mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-08 12:32:30 +08:00
34f829e1b1
### What problem does this PR solve? Correct several spelling errors, such as: Ouline -> Outline ### Type of change - [x] Documentation Update
916 lines
62 KiB
JSON
916 lines
62 KiB
JSON
{
|
||
"id": 12,
|
||
"title": "Generate SEO Blog",
|
||
"description": "This workflow 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.",
|
||
"canvas_type": "Marketing",
|
||
"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,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"
|
||
}
|