mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-05 10:58:34 +08:00
Feat: update templates && add resume template (#14124)
### What problem does this PR solve? Feat: update templates && add resume template ### Type of change - [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Magicbook1108
@@ -14,17 +14,17 @@
|
||||
"canvas_category": "dataflow_canvas",
|
||||
"dsl": {
|
||||
"components": {
|
||||
"Extractor:CleverPianosInvite": {
|
||||
"Extractor:CurlyEmusJam": {
|
||||
"downstream": [
|
||||
"Tokenizer:ShyBalloonsSmell"
|
||||
"Tokenizer:WittySunsListen"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Extractor",
|
||||
"params": {
|
||||
"field_name": "summary",
|
||||
"field_name": "metadata",
|
||||
"frequencyPenaltyEnabled": true,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "Qwen/Qwen3-8B@SILICONFLOW",
|
||||
"llm_id": "THUDM/GLM-4.1V-9B-Thinking@SILICONFLOW",
|
||||
"maxTokensEnabled": false,
|
||||
"max_tokens": 256,
|
||||
"outputs": {
|
||||
@@ -37,25 +37,25 @@
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "Text to Summarize:\n{Extractor:SunnyCooksSpend@chunks}",
|
||||
"content": "Content:\n{Extractor:SmartWindowsHammer@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.",
|
||||
"sys_prompt": "Extract important structured information from the given content. Output ONLY a valid JSON string with no additional text. If no important structured information is found, output an empty JSON object: {}.\n\nImportant structured information may include: names, dates, locations, events, key facts, numerical data, or other extractable entities.",
|
||||
"temperature": 0.1,
|
||||
"temperatureEnabled": true,
|
||||
"tenant_llm_id": 54,
|
||||
"tenant_llm_id": 63,
|
||||
"topPEnabled": true,
|
||||
"top_p": 0.3
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"Extractor:SunnyCooksSpend"
|
||||
"Extractor:SmartWindowsHammer"
|
||||
]
|
||||
},
|
||||
"Extractor:EasyToesFail": {
|
||||
"Extractor:LazyCarpetsKiss": {
|
||||
"downstream": [
|
||||
"Extractor:SunnyCooksSpend"
|
||||
"Extractor:LovelyPearsRest"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Extractor",
|
||||
@@ -63,7 +63,7 @@
|
||||
"field_name": "summary",
|
||||
"frequencyPenaltyEnabled": true,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "Qwen/Qwen3-8B@SILICONFLOW",
|
||||
"llm_id": "THUDM/GLM-4.1V-9B-Thinking@SILICONFLOW",
|
||||
"maxTokensEnabled": false,
|
||||
"max_tokens": 256,
|
||||
"outputs": {
|
||||
@@ -76,25 +76,25 @@
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "Text to Summarize:\n{TokenChunker:SixtyShirtsFeel@chunks}",
|
||||
"content": "Text to Summarize:\n{TokenChunker:BumpyStarsPress@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": 54,
|
||||
"tenant_llm_id": 63,
|
||||
"topPEnabled": true,
|
||||
"top_p": 0.3
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"TokenChunker:SixtyShirtsFeel"
|
||||
"TokenChunker:BumpyStarsPress"
|
||||
]
|
||||
},
|
||||
"Extractor:SunnyCooksSpend": {
|
||||
"Extractor:LovelyPearsRest": {
|
||||
"downstream": [
|
||||
"Extractor:CleverPianosInvite"
|
||||
"Extractor:SmartWindowsHammer"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Extractor",
|
||||
@@ -102,7 +102,7 @@
|
||||
"field_name": "keywords",
|
||||
"frequencyPenaltyEnabled": true,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "Qwen/Qwen3-8B@SILICONFLOW",
|
||||
"llm_id": "THUDM/GLM-4.1V-9B-Thinking@SILICONFLOW",
|
||||
"maxTokensEnabled": false,
|
||||
"max_tokens": 256,
|
||||
"outputs": {
|
||||
@@ -115,20 +115,59 @@
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "Text Content\n{Extractor:EasyToesFail@chunks}",
|
||||
"content": "Text Content\n{Extractor:LazyCarpetsKiss@chunks}",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "Role\nYou are a text analyzer.\n\nTask\nExtract the most important keywords/phrases of a given piece of text content.\n\nRequirements\n- Summarize the text content, and give the top 5 important keywords/phrases.\n- The keywords MUST be in the same language as the given piece of text content.\n- The keywords are delimited by ENGLISH COMMA.\n- Output keywords ONLY.",
|
||||
"temperature": 0.1,
|
||||
"temperatureEnabled": true,
|
||||
"tenant_llm_id": 54,
|
||||
"tenant_llm_id": 63,
|
||||
"topPEnabled": true,
|
||||
"top_p": 0.3
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"Extractor:EasyToesFail"
|
||||
"Extractor:LazyCarpetsKiss"
|
||||
]
|
||||
},
|
||||
"Extractor:SmartWindowsHammer": {
|
||||
"downstream": [
|
||||
"Extractor:CurlyEmusJam"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Extractor",
|
||||
"params": {
|
||||
"field_name": "questions",
|
||||
"frequencyPenaltyEnabled": true,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "THUDM/GLM-4.1V-9B-Thinking@SILICONFLOW",
|
||||
"maxTokensEnabled": false,
|
||||
"max_tokens": 256,
|
||||
"outputs": {
|
||||
"chunks": {
|
||||
"type": "Array<Object>",
|
||||
"value": []
|
||||
}
|
||||
},
|
||||
"presencePenaltyEnabled": true,
