mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-08 12:32:30 +08:00
52ceac62ab
### What does this PR solve? German translation for all agent template and optimizing line breaks in the title for the new translation. ### Type of change - [x] New Feature (non-breaking change which adds functionality)
908 lines
68 KiB
JSON
908 lines
68 KiB
JSON
{
|
||
"id": 8,
|
||
"title": {
|
||
"en": "Generate SEO Blog",
|
||
"de": "SEO Blog generieren",
|
||
"zh": "生成SEO博客"},
|
||
"description": {
|
||
"en": "This is a multi-agent version of the SEO blog generation workflow. It simulates a small team of AI “writers”, where each agent plays a specialized role — just like a real editorial team.",
|
||
"de": "Dies ist eine Multi-Agenten-Version des Workflows zur Erstellung von SEO-Blogs. Sie simuliert ein kleines Team von KI-„Autoren“, in dem jeder Agent eine spezielle Rolle übernimmt – genau wie in einem echten Redaktionsteam.",
|
||
"zh": "多智能体架构可根据简单的用户输入自动生成完整的SEO博客文章。模拟小型“作家”团队，其中每个智能体扮演一个专业角色——就像真正的编辑团队。"},
|
||
"canvas_type": "Agent",
|
||
"dsl": {
|
||
"components": {
|
||
"Agent:LuckyApplesGrab": {
|
||
"downstream": [
|
||
"Message:ModernSwansThrow"
|
||
],
|
||
"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": 3,
|
||
"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 **Lead Agent**, responsible for initiating the multi-agent SEO blog generation process. You will receive the user\u2019s topic and blog goal, interpret the intent, and coordinate the downstream writing agents.\n\n# Goals\n\n1. Parse the user's initial input.\n\n2. Generate a high-level blog intent summary and writing plan.\n\n3. Provide clear instructions to the following Sub_Agents:\n\n - `Outline Agent` \u2192 Create the blog outline.\n\n - `Body Agent` \u2192 Write all sections based on outline.\n\n - `Editor Agent` \u2192 Polish and finalize the blog post.\n\n4. Merge outputs into a complete, readable blog draft in Markdown format.\n\n# Input\n\nYou will receive:\n\n- Blog topic\n\n- Target audience\n\n- Blog goal (e.g., SEO, education, product marketing)\n\n# Output Format\n\n```markdown\n\n## Parsed Writing Plan\n\n- **Topic**: [Extracted from user input]\n\n- **Audience**: [Summarized from user input]\n\n- **Intent**: [Inferred goal and style]\n\n- **Blog Type**: [e.g., Tutorial / Informative Guide / Marketing Content]\n\n- **Long-tail Keywords**: \n\n - keyword 1\n\n - keyword 2\n\n - keyword 3\n\n - ...\n\n## Instructions for Outline Agent\n\nPlease generate a structured outline including H2 and H3 headings. Assign 1\u20132 relevant keywords to each section. Keep it aligned with the user\u2019s intent and audience level.\n\n## Instructions for Body Agent\n\nWrite the full content based on the outline. Each section should be concise (500\u2013600 words), informative, and optimized for SEO. Use `Tavily Search` only when additional examples or context are needed.\n\n## Instructions for Editor Agent\n\nReview and refine the combined content. Improve transitions, ensure keyword integration, and add a meta title + meta description. Maintain Markdown formatting.\n\n\n## Guides\n\n- Do not generate blog content directly.\n\n- Focus on correct intent recognition and instruction generation.\n\n- Keep communication to downstream agents simple, scoped, and accurate.\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\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": "0.1",
|
||
"temperatureEnabled": true,
|
||
"tools": [
|
||
{
|
||
"component_name": "Agent",
|
||
"id": "Agent:SlickSpidersTurn",
