mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-08 16:38:01 +08:00
344 lines
24 KiB
JSON
344 lines
24 KiB
JSON
{
|
||
"id": 20,
|
||
"title": {
|
||
"en": "Reflective academic paper generator",
|
||
"de": "Schreibhilfe für Reflexionspapiere",
|
||
"zh": "学术论文生成助手"
|
||
},
|
||
"description": {
|
||
"en": "A reflective academic paper generator using local knowledge base, with advanced capabilities in task planning, reasoning, and reflective analysis. Recommended for academic research paper Q&A",
|
||
"de": "Ein Berichtsgenerierungsassistent, der eine lokale Wissensdatenbank nutzt, mit erweiterten Fähigkeiten in Aufgabenplanung, Schlussfolgerung und reflektierender Analyse. Empfohlen für akademische Forschungspapier-Fragen und -Antworten.",
|
||
"zh": "一个使用本地知识库的学术论文生成助手，具备高级能力，包括任务规划、推理和反思性分析。推荐用于学术研究论文问答。"
|
||
},
|
||
"canvas_type": "Agent",
|
||
"canvas_types": [
|
||
"Agent",
|
||
"Recommended"
|
||
],
|
||
"dsl": {
|
||
"components": {
|
||
"Agent:NewPumasLick": {
|
||
"downstream": [
|
||
"Message:OrangeYearsShine"
|
||
],
|
||
"obj": {
|
||
"component_name": "Agent",
|
||
"params": {
|
||
"delay_after_error": 1,
|
||
"description": "",
|
||
"exception_comment": "",
|
||
"exception_default_value": "",
|
||
"exception_goto": [],
|
||
"exception_method": null,
|
||
"frequencyPenaltyEnabled": false,
|
||
"frequency_penalty": 0.5,
|
||
"llm_id": "qwen3-235b-a22b-instruct-2507@Tongyi-Qianwen",
|
||
"maxTokensEnabled": true,
|
||
"max_retries": 3,
|
||
"max_rounds": 3,
|
||
"max_tokens": 128000,
|
||
"mcp": [],
|
||
"message_history_window_size": 12,
|
||
"outputs": {
|
||
"content": {
|
||
"type": "string",
|
||
"value": ""
|
||
}
|
||
},
|
||
"parameter": "Precise",
|
||
"presencePenaltyEnabled": false,
|
||
"presence_penalty": 0.5,
|
||
"prompts": [
|
||
{
|
||
"content": "# User Query\n {sys.query}",
|
||
"role": "user"
|
||
}
|
||
],
|
||
"sys_prompt": "## Role & Task\nYou are a **“Knowledge Base Retrieval Q\\&A Agent”** whose goal is to break down the user’s question into retrievable subtasks, and then produce a multi-source-verified, structured, and actionable research report using the internal knowledge base.\n## Execution Framework (Detailed Steps & Key Points)\n1. **Assessment & Decomposition**\n * Actions:\n * Automatically extract: main topic, subtopics, entities (people/organizations/products/technologies), time window, geographic/business scope.\n * Output as a list: N facts/data points that must be collected (*N* ranges from 5–20 depending on question complexity).\n2. **Query Type Determination (Rule-Based)**\n * Example rules:\n * If the question involves a single issue but requests “method comparison/multiple explanations” → use **depth-first**.\n * If the question can naturally be split into ≥3 independent sub-questions → use **breadth-first**.\n * If the question can be answered by a single fact/specification/definition → use **simple query**.\n3. **Research Plan Formulation**\n * Depth-first: define 3–5 perspectives (methodology/stakeholders/time dimension/technical route, etc.), assign search keywords, target document types, and output format for each perspective.\n * Breadth-first: list subtasks, prioritize them, and assign search terms.\n * Simple query: directly provide the search sentence and required fields.\n4. **Retrieval Execution**\n * After retrieval: perform coverage check (does it contain the key facts?) and quality check (source diversity, authority, latest update time).\n * If standards are not met, automatically loop: rewrite queries (synonyms/cross-domain terms) and retry ≤3 times, or flag as requiring external search.\n5. **Integration & Reasoning**\n * Build the answer using a **fact–evidence–reasoning** chain. For each conclusion, attach 1–2 strongest pieces of evidence.