mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-13 16:38:26 +08:00
feat: support multiple canvas_types for agent templates and remove duplicate files (#14030)
### What problem does this PR solve? Closes #13907 The template catalog had duplicate files (e.g. `*_r.json`) only to place the same template into multiple sidebar groups. This increases maintenance cost and makes template updates error-prone. This PR adds first-class support for multiple template categories in a single file via `canvas_types`, then removes duplicate template files. What changed: - Added `canvas_types` to `CanvasTemplate` model and DB migration. - Added normalization logic when loading templates: - accepts legacy `canvas_type` - accepts new `canvas_types` - merges/deduplicates values - preserves backward compatibility by keeping `canvas_type` as first normalized value. - Updated template import flow to load only `.json` files and in stable sorted order. - Updated frontend template filtering to match on `canvas_types` first, with fallback to legacy `canvas_type`. - Consolidated duplicated template pairs into single files and removed: - `deep_search_r.json` - `reflective_academic_paper_generator_r.json` - `seo_article_writer_r.json` - Added regression/edge-case tests for category normalization and route serialization expectations. ### Type of change - [ ] Bug Fix (non-breaking change which fixes an issue) - [x] New Feature (non-breaking change which adds functionality) - [ ] Documentation Update - [ ] Refactoring - [ ] Performance Improvement - [ ] Other (please describe):
This commit is contained in:
bitloi
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -9,6 +9,7 @@
|
||||
"de": "SEO-Blog-Magnetiseur automatisch einen vollständigen SEO-optimierten Blogartikel basierend auf einer einfachen Benutzereingabe. Sie benötigen keine Schreiberfahrung. Geben Sie einfach ein Thema oder eine kurze Anfrage ein – das System übernimmt den Rest.",
|
||||
"zh": "此 SEO 博客写手根据简单的用户输入自动生成完整的SEO博客文章。你无需任何写作经验，只需提供一个主题或简短请求，系统将处理其余部分。"},
|
||||
"canvas_type": "Marketing",
|
||||
"canvas_types": ["Marketing", "Recommended"],
|
||||
"dsl": {
|
||||
"components": {
|
||||
"Agent:BetterSitesSend": {
|
||||
@@ -918,4 +919,4 @@
|
||||
"retrieval": []
|
||||
},
|
||||
"avatar": "data:image/jpeg;base64,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"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -9,6 +9,7 @@
|
||||
"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": {
|
||||
@@ -330,4 +331,4 @@
|
||||
"retrieval": []
|
||||
},
|
||||
"avatar": "data:image/png;base64,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"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,333 +0,0 @@
|
||||
{
|
||||
"id": 21,
|
||||
"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": "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 **\u201cKnowledge Base Retrieval Q\\&A Agent\u201d** whose goal is to break down the user\u2019s 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\u201320 depending on question complexity).\n2. **Query Type Determination (Rule-Based)**\n * Example rules:\n * If the question involves a single issue but requests \u201cmethod comparison/multiple explanations\u201d \u2192 use **depth-first**.\n * If the question can naturally be split into \u22653 independent sub-questions \u2192 use **breadth-first**.\n * If the question can be answered by a single fact/specification/definition \u2192 use **simple query**.\n3. **Research Plan Formulation**\n * Depth-first: define 3\u20135 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 \u22643 times, or flag as requiring external search.\n5. **Integration & Reasoning**\n * Build the answer using a **fact\u2013evidence\u2013reasoning** chain. For each conclusion, attach 1\u20132 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\u2019s preferred language\n",
|
||||
"temperature": "0.1",
|
||||
"temperatureEnabled": true,
|
||||
"tools": [
|
||||
{
|
||||
"component_name": "Retrieval",
|
||||
"name": "Retrieval",
|
||||
"params": {
|
||||
"cross_languages": [],
|
||||
"description": "",
|
||||
"empty_response": "",
|
||||
"kb_ids": [],
|
||||
"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
|
||||
}
|
||||
}
|
||||
],
|
||||
"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": "\u4f60\u597d\uff01 \u6211\u662f\u4f60\u7684\u52a9\u7406\uff0c\u6709\u4ec0\u4e48\u53ef\u4ee5\u5e2e\u5230\u4f60\u7684\u5417\uff1f"
|
||||
}
|
||||
},
|
||||
"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": "\u4f60\u597d\uff01 \u6211\u662f\u4f60\u7684\u52a9\u7406\uff0c\u6709\u4ec0\u4e48\u53ef\u4ee5\u5e2e\u5230\u4f60\u7684\u5417\uff1f"
|
||||
},
|
||||
"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 **\u201cKnowledge Base Retrieval Q\\&A Agent\u201d** whose goal is to break down the user\u2019s 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\u201320 depending on question complexity).\n2. **Query Type Determination (Rule-Based)**\n * Example rules:\n * If the question involves a single issue but requests \u201cmethod comparison/multiple explanations\u201d \u2192 use **depth-first**.\n * If the question can naturally be split into \u22653 independent sub-questions \u2192 use **breadth-first**.\n * If the question can be answered by a single fact/specification/definition \u2192 use **simple query**.\n3. **Research Plan Formulation**\n * Depth-first: define 3\u20135 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 \u22643 times, or flag as requiring external search.\n5. **Integration & Reasoning**\n * Build the answer using a **fact\u2013evidence\u2013reasoning** chain. For each conclusion, attach 1\u20132 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\u2019s preferred language\n",
|
||||
"temperature": "0.1",
|
||||
"temperatureEnabled": true,
|
||||
"tools": [
|
||||
{
|
||||
"component_name": "Retrieval",
|
||||
"name": "Retrieval",
|
||||
"params": {
|
||||
"cross_languages": [],
|
||||
"description": "",
|
||||
"empty_response": "",
|
||||
"kb_ids": [],
|
||||
"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
|
||||
}
|
||||
}
|
||||
],
|
||||
"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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"
|
||||
}
|
||||
@@ -1,921 +0,0 @@
|
||||
{
|
||||
"id": 4,
|
||||
"title": {
|
||||
"en": "SEO article writer",
|
||||
"de": "SEO-Blog-Magnetiseur",
|
||||
"zh": "SEO 博客写手"},
|
||||
"description": {
|
||||
"en": "This SEO article writer automatically generates a complete SEO-optimized blog article based on a simple user input. You don't need any writing experience. Just provide a topic or short request — the system will handle the rest.",
|
||||