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "Text Content\n{Extractor:LovelyPearsRest@chunks}",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "Role\nYou are a text analyzer.\n\nTask\nPropose 3 questions about a given piece of text content.\n\nRequirements\n- Understand and summarize the text content, and propose the top 3 important questions.\n- The questions SHOULD NOT have overlapping meanings.\n- The questions SHOULD cover the main content of the text as much as possible.\n- The questions MUST be in the same language as the given piece of text content.\n- One question per line.\n- Output questions ONLY.",
|
||||
"temperature": 0.1,
|
||||
"temperatureEnabled": true,
|
||||
"tenant_llm_id": 63,
|
||||
"topPEnabled": true,
|
||||
"top_p": 0.3
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"Extractor:LovelyPearsRest"
|
||||
]
|
||||
},
|
||||
"File": {
|
||||
@@ -143,7 +182,7 @@
|
||||
},
|
||||
"Parser:HipSignsRhyme": {
|
||||
"downstream": [
|
||||
"TokenChunker:SixtyShirtsFeel"
|
||||
"TokenChunker:BumpyStarsPress"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Parser",
|
||||
@@ -175,6 +214,7 @@
|
||||
]
|
||||
},
|
||||
"docx": {
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "json",
|
||||
"preprocess": "main_content",
|
||||
"suffix": [
|
||||
@@ -221,6 +261,7 @@
|
||||
"system_prompt": ""
|
||||
},
|
||||
"markdown": {
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "json",
|
||||
"preprocess": "main_content",
|
||||
"suffix": [
|
||||
@@ -231,6 +272,7 @@
|
||||
"vlm": {}
|
||||
},
|
||||
"pdf": {
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "json",
|
||||
"parse_method": "DeepDOC",
|
||||
"preprocess": "main_content",
|
||||
@@ -249,6 +291,7 @@
|
||||
]
|
||||
},
|
||||
"spreadsheet": {
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "html",
|
||||
"parse_method": "DeepDOC",
|
||||
"preprocess": "main_content",
|
||||
@@ -286,9 +329,9 @@
|
||||
"File"
|
||||
]
|
||||
},
|
||||
"TokenChunker:SixtyShirtsFeel": {
|
||||
"TokenChunker:BumpyStarsPress": {
|
||||
"downstream": [
|
||||
"Extractor:EasyToesFail"
|
||||
"Extractor:LazyCarpetsKiss"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "TokenChunker",
|
||||
@@ -312,7 +355,7 @@
|
||||
"Parser:HipSignsRhyme"
|
||||
]
|
||||
},
|
||||
"Tokenizer:ShyBalloonsSmell": {
|
||||
"Tokenizer:WittySunsListen": {
|
||||
"downstream": [],
|
||||
"obj": {
|
||||
"component_name": "Tokenizer",
|
||||
@@ -327,7 +370,7 @@
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"Extractor:CleverPianosInvite"
|
||||
"Extractor:CurlyEmusJam"
|
||||
]
|
||||
}
|
||||
},
|
||||
@@ -337,9 +380,6 @@
|
||||
"graph": {
|
||||
"edges": [
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__Filestart-Parser:HipSignsRhymeend",
|
||||
"source": "File",
|
||||
"sourceHandle": "start",
|
||||
@@ -347,54 +387,59 @@
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__Parser:HipSignsRhymestart-TokenChunker:SixtyShirtsFeelend",
|
||||
"id": "xy-edge__Parser:HipSignsRhymestart-TokenChunker:BumpyStarsPressend",
|
||||
"source": "Parser:HipSignsRhyme",
|
||||
"sourceHandle": "start",
|
||||
"target": "TokenChunker:SixtyShirtsFeel",
|
||||
"target": "TokenChunker:BumpyStarsPress",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__TokenChunker:SixtyShirtsFeelstart-Extractor:EasyToesFailend",
|
||||
"source": "TokenChunker:SixtyShirtsFeel",
|
||||
"id": "xy-edge__TokenChunker:BumpyStarsPressstart-Extractor:LazyCarpetsKissend",
|
||||
"source": "TokenChunker:BumpyStarsPress",
|
||||
"sourceHandle": "start",
|
||||
"target": "Extractor:EasyToesFail",
|
||||
"target": "Extractor:LazyCarpetsKiss",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__Extractor:EasyToesFailstart-Extractor:SunnyCooksSpendend",
|
||||
"id": "xy-edge__Extractor:LazyCarpetsKissstart-Extractor:LovelyPearsRestend",
|
||||
"source": "Extractor:LazyCarpetsKiss",
|
||||
"sourceHandle": "start",
|
||||
"target": "Extractor:LovelyPearsRest",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__Extractor:LovelyPearsReststart-Extractor:SmartWindowsHammerend",
|
||||
"selected": false,
|
||||
"source": "Extractor:EasyToesFail",
|
||||
"source": "Extractor:LovelyPearsRest",
|
||||
"sourceHandle": "start",
|
||||
"target": "Extractor:SunnyCooksSpend",
|
||||
"target": "Extractor:SmartWindowsHammer",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__Extractor:SunnyCooksSpendstart-Extractor:CleverPianosInviteend",
|
||||
"source": "Extractor:SunnyCooksSpend",
|
||||
"id": "xy-edge__Extractor:SmartWindowsHammerstart-Extractor:CurlyEmusJamend",
|
||||
"selected": false,
|
||||
"source": "Extractor:SmartWindowsHammer",
|
||||
"sourceHandle": "start",
|
||||
"target": "Extractor:CleverPianosInvite",
|
||||
"target": "Extractor:CurlyEmusJam",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__Extractor:CleverPianosInvitestart-Tokenizer:ShyBalloonsSmellend",
|
||||
"source": "Extractor:CleverPianosInvite",
|
||||
"id": "xy-edge__Extractor:CurlyEmusJamstart-Tokenizer:WittySunsListenend",
|
||||
"source": "Extractor:CurlyEmusJam",
|
||||