\n---\n## Quality Gate Checklist (Verify at Each Stage)\n* **Stage 1 (Decomposition)**:\n * [ ] Key concepts and expected outputs identified\n * [ ] Required facts/data points listed\n* **Stage 2 (Retrieval)**:\n * [ ] Meets quality standards (see above)\n * [ ] If not met: execute query iteration\n* **Stage 3 (Generation)**:\n * [ ] Each conclusion has at least one direct evidence source\n * [ ] State assumptions/uncertainties\n * [ ] Provide next-step suggestions or experiment/retrieval plans\n * [ ] Final length and depth match user expectations (comply with word count/format if specified)\n---\n## Core Principles\n1. **Strict reliance on the knowledge base**: answers must be **fully bounded** by the content retrieved from the knowledge base.\n2. **No fabrication**: do not generate, infer, or create information that is not explicitly present in the knowledge base.\n3. **Accuracy first**: prefer incompleteness over inaccurate content.\n4. **Output format**:\n * Hierarchically clear modular structure\n * Logical grouping according to the MECE principle\n * Professionally presented formatting\n * Step-by-step cognitive guidance\n * Reasonable use of headings and dividers for clarity\n * *Italicize* key parameters\n * **Bold** critical information\n5. **LaTeX formula requirements**:\n * Inline formulas: start and end with `$`\n * Block formulas: start and end with `$$`, each `$$` on its own line\n * Block formula content must comply with LaTeX math syntax\n * Verify formula correctness\n---\n## Additional Notes (Interaction & Failure Strategy)\n* If the knowledge base does not cover critical facts: explicitly inform the user (with sample wording)\n* For time-sensitive issues: enforce time filtering in the search request, and indicate the latest retrieval date in the answer.\n* Language requirement: answer in the user’s preferred language\n",
|
||
"temperature": "0.1",
|
||
"temperatureEnabled": true,
|
||
"tools": [
|
||
{
|
||
"component_name": "Retrieval",
|
||
"name": "Retrieval",
|
||
"params": {
|
||
"cross_languages": [],
|
||
"description": "",
|
||
"empty_response": "",
|
||
"kb_ids": [],
|
||
"retrieval_from": "dataset",
|
||
"keywords_similarity_weight": 0.7,
|
||
"outputs": {
|
||
"formalized_content": {
|
||
"type": "string",
|
||
"value": ""
|
||
}
|
||
},
|
||
"rerank_id": "",
|
||
"similarity_threshold": 0.2,
|
||
"top_k": 1024,
|
||
"top_n": 8,
|
||
"use_kg": false
|
||
},
|
||
"id": "Retrieval:NewPumasLick"
|
||
}
|
||
],
|
||
"topPEnabled": false,
|
||
"top_p": 0.75,
|
||
"user_prompt": "",
|
||
"visual_files_var": ""
|
||
}
|
||
},
|
||
"upstream": [
|
||
"begin"
|
||
]
|
||
},
|
||
"Message:OrangeYearsShine": {
|
||
"downstream": [],
|
||
"obj": {
|
||
"component_name": "Message",
|
||
"params": {
|
||
"content": [
|
||
"{Agent:NewPumasLick@content}"
|
||
]
|
||
}
|
||
},
|
||
"upstream": [
|
||
"Agent:NewPumasLick"
|
||
]
|
||
},
|
||
"begin": {
|
||
"downstream": [
|
||
"Agent:NewPumasLick"
|
||
],
|
||
"obj": {
|
||
"component_name": "Begin",
|
||
"params": {
|
||
"enablePrologue": true,
|
||
"inputs": {},
|
||
"mode": "conversational",
|
||
"prologue": "你好！ 我是你的助理，有什么可以帮到你的吗？"
|
||
}
|
||
},
|
||
"upstream": []
|
||
}
|
||
},
|
||
"globals": {
|
||
"sys.conversation_turns": 0,
|
||
"sys.files": [],
|
||
"sys.query": "",
|
||
"sys.user_id": ""
|
||
},
|
||
"graph": {
|
||
"edges": [
|
||
{
|
||
"data": {
|
||
"isHovered": false
|
||
},
|
||
"id": "xy-edge__beginstart-Agent:NewPumasLickend",
|
||
"source": "begin",
|
||
"sourceHandle": "start",
|
||
"target": "Agent:NewPumasLick",
|
||
"targetHandle": "end"
|
||
},
|
||
{
|
||
"data": {
|
||
"isHovered": false
|
||
},
|
||
"id": "xy-edge__Agent:NewPumasLickstart-Message:OrangeYearsShineend",
|
||
"markerEnd": "logo",
|
||
"source": "Agent:NewPumasLick",
|
||
"sourceHandle": "start",
|
||
"style": {
|
||
"stroke": "rgba(91, 93, 106, 1)",
|
||
"strokeWidth": 1
|
||
},
|
||
"target": "Message:OrangeYearsShine",
|
||
"targetHandle": "end",
|
||
"type": "buttonEdge",
|
||
"zIndex": 1001