"de": "SEO-Blog-Magnetiseur automatisch einen vollständigen SEO-optimierten Blogartikel basierend auf einer einfachen Benutzereingabe. Sie benötigen keine Schreiberfahrung. Geben Sie einfach ein Thema oder eine kurze Anfrage ein – das System übernimmt den Rest.",
|
||||
"zh": "此 SEO 博客写手根据简单的用户输入自动生成完整的SEO博客文章。你无需任何写作经验，只需提供一个主题或简短请求，系统将处理其余部分。"},
|
||||
"canvas_type": "Recommended",
|
||||
"dsl": {
|
||||
"components": {
|
||||
"Agent:BetterSitesSend": {
|
||||
"downstream": [
|
||||
"Agent:EagerNailsRemain"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Agent",
|
||||
"params": {
|
||||
"delay_after_error": 1,
|
||||
"description": "",
|
||||
"exception_comment": "",
|
||||
"exception_default_value": "",
|
||||
"exception_goto": [],
|
||||
"exception_method": null,
|
||||
"frequencyPenaltyEnabled": false,
|
||||
"frequency_penalty": 0.3,
|
||||
"llm_id": "deepseek-chat@DeepSeek",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 3,
|
||||
"max_tokens": 4096,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
}
|
||||
},
|
||||
"parameter": "Balance",
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.2,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "# Role\n\nYou are the **Outline_Agent**, responsible for generating a clear and SEO-optimized blog outline based on the user's parsed writing intent and keyword strategy.\n\n# Tool Access:\n\n- You have access to a search tool called `Tavily Search`.\n\n- If you are unsure how to structure a section, you may call this tool to search for related blog outlines or content from Google.\n\n- Do not overuse it. Your job is to extract **structure**, not to write paragraphs.\n\n\n# Goals\n\n1. Create a well-structured outline with appropriate H2 and H3 headings.\n\n2. Ensure logical flow from introduction to conclusion.\n\n3. Assign 1\u20132 suggested long-tail keywords to each major section for SEO alignment.\n\n4. Make the structure suitable for downstream paragraph writing.\n\n\n\n\n#Note\n\n- Use concise, scannable section titles.\n\n- Do not write full paragraphs.\n\n- Prioritize clarity, logical progression, and SEO alignment.\n\n\n\n- If the blog type is \u201cTutorial\u201d or \u201cHow-to\u201d, include step-based sections.\n\n\n# Input\n\nYou will receive:\n\n- Writing Type (e.g., Tutorial, Informative Guide)\n\n- Target Audience\n\n- User Intent Summary\n\n- 3\u20135 long-tail keywords\n\n\nUse this information to design a structure that both informs readers and maximizes search engine visibility.\n\n# Output Format\n\n```markdown\n\n## Blog Title (suggested)\n\n[Give a short, SEO-friendly title suggestion]\n\n## Outline\n\n### Introduction\n\n- Purpose of the article\n\n- Brief context\n\n- **Suggested keywords**: [keyword1, keyword2]\n\n### H2: [Section Title 1]\n\n- [Short description of what this section will cover]\n\n- **Suggested keywords**: [keyword1, keyword2]\n\n### H2: [Section Title 2]\n\n- [Short description of what this section will cover]\n\n- **Suggested keywords**: [keyword1, keyword2]\n\n### H2: [Section Title 3]\n\n- [Optional H3 Subsection Title A]\n\n - [Explanation of sub-point]\n\n- [Optional H3 Subsection Title B]\n\n - [Explanation of sub-point]\n\n- **Suggested keywords**: [keyword1]\n\n### Conclusion\n\n- Recap key takeaways\n\n- Optional CTA (Call to Action)\n\n- **Suggested keywords**: [keyword3]\n\n",
|
||||
"temperature": 0.5,
|
||||
"temperatureEnabled": true,
|
||||
"tools": [
|
||||
{
|
||||
"component_name": "TavilySearch",
|
||||
"name": "TavilySearch",
|
||||
"params": {
|
||||
"api_key": "",
|
||||
"days": 7,
|
||||
"exclude_domains": [],
|
||||
"include_answer": false,
|
||||
"include_domains": [],
|
||||
"include_image_descriptions": false,
|
||||
"include_images": false,
|
||||
"include_raw_content": true,
|
||||
"max_results": 5,
|
||||
"outputs": {
|
||||
"formalized_content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
},
|
||||
"json": {
|
||||
"type": "Array<Object>",
|
||||
"value": []
|
||||
}
|
||||
},
|
||||
"query": "sys.query",
|
||||
"search_depth": "basic",
|
||||
"topic": "general"
|
||||
}
|
||||
}
|
||||
],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.85,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"Agent:ClearRabbitsScream"
|
||||
]
|
||||
},
|
||||
"Agent:ClearRabbitsScream": {
|
||||
"downstream": [
|
||||
"Agent:BetterSitesSend"
|
||||
],
|
||||
"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": "deepseek-chat@DeepSeek",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 1,
|
||||
"max_tokens": 4096,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
}
|
||||
},
|
||||
"parameter": "Precise",
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.5,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "The user query is {sys.query}",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "# Role\n\nYou are the **Parse_And_Keyword_Agent**, responsible for interpreting a user's blog writing request and generating a structured writing intent summary and keyword strategy for SEO-optimized content generation.\n\n# Goals\n\n1. Extract and infer the user's true writing intent, even if the input is informal or vague.\n\n2. Identify the writing type, target audience, and implied goal.\n\n3. Suggest 3\u20135 long-tail keywords based on the input and context.\n\n4. Output all data in a Markdown format for downstream agents.\n\n# Operating Guidelines\n\n\n- If the user's input lacks clarity, make reasonable and **conservative** assumptions based on SEO best practices.\n\n- Always choose one clear \"Writing Type\" from the list below.\n\n- Your job is not to write the blog \u2014 only to structure the brief.\n\n# Output Format\n\n```markdown\n## Writing Type\n\n[Choose one: Tutorial / Informative Guide / Marketing Content / Case Study / Opinion Piece / How-to / Comparison Article]\n\n## Target Audience\n\n[Try to be specific based on clues in the input: e.g., marketing managers, junior developers, SEO beginners]\n\n## User Intent Summary\n\n[A 1\u20132 sentence summary of what the user wants to achieve with the blog post]\n\n## Suggested Long-tail Keywords\n\n- keyword 1\n\n- keyword 2\n\n- keyword 3\n\n- keyword 4 (optional)\n\n- keyword 5 (optional)\n\n\n\n\n## Input Examples (and how to handle them)\n\nInput: \"I want to write about RAGFlow.\"\n\u2192 Output: Informative Guide, Audience: AI developers, Intent: explain what RAGFlow is and its use cases\n\nInput: \"Need a blog to promote our prompt design tool.\"\n\u2192 Output: Marketing Content, Audience: product managers or tool adopters, Intent: raise awareness and interest in the product\n\n\n\nInput: \"How to get more Google traffic using AI\"\n\u2192 Output: How-to, Audience: SEO marketers, Intent: guide readers on applying AI for SEO growth",
|
||||
"temperature": 0.2,
|
||||
"temperatureEnabled": true,
|
||||