|
||
"name": "Outline Agent",
|
||
"params": {
|
||
"delay_after_error": 1,
|
||
"description": "Generates a clear and SEO-friendly blog outline using H2/H3 headings based on the topic, audience, and intent provided by the lead agent. Each section includes suggested keywords for optimized downstream writing.\n",
|
||
"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": 2,
|
||
"max_tokens": 4096,
|
||
"mcp": [],
|
||
"message_history_window_size": 12,
|
||
"outputs": {
|
||
"content": {
|
||
"type": "string",
|
||
"value": ""
|
||
}
|
||
},
|
||
"parameter": "Balance",
|
||
"presencePenaltyEnabled": false,
|
||
"presence_penalty": 0.2,
|
||
"prompts": [
|
||
{
|
||
"content": "{sys.query}",
|
||
"role": "user"
|
||
}
|
||
],
|
||
"sys_prompt": "# Role\n\nYou are the **Outline Agent**, a sub-agent in a multi-agent SEO blog writing system. You operate under the instruction of the `Lead Agent`, and your sole responsibility is to create a clear, well-structured, and SEO-optimized blog outline.\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": "This is the order you need to send to the agent.",
|
||
"visual_files_var": ""
|
||
}
|
||
},
|
||
{
|
||
"component_name": "Agent",
|
||
"id": "Agent:IcyPawsRescue",
|
||
"name": "Body Agent",
|
||
"params": {
|
||
"delay_after_error": 1,
|
||
"description": "Writes the full blog content section-by-section following the outline structure. It integrates target keywords naturally and uses Tavily Search only when additional facts or examples are needed.\n",
|
||
"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": 3,
|
||
"max_tokens": 4096,
|
||
"mcp": [],
|
||
"message_history_window_size": 12,
|
||
"outputs": {
|
||
"content": {
|
||
"type": "string",
|
||
"value": ""
|
||
}
|
||
},
|
||
"parameter": "Precise",
|
||
"presencePenaltyEnabled": false,
|
||
"presence_penalty": 0.5,
|
||
"prompts": [
|
||
{
|
||
"content": "{sys.query}",
|
||
"role": "user"
|
||
}
|
||
],
|
||
"sys_prompt": "# Role\n\nYou are the **Body Agent**, a sub-agent in a multi-agent SEO blog writing system. You operate under the instruction of the `Lead Agent`, and your job is to write the full blog content based on the outline created by the `OutlineWriter_Agent`.\n\n\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": "This is the order you need to send to the agent.",
|
||
"visual_files_var": ""
|
||
}
|
||
},
|
||
{
|
||
"component_name": "Agent",
|
||
"id": "Agent:TenderAdsAllow",
|
||
"name": "Editor Agent",
|
||
"params": {
|
||
"delay_after_error": 1,
|
||
"description": "Polishes and finalizes the entire blog post. Enhances clarity, checks keyword usage, improves flow, and generates a meta title and description for SEO. Operates after all sections are completed.\n\n",
|
||
"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": 2,
|
||
"max_tokens": 4096,
|
||
"mcp": [],
|
||
"message_history_window_size": 12,
|
||
"outputs": {
|
||
"content": {
|
||
"type": "string",
|
||
"value": ""
|
||
}
|
||
},
|
||
"parameter": "Precise",
|
||
"presencePenaltyEnabled": false,
|
||
"presence_penalty": 0.5,
|
||
"prompts": [
|
||
{
|
||
"content": "{sys.query}",
|
||
"role": "user"
|
||
}
|
||
],
|
||
"sys_prompt": "# Role\n\nYou are the **Editor Agent**, the final agent in a multi-agent SEO blog writing workflow. You are 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## Integration Responsibilities\n\n- Maintain alignment with Lead Agent's original intent and audience\n\n- Preserve the structure and keyword strategy from Outline Agent\n\n- Enhance and polish Body Agent's content without altering core information\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\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",