"sourceHandle": "start",
|
||||
"target": "Tokenizer:ShyBalloonsSmell",
|
||||
"target": "Tokenizer:WittySunsListen",
|
||||
"targetHandle": "end"
|
||||
}
|
||||
],
|
||||
@@ -406,7 +451,7 @@
|
||||
},
|
||||
"id": "File",
|
||||
"measured": {
|
||||
"height": 49,
|
||||
"height": 50,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
@@ -441,12 +486,14 @@
|
||||
"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"
|
||||
@@ -475,6 +522,7 @@
|
||||
},
|
||||
{
|
||||
"fileFormat": "markdown",
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "json",
|
||||
"preprocess": "main_content"
|
||||
},
|
||||
@@ -495,6 +543,7 @@
|
||||
},
|
||||
{
|
||||
"fileFormat": "docx",
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "json",
|
||||
"preprocess": "main_content"
|
||||
},
|
||||
@@ -547,9 +596,9 @@
|
||||
"label": "TokenChunker",
|
||||
"name": "Token Chunker_0"
|
||||
},
|
||||
"id": "TokenChunker:SixtyShirtsFeel",
|
||||
"id": "TokenChunker:BumpyStarsPress",
|
||||
"measured": {
|
||||
"height": 73,
|
||||
"height": 74,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
@@ -567,7 +616,7 @@
|
||||
"field_name": "summary",
|
||||
"frequencyPenaltyEnabled": true,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "Qwen/Qwen3-8B@SILICONFLOW",
|
||||
"llm_id": "THUDM/GLM-4.1V-9B-Thinking@SILICONFLOW",
|
||||
"maxTokensEnabled": false,
|
||||
"max_tokens": 256,
|
||||
"outputs": {
|
||||
@@ -578,26 +627,25 @@
|
||||
},
|
||||
"presencePenaltyEnabled": true,
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": "Text to Summarize:\n{TokenChunker:SixtyShirtsFeel@chunks}",
|
||||
"prompts": "Text to Summarize:\n{TokenChunker:BumpyStarsPress@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": 54,
|
||||
"tenant_llm_id": 63,
|
||||
"topPEnabled": true,
|
||||
"top_p": 0.3
|
||||
},
|
||||
"label": "Extractor",
|
||||
"name": "Summarization"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Extractor:EasyToesFail",
|
||||
"id": "Extractor:LazyCarpetsKiss",
|
||||
"measured": {
|
||||
"height": 89,
|
||||
"height": 90,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 606.9117864444606,
|
||||
"y": 295.54747604679164
|
||||
"x": 916.9952409420641,
|
||||
"y": 195.39629819663406
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
@@ -610,7 +658,7 @@
|
||||
"field_name": "keywords",
|
||||
"frequencyPenaltyEnabled": true,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "Qwen/Qwen3-8B@SILICONFLOW",
|
||||
"llm_id": "THUDM/GLM-4.1V-9B-Thinking@SILICONFLOW",
|
||||
"maxTokensEnabled": false,
|
||||
"max_tokens": 256,
|
||||
"outputs": {
|
||||
@@ -621,26 +669,26 @@
|
||||
},
|
||||
"presencePenaltyEnabled": true,
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": "Text Content\n{Extractor:EasyToesFail@chunks}",
|
||||
"prompts": "Text Content\n{Extractor:LazyCarpetsKiss@chunks}",
|
||||
"sys_prompt": "Role\nYou are a text analyzer.\n\nTask\nExtract the most important keywords/phrases of a given piece of text content.\n\nRequirements\n- Summarize the text content, and give the top 5 important keywords/phrases.\n- The keywords MUST be in the same language as the given piece of text content.\n- The keywords are delimited by ENGLISH COMMA.\n- Output keywords ONLY.",
|
||||
"temperature": 0.1,
|
||||
"temperatureEnabled": true,
|
||||
"tenant_llm_id": 54,
|
||||
"tenant_llm_id": 63,
|
||||
"topPEnabled": true,
|
||||
"top_p": 0.3
|
||||
},
|
||||
"label": "Extractor",
|
||||
"name": "Auto Keywords"
|
||||
"name": "Auto Keyword"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Extractor:SunnyCooksSpend",
|
||||
"id": "Extractor:LovelyPearsRest",
|
||||
"measured": {
|
||||
"height": 89,
|
||||
"height": 90,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 598.3422026718366,
|
||||
"y": 414.3467657992519
|
||||
"x": 983.5410692821999,
|
||||
"y": 301.1557383781162
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
@@ -650,10 +698,10 @@
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"field_name": "summary",
|
||||
"field_name": "questions",
|
||||
"frequencyPenaltyEnabled": true,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "Qwen/Qwen3-8B@SILICONFLOW",
|
||||
"llm_id": "THUDM/GLM-4.1V-9B-Thinking@SILICONFLOW",
|
||||
"maxTokensEnabled": false,
|
||||
"max_tokens": 256,
|
||||
"outputs": {
|
||||
@@ -664,26 +712,69 @@
|
||||
},
|
||||
"presencePenaltyEnabled": true,
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": "Text to Summarize:\n{Extractor:SunnyCooksSpend@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.",
|
||||
"prompts": "Text Content\n{Extractor:LovelyPearsRest@chunks}",
|
||||
"sys_prompt": "Role\nYou are a text analyzer.\n\nTask\nPropose 3 questions about a given piece of text content.\n\nRequirements\n- Understand and summarize the text content, and propose the top 3 important questions.\n- The questions SHOULD NOT have overlapping meanings.\n- The questions SHOULD cover the main content of the text as much as possible.\n- The questions MUST be in the same language as the given piece of text content.\n- One question per line.\n- Output questions ONLY.",