"tools": [],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.75,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"begin"
|
||||
]
|
||||
},
|
||||
"Agent:EagerNailsRemain": {
|
||||
"downstream": [
|
||||
"Agent:LovelyHeadsOwn"
|
||||
],
|
||||
"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": "deepseek-chat@DeepSeek",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 5,
|
||||
"max_tokens": 4096,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
}
|
||||
},
|
||||
"parameter": "Precise",
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.5,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\n\n\nThe Outline agent output is {Agent:BetterSitesSend@content}",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "# Role\n\nYou are the **Body_Agent**, responsible for generating the full content of each section of an SEO-optimized blog based on the provided outline and keyword strategy.\n\n# Tool Access:\n\nYou can use the `Tavily Search` tool to retrieve relevant content, statistics, or examples to support each section you're writing.\n\nUse it **only** when the provided outline lacks enough information, or if the section requires factual grounding.\n\nAlways cite the original link or indicate source where possible.\n\n\n# Goals\n\n1. Write each section (based on H2/H3 structure) as a complete and natural blog paragraph.\n\n2. Integrate the suggested long-tail keywords naturally into each section.\n\n3. When appropriate, use the `Tavily Search` tool to enrich your writing with relevant facts, examples, or quotes.\n\n4. Ensure each section is clear, engaging, and informative, suitable for both human readers and search engines.\n\n\n# Style Guidelines\n\n- Write in a tone appropriate to the audience. Be explanatory, not promotional, unless it's a marketing blog.\n\n- Avoid generic filler content. Prioritize clarity, structure, and value.\n\n- Ensure SEO keywords are embedded seamlessly, not forcefully.\n\n\n\n- Maintain writing rhythm. Vary sentence lengths. Use transitions between ideas.\n\n\n# Input\n\n\nYou will receive:\n\n- Blog title\n\n- Structured outline (including section titles, keywords, and descriptions)\n\n- Target audience\n\n- Blog type and user intent\n\nYou must **follow the outline strictly**. Write content **section-by-section**, based on the structure.\n\n\n# Output Format\n\n```markdown\n\n## H2: [Section Title]\n\n[Your generated content for this section \u2014 500-600 words, using keywords naturally.]\n\n",
|
||||
"temperature": 0.2,
|
||||
"temperatureEnabled": true,
|
||||
"tools": [
|
||||
{
|
||||
"component_name": "TavilySearch",
|
||||
"name": "TavilySearch",
|
||||
"params": {
|
||||
"api_key": "",
|
||||
"days": 7,
|
||||
"exclude_domains": [],
|
||||
"include_answer": false,
|
||||
"include_domains": [],
|
||||
"include_image_descriptions": false,
|
||||
"include_images": false,
|
||||
"include_raw_content": true,
|
||||
"max_results": 5,
|
||||
"outputs": {
|
||||
"formalized_content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
},
|
||||
"json": {
|
||||
"type": "Array<Object>",
|
||||
"value": []
|
||||
}
|
||||
},
|
||||
"query": "sys.query",
|
||||
"search_depth": "basic",
|
||||
"topic": "general"
|
||||
}
|
||||
}
|
||||
],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.75,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"Agent:BetterSitesSend"
|
||||
]
|
||||
},
|
||||
"Agent:LovelyHeadsOwn": {
|
||||
"downstream": [
|
||||
"Message:LegalBeansBet"
|
||||
],
|
||||
"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": "deepseek-chat@DeepSeek",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 5,
|
||||
"max_tokens": 4096,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
}
|
||||
},
|
||||
"parameter": "Precise",
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.5,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\nThe Outline agent output is {Agent:BetterSitesSend@content}\n\nThe Body agent output is {Agent:EagerNailsRemain@content}",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "# Role\n\nYou are the **Editor_Agent**, responsible for finalizing the blog post for both human readability and SEO effectiveness.\n\n# Goals\n\n1. Polish the entire blog content for clarity, coherence, and style.\n\n2. Improve transitions between sections, ensure logical flow.\n\n3. Verify that keywords are used appropriately and effectively.\n\n4. Conduct a lightweight SEO audit \u2014 checking keyword density, structure (H1/H2/H3), and overall searchability.\n\n\n\n# Style Guidelines\n\n- Be precise. Avoid bloated or vague language.\n\n- Maintain an informative and engaging tone, suitable to the target audience.\n\n- Do not remove keywords unless absolutely necessary for clarity.\n\n- Ensure paragraph flow and section continuity.\n\n\n# Input\n\nYou will receive:\n\n- Full blog content, written section-by-section\n\n- Original outline with suggested keywords\n\n- Target audience and writing type\n\n# Output Format\n\n```markdown\n\n[The revised, fully polished blog post content goes here.]\n\n",
|
||||
"temperature": 0.2,
|
||||
"temperatureEnabled": true,
|
||||
"tools": [],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.75,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"Agent:EagerNailsRemain"
|
||||
]
|
||||
},
|
||||
"Message:LegalBeansBet": {
|
||||
"downstream": [],
|
||||
"obj": {
|
||||
"component_name": "Message",
|
||||
"params": {
|
||||
"content": [
|
||||
"{Agent:LovelyHeadsOwn@content}"
|
||||
]
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"Agent:LovelyHeadsOwn"
|
||||
]
|
||||
},
|
||||
"begin": {
|
||||
"downstream": [
|
||||
"Agent:ClearRabbitsScream"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Begin",
|
||||
"params": {
|
||||
"enablePrologue": true,
|
||||
"inputs": {},
|
||||
"mode": "conversational",
|
||||
"prologue": "Hi! I'm your SEO blog assistant.\n\nTo get started, please tell me:\n1. What topic you want the blog to cover\n2. Who is the target audience\n3. What you hope to achieve with this blog (e.g., SEO traffic, teaching beginners, promoting a product)\n"
|
||||
}
|
||||
},
|
||||
"upstream": []
|
||||
}
|
||||
},
|
||||
"globals": {
|
||||
"sys.conversation_turns": 0,
|
||||
"sys.files": [],
|
||||
"sys.query": "",
|
||||
"sys.user_id": ""
|
||||
},
|
||||
"graph": {
|
||||
"edges": [
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__beginstart-Agent:ClearRabbitsScreamend",
|
||||
"source": "begin",
|
||||
"sourceHandle": "start",
|
||||
"target": "Agent:ClearRabbitsScream",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__Agent:ClearRabbitsScreamstart-Agent:BetterSitesSendend",
|
||||
"source": "Agent:ClearRabbitsScream",
|
||||
"sourceHandle": "start",
|
||||