|
||
"temperature": 0.2,
|
||
"temperatureEnabled": true,
|
||
"tools": [],
|
||
"topPEnabled": false,
|
||
"top_p": 0.75,
|
||
"user_prompt": "This is the order you need to send to the agent.",
|
||
"visual_files_var": ""
|
||
}
|
||
}
|
||
],
|
||
"topPEnabled": false,
|
||
"top_p": 0.75,
|
||
"user_prompt": "",
|
||
"visual_files_var": ""
|
||
}
|
||
},
|
||
"upstream": [
|
||
"begin"
|
||
]
|
||
},
|
||
"Message:ModernSwansThrow": {
|
||
"downstream": [],
|
||
"obj": {
|
||
"component_name": "Message",
|
||
"params": {
|
||
"content": [
|
||
"{Agent:LuckyApplesGrab@content}"
|
||
]
|
||
}
|
||
},
|
||
"upstream": [
|
||
"Agent:LuckyApplesGrab"
|
||
]
|
||
},
|
||
"begin": {
|
||
"downstream": [
|
||
"Agent:LuckyApplesGrab"
|
||
],
|
||
"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:LuckyApplesGrabend",
|
||
"source": "begin",
|
||
"sourceHandle": "start",
|
||
"target": "Agent:LuckyApplesGrab",
|
||
"targetHandle": "end"
|
||
},
|
||
{
|
||
"data": {
|
||
"isHovered": false
|
||
},
|
||
"id": "xy-edge__Agent:LuckyApplesGrabstart-Message:ModernSwansThrowend",
|
||
"source": "Agent:LuckyApplesGrab",
|
||
"sourceHandle": "start",
|
||
"target": "Message:ModernSwansThrow",
|
||
"targetHandle": "end"
|
||
},
|
||
{
|
||
"data": {
|
||
"isHovered": false
|
||
},
|
||
"id": "xy-edge__Agent:LuckyApplesGrabagentBottom-Agent:SlickSpidersTurnagentTop",
|
||
"source": "Agent:LuckyApplesGrab",
|
||
"sourceHandle": "agentBottom",
|
||
"target": "Agent:SlickSpidersTurn",
|
||
"targetHandle": "agentTop"
|
||
},
|
||
{
|
||
"data": {
|
||
"isHovered": false
|
||
},
|
||
"id": "xy-edge__Agent:LuckyApplesGrabagentBottom-Agent:IcyPawsRescueagentTop",
|
||
"source": "Agent:LuckyApplesGrab",
|
||
"sourceHandle": "agentBottom",
|
||
"target": "Agent:IcyPawsRescue",
|
||
"targetHandle": "agentTop"
|
||
},
|
||
{
|
||
"data": {
|
||
"isHovered": false
|
||
},
|
||
"id": "xy-edge__Agent:LuckyApplesGrabagentBottom-Agent:TenderAdsAllowagentTop",
|
||
"source": "Agent:LuckyApplesGrab",
|
||
"sourceHandle": "agentBottom",
|
||
"target": "Agent:TenderAdsAllow",
|
||
"targetHandle": "agentTop"
|
||
},
|
||
{
|
||
"data": {
|
||
"isHovered": false
|
||
},
|
||
"id": "xy-edge__Agent:SlickSpidersTurntool-Tool:ThreeWallsRingend",
|
||
"source": "Agent:SlickSpidersTurn",
|
||
"sourceHandle": "tool",
|
||
"target": "Tool:ThreeWallsRing",
|
||
"targetHandle": "end"
|
||
},
|
||
{
|
||
"data": {
|
||
"isHovered": false
|
||
},
|
||
"id": "xy-edge__Agent:IcyPawsRescuetool-Tool:FloppyJokesItchend",
|
||
"source": "Agent:IcyPawsRescue",
|
||
"sourceHandle": "tool",
|
||
"target": "Tool:FloppyJokesItch",
|
||
"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"
|
||
},
|
||
"dragging": false,
|
||
"id": "begin",
|
||
"measured": {
|
||
"height": 48,
|
||
"width": 200
|
||
},
|
||
"position": {
|
||
"x": 38.19445084117184,
|
||
"y": 183.9781832844475
|
||
},
|
||
"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": 3,
|
||