|
||
},
|
||
{
|
||
"data": {
|
||
"isHovered": false
|
||
},
|
||
"id": "xy-edge__Agent:NewPumasLicktool-Tool:AllBirdsNailend",
|
||
"selected": false,
|
||
"source": "Agent:NewPumasLick",
|
||
"sourceHandle": "tool",
|
||
"target": "Tool:AllBirdsNail",
|
||
"targetHandle": "end"
|
||
}
|
||
],
|
||
"nodes": [
|
||
{
|
||
"data": {
|
||
"form": {
|
||
"enablePrologue": true,
|
||
"inputs": {},
|
||
"mode": "conversational",
|
||
"prologue": "你好！ 我是你的助理，有什么可以帮到你的吗？"
|
||
},
|
||
"label": "Begin",
|
||
"name": "begin"
|
||
},
|
||
"dragging": false,
|
||
"id": "begin",
|
||
"measured": {
|
||
"height": 48,
|
||
"width": 200
|
||
},
|
||
"position": {
|
||
"x": -9.569875358221438,
|
||
"y": 205.84018385864917
|
||
},
|
||
"selected": false,
|
||
"sourcePosition": "left",
|
||
"targetPosition": "right",
|
||
"type": "beginNode"
|
||
},
|
||
{
|
||
"data": {
|
||
"form": {
|
||
"content": [
|
||
"{Agent:NewPumasLick@content}"
|
||
]
|
||
},
|
||
"label": "Message",
|
||
"name": "Response"
|
||
},
|
||
"dragging": false,
|
||
"id": "Message:OrangeYearsShine",
|
||
"measured": {
|
||
"height": 56,
|
||
"width": 200
|
||
},
|
||
"position": {
|
||
"x": 734.4061285881053,
|
||
"y": 199.9706031723009
|
||
},
|
||
"selected": false,
|
||
"sourcePosition": "right",
|
||
"targetPosition": "left",
|
||
"type": "messageNode"
|
||
},
|
||
{
|
||
"data": {
|
||
"form": {
|
||
"delay_after_error": 1,
|
||
"description": "",
|
||
"exception_comment": "",
|
||
"exception_default_value": "",
|
||
"exception_goto": [],
|
||
"exception_method": null,
|
||
"frequencyPenaltyEnabled": false,
|
||
"frequency_penalty": 0.5,
|
||
"llm_id": "qwen3-235b-a22b-instruct-2507@Tongyi-Qianwen",
|
||
"maxTokensEnabled": true,
|
||
"max_retries": 3,
|
||
"max_rounds": 3,
|
||
"max_tokens": 128000,
|
||
"mcp": [],
|
||
"message_history_window_size": 12,
|
||
"outputs": {
|
||
"content": {
|
||
"type": "string",
|
||
"value": ""
|
||
}
|
||
},
|
||
"parameter": "Precise",
|
||
"presencePenaltyEnabled": false,
|
||
"presence_penalty": 0.5,
|
||
"prompts": [
|
||
{
|
||
"content": "# User Query\n {sys.query}",
|
||
"role": "user"
|
||
}
|
||
],
|
||
"sys_prompt": "## Role & Task\nYou are a **“Knowledge Base Retrieval Q\\&A Agent”** whose goal is to break down the user’s question into retrievable subtasks, and then produce a multi-source-verified, structured, and actionable research report using the internal knowledge base.\n## Execution Framework (Detailed Steps & Key Points)\n1. **Assessment & Decomposition**\n * Actions:\n * Automatically extract: main topic, subtopics, entities (people/organizations/products/technologies), time window, geographic/business scope.\n * Output as a list: N facts/data points that must be collected (*N* ranges from 5–20 depending on question complexity).\n2. **Query Type Determination (Rule-Based)**\n * Example rules:\n * If the question involves a single issue but requests “method comparison/multiple explanations” → use **depth-first**.\n * If the question can naturally be split into ≥3 independent sub-questions → use **breadth-first**.\n * If the question can be answered by a single fact/specification/definition → use **simple query**.\n3. **Research Plan Formulation**\n * Depth-first: define 3–5 perspectives (methodology/stakeholders/time dimension/technical route, etc.), assign search keywords, target document types, and output format for each perspective.\n * Breadth-first: list subtasks, prioritize them, and assign search terms.\n * Simple query: directly provide the search sentence and required fields.\n4. **Retrieval Execution**\n * After retrieval: perform coverage check (does it contain the key facts?) and quality check (source diversity, authority, latest update time).\n * If standards are not met, automatically loop: rewrite queries (synonyms/cross-domain terms) and retry ≤3 times, or flag as requiring external search.