"target": "Agent:BetterSitesSend",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__Agent:BetterSitesSendtool-Tool:SharpPensBurnend",
|
||||
"source": "Agent:BetterSitesSend",
|
||||
"sourceHandle": "tool",
|
||||
"target": "Tool:SharpPensBurn",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__Agent:BetterSitesSendstart-Agent:EagerNailsRemainend",
|
||||
"source": "Agent:BetterSitesSend",
|
||||
"sourceHandle": "start",
|
||||
"target": "Agent:EagerNailsRemain",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"id": "xy-edge__Agent:EagerNailsRemaintool-Tool:WickedDeerHealend",
|
||||
"source": "Agent:EagerNailsRemain",
|
||||
"sourceHandle": "tool",
|
||||
"target": "Tool:WickedDeerHeal",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__Agent:EagerNailsRemainstart-Agent:LovelyHeadsOwnend",
|
||||
"source": "Agent:EagerNailsRemain",
|
||||
"sourceHandle": "start",
|
||||
"target": "Agent:LovelyHeadsOwn",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__Agent:LovelyHeadsOwnstart-Message:LegalBeansBetend",
|
||||
"source": "Agent:LovelyHeadsOwn",
|
||||
"sourceHandle": "start",
|
||||
"target": "Message:LegalBeansBet",
|
||||
"targetHandle": "end"
|
||||
}
|
||||
],
|
||||
"nodes": [
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"enablePrologue": true,
|
||||
"inputs": {},
|
||||
"mode": "conversational",
|
||||
"prologue": "Hi! I'm your SEO blog assistant.\n\nTo get started, please tell me:\n1. What topic you want the blog to cover\n2. Who is the target audience\n3. What you hope to achieve with this blog (e.g., SEO traffic, teaching beginners, promoting a product)\n"
|
||||
},
|
||||
"label": "Begin",
|
||||
"name": "begin"
|
||||
},
|
||||
"id": "begin",
|
||||
"measured": {
|
||||
"height": 48,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 50,
|
||||
"y": 200
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "left",
|
||||
"targetPosition": "right",
|
||||
"type": "beginNode"
|
||||
},
|
||||
{
|
||||
"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": "deepseek-chat@DeepSeek",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 1,
|
||||
"max_tokens": 4096,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
}
|
||||
},
|
||||
"parameter": "Precise",
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.5,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "The user query is {sys.query}",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "# Role\n\nYou are the **Parse_And_Keyword_Agent**, responsible for interpreting a user's blog writing request and generating a structured writing intent summary and keyword strategy for SEO-optimized content generation.\n\n# Goals\n\n1. Extract and infer the user's true writing intent, even if the input is informal or vague.\n\n2. Identify the writing type, target audience, and implied goal.\n\n3. Suggest 3\u20135 long-tail keywords based on the input and context.\n\n4. Output all data in a Markdown format for downstream agents.\n\n# Operating Guidelines\n\n\n- If the user's input lacks clarity, make reasonable and **conservative** assumptions based on SEO best practices.\n\n- Always choose one clear \"Writing Type\" from the list below.\n\n- Your job is not to write the blog \u2014 only to structure the brief.\n\n# Output Format\n\n```markdown\n## Writing Type\n\n[Choose one: Tutorial / Informative Guide / Marketing Content / Case Study / Opinion Piece / How-to / Comparison Article]\n\n## Target Audience\n\n[Try to be specific based on clues in the input: e.g., marketing managers, junior developers, SEO beginners]\n\n## User Intent Summary\n\n[A 1\u20132 sentence summary of what the user wants to achieve with the blog post]\n\n## Suggested Long-tail Keywords\n\n- keyword 1\n\n- keyword 2\n\n- keyword 3\n\n- keyword 4 (optional)\n\n- keyword 5 (optional)\n\n\n\n\n## Input Examples (and how to handle them)\n\nInput: \"I want to write about RAGFlow.\"\n\u2192 Output: Informative Guide, Audience: AI developers, Intent: explain what RAGFlow is and its use cases\n\nInput: \"Need a blog to promote our prompt design tool.\"\n\u2192 Output: Marketing Content, Audience: product managers or tool adopters, Intent: raise awareness and interest in the product\n\n\n\nInput: \"How to get more Google traffic using AI\"\n\u2192 Output: How-to, Audience: SEO marketers, Intent: guide readers on applying AI for SEO growth",
|
||||
"temperature": 0.2,
|
||||
"temperatureEnabled": true,
|
||||
"tools": [],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.75,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
},
|
||||
"label": "Agent",
|
||||
"name": "Parse And Keyword Agent"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Agent:ClearRabbitsScream",
|
||||
"measured": {
|
||||
"height": 84,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 344.7766966202233,
|
||||
"y": 234.82202253184496
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "agentNode"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"delay_after_error": 1,
|
||||
"description": "",
|
||||
"exception_comment": "",
|
||||
"exception_default_value": "",
|
||||
"exception_goto": [],
|
||||
"exception_method": null,
|
||||
"frequencyPenaltyEnabled": false,
|
||||
"frequency_penalty": 0.3,
|
||||
"llm_id": "deepseek-chat@DeepSeek",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 3,
|
||||
"max_tokens": 4096,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
}
|
||||
},
|
||||
"parameter": "Balance",
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.2,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "# Role\n\nYou are the **Outline_Agent**, responsible for generating a clear and SEO-optimized blog outline based on the user's parsed writing intent and keyword strategy.\n\n# Tool Access:\n\n- You have access to a search tool called `Tavily Search`.\n\n- If you are unsure how to structure a section, you may call this tool to search for related blog outlines or content from Google.\n\n- Do not overuse it. Your job is to extract **structure**, not to write paragraphs.\n\n\n# Goals\n\n1. Create a well-structured outline with appropriate H2 and H3 headings.\n\n2. Ensure logical flow from introduction to conclusion.\n\n3. Assign 1\u20132 suggested long-tail keywords to each major section for SEO alignment.\n\n4. Make the structure suitable for downstream paragraph writing.\n\n\n\n\n#Note\n\n- Use concise, scannable section titles.\n\n- Do not write full paragraphs.\n\n- Prioritize clarity, logical progression, and SEO alignment.\n\n\n\n- If the blog type is \u201cTutorial\u201d or \u201cHow-to\u201d, include step-based sections.\n\n\n# Input\n\nYou will receive:\n\n- Writing Type (e.g., Tutorial, Informative Guide)\n\n- Target Audience\n\n- User Intent Summary\n\n- 3\u20135 long-tail keywords\n\n\nUse this information to design a structure that both informs readers and maximizes search engine visibility.\n\n# Output Format\n\n```markdown\n\n## Blog Title (suggested)\n\n[Give a short, SEO-friendly title suggestion]\n\n## Outline\n\n### Introduction\n\n- Purpose of the article\n\n- Brief context\n\n- **Suggested keywords**: [keyword1, keyword2]\n\n### H2: [Section Title 1]\n\n- [Short description of what this section will cover]\n\n- **Suggested keywords**: [keyword1, keyword2]\n\n### H2: [Section Title 2]\n\n- [Short description of what this section will cover]\n\n- **Suggested keywords**: [keyword1, keyword2]\n\n### H2: [Section Title 3]\n\n- [Optional H3 Subsection Title A]\n\n - [Explanation of sub-point]\n\n- [Optional H3 Subsection Title B]\n\n - [Explanation of sub-point]\n\n- **Suggested keywords**: [keyword1]\n\n### Conclusion\n\n- Recap key takeaways\n\n- Optional CTA (Call to Action)\n\n- **Suggested keywords**: [keyword3]\n\n",