"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 **Lead Agent**, responsible for initiating the multi-agent SEO blog generation process. You will receive the user\u2019s topic and blog goal, interpret the intent, and coordinate the downstream writing agents.\n\n# Goals\n\n1. Parse the user's initial input.\n\n2. Generate a high-level blog intent summary and writing plan.\n\n3. Provide clear instructions to the following Sub_Agents:\n\n - `Outline Agent` \u2192 Create the blog outline.\n\n - `Body Agent` \u2192 Write all sections based on outline.\n\n - `Editor Agent` \u2192 Polish and finalize the blog post.\n\n4. Merge outputs into a complete, readable blog draft in Markdown format.\n\n# Input\n\nYou will receive:\n\n- Blog topic\n\n- Target audience\n\n- Blog goal (e.g., SEO, education, product marketing)\n\n# Output Format\n\n```markdown\n\n## Parsed Writing Plan\n\n- **Topic**: [Extracted from user input]\n\n- **Audience**: [Summarized from user input]\n\n- **Intent**: [Inferred goal and style]\n\n- **Blog Type**: [e.g., Tutorial / Informative Guide / Marketing Content]\n\n- **Long-tail Keywords**: \n\n - keyword 1\n\n - keyword 2\n\n - keyword 3\n\n - ...\n\n## Instructions for Outline Agent\n\nPlease generate a structured outline including H2 and H3 headings. Assign 1\u20132 relevant keywords to each section. Keep it aligned with the user\u2019s intent and audience level.\n\n## Instructions for Body Agent\n\nWrite the full content based on the outline. Each section should be concise (500\u2013600 words), informative, and optimized for SEO. Use `Tavily Search` only when additional examples or context are needed.\n\n## Instructions for Editor Agent\n\nReview and refine the combined content. Improve transitions, ensure keyword integration, and add a meta title + meta description. Maintain Markdown formatting.\n\n\n## Guides\n\n- Do not generate blog content directly.\n\n- Focus on correct intent recognition and instruction generation.\n\n- Keep communication to downstream agents simple, scoped, and accurate.\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\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": "0.1",
|
||
"temperatureEnabled": true,
|
||
"tools": [],
|
||
"topPEnabled": false,
|
||
"top_p": 0.75,
|
||
"user_prompt": "",
|
||
"visual_files_var": ""
|
||
},
|
||
"label": "Agent",
|
||
"name": "Lead Agent"
|
||
},
|
||
"id": "Agent:LuckyApplesGrab",
|
||
"measured": {
|
||
"height": 84,
|
||
"width": 200
|
||
},
|
||
"position": {
|
||
"x": 350,
|
||
"y": 200
|
||
},
|
||
"selected": false,
|
||
"sourcePosition": "right",
|
||
"targetPosition": "left",
|
||
"type": "agentNode"
|
||
},
|
||
{
|
||
"data": {
|
||
"form": {
|
||
"content": [
|
||
"{Agent:LuckyApplesGrab@content}"
|
||
]
|
||
},
|
||
"label": "Message",
|
||
"name": "Response"
|
||
},
|
||
"dragging": false,
|
||
"id": "Message:ModernSwansThrow",
|
||
"measured": {
|
||
"height": 56,
|
||
"width": 200
|
||
},
|
||
"position": {
|
||
"x": 669.394830760932,
|
||
"y": 190.72421137520644
|
||
},
|
||
"selected": false,
|
||
"sourcePosition": "right",
|
||
"targetPosition": "left",
|
||
"type": "messageNode"
|
||
},
|
||
{
|
||
"data": {
|
||
"form": {
|
||
"delay_after_error": 1,
|
||
"description": "Generates a clear and SEO-friendly blog outline using H2/H3 headings based on the topic, audience, and intent provided by the lead agent. Each section includes suggested keywords for optimized downstream writing.\n",
|
||
"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": 2,
|
||
"max_tokens": 4096,
|
||
"mcp": [],
|
||
"message_history_window_size": 12,
|
||
"outputs": {
|
||
"content": {
|
||
"type": "string",
|
||
"value": ""
|
||
}
|
||
},
|
||
"parameter": "Balance",
|
||
"presencePenaltyEnabled": false,
|
||
"presence_penalty": 0.2,
|
||
"prompts": [
|
||
{
|
||
"content": "{sys.query}",
|
||
"role": "user"
|
||
}
|
||
],
|
||