|
||||
"temperature": 0.1,
|
||||
"temperatureEnabled": true,
|
||||
"tenant_llm_id": 54,
|
||||
"tenant_llm_id": 63,
|
||||
"topPEnabled": true,
|
||||
"top_p": 0.3
|
||||
},
|
||||
"label": "Extractor",
|
||||
"name": "Auto Questions"
|
||||
"name": "Auto Question"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Extractor:CleverPianosInvite",
|
||||
"id": "Extractor:SmartWindowsHammer",
|
||||
"measured": {
|
||||
"height": 89,
|
||||
"height": 90,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 594.401162655802,
|
||||
"y": 536.2317513894384
|
||||
"x": 1021.1009769800036,
|
||||
"y": 421.67760363913044
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "contextNode"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"field_name": "metadata",
|
||||
"frequencyPenaltyEnabled": true,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "THUDM/GLM-4.1V-9B-Thinking@SILICONFLOW",
|
||||
"maxTokensEnabled": false,
|
||||
"max_tokens": 256,
|
||||
"outputs": {
|
||||
"chunks": {
|
||||
"type": "Array<Object>",
|
||||
"value": []
|
||||
}
|
||||
},
|
||||
"presencePenaltyEnabled": true,
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": "Content:\n{Extractor:SmartWindowsHammer@chunks}",
|
||||
"sys_prompt": "Extract important structured information from the given content. Output ONLY a valid JSON string with no additional text. If no important structured information is found, output an empty JSON object: {}.\n\nImportant structured information may include: names, dates, locations, events, key facts, numerical data, or other extractable entities.",
|
||||
"temperature": 0.1,
|
||||
"temperatureEnabled": true,
|
||||
"tenant_llm_id": 63,
|
||||
"topPEnabled": true,
|
||||
"top_p": 0.3
|
||||
},
|
||||
"label": "Extractor",
|
||||
"name": "Auto Metadata"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Extractor:CurlyEmusJam",
|
||||
"measured": {
|
||||
"height": 90,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 1065.7115140232393,
|
||||
"y": 527.4370438206126
|
||||
},
|
||||
"selected": true,
|
||||
"sourcePosition": "right",
|
||||
@@ -705,14 +796,14 @@
|
||||
"name": "Indexer_0"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Tokenizer:ShyBalloonsSmell",
|
||||
"id": "Tokenizer:WittySunsListen",
|
||||
"measured": {
|
||||
"height": 113,
|
||||
"height": 114,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 911.3724897632962,
|
||||
"y": 186.00527380751004
|
||||
"x": 1327.3247542536642,
|
||||
"y": 164.72133416115918
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
|
||||
@@ -14,9 +14,9 @@
|
||||
"canvas_category": "dataflow_canvas",
|
||||
"dsl": {
|
||||
"components": {
|
||||
"Extractor:PublicPlumsKiss": {
|
||||
"Extractor:SharpTaxisSay": {
|
||||
"downstream": [
|
||||
"Tokenizer:FullBottlesDeny"
|
||||
"Tokenizer:ShaggyShrimpsLose"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Extractor",
|
||||
@@ -24,7 +24,7 @@
|
||||
"field_name": "summary",
|
||||
"frequencyPenaltyEnabled": true,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "Qwen/Qwen3-8B@SILICONFLOW",
|
||||
"llm_id": "THUDM/GLM-4.1V-9B-Thinking@SILICONFLOW",
|
||||
"maxTokensEnabled": false,
|
||||
"max_tokens": 256,
|
||||
"outputs": {
|
||||
@@ -37,20 +37,20 @@
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "Text to Summarize:\n{TokenChunker:FancyCitiesStick@chunks}",
|
||||
"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": 54,
|
||||
"tenant_llm_id": 63,
|
||||
"topPEnabled": true,
|
||||
"top_p": 0.3
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"TokenChunker:FancyCitiesStick"
|
||||
"TokenChunker:ModernPetsKneel"
|
||||
]
|
||||
},
|
||||
"File": {
|
||||
@@ -65,7 +65,7 @@
|
||||
},
|
||||
"Parser:HipSignsRhyme": {
|
||||
"downstream": [
|
||||
"TokenChunker:FancyCitiesStick"
|
||||
"TokenChunker:ModernPetsKneel"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Parser",
|
||||
@@ -97,6 +97,7 @@
|
||||
]
|
||||
},
|
||||
"docx": {
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "json",
|
||||
"preprocess": "main_content",
|
||||
"suffix": [
|
||||
@@ -143,6 +144,7 @@
|
||||
"system_prompt": ""
|
||||
},
|
||||
"markdown": {
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "json",
|
||||
"preprocess": "main_content",
|
||||
"suffix": [
|
||||
@@ -153,6 +155,7 @@
|
||||
"vlm": {}
|
||||
},
|
||||
"pdf": {
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "json",
|
||||
"parse_method": "DeepDOC",
|
||||
"preprocess": "main_content",
|
||||
@@ -171,6 +174,7 @@
|
||||
]
|
||||
},
|
||||
"spreadsheet": {
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "html",
|
||||
"parse_method": "DeepDOC",
|
||||
"preprocess": "main_content",
|
||||
@@ -208,9 +212,9 @@
|
||||
"File"
|
||||
]
|
||||
},
|
||||
"TokenChunker:FancyCitiesStick": {
|
||||
"TokenChunker:ModernPetsKneel": {
|
||||
"downstream": [
|
||||
"Extractor:PublicPlumsKiss"
|
||||
"Extractor:SharpTaxisSay"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "TokenChunker",