|
||||
"temperature": 0.5,
|
||||
"temperatureEnabled": true,
|
||||
"tools": [
|
||||
{
|
||||
"component_name": "TavilySearch",
|
||||
"name": "TavilySearch",
|
||||
"params": {
|
||||
"api_key": "",
|
||||
"days": 7,
|
||||
"exclude_domains": [],
|
||||
"include_answer": false,
|
||||
"include_domains": [],
|
||||
"include_image_descriptions": false,
|
||||
"include_images": false,
|
||||
"include_raw_content": true,
|
||||
"max_results": 5,
|
||||
"outputs": {
|
||||
"formalized_content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
},
|
||||
"json": {
|
||||
"type": "Array<Object>",
|
||||
"value": []
|
||||
}
|
||||
},
|
||||
"query": "sys.query",
|
||||
"search_depth": "basic",
|
||||
"topic": "general"
|
||||
}
|
||||
}
|
||||
],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.85,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
},
|
||||
"label": "Agent",
|
||||
"name": "Outline Agent"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Agent:BetterSitesSend",
|
||||
"measured": {
|
||||
"height": 84,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 613.4368763415628,
|
||||
"y": 164.3074269048589
|
||||
},
|
||||
"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_0"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Tool:SharpPensBurn",
|
||||
"measured": {
|
||||
"height": 44,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 580.1877078861457,
|
||||
"y": 287.7669662022325
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "toolNode"
|
||||
},
|
||||
{
|
||||
"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": "deepseek-chat@DeepSeek",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 5,
|
||||
"max_tokens": 4096,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
}
|
||||
},
|
||||
"parameter": "Precise",
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.5,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\n\n\nThe Outline agent output is {Agent:BetterSitesSend@content}",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "# Role\n\nYou are the **Body_Agent**, responsible for generating the full content of each section of an SEO-optimized blog based on the provided outline and keyword strategy.\n\n# Tool Access:\n\nYou can use the `Tavily Search` tool to retrieve relevant content, statistics, or examples to support each section you're writing.\n\nUse it **only** when the provided outline lacks enough information, or if the section requires factual grounding.\n\nAlways cite the original link or indicate source where possible.\n\n\n# Goals\n\n1. Write each section (based on H2/H3 structure) as a complete and natural blog paragraph.\n\n2. Integrate the suggested long-tail keywords naturally into each section.\n\n3. When appropriate, use the `Tavily Search` tool to enrich your writing with relevant facts, examples, or quotes.\n\n4. Ensure each section is clear, engaging, and informative, suitable for both human readers and search engines.\n\n\n# Style Guidelines\n\n- Write in a tone appropriate to the audience. Be explanatory, not promotional, unless it's a marketing blog.\n\n- Avoid generic filler content. Prioritize clarity, structure, and value.\n\n- Ensure SEO keywords are embedded seamlessly, not forcefully.\n\n\n\n- Maintain writing rhythm. Vary sentence lengths. Use transitions between ideas.\n\n\n# Input\n\n\nYou will receive:\n\n- Blog title\n\n- Structured outline (including section titles, keywords, and descriptions)\n\n- Target audience\n\n- Blog type and user intent\n\nYou must **follow the outline strictly**. Write content **section-by-section**, based on the structure.\n\n\n# Output Format\n\n```markdown\n\n## H2: [Section Title]\n\n[Your generated content for this section \u2014 500-600 words, using keywords naturally.]\n\n",
|
||||
"temperature": 0.2,
|
||||
"temperatureEnabled": true,
|
||||
"tools": [
|
||||
{
|
||||
"component_name": "TavilySearch",
|
||||
"name": "TavilySearch",
|
||||
"params": {
|
||||
"api_key": "",
|
||||
"days": 7,
|
||||
"exclude_domains": [],
|
||||
"include_answer": false,
|
||||
"include_domains": [],
|
||||
"include_image_descriptions": false,
|
||||
"include_images": false,
|
||||
"include_raw_content": true,
|
||||
"max_results": 5,
|
||||
"outputs": {
|
||||
"formalized_content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
},
|
||||
"json": {
|
||||
"type": "Array<Object>",
|
||||
"value": []
|
||||
}
|
||||
},
|
||||
"query": "sys.query",
|
||||
"search_depth": "basic",
|
||||
"topic": "general"
|
||||
}
|
||||
}
|
||||
],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.75,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
},
|
||||
"label": "Agent",
|
||||
"name": "Body Agent"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Agent:EagerNailsRemain",
|
||||
"measured": {
|
||||
"height": 84,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 889.0614605692713,
|
||||
"y": 247.00973041799065
|
||||
},
|
||||
"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_1"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Tool:WickedDeerHeal",
|
||||
"measured": {
|
||||
"height": 44,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 853.2006404239659,
|
||||
"y": 364.37541577229143
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "toolNode"
|
||||
},
|
||||
{
|
||||
"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": "deepseek-chat@DeepSeek",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 5,
|
||||
"max_tokens": 4096,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
}
|
||||
},
|
||||
"parameter": "Precise",