"sys_prompt": "# Role\n\nYou are the **Outline Agent**, a sub-agent in a multi-agent SEO blog writing system. You operate under the instruction of the `Lead Agent`, and your sole responsibility is to create a clear, well-structured, and SEO-optimized blog outline.\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": "This is the order you need to send to the agent.",
|
||
"visual_files_var": ""
|
||
},
|
||
"label": "Agent",
|
||
"name": "Outline Agent"
|
||
},
|
||
"dragging": false,
|
||
"id": "Agent:SlickSpidersTurn",
|
||
"measured": {
|
||
"height": 84,
|
||
"width": 200
|
||
},
|
||
"position": {
|
||
"x": 100.60137004146719,
|
||
"y": 411.67654846431367
|
||
},
|
||
"selected": false,
|
||
"sourcePosition": "right",
|
||
"targetPosition": "left",
|
||
"type": "agentNode"
|
||
},
|
||
{
|
||
"data": {
|
||
"form": {
|
||
"delay_after_error": 1,
|
||
"description": "Writes the full blog content section-by-section following the outline structure. It integrates target keywords naturally and uses Tavily Search only when additional facts or examples are needed.\n",
|
||
"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": 3,
|
||
"max_tokens": 4096,
|
||
"mcp": [],
|
||
"message_history_window_size": 12,
|
||
"outputs": {
|
||
"content": {
|
||
"type": "string",
|
||
"value": ""
|
||
}
|
||
},
|
||
"parameter": "Precise",
|
||
"presencePenaltyEnabled": false,
|
||
"presence_penalty": 0.5,
|
||
"prompts": [
|
||
{
|
||
"content": "{sys.query}",
|
||
"role": "user"
|
||
}
|
||
],
|
||
"sys_prompt": "# Role\n\nYou are the **Body Agent**, a sub-agent in a multi-agent SEO blog writing system. You operate under the instruction of the `Lead Agent`, and your job is to write the full blog content based on the outline created by the `OutlineWriter_Agent`.\n\n\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": "This is the order you need to send to the agent.",
|
||
"visual_files_var": ""
|
||
},
|
||
"label": "Agent",
|
||
"name": "Body Agent"
|
||
},
|
||
"dragging": false,
|
||
"id": "Agent:IcyPawsRescue",
|
||
"measured": {
|
||
"height": 84,
|
||
"width": 200
|
||
},
|
||
"position": {
|
||
"x": 439.3374395738501,
|
||
"y": 366.1408588516909
|
||
},
|
||
"selected": false,
|
||
"sourcePosition": "right",
|
||
"targetPosition": "left",
|
||
"type": "agentNode"
|
||
},
|
||
{
|
||
"data": {
|
||
"form": {
|
||
"delay_after_error": 1,
|
||
"description": "Polishes and finalizes the entire blog post. Enhances clarity, checks keyword usage, improves flow, and generates a meta title and description for SEO. Operates after all sections are completed.\n\n",
|
||
"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": 2,
|
||
"max_tokens": 4096,
|
||
"mcp": [],
|
||
"message_history_window_size": 12,
|
||
"outputs": {
|
||
"content": {
|
||
"type": "string",
|
||
"value": ""
|
||
}
|
||
},
|
||
"parameter": "Precise",
|
||
"presencePenaltyEnabled": false,
|
||
"presence_penalty": 0.5,
|
||
"prompts": [
|
||
{
|
||
"content": "{sys.query}",
|
||
"role": "user"
|
||
}
|
||
],
|
||
"sys_prompt": "# Role\n\nYou are the **Editor Agent**, the final agent in a multi-agent SEO blog writing workflow. You are 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## Integration Responsibilities\n\n- Maintain alignment with Lead Agent's original intent and audience\n\n- Preserve the structure and keyword strategy from Outline Agent\n\n- Enhance and polish Body Agent's content without altering core information\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\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",
|
||