|
||||
@@ -234,7 +238,7 @@
|
||||
"Parser:HipSignsRhyme"
|
||||
]
|
||||
},
|
||||
"Tokenizer:FullBottlesDeny": {
|
||||
"Tokenizer:ShaggyShrimpsLose": {
|
||||
"downstream": [],
|
||||
"obj": {
|
||||
"component_name": "Tokenizer",
|
||||
@@ -249,17 +253,12 @@
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"Extractor:PublicPlumsKiss"
|
||||
"Extractor:SharpTaxisSay"
|
||||
]
|
||||
}
|
||||
},
|
||||
"globals": {
|
||||
"sys.conversation_turns": 0,
|
||||
"sys.date": "",
|
||||
"sys.files": [],
|
||||
"sys.history": [],
|
||||
"sys.query": "",
|
||||
"sys.user_id": ""
|
||||
"sys.history": []
|
||||
},
|
||||
"graph": {
|
||||
"edges": [
|
||||
@@ -271,28 +270,31 @@
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"id": "xy-edge__Parser:HipSignsRhymestart-TokenChunker:FancyCitiesStickend",
|
||||
"id": "xy-edge__Parser:HipSignsRhymestart-TokenChunker:ModernPetsKneelend",
|
||||
"source": "Parser:HipSignsRhyme",
|
||||
"sourceHandle": "start",
|
||||
"target": "TokenChunker:FancyCitiesStick",
|
||||
"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__TokenChunker:FancyCitiesStickstart-Extractor:PublicPlumsKissend",
|
||||
"source": "TokenChunker:FancyCitiesStick",
|
||||
"id": "xy-edge__Extractor:SharpTaxisSaystart-Tokenizer:ShaggyShrimpsLoseend",
|
||||
"markerEnd": "logo",
|
||||
"source": "Extractor:SharpTaxisSay",
|
||||
"sourceHandle": "start",
|
||||
"target": "Extractor:PublicPlumsKiss",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"id": "xy-edge__Extractor:PublicPlumsKissstart-Tokenizer:FullBottlesDenyend",
|
||||
"source": "Extractor:PublicPlumsKiss",
|
||||
"sourceHandle": "start",
|
||||
"target": "Tokenizer:FullBottlesDeny",
|
||||
"targetHandle": "end"
|
||||
"target": "Tokenizer:ShaggyShrimpsLose",
|
||||
"targetHandle": "end",
|
||||
"type": "buttonEdge",
|
||||
"zIndex": 1001
|
||||
}
|
||||
],
|
||||
"nodes": [
|
||||
@@ -303,7 +305,7 @@
|
||||
},
|
||||
"id": "File",
|
||||
"measured": {
|
||||
"height": 49,
|
||||
"height": 50,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
@@ -338,12 +340,14 @@
|
||||
"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"
|
||||
@@ -372,6 +376,7 @@
|
||||
},
|
||||
{
|
||||
"fileFormat": "markdown",
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "json",
|
||||
"preprocess": "main_content"
|
||||
},
|
||||
@@ -392,6 +397,7 @@
|
||||
},
|
||||
{
|
||||
"fileFormat": "docx",
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "json",
|
||||
"preprocess": "main_content"
|
||||
},
|
||||
@@ -409,7 +415,7 @@
|
||||
"dragging": false,
|
||||
"id": "Parser:HipSignsRhyme",
|
||||
"measured": {
|
||||
"height": 197,
|
||||
"height": 57,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
@@ -424,7 +430,6 @@
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"children_delimiters": [],
|
||||
"chunk_token_size": 512,
|
||||
"delimiter_mode": "token_size",
|
||||
"delimiters": [
|
||||
@@ -444,62 +449,19 @@
|
||||
"label": "TokenChunker",
|
||||
"name": "Token Chunker_0"
|
||||
},
|
||||
"id": "TokenChunker:FancyCitiesStick",
|
||||
"id": "TokenChunker:ModernPetsKneel",
|
||||
"measured": {
|
||||
"height": 73,
|
||||
"height": 74,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 616.9952409420641,
|
||||
"y": 195.39629819663406
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "chunkerNode"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"field_name": "summary",
|
||||
"frequencyPenaltyEnabled": true,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "Qwen/Qwen3-8B@SILICONFLOW",
|
||||
"maxTokensEnabled": false,
|
||||
"max_tokens": 256,
|
||||
"outputs": {
|
||||
"chunks": {
|
||||
"type": "Array<Object>",
|
||||
"value": []
|
||||
}
|
||||
},
|
||||
"presencePenaltyEnabled": true,
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": "Text to Summarize:\n{TokenChunker:FancyCitiesStick@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": 54,
|
||||
"topPEnabled": true,
|
||||
"top_p": 0.3
|
||||
},
|
||||
"label": "Extractor",
|
||||
"name": "Summarizer"
|
||||
},
|
||||
"id": "Extractor:PublicPlumsKiss",
|
||||
"measured": {
|
||||
"height": 89,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 916.9952409420641,
|
||||
"y": 195.39629819663406
|
||||
},
|
||||
"selected": true,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "contextNode"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
@@ -514,15 +476,17 @@
|
||||
"label": "Tokenizer",
|
||||
"name": "Indexer_0"
|
||||
},
|
||||
"id": "Tokenizer:FullBottlesDeny",
|
||||
"dragging": false,
|
||||
"id": "Tokenizer:ShaggyShrimpsLose",
|
||||
"measured": {
|
||||
"height": 113,
|
||||
"height": 114,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 1216.9952409420641,
|
||||
"y": 195.39629819663406
|
||||
"x": 1188.9891545215792,
|
||||
"y": 159.26426539640332
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "tokenizerNode"
|
||||
@@ -530,26 +494,45 @@
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"text": "Using summary to build both text and vector indexes."