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.5,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "The parse and keyword agent output is {Agent:ClearRabbitsScream@content}\n\nThe Outline agent output is {Agent:BetterSitesSend@content}\n\nThe Body agent output is {Agent:EagerNailsRemain@content}",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "# Role\n\nYou are the **Editor_Agent**, responsible for finalizing the blog post for both human readability and SEO effectiveness.\n\n# Goals\n\n1. Polish the entire blog content for clarity, coherence, and style.\n\n2. Improve transitions between sections, ensure logical flow.\n\n3. Verify that keywords are used appropriately and effectively.\n\n4. Conduct a lightweight SEO audit \u2014 checking keyword density, structure (H1/H2/H3), and overall searchability.\n\n\n\n# Style Guidelines\n\n- Be precise. Avoid bloated or vague language.\n\n- Maintain an informative and engaging tone, suitable to the target audience.\n\n- Do not remove keywords unless absolutely necessary for clarity.\n\n- Ensure paragraph flow and section continuity.\n\n\n# Input\n\nYou will receive:\n\n- Full blog content, written section-by-section\n\n- Original outline with suggested keywords\n\n- Target audience and writing type\n\n# Output Format\n\n```markdown\n\n[The revised, fully polished blog post content goes here.]\n\n",
|
||||
"temperature": 0.2,
|
||||
"temperatureEnabled": true,
|
||||
"tools": [],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.75,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
},
|
||||
"label": "Agent",
|
||||
"name": "Editor Agent"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Agent:LovelyHeadsOwn",
|
||||
"measured": {
|
||||
"height": 84,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 1160.3332919804993,
|
||||
"y": 149.50806732882472
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "agentNode"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"content": [
|
||||
"{Agent:LovelyHeadsOwn@content}"
|
||||
]
|
||||
},
|
||||
"label": "Message",
|
||||
"name": "Response"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Message:LegalBeansBet",
|
||||
"measured": {
|
||||
"height": 56,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 1370.6665839609984,
|
||||
"y": 267.0323933738015
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "messageNode"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"text": "This workflow automatically generates a complete SEO-optimized blog article based on a simple user input. You don\u2019t need any writing experience. Just provide a topic or short request \u2014 the system will handle the rest.\n\nThe process includes the following key stages:\n\n1. **Understanding your topic and goals**\n2. **Designing the blog structure**\n3. **Writing high-quality content**\n\n\n"
|
||||
},
|
||||
"label": "Note",
|
||||
"name": "Workflow Overall Description"
|
||||
},
|
||||
"dragHandle": ".note-drag-handle",
|
||||
"dragging": false,
|
||||
"height": 205,
|
||||
"id": "Note:SlimyGhostsWear",
|
||||
"measured": {
|
||||
"height": 205,
|
||||
"width": 415
|
||||
},
|
||||
"position": {
|
||||
"x": -284.3143151688742,
|
||||
"y": 150.47632147913419
|
||||
},
|
||||
"resizing": false,
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "noteNode",
|
||||
"width": 415
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"text": "**Purpose**: \nThis agent reads the user\u2019s input and figures out what kind of blog needs to be written.\n\n**What it does**:\n- Understands the main topic you want to write about \n- Identifies who the blog is for (e.g., beginners, marketers, developers) \n- Determines the writing purpose (e.g., SEO traffic, product promotion, education) \n- Suggests 3\u20135 long-tail SEO keywords related to the topic"
|
||||
},
|
||||
"label": "Note",
|
||||
"name": "Parse And Keyword Agent"
|
||||
},
|
||||
"dragHandle": ".note-drag-handle",
|
||||
"dragging": false,
|
||||
"height": 152,
|
||||
"id": "Note:EmptyChairsShake",
|
||||
"measured": {
|
||||
"height": 152,
|
||||
"width": 340
|
||||
},
|
||||
"position": {
|
||||
"x": 295.04147626768133,
|
||||
"y": 372.2755718118446
|
||||
},
|
||||
"resizing": false,
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "noteNode",
|
||||
"width": 340
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"text": "**Purpose**: \nThis agent builds the blog structure \u2014 just like writing a table of contents before you start writing the full article.\n\n**What it does**:\n- Suggests a clear blog title that includes important keywords \n- Breaks the article into sections using H2 and H3 headings (like a professional blog layout) \n- Assigns 1\u20132 recommended keywords to each section to help with SEO \n- Follows the writing goal and target audience set in the previous step"
|
||||
},
|
||||
"label": "Note",
|
||||
"name": "Outline Agent"
|
||||
},
|
||||
"dragHandle": ".note-drag-handle",
|
||||
"dragging": false,
|
||||
"height": 146,
|
||||
"id": "Note:TallMelonsNotice",
|
||||
"measured": {
|
||||
"height": 146,
|
||||
"width": 343
|
||||
},
|
||||
"position": {
|
||||
"x": 598.5644991893463,
|
||||
"y": 5.801054564756448
|
||||
},
|
||||
"resizing": false,
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "noteNode",
|
||||
"width": 343
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"text": "**Purpose**: \nThis agent is responsible for writing the actual content of the blog \u2014 paragraph by paragraph \u2014 based on the outline created earlier.\n\n**What it does**:\n- Looks at each H2/H3 section in the outline \n- Writes 150\u2013220 words of clear, helpful, and well-structured content per section \n- Includes the suggested SEO keywords naturally (not keyword stuffing) \n- Uses real examples or facts if needed (by calling a web search tool like Tavily)"
|
||||
},
|
||||
"label": "Note",
|
||||
"name": "Body Agent"
|
||||
},
|
||||
"dragHandle": ".note-drag-handle",
|
||||
"dragging": false,
|
||||
"height": 137,
|
||||
"id": "Note:RipeCougarsBuild",
|
||||
"measured": {
|
||||
"height": 137,
|
||||
"width": 319
|
||||
},
|
||||
"position": {
|
||||
"x": 860.4854129814981,
|
||||
"y": 427.2196835690842
|
||||
},
|
||||
"resizing": false,
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "noteNode",
|
||||
"width": 319
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"text": "**Purpose**: \nThis agent reviews the entire blog draft to make sure it is smooth, professional, and SEO-friendly. It acts like a human editor before publishing.\n\n**What it does**:\n- Polishes the writing: improves sentence clarity, fixes awkward phrasing \n- Makes sure the content flows well from one section to the next \n- Double-checks keyword usage: are they present, natural, and not overused? \n- Verifies the blog structure (H1, H2, H3 headings) is correct \n- Adds two key SEO elements:\n - **Meta Title** (shows up in search results)\n - **Meta Description** (summary for Google and social sharing)"
|
||||
},
|
||||
"label": "Note",
|
||||
"name": "Editor Agent"
|
||||
},
|
||||
