source": "TokenChunker:ModernPetsKneel", "sourceHandle": "start", "target": "Extractor:SharpTaxisSay", "targetHandle": "end" }, { "data": { "isHovered": false }, "id": "xy-edge__Extractor:SharpTaxisSaystart-Tokenizer:ShaggyShrimpsLoseend", "markerEnd": "logo", "source": "Extractor:SharpTaxisSay", "sourceHandle": "start", "target": "Tokenizer:ShaggyShrimpsLose", "targetHandle": "end", "type": "buttonEdge", "zIndex": 1001 } ], "nodes": [ { "data": { "label": "File", "name": "File" }, "id": "File", "measured": { "height": 50, "width": 200 }, "position": { "x": 50, "y": 200 }, "sourcePosition": "left", "targetPosition": "right", "type": "beginNode" }, { "data": { "form": { "outputs": { "html": { "type": "string", "value": "" }, "json": { "type": "Array", "value": [] }, "markdown": { "type": "string", "value": "" }, "text": { "type": "string", "value": "" } }, "setups": [ { "fileFormat": "pdf", "flatten_media_to_text": false, "output_format": "json", "parse_method": "DeepDOC", "preprocess": "main_content" }, { "fileFormat": "spreadsheet", "flatten_media_to_text": false, "output_format": "html", "parse_method": "DeepDOC", "preprocess": "main_content" }, { "fileFormat": "image", "output_format": "text", "parse_method": "ocr", "preprocess": "main_content", "system_prompt": "" }, { "fields": [ "from", "to", "cc", "bcc", "date", "subject", "body", "attachments" ], "fileFormat": "email", "output_format": "text", "preprocess": "main_content" }, { "fileFormat": "markdown", "flatten_media_to_text": false, "output_format": "json", "preprocess": "main_content" }, { "fileFormat": "text&code", "output_format": "json", "preprocess": "main_content" }, { "fileFormat": "html", "output_format": "json", "preprocess": "main_content" }, { "fileFormat": "doc", "output_format": "json", "preprocess": "main_content" }, { "fileFormat": "docx", "flatten_media_to_text": false, "output_format": "json", "preprocess": "main_content" }, { "fileFormat": "slides", "output_format": "json", "parse_method": "DeepDOC", "preprocess": "main_content" } ] }, "label": "Parser", "name": "Parser_0" }, "dragging": false, "id": "Parser:HipSignsRhyme", "measured": { "height": 57, "width": 200 }, "position": { "x": 316.99524094206413, "y": 195.39629819663406 }, "selected": false, "sourcePosition": "right", "targetPosition": "left", "type": "parserNode" }, { "data": { "form": { "chunk_token_size": 512, "delimiter_mode": "token_size", "delimiters": [ { "value": "\n" } ], "image_table_context_window": 0, "outputs": { "chunks": { "type": "Array", "value": [] } }, "overlapped_percent": 0 }, "label": "TokenChunker", "name": "Token Chunker_0" }, "id": "TokenChunker:ModernPetsKneel", "measured": { "height": 74, "width": 200 }, "position": { "x": 616.9952409420641, "y": 195.39629819663406 }, "sourcePosition": "right", "targetPosition": "left", "type": "chunkerNode" }, { "data": { "form": { "fields": "text", "filename_embd_weight": 0.1, "outputs": {}, "search_method": [ "embedding", "full_text" ] }, "label": "Tokenizer", "name": "Indexer_0" }, "dragging": false, "id": "Tokenizer:ShaggyShrimpsLose", "measured": { "height": 114, "width": 200 }, "position": { "x": 1188.9891545215792, "y": 159.26426539640332 }, "selected": false, "sourcePosition": "right", "targetPosition": "left", "type": "tokenizerNode" }, { "data": { "form": { "field_name": "summary", "frequencyPenaltyEnabled": true, "frequency_penalty": 0.7, "llm_id": "THUDM/GLM-4.1V-9B-Thinking@SILICONFLOW", "maxTokensEnabled": false, "max_tokens": 256, "outputs": { "chunks": { "type": "Array", "value": [] } }, "presencePenaltyEnabled": true, "presence_penalty": 0.4, "prompts": "Text to Summarize:\n{TokenChunker:ModernPetsKneel@chunks}", "sys_prompt": "Act as a precise summarizer. Your task is to create a summary of the provided content that is both concise and faithful to the original.\n\nKey Instructions:\n1. Accuracy: Strictly base the summary on the information given. Do not introduce any new facts, conclusions, or interpretations that are not explicitly stated.\n2. Language: Write the summary in the same language as the source text.\n3. Objectivity: Present the key points without bias, preserving the original intent and tone of the content. Do not editorialize.\n4. Conciseness: Focus on the most important ideas, omitting minor details and fluff.", "temperature": 0.1, "temperatureEnabled": true, "tenant_llm_id": 63, "topPEnabled": true, "top_p": 0.3 }, "label": "Extractor", "name": "Summarization" }, "dragging": false, "id": "Extractor:SharpTaxisSay", "measured": { "height": 90, "width": 200 }, "position": { "x": 878.855872986265, "y": 177.33028179651868 }, "selected": true, "sourcePosition": "right", "targetPosition": "left", "type": "contextNode" } ] }, "history": [], "messages": [], "path": [], "retrieval": [], "variables": [] }, "avatar": "data:image/png;base64,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" }