|
||||
"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<Object>",
|
||||
"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": "Note",
|
||||
"name": "Index Summary"
|
||||
"label": "Extractor",
|
||||
"name": "Summarization"
|
||||
},
|
||||
"dragHandle": ".note-drag-handle",
|
||||
"dragging": false,
|
||||
"id": "Note:ElevenKingsPick",
|
||||
"id": "Extractor:SharpTaxisSay",
|
||||
"measured": {
|
||||
"height": 127,
|
||||
"width": 267
|
||||
"height": 90,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 735.9586746349814,
|
||||
"y": 315.614230763182
|
||||
"x": 878.855872986265,
|
||||
"y": 177.33028179651868
|
||||
},
|
||||
"selected": false,
|
||||
"selected": true,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "noteNode"
|
||||
"type": "contextNode"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
604
agent/templates/ingestion_pipeline_Resume.json
Normal file
604
agent/templates/ingestion_pipeline_Resume.json
Normal file
File diff suppressed because one or more lines are too long
@@ -14,9 +14,9 @@
|
||||
"canvas_category": "dataflow_canvas",
|
||||
"dsl": {
|
||||
"components": {
|
||||
"Extractor:PublicPlumsKiss": {
|
||||
"Extractor:DryRatsGive": {
|
||||
"downstream": [
|
||||
"Tokenizer:FullBottlesDeny"
|
||||
"Tokenizer:WackyOnionsFly"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Extractor",
|
||||
@@ -24,7 +24,7 @@
|
||||
"field_name": "summary",
|
||||
"frequencyPenaltyEnabled": true,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "Qwen/Qwen3-8B@SILICONFLOW",
|
||||
"llm_id": "THUDM/GLM-4.1V-9B-Thinking@SILICONFLOW",
|
||||
"maxTokensEnabled": false,
|
||||
"max_tokens": 256,
|
||||
"outputs": {
|
||||
@@ -37,20 +37,20 @@
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "Text to Summarize:\n[Insert text here]",
|
||||
"content": "Text to Summarize:\n{TitleChunker:WideResultsTeach@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": 54,
|
||||
"tenant_llm_id": 63,
|
||||
"topPEnabled": true,
|
||||
"top_p": 0.3
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"TokenChunker:FancyCitiesStick"
|
||||
"TitleChunker:WideResultsTeach"
|
||||
]
|
||||
},
|
||||
"File": {
|
||||
@@ -65,7 +65,7 @@
|
||||
},
|
||||
"Parser:HipSignsRhyme": {
|
||||
"downstream": [
|
||||
"TokenChunker:FancyCitiesStick"
|
||||
"TitleChunker:WideResultsTeach"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Parser",
|
||||
@@ -97,6 +97,7 @@
|
||||
]
|
||||
},
|
||||
"docx": {
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "json",
|
||||
"preprocess": "main_content",
|
||||
"suffix": [
|
||||
@@ -143,6 +144,7 @@
|
||||
"system_prompt": ""
|
||||
},
|
||||
"markdown": {
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "json",
|
||||
"preprocess": "main_content",
|
||||
"suffix": [
|
||||
@@ -153,6 +155,7 @@
|
||||
"vlm": {}
|
||||
},
|
||||
"pdf": {
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "json",
|
||||
"parse_method": "DeepDOC",
|
||||
"preprocess": "main_content",
|
||||
@@ -171,6 +174,7 @@
|
||||
]
|
||||
},
|
||||
"spreadsheet": {
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "html",
|
||||
"parse_method": "DeepDOC",
|
||||
"preprocess": "main_content",
|
||||
@@ -208,33 +212,58 @@
|
||||
"File"
|
||||
]
|
||||
},
|
||||
"TokenChunker:FancyCitiesStick": {
|
||||
"TitleChunker:WideResultsTeach": {
|
||||
"downstream": [
|
||||
"Extractor:PublicPlumsKiss"
|
||||
"Extractor:DryRatsGive"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "TokenChunker",
|
||||
"component_name": "TitleChunker",
|
||||
"params": {
|
||||
"children_delimiters": [],
|
||||
"chunk_token_size": 512,
|
||||
"delimiter_mode": "token_size",
|
||||
"delimiters": [],
|
||||
"image_context_size": 0,
|
||||
"outputs": {
|
||||
"chunks": {
|
||||
"type": "Array<Object>",
|
||||
"value": []
|
||||
}
|
||||
},
|
||||
"overlapped_percent": 0,
|
||||
"table_context_size": 0
|
||||
"hierarchy": 3,
|
||||
"include_heading_content": false,
|
||||
"levels": [
|
||||
[
|
||||
"^#[^#]",
|
||||
"^##[^#]",
|
||||
"^###[^#]",
|
||||
"^####[^#]"
|
||||
],
|
||||
[
|
||||
"\u7b2c[\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e0-9]+(\u5206?\u7f16|\u90e8\u5206)",
|
||||
"\u7b2c[\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e0-9]+\u7ae0",
|
||||
"\u7b2c[\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e0-9]+\u8282",
|
||||
"\u7b2c[\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e0-9]+\u6761",
|
||||
"[\\(\uff08][\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e]+[\\)\uff09]"