"dragHandle": ".note-drag-handle",
|
||||
"height": 146,
|
||||
"id": "Note:OpenTurkeysSell",
|
||||
"measured": {
|
||||
"height": 146,
|
||||
"width": 320
|
||||
},
|
||||
"position": {
|
||||
"x": 1129,
|
||||
"y": -30
|
||||
},
|
||||
"resizing": false,
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "noteNode",
|
||||
"width": 320
|
||||
}
|
||||
]
|
||||
},
|
||||
"history": [],
|
||||
"messages": [],
|
||||
"path": [],
|
||||
"retrieval": []
|
||||
},
|
||||
"avatar": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/4gHYSUNDX1BST0ZJTEUAAQEAAAHIAAAAAAQwAABtbnRyUkdCIFhZWiAH4AABAAEAAAAAAABhY3NwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAQAA9tYAAQAAAADTLQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlkZXNjAAAA8AAAACRyWFlaAAABFAAAABRnWFlaAAABKAAAABRiWFlaAAABPAAAABR3dHB0AAABUAAAABRyVFJDAAABZAAAAChnVFJDAAABZAAAAChiVFJDAAABZAAAAChjcHJ0AAABjAAAADxtbHVjAAAAAAAAAAEAAAAMZW5VUwAAAAgAAAAcAHMAUgBHAEJYWVogAAAAAAAAb6IAADj1AAADkFhZWiAAAAAAAABimQAAt4UAABjaWFlaIAAAAAAAACSgAAAPhAAAts9YWVogAAAAAAAA9tYAAQAAAADTLXBhcmEAAAAAAAQAAAACZmYAAPKnAAANWQAAE9AAAApbAAAAAAAAAABtbHVjAAAAAAAAAAEAAAAMZW5VUwAAACAAAAAcAEcAbwBvAGcAbABlACAASQBuAGMALgAgADIAMAAxADb/2wBDAAEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQH/2wBDAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQEBAQH/wAARCAAwADADASIAAhEBAxEB/8QAGQAAAwEBAQAAAAAAAAAAAAAABgkKBwUI/8QAMBAAAAYCAQIEBQQCAwAAAAAAAQIDBAUGBxEhCAkAEjFBFFFhcaETFiKRFyOx8PH/xAAaAQACAwEBAAAAAAAAAAAAAAACAwABBgQF/8QALBEAAgIBAgUCBAcAAAAAAAAAAQIDBBEFEgATITFRIkEGIzJhFBUWgaGx8P/aAAwDAQACEQMRAD8AfF2hez9089t7pvxgQMa1Gb6qZ6oQE9m/NEvCIStyPfJSOF/M1epzMugo/qtMqbiRc1mJjoJKCLMNIxKcsLJedfO1Ct9cI63x9fx6CA/19t+oh4LFA5HfuAgP/A8eOIsnsTBrkBHXA7+v53+Q+ficTgJft9gIgA+/P9/1r342O/YA8A8k3/if+IbAN7+2/f8AAiI6H19PGoPyESTMZQPKUAHkQEN+3r9dh78/YPGUTk2wb/qAZZIugH1OHH5DjkdfbnWw2DsOxPj+xjrnx2H39unBopJGBn9s+PHv1HXjPJtH+J+B40O9a16h/wB/92j/ALrPa/wR104UyAobHlXhuo2HrEtK4qy3CwjKOuJLRHJLSkXWrFKs/gVrJVrE8TUiH8bPrP20UEu8m4hNpMJJuTOfnbUw/kUqyZgMHGjAO9+mtDsQ53sdcB6eMhnpEjhNQxRKICAgHy5+/roOdjr7c+J6O4x07dx484/n7nzw1gexBGfIPkZ/3t39uGpqc6+fP5/Ht8vGFZCzJjWpWuBxvO2yPjrtclUUK7BqmUI4fuASeyhG5FzFI0Bw4aQ0iZNoDgzvRW4qtyFkI4XmwyEk2YNnDp0sVBu3IUyy5iqH8gqKERSIRNIii67hddRJs1at01Xbx2sgzZoLu10UFJR+4V1A5cxF3FqNcLvjwcno43uuLrOxZYjujaClcb4QQfxEizpFiQyM9olcueRnjC2ZMt9iY06zL0qytrMSqSOVGsfHMaGhZ3l4lSRI2MqE74zJvRTveNFWWIh3RWw+XCAM5icKQLrCH57T17FhErSlRXnWvyZXKQwWJ3eraD14p5YuZCFgacskK2oGkVuKO5GYTHzf7DaD12cBD3DgPOIDrWw9PnrXPgDkpVsUDGMG+DD6E9gHXIjrYjwUPQTCXYgHPhIV974+F6E1hpC14Yzmzj56YaQEeZhXsayD1zLPW7pygxaMf81Nzu1iJsnIuDIKnaJAkPldqrHaoORZ73tMVEbFdSXT9nVgRQgnBq6j8e/HCIEATpAnH5KlmRVkFRFJwks/bqImSXJ5VFyA3N6Ikh3bCW3YHp5cowOmCfTgA+xJCnrjtwHKcLvJj2ZGcTRFj19kEhckdzgEjKnABGSSzdc1Fe5byXXGNjKdvRcw5NxvLidNZFFCxUa62KrzMaChw8hhYScFJtROAgmuLByq1MsgkZYPaVVuDe0wraRaqAdJwgRQo+YR8xTlAQNx6b49w41vXiJpCalLh1jZhyrTqRM4+jstdRmYryNkydLQRWg1LNGcWd5jIFFvCythlIySa0mNu74sKRQtaWsTmupqPItw0lE52ufpyYzrSkx6cw5bLmBEpkTsz+dt8P5QFuCRtAIkBH9MuwKHICIaDQhnojMs9mKaeGcrMxXlQtAYkdVljimRrE5MqI4zL8oSqQ6wxjodBqK05qdK3Vo3aCSVkBW7bjuC1NFJJBPaqyx6fp6pWkliYLXK2XrukkRu2CCVoSWMgsdMyySKwoLFcIGWSTUMg4IBgTcICoBhRcplMcpFkhIqQp1ClMBTmA0Zfe1zpjvHfXff65bZlzXpB3jjGTgiirmPjAfs16PHqHeQ75Wbj3xxZpOEkV3LRJJSPdomUBZISJLncV2k+8D07dxXp7xsYuTapA9UkJUYWIzNhadnWEZeCXGLQQiJi1ViHfhHL2unWh+mlORsrW0JFpEFnGVfm1mU4kq0FY3eD6corJncv6dr5NLSMNXVaTUksjTiMnaq8uFfSVuDyiJ1iZpy0LOJtpa3YfkcQ5fdozyxI2m5qqcrHN61YYmHsh6v3o9ParYmYJEtlhIx6+gUbjgD23M6oqg92YL0JyF6Bps+qDValVA9h9Lj5SZI3SHXdEQlj1wiQtLLIe6pGzjO3BlBkK1hxpblLVH5wdW0BcFKf/JwRtjsot2z8omaSdxbzzk1iEjsE0AM9rrRZNRIrVyo7dGO6E+oh8axLlJ5H5VaJKx7ePRGFbW6vUeFfHQIWPTI9Tm7HHfuhqY7E6C7JFqUzM6iZXIoncNxX7+bIVdJnTT48x3OQU1krIDW3UeixVhyISzYz6cadY5Xph6TseRNTRsTElzzBn9Vlly0TAERsdgnMYyLROjyFbg5R4ZlsGaMT4yNi2Zlq1GwjZB3jq0PsaJfA3t0jL0W0Y9xf1V41lpWckXMLaZiwxuKYPqc6LlHdkeRF+Qxswx5ASDqBVrsL+2A/N6SiCbYymV2BywJiMZj3GRRMTnL+lVyHCll3R7Szv0vqXMtQ74T+HijljIScLaEpkKCB3rqMBIi0jPs5JeOKTZMZEi5VVnouzy0k3jXjWSMlY6UcVGDxlKMVDqx91SILWSi3D2KdgYy3kP8E9X/AE1SnRXBNdNRMlefT6g7aY6giK+cPLGNg0bY68rcnpsNh9PqIBve/EcPQ3WIq2dR93xpSgk5SAZ9R6MLAOZFUkpLSUDXp6/KPpGUkmTdswlnKnwbl5ITMdGwcXJi7LKsqzUmT5tWYmkXuF9wjBvb76b7dHheazJ9RElUJOCxViuMlUJC0Gtz6PKyjLBY4qMWUe12r1xZ6lOyT6XPEBKN2CkTDOlZd02TBdTMt7Upx2knrkdCv1UKjDKn1A7XBYH6SCOOrWn5Oi/DtRiu+GleRthDL8rXdVjZlcfWrSIxVlGGGCOnH//Z"
|
||||
}
|
||||
@@ -1063,6 +1063,7 @@ class CanvasTemplate(DataBaseModel):
|
||||
title = JSONField(null=True, default=dict, help_text="Canvas title")
|
||||
description = JSONField(null=True, default=dict, help_text="Canvas description")
|
||||
canvas_type = CharField(max_length=32, null=True, help_text="Canvas type", index=True)
|
||||
canvas_types = ListField(null=True, default=list, help_text="Canvas types")
|
||||
canvas_category = CharField(max_length=32, null=False, default="agent_canvas", help_text="Canvas category: agent_canvas|dataflow_canvas", index=True)
|
||||
dsl = JSONField(null=True, default={})
|
||||
|
||||
@@ -1615,6 +1616,7 @@ def migrate_db():
|
||||
alter_db_column_type(migrator, "canvas_template", "description", JSONField(null=True, default=dict, help_text="Canvas description"))
|
||||
alter_db_add_column(migrator, "user_canvas", "canvas_category", CharField(max_length=32, null=False, default="agent_canvas", help_text="agent_canvas|dataflow_canvas", index=True))
|
||||
alter_db_add_column(migrator, "canvas_template", "canvas_category", CharField(max_length=32, null=False, default="agent_canvas", help_text="agent_canvas|dataflow_canvas", index=True))
|
||||
alter_db_add_column(migrator, "canvas_template", "canvas_types", ListField(null=True, default=list, help_text="Canvas types"))
|
||||
alter_db_add_column(migrator, "knowledgebase", "pipeline_id", CharField(max_length=32, null=True, help_text="Pipeline ID", index=True))
|
||||
alter_db_add_column(migrator, "document", "pipeline_id", CharField(max_length=32, null=True, help_text="Pipeline ID", index=True))
|
||||
alter_db_add_column(migrator, "knowledgebase", "graphrag_task_id", CharField(max_length=32, null=True, help_text="Gragh RAG task ID", index=True))
|
||||
|
||||
@@ -35,6 +35,7 @@ from api.db.services.llm_service import LLMService, LLMBundle, get_init_tenant_l
|
||||
from api.db.services.user_service import TenantService, UserTenantService
|
||||
from api.db.services.system_settings_service import SystemSettingsService
|
||||
from api.db.services.dialog_service import DialogService
|
||||
from api.db.template_utils import normalize_canvas_template_categories
|
||||
from api.db.joint_services.memory_message_service import init_message_id_sequence, init_memory_size_cache, fix_missing_tokenized_memory
|
||||
from api.db.joint_services.tenant_model_service import get_tenant_default_model_by_type
|
||||
from common.constants import LLMType
|
||||
@@ -166,16 +167,21 @@ def add_graph_templates():
|
||||
logging.warning("Missing agent templates!")