"temperature": 0.2,
|
||
"temperatureEnabled": true,
|
||
"tools": [],
|
||
"topPEnabled": false,
|
||
"top_p": 0.75,
|
||
"user_prompt": "This is the order you need to send to the agent.",
|
||
"visual_files_var": ""
|
||
},
|
||
"label": "Agent",
|
||
"name": "Editor Agent"
|
||
},
|
||
"dragging": false,
|
||
"id": "Agent:TenderAdsAllow",
|
||
"measured": {
|
||
"height": 84,
|
||
"width": 200
|
||
},
|
||
"position": {
|
||
"x": 730.8513124709204,
|
||
"y": 327.351197329827
|
||
},
|
||
"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:ThreeWallsRing",
|
||
"measured": {
|
||
"height": 48,
|
||
"width": 200
|
||
},
|
||
"position": {
|
||
"x": -26.93431957115564,
|
||
"y": 531.4384641920368
|
||
},
|
||
"selected": false,
|
||
"sourcePosition": "right",
|
||
"targetPosition": "left",
|
||
"type": "toolNode"
|
||
},
|
||
{
|
||
"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:FloppyJokesItch",
|
||
"measured": {
|
||
"height": 48,
|
||
"width": 200
|
||
},
|
||
"position": {
|
||
"x": 414.6786783453011,
|
||
"y": 499.39483076093194
|
||
},
|
||
"selected": false,
|
||
"sourcePosition": "right",
|
||
"targetPosition": "left",
|
||
"type": "toolNode"
|
||
},
|
||
{
|
||
"data": {
|
||
"form": {
|
||
"text": "This is a multi-agent version of the SEO blog generation workflow. It simulates a small team of AI \u201cwriters\u201d, where each agent plays a specialized role \u2014 just like a real editorial team.\n\nInstead of one AI doing everything in order, this version uses a **Lead Agent** to assign tasks to different sub-agents, who then write and edit the blog in parallel. The Lead Agent manages everything and produces the final output.\n\n### Why use multi-agent format?\n\n- Better control over each stage of writing \n- Easier to reuse agents across tasks \n- More human-like workflow (planning \u2192 writing \u2192 editing \u2192 publishing) \n- Easier to scale and customize for advanced users\n\n### Flow Summary:\n\n1. `LeadWriter_Agent` takes your input and creates a plan\n2. It sends that plan to:\n - `OutlineWriter_Agent`: build blog structure\n - `BodyWriter_Agent`: write full content\n - `FinalEditor_Agent`: polish and finalize\n3. `LeadWriter_Agent` collects all results and outputs the final blog post\n"
|
||
},
|
||
"label": "Note",
|
||
"name": "Workflow Overall Description"
|
||
},
|
||
"dragHandle": ".note-drag-handle",
|
||
"dragging": false,
|
||
"height": 208,
|
||
"id": "Note:ElevenVansInvent",
|
||
"measured": {
|
||
"height": 208,
|
||
"width": 518
|
||
},
|
||
"position": {
|
||
"x": -336.6586460874556,
|
||
"y": 113.43253511344867
|
||
},
|
||
"resizing": false,
|
||
"selected": false,
|
||
"sourcePosition": "right",
|
||
"targetPosition": "left",
|
||
"type": "noteNode",
|
||
"width": 518
|
||
},
|
||
{
|
||
"data": {
|
||
"form": {
|
||
"text": "**Purpose**: \nThis is the central agent that controls the entire writing process.\n\n**What it does**:\n- Reads your blog topic and intent\n- Generates a clear writing plan (topic, audience, goal, keywords)\n- Sends instructions to all sub-agents\n- Waits for their responses and checks quality\n- If any section is missing or weak, it can request a rewrite\n- Finally, it assembles all parts into a complete blog and sends it back to you\n"
|
||
},
|
||
"label": "Note",
|
||
"name": "Lead Agent"
|
||
},
|
||
"dragHandle": ".note-drag-handle",
|
||
"dragging": false,
|
||
"height": 146,
|
||
"id": "Note:EmptyClubsGreet",
|
||
"measured": {
|
||
"height": 146,
|
||
"width": 334
|
||
},
|
||
"position": {
|
||