\n5. **Integration & Reasoning**\n * Build the answer using a **fact–evidence–reasoning** chain. For each conclusion, attach 1–2 strongest pieces of evidence.\n---\n## Quality Gate Checklist (Verify at Each Stage)\n* **Stage 1 (Decomposition)**:\n * [ ] Key concepts and expected outputs identified\n * [ ] Required facts/data points listed\n* **Stage 2 (Retrieval)**:\n * [ ] Meets quality standards (see above)\n * [ ] If not met: execute query iteration\n* **Stage 3 (Generation)**:\n * [ ] Each conclusion has at least one direct evidence source\n * [ ] State assumptions/uncertainties\n * [ ] Provide next-step suggestions or experiment/retrieval plans\n * [ ] Final length and depth match user expectations (comply with word count/format if specified)\n---\n## Core Principles\n1. **Strict reliance on the knowledge base**: answers must be **fully bounded** by the content retrieved from the knowledge base.\n2. **No fabrication**: do not generate, infer, or create information that is not explicitly present in the knowledge base.\n3. **Accuracy first**: prefer incompleteness over inaccurate content.\n4. **Output format**:\n * Hierarchically clear modular structure\n * Logical grouping according to the MECE principle\n * Professionally presented formatting\n * Step-by-step cognitive guidance\n * Reasonable use of headings and dividers for clarity\n * *Italicize* key parameters\n * **Bold** critical information\n5. **LaTeX formula requirements**:\n * Inline formulas: start and end with `$`\n * Block formulas: start and end with `$$`, each `$$` on its own line\n * Block formula content must comply with LaTeX math syntax\n * Verify formula correctness\n---\n## Additional Notes (Interaction & Failure Strategy)\n* If the knowledge base does not cover critical facts: explicitly inform the user (with sample wording)\n* For time-sensitive issues: enforce time filtering in the search request, and indicate the latest retrieval date in the answer.\n* Language requirement: answer in the user’s preferred language\n",
|
||
"temperature": "0.1",
|
||
"temperatureEnabled": true,
|
||
"tools": [
|
||
{
|
||
"component_name": "Retrieval",
|
||
"name": "Retrieval",
|
||
"params": {
|
||
"cross_languages": [],
|
||
"description": "",
|
||
"empty_response": "",
|
||
"kb_ids": [],
|
||
"retrieval_from": "dataset",
|
||
"keywords_similarity_weight": 0.7,
|
||
"outputs": {
|
||
"formalized_content": {
|
||
"type": "string",
|
||
"value": ""
|
||
}
|
||
},
|
||
"rerank_id": "",
|
||
"similarity_threshold": 0.2,
|
||
"top_k": 1024,
|
||
"top_n": 8,
|
||
"use_kg": false
|
||
},
|
||
"id": "Retrieval:NewPumasLick"
|
||
}
|
||
],
|
||
"topPEnabled": false,
|
||
"top_p": 0.75,
|
||
"user_prompt": "",
|
||
"visual_files_var": ""
|
||
},
|
||
"label": "Agent",
|
||
"name": "Knowledge Base Agent"
|
||
},
|
||
"dragging": false,
|
||
"id": "Agent:NewPumasLick",
|
||
"measured": {
|
||
"height": 84,
|
||
"width": 200
|
||
},
|
||
"position": {
|
||
"x": 347.00048227952215,
|
||
"y": 186.49109364794631
|
||
},
|
||
"selected": false,
|
||
"sourcePosition": "right",
|
||
"targetPosition": "left",
|
||
"type": "agentNode"
|
||
},
|
||
{
|
||
"data": {
|
||
"form": {
|
||
"description": "This is an agent for a specific task.",
|
||
"user_prompt": "This is the order you need to send to the agent."
|
||
},
|
||
"label": "Tool",
|
||
"name": "flow.tool_10"
|
||
},
|
||
"dragging": false,
|
||
"id": "Tool:AllBirdsNail",
|
||
"measured": {
|
||
"height": 48,
|
||
"width": 200
|
||
},
|
||
"position": {
|
||
"x": 220.24819746977118,
|
||
"y": 403.31576836482583
|
||
},
|
||
"selected": false,
|
||
"sourcePosition": "right",
|
||
"targetPosition": "left",
|
||
"type": "toolNode"
|
||
}
|
||
]
|
||
},
|
||
"history": [],
|
||
"memory": [],
|
||
"messages": [],
|
||
"path": [],
|
||
"retrieval": []
|
||
},
|
||
"avatar": "data:image/png;base64,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"
|
||
}
|