|
||||
return
|
||||
|
||||
for fnm in os.listdir(dir):
|
||||
for fnm in sorted(os.listdir(dir)):
|
||||
if not fnm.endswith(".json"):
|
||||
logging.debug("Skipping non-json template file in %s: %s", dir, fnm)
|
||||
continue
|
||||
template_path = os.path.join(dir, fnm)
|
||||
try:
|
||||
with open(os.path.join(dir, fnm), "r", encoding="utf-8") as f:
|
||||
cnvs = json.load(f)
|
||||
with open(template_path, "r", encoding="utf-8") as f:
|
||||
cnvs = normalize_canvas_template_categories(json.load(f))
|
||||
logging.info("Loaded and normalized template file: %s", template_path)
|
||||
try:
|
||||
CanvasTemplateService.save(**cnvs)
|
||||
except Exception:
|
||||
CanvasTemplateService.update_by_id(cnvs["id"], cnvs)
|
||||
except Exception as e:
|
||||
logging.exception(f"Add agent templates error: {e}")
|
||||
logging.exception("Add agent templates error for %s: %s", template_path, e)
|
||||
|
||||
|
||||
def init_web_data():
|
||||
|
||||
77
api/db/template_utils.py
Normal file
77
api/db/template_utils.py
Normal file
@@ -0,0 +1,77 @@
|
||||
#
|
||||
# Copyright 2026 The InfiniFlow Authors. All Rights Reserved.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
#
|
||||
|
||||
import logging
|
||||
from typing import Any
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def _collect_canvas_types(canvas_type: Any, canvas_types: Any) -> list[str]:
|
||||
categories: list[str] = []
|
||||
|
||||
if isinstance(canvas_type, str):
|
||||
category = canvas_type.strip()
|
||||
if category:
|
||||
categories.append(category)
|
||||
|
||||
iterable_types: list[Any]
|
||||
if isinstance(canvas_types, list):
|
||||
iterable_types = canvas_types
|
||||
elif canvas_types is None:
|
||||
iterable_types = []
|
||||
else:
|
||||
iterable_types = [canvas_types]
|
||||
|
||||
for item in iterable_types:
|
||||
if not isinstance(item, str):
|
||||
continue
|
||||
category = item.strip()
|
||||
if not category:
|
||||
continue
|
||||
categories.append(category)
|
||||
|
||||
deduplicated: list[str] = []
|
||||
seen: set[str] = set()
|
||||
for category in categories:
|
||||
if category in seen:
|
||||
continue
|
||||
seen.add(category)
|
||||
deduplicated.append(category)
|
||||
|
||||
return deduplicated
|
||||
|
||||
|
||||
def normalize_canvas_template_categories(template: dict[str, Any]) -> dict[str, Any]:
|
||||
normalized = dict(template)
|
||||
raw_canvas_type = normalized.get("canvas_type")
|
||||
raw_canvas_types = normalized.get("canvas_types")
|
||||
canvas_types = _collect_canvas_types(
|
||||
raw_canvas_type,
|
||||
raw_canvas_types,
|
||||
)
|
||||
normalized["canvas_types"] = canvas_types
|
||||
normalized["canvas_type"] = canvas_types[0] if canvas_types else None
|
||||
if raw_canvas_type != normalized["canvas_type"] or raw_canvas_types != normalized["canvas_types"]:
|
||||
logger.debug(
|
||||
"Normalized canvas categories for template_id=%s: canvas_type=%r -> %r, canvas_types=%r -> %r",
|
||||
normalized.get("id"),
|
||||
raw_canvas_type,
|
||||
normalized["canvas_type"],
|
||||
raw_canvas_types,
|
||||
normalized["canvas_types"],
|
||||
)
|
||||
return normalized
|
||||
@@ -515,12 +515,12 @@ def test_templates_rm_save_get_matrix_unit(monkeypatch):
|
||||
self.template_id = template_id
|
||||
|
||||
def to_dict(self):
|
||||
return {"id": self.template_id}
|
||||
return {"id": self.template_id, "canvas_type": "Recommended", "canvas_types": ["Recommended", "Agent"]}
|
||||
|
||||
monkeypatch.setattr(module.CanvasTemplateService, "get_all", lambda: [_Template("tpl-1")])
|
||||
res = module.templates()
|
||||
assert res["code"] == module.RetCode.SUCCESS
|
||||
assert res["data"] == [{"id": "tpl-1"}]
|
||||
assert res["data"] == [{"id": "tpl-1", "canvas_type": "Recommended", "canvas_types": ["Recommended", "Agent"]}]
|
||||
|
||||
_set_request_json(monkeypatch, module, {"canvas_ids": ["c1", "c2"]})
|
||||
monkeypatch.setattr(module.UserCanvasService, "accessible", lambda *_args, **_kwargs: False)
|
||||
|
||||
66
test/unit_test/api/db/test_template_utils.py
Normal file
66
test/unit_test/api/db/test_template_utils.py
Normal file
@@ -0,0 +1,66 @@
|
||||
#
|
||||
# Copyright 2026 The InfiniFlow Authors. All Rights Reserved.
|
||||
#
|
||||
# Licensed under the Apache License, Version 2.0 (the "License");
|
||||
# you may not use this file except in compliance with the License.
|
||||
# You may obtain a copy of the License at
|
||||
#
|
||||
# http://www.apache.org/licenses/LICENSE-2.0
|
||||
#
|
||||
# Unless required by applicable law or agreed to in writing, software
|
||||
# distributed under the License is distributed on an "AS IS" BASIS,
|
||||
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
# See the License for the specific language governing permissions and
|
||||
# limitations under the License.
|
||||
#
|
||||
|
||||
import pytest
|
||||
|
||||
from api.db.template_utils import normalize_canvas_template_categories
|
||||
|
||||
|
||||
@pytest.mark.p2
|
||||
def test_normalize_canvas_template_categories_legacy_canvas_type():
|
||||
payload = {"id": 1, "canvas_type": "Recommended"}
|
||||
|
||||
normalized = normalize_canvas_template_categories(payload)
|
||||
|
||||
assert normalized["canvas_type"] == "Recommended"
|
||||
assert normalized["canvas_types"] == ["Recommended"]
|
||||
|
||||
|
||||
@pytest.mark.p2
|
||||
def test_normalize_canvas_template_categories_with_canvas_types_only():
|
||||
payload = {
|
||||
"id": 1,
|
||||
"canvas_types": ["Recommended", "Agent", "Agent", " ", 1, None],
|
||||
}
|
||||
|
||||
normalized = normalize_canvas_template_categories(payload)
|
||||
|
||||
assert normalized["canvas_type"] == "Recommended"
|
||||
assert normalized["canvas_types"] == ["Recommended", "Agent"]
|
||||
|
||||
|
||||
@pytest.mark.p2
|
||||
def test_normalize_canvas_template_categories_merges_legacy_and_new_field():
|
||||
payload = {
|
||||
"id": 1,
|
||||
"canvas_type": "Marketing",
|
||||
"canvas_types": ["Recommended", "Marketing", "Agent"],
|
||||
}
|
||||
|
||||
normalized = normalize_canvas_template_categories(payload)
|
||||
|
||||
assert normalized["canvas_type"] == "Marketing"
|
||||
assert normalized["canvas_types"] == ["Marketing", "Recommended", "Agent"]
|
||||
|
||||
|
||||
@pytest.mark.p2
|
||||
def test_normalize_canvas_template_categories_no_valid_categories():
|
||||
payload = {"id": 1, "canvas_type": " ", "canvas_types": [None, 3, " "]}
|
||||
|
||||
normalized = normalize_canvas_template_categories(payload)
|
||||
|
||||
assert normalized["canvas_type"] is None
|
||||
assert normalized["canvas_types"] == []
|
||||
@@ -87,6 +87,7 @@ export declare interface IFlow {
|
||||
export interface IFlowTemplate {
|
||||
avatar: string;
|
||||
canvas_type: string;
|
||||
canvas_types?: string[];
|
||||
create_date: string;
|
||||
create_time: number;
|
||||
canvas_category?: string;
|
||||
|
||||
@@ -78,10 +78,18 @@ export default function AgentTemplates() {
|
||||
if (!selectMenuItem) {
|
||||
return templateList;
|
||||
}
|
||||
const selectedCanvasType = selectMenuItem.toLocaleLowerCase();
|
||||
return templateList.filter(
|
||||
(item) =>
|
||||
item.canvas_type?.toLocaleLowerCase() ===
|
||||
selectMenuItem?.toLocaleLowerCase(),
|
||||
(item) => {
|
||||
if (Array.isArray(item.canvas_types) && item.canvas_types.length > 0) {
|
||||
return item.canvas_types.some(
|
||||
(canvasType) =>
|
||||
typeof canvasType === 'string' &&
|
||||
canvasType.toLocaleLowerCase() === selectedCanvasType,
|
||||
);
|
||||
}
|
||||
return item.canvas_type?.toLocaleLowerCase() === selectedCanvasType;
|
||||
},
|
||||
);
|
||||
}, [selectMenuItem, templateList]);
|
||||
|
||||
|
||||
Reference in New Issue
Block a user