"x": 390.1408623279084,
|
||
"y": 2.6521144030202493
|
||
},
|
||
"resizing": false,
|
||
"selected": false,
|
||
"sourcePosition": "right",
|
||
"targetPosition": "left",
|
||
"type": "noteNode",
|
||
"width": 334
|
||
},
|
||
{
|
||
"data": {
|
||
"form": {
|
||
"text": "**Purpose**: \nThis agent is responsible for building the blog's structure. It creates an outline that shows what the article will cover and how it's organized.\n\n**What it does**:\n- Suggests a blog title that matches the topic and keywords \n- Breaks the article into sections using H2 and H3 headers \n- Adds a short description of what each section should include \n- Assigns SEO keywords to each section for better search visibility \n- Uses search data (via Tavily Search) to find how similar blogs are structured"
|
||
},
|
||
"label": "Note",
|
||
"name": "Outline Agent"
|
||
},
|
||
"dragHandle": ".note-drag-handle",
|
||
"dragging": false,
|
||
"height": 157,
|
||
"id": "Note:CurlyTigersDouble",
|
||
"measured": {
|
||
"height": 157,
|
||
"width": 394
|
||
},
|
||
"position": {
|
||
"x": -60.03139680691618,
|
||
"y": 595.8208080534818
|
||
},
|
||
"resizing": false,
|
||
"selected": false,
|
||
"sourcePosition": "right",
|
||
"targetPosition": "left",
|
||
"type": "noteNode",
|
||
"width": 394
|
||
},
|
||
{
|
||
"data": {
|
||
"form": {
|
||
"text": "**Purpose**: \nThis agent is in charge of writing the full blog content, section by section, based on the outline it receives.\n\n**What it does**:\n- Takes each section heading from the outline (H2 / H3)\n- Writes a complete paragraph (150\u2013220 words) under each section\n- Naturally includes the keywords provided for that section\n- Uses the Tavily Search tool to add real-world examples, definitions, or facts if needed\n- Makes sure each section is clear, useful, and easy to read\n"
|
||
},
|
||
"label": "Note",
|
||
"name": "Body Agent"
|
||
},
|
||
"dragHandle": ".note-drag-handle",
|
||
"dragging": false,
|
||
"height": 164,
|
||
"id": "Note:StrongKingsCamp",
|
||
"measured": {
|
||
"height": 164,
|
||
"width": 408
|
||
},
|
||
"position": {
|
||
"x": 446.54943226110845,
|
||
"y": 590.9443887062529
|
||
},
|
||
"resizing": false,
|
||
"selected": false,
|
||
"sourcePosition": "right",
|
||
"targetPosition": "left",
|
||
"type": "noteNode",
|
||
"width": 408
|
||
},
|
||
{
|
||
"data": {
|
||
"form": {
|
||
"text": "**Purpose**: \nThis agent reviews, polishes, and finalizes the blog post written by the BodyWriter_Agent. It ensures everything is clean, smooth, and SEO-compliant.\n\n**What it does**:\n- Improves grammar, sentence flow, and transitions \n- Makes sure the content reads naturally and professionally \n- Checks whether keywords are present and well integrated (but not overused) \n- Verifies that the structure follows the correct H1/H2/H3 format \n"
|
||
},
|
||
"label": "Note",
|
||
"name": "Editor Agent"
|
||
},
|
||
"dragHandle": ".note-drag-handle",
|
||
"dragging": false,
|
||
"height": 147,
|
||
"id": "Note:OpenOttersShow",
|
||
"measured": {
|
||
"height": 147,
|
||
"width": 357
|
||
},
|
||
"position": {
|
||
"x": 976.6858726228803,
|
||
"y": 422.7404806291804
|
||
},
|
||
"resizing": false,
|
||
"selected": false,
|
||
"sourcePosition": "right",
|
||
"targetPosition": "left",
|
||
"type": "noteNode",
|
||
"width": 357
|
||
}
|
||
]
|
||
},
|
||
"history": [],
|
||
"messages": [],
|
||
"path": [],
|
||
"retrieval": []
|
||
},
|
||
"avatar": "data:image/jpeg;base64,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"
|
||
} |