|
||||
],
|
||||
[
|
||||
"\u7b2c[0-9]+\u7ae0",
|
||||
"\u7b2c[0-9]+\u8282",
|
||||
"[0-9]{1,2}[\\. \u3001]",
|
||||
"[0-9]{1,2}\\.[0-9]{1,2}($|[^a-zA-Z/%~.-])",
|
||||
"[0-9]{1,2}\\.[0-9]{1,2}\\.[0-9]{1,2}"
|
||||
],
|
||||
[
|
||||
"\u7b2c[\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e0-9]+\u7ae0",
|
||||
"\u7b2c[\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e0-9]+\u8282",
|
||||
"[\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e]+[ \u3001]",
|
||||
"[\\(\uff08][\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e]+[\\)\uff09]",
|
||||
"[\\(\uff08][0-9]{,2}[\\)\uff09]"
|
||||
],
|
||||
[
|
||||
"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"
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"Parser:HipSignsRhyme"
|
||||
]
|
||||
},
|
||||
"Tokenizer:FullBottlesDeny": {
|
||||
"Tokenizer:WackyOnionsFly": {
|
||||
"downstream": [],
|
||||
"obj": {
|
||||
"component_name": "Tokenizer",
|
||||
@@ -249,17 +278,12 @@
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"Extractor:PublicPlumsKiss"
|
||||
"Extractor:DryRatsGive"
|
||||
]
|
||||
}
|
||||
},
|
||||
"globals": {
|
||||
"sys.conversation_turns": 0,
|
||||
"sys.date": "",
|
||||
"sys.files": [],
|
||||
"sys.history": [],
|
||||
"sys.query": "",
|
||||
"sys.user_id": ""
|
||||
"sys.history": []
|
||||
},
|
||||
"graph": {
|
||||
"edges": [
|
||||
@@ -271,27 +295,24 @@
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"id": "xy-edge__Parser:HipSignsRhymestart-TokenChunker:FancyCitiesStickend",
|
||||
"id": "xy-edge__Parser:HipSignsRhymestart-TitleChunker:WideResultsTeachend",
|
||||
"source": "Parser:HipSignsRhyme",
|
||||
"sourceHandle": "start",
|
||||
"target": "TokenChunker:FancyCitiesStick",
|
||||
"target": "TitleChunker:WideResultsTeach",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__TokenChunker:FancyCitiesStickstart-Extractor:PublicPlumsKissend",
|
||||
"source": "TokenChunker:FancyCitiesStick",
|
||||
"id": "xy-edge__TitleChunker:WideResultsTeachstart-Extractor:DryRatsGiveend",
|
||||
"source": "TitleChunker:WideResultsTeach",
|
||||
"sourceHandle": "start",
|
||||
"target": "Extractor:PublicPlumsKiss",
|
||||
"target": "Extractor:DryRatsGive",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"id": "xy-edge__Extractor:PublicPlumsKissstart-Tokenizer:FullBottlesDenyend",
|
||||
"source": "Extractor:PublicPlumsKiss",
|
||||
"id": "xy-edge__Extractor:DryRatsGivestart-Tokenizer:WackyOnionsFlyend",
|
||||
"source": "Extractor:DryRatsGive",
|
||||
"sourceHandle": "start",
|
||||
"target": "Tokenizer:FullBottlesDeny",
|
||||
"target": "Tokenizer:WackyOnionsFly",
|
||||
"targetHandle": "end"
|
||||
}
|
||||
],
|
||||
@@ -303,7 +324,7 @@
|
||||
},
|
||||
"id": "File",
|
||||
"measured": {
|
||||
"height": 49,
|
||||
"height": 50,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
@@ -338,12 +359,14 @@
|
||||
"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"
|
||||
@@ -372,6 +395,7 @@
|
||||
},
|
||||
{
|
||||
"fileFormat": "markdown",
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "json",
|
||||
"preprocess": "main_content"
|
||||
},
|
||||
@@ -392,6 +416,7 @@
|
||||
},
|
||||
{
|
||||
"fileFormat": "docx",
|
||||
"flatten_media_to_text": false,
|
||||
"output_format": "json",
|
||||
"preprocess": "main_content"
|
||||
},
|
||||
@@ -424,28 +449,113 @@
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"chunk_token_size": 512,
|
||||
"delimiter_mode": "token_size",
|
||||
"delimiters": [
|
||||
{
|
||||
"value": "\n"
|
||||
}
|
||||
],
|
||||
"image_table_context_window": 0,
|
||||
"hierarchy": "3",
|
||||
"include_heading_content": false,
|
||||
"method": "hierarchy",
|
||||
"outputs": {
|
||||
"chunks": {
|
||||
"type": "Array<Object>",
|
||||
"value": []
|
||||
}
|
||||
},
|
||||
"overlapped_percent": 0
|
||||
"rules": [
|
||||
{
|
||||
"levels": [
|
||||
{
|
||||
"expression": "^#[^#]"
|
||||
},
|
||||
{
|
||||
"expression": "^##[^#]"
|
||||
},
|
||||
{
|
||||
"expression": "^###[^#]"
|
||||
},
|
||||
{
|
||||
"expression": "^####[^#]"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"levels": [
|
||||
{
|
||||
"expression": "\u7b2c[\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e0-9]+(\u5206?\u7f16|\u90e8\u5206)"
|
||||
},
|
||||
{
|
||||
"expression": "\u7b2c[\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e0-9]+\u7ae0"
|
||||
},
|
||||
{
|
||||
"expression": "\u7b2c[\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e0-9]+\u8282"
|
||||
},
|
||||
{
|
||||
"expression": "\u7b2c[\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e0-9]+\u6761"
|
||||
},
|
||||
{
|
||||
"expression": "[\\(\uff08][\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e]+[\\)\uff09]"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"levels": [
|
||||
{
|
||||
"expression": "\u7b2c[0-9]+\u7ae0"
|
||||
},
|
||||
{
|
||||
"expression": "\u7b2c[0-9]+\u8282"
|
||||
},
|
||||
{
|
||||
"expression": "[0-9]{1,2}[\\. \u3001]"
|
||||
},
|
||||
{
|
||||
"expression": "[0-9]{1,2}\\.[0-9]{1,2}($|[^a-zA-Z/%~.-])"
|
||||
},
|
||||
{
|
||||
"expression": "[0-9]{1,2}\\.[0-9]{1,2}\\.[0-9]{1,2}"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"levels": [
|
||||
{
|
||||
"expression": "\u7b2c[\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e0-9]+\u7ae0"
|
||||
},
|
||||
{
|
||||
"expression": "\u7b2c[\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e0-9]+\u8282"
|
||||
},
|
||||
{
|
||||
"expression": "[\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e]+[ \u3001]"
|
||||
},
|
||||
{
|
||||
"expression": "[\\(\uff08][\u96f6\u4e00\u4e8c\u4e09\u56db\u4e94\u516d\u4e03\u516b\u4e5d\u5341\u767e]+[\\)\uff09]"
|
||||
},
|
||||
{
|
||||
"expression": "[\\(\uff08][0-9]{,2}[\\)\uff09]"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"levels": [
|
||||
{
|
||||
"expression": "PART (ONE|TWO|THREE|FOUR|FIVE|SIX|SEVEN|EIGHT|NINE|TEN)"
|
||||
},
|
||||
{
|
||||
"expression": "Chapter (I+V?|VI*|XI|IX|X)"
|
||||
},
|
||||
{
|
||||
"expression": "Section [0-9]+"
|
||||
},
|
||||
{
|
||||
"expression": "Article [0-9]+"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"label": "TokenChunker",
|
||||
"name": "Token Chunker_0"
|
||||
"label": "TitleChunker",
|
||||
"name": "Title Chunker_0"
|
||||
},
|
||||
"id": "TokenChunker:FancyCitiesStick",
|
||||
"id": "TitleChunker:WideResultsTeach",
|
||||
"measured": {
|
||||
"height": 73,
|
||||
"height": 74,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
@@ -462,7 +572,7 @@
|
||||
"field_name": "summary",
|
||||
"frequencyPenaltyEnabled": true,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "Qwen/Qwen3-8B@SILICONFLOW",
|
||||
"llm_id": "THUDM/GLM-4.1V-9B-Thinking@SILICONFLOW",
|
||||
"maxTokensEnabled": false,
|
||||
"max_tokens": 256,
|
||||
"outputs": {
|
||||
@@ -473,27 +583,27 @@
|
||||
},
|
||||
"presencePenaltyEnabled": true,
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": "Text to Summarize:\n[Insert text here]",
|
||||
"prompts": "Text to Summarize:\n{TitleChunker:WideResultsTeach@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": 54,
|
||||
"tenant_llm_id": 63,
|
||||
"topPEnabled": true,
|
||||
"top_p": 0.3
|
||||
},
|
||||
"label": "Extractor",
|
||||
"name": "Summarizer"
|
||||
"name": "Transformer_0"
|
||||
},
|
||||
"id": "Extractor:PublicPlumsKiss",
|
||||
"id": "Extractor:DryRatsGive",
|
||||
"measured": {
|
||||
"height": 89,
|
||||
"height": 90,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 916.9952409420641,
|
||||
"y": 195.39629819663406
|
||||
},
|
||||
"selected": false,
|
||||
"selected": true,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "contextNode"
|
||||
@@ -512,9 +622,9 @@
|
||||
"label": "Tokenizer",
|
||||
"name": "Indexer_0"
|
||||
},
|
||||
"id": "Tokenizer:FullBottlesDeny",
|
||||
"id": "Tokenizer:WackyOnionsFly",
|
||||
"measured": {
|
||||
"height": 113,
|
||||
"height": 114,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
@@ -524,34 +634,11 @@
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "tokenizerNode"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"text": "Using summary to build both text and vector indexes."
|
||||
},
|
||||
"label": "Note",
|
||||
"name": "Index Summary"
|
||||
},
|
||||
"dragHandle": ".note-drag-handle",
|
||||
"dragging": false,
|
||||
"id": "Note:ElevenKingsPick",
|
||||
"measured": {
|
||||
"height": 127,
|
||||
"width": 267
|
||||
},
|
||||
"position": {
|
||||
"x": 735.9586746349814,
|
||||
"y": 315.614230763182
|
||||
},
|
||||
"selected": true,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "noteNode"
|
||||
}
|
||||
]
|
||||
},
|
||||
"history": [],
|
||||
"messages": [],
|
||||
"path": [],
|
||||
"retrieval": [],
|
||||
"variables": []
|
||||
|
||||
@@ -222,7 +222,7 @@ class BaseTitleChunker(ABC):
|
||||
if level < BODY_LEVEL:
|
||||
most_level = level
|
||||
break
|
||||
|
||||
|
||||
return {
|
||||
"levels": levels,
|
||||
"most_level": most_level,
|
||||
|
||||
Reference in New Issue
Block a user