AI_POC/TERES_fastapi_backend
12
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

将flask改成fastapi

Browse Source
This commit is contained in:
dangzerong
2025-10-13 13:18:03 +08:00
commit 88db2539b0
476 changed files with 739741 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

421
agent/templates/choose_your_knowledge_base_agent.json Normal file
View File

File diff suppressed because one or more lines are too long

439
agent/templates/choose_your_knowledge_base_workflow.json Normal file
View File

File diff suppressed because one or more lines are too long

802
agent/templates/customer_review_analysis.json Normal file
View File

File diff suppressed because one or more lines are too long

715
agent/templates/customer_service.json Normal file
View File

File diff suppressed because one or more lines are too long

885
agent/templates/customer_support.json Normal file
View File

File diff suppressed because one or more lines are too long

427
agent/templates/cv_analysis_and_candidate_evaluation.json Normal file
View File

File diff suppressed because one or more lines are too long

852
agent/templates/deep_research.json Normal file
View File

File diff suppressed because one or more lines are too long

853
agent/templates/deep_search_r.json Normal file
View File

File diff suppressed because one or more lines are too long

1054
agent/templates/ecommerce_customer_service_workflow.json Normal file
View File

File diff suppressed because one or more lines are too long

906
agent/templates/generate_SEO_blog.json Normal file
View File

@@ -0,0 +1,906 @@
{
"id": 8,
"title": {
"en": "Generate SEO Blog",
"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.",
"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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"
}

267
agent/templates/image_lingo.json Normal file
View File

File diff suppressed because one or more lines are too long

331
agent/templates/knowledge_base_report.json Normal file
View File

@@ -0,0 +1,331 @@
{
"id": 20,
"title": {
"en": "Report Agent Using Knowledge Base",
"zh": "知识库检索智能体"},
"description": {
"en": "A report generation assistant using local knowledge base, with advanced capabilities in task planning, reasoning, and reflective analysis. Recommended for academic research paper Q&A",
"zh": "一个使用本地知识库的报告生成助手，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",
"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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"
}

331
agent/templates/knowledge_base_report_r.json Normal file
View File

@@ -0,0 +1,331 @@
{
"id": 21,
"title": {
"en": "Report Agent Using Knowledge Base",
"zh": "知识库检索智能体"},
"description": {
"en": "A report generation assistant using local knowledge base, with advanced capabilities in task planning, reasoning, and reflective analysis. Recommended for academic research paper Q&A",
"zh": "一个使用本地知识库的报告生成助手，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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"
}

919
agent/templates/market_generate_seo_blog.json Normal file
View File

@@ -0,0 +1,919 @@
{
"id": 12,
"title": {
"en": "Generate SEO Blog",
"zh": "生成SEO博客"},
"description": {
"en": "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.",
"zh": "此工作流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",
"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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"
}

919
agent/templates/seo_blog.json Normal file
View File

@@ -0,0 +1,919 @@
{
"id": 4,
"title": {
"en": "Generate SEO Blog",
"zh": "生成SEO博客"},
"description": {
"en": "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.",
"zh": "此工作流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,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"
}

716
agent/templates/sql_assistant.json Normal file
View File

@@ -0,0 +1,716 @@
{
"id": 17,
"title": {
"en": "SQL Assistant",
"zh": "SQL助理"},
"description": {
"en": "SQL Assistant is an AI-powered tool that lets business users turn plain-English questions into fully formed SQL queries. Simply type your question (e.g., “Show me last quarter’s top 10 products by revenue”) and SQL Assistant generates the exact SQL, runs it against your database, and returns the results in seconds. ",
"zh": "用户能够将简单文本问题转化为完整的SQL查询并输出结果。只需输入您的问题（例如，“展示上个季度前十名按收入排序的产品”），SQL助理就会生成精确的SQL语句，对其运行您的数据库，并几秒钟内返回结果。"},
"canvas_type": "Marketing",
"dsl": {
"components": {
"Agent:WickedGoatsDivide": {
"downstream": [
"ExeSQL:TiredShirtsPull"
],
"obj": {
"component_name": "Agent",
"params": {
"delay_after_error": 1,
"description": "",
"exception_default_value": "",
"exception_goto": [],
"exception_method": "",
"frequencyPenaltyEnabled": false,
"frequency_penalty": 0.7,
"llm_id": "qwen-max@Tongyi-Qianwen",
"maxTokensEnabled": false,
"max_retries": 3,
"max_rounds": 5,
"max_tokens": 256,
"mcp": [],
"message_history_window_size": 12,
"outputs": {
"content": {
"type": "string",
"value": ""
}
},
"presencePenaltyEnabled": false,
"presence_penalty": 0.4,
"prompts": [
{
"content": "User's query: {sys.query}\n\nSchema: {Retrieval:HappyTiesFilm@formalized_content}\n\nSamples about question to SQL: {Retrieval:SmartNewsHammer@formalized_content}\n\nDescription about meanings of tables and files: {Retrieval:SweetDancersAppear@formalized_content}",
"role": "user"
}
],
"sys_prompt": "### ROLE\nYou are a Text-to-SQL assistant. \nGiven a relational database schema and a natural-language request, you must produce a **single, syntactically-correct MySQL query** that answers the request. \nReturn **nothing except the SQL statement itself**\u2014no code fences, no commentary, no explanations, no comments, no trailing semicolon if not required.\n\n\n### EXAMPLES \n-- Example 1 \nUser: List every product name and its unit price. \nSQL:\nSELECT name, unit_price FROM Products;\n\n-- Example 2 \nUser: Show the names and emails of customers who placed orders in January 2025. \nSQL:\nSELECT DISTINCT c.name, c.email\nFROM Customers c\nJOIN Orders o ON o.customer_id = c.id\nWHERE o.order_date BETWEEN '2025-01-01' AND '2025-01-31';\n\n-- Example 3 \nUser: How many orders have a status of \"Completed\" for each month in 2024? \nSQL:\nSELECT DATE_FORMAT(order_date, '%Y-%m') AS month,\n COUNT(*) AS completed_orders\nFROM Orders\nWHERE status = 'Completed'\n AND YEAR(order_date) = 2024\nGROUP BY month\nORDER BY month;\n\n-- Example 4 \nUser: Which products generated at least \\$10 000 in total revenue? \nSQL:\nSELECT p.id, p.name, SUM(oi.quantity * oi.unit_price) AS revenue\nFROM Products p\nJOIN OrderItems oi ON oi.product_id = p.id\nGROUP BY p.id, p.name\nHAVING revenue >= 10000\nORDER BY revenue DESC;\n\n\n### OUTPUT GUIDELINES\n1. Think through the schema and the request. \n2. Write **only** the final MySQL query. \n3. Do **not** wrap the query in back-ticks or markdown fences. \n4. Do **not** add explanations, comments, or additional text\u2014just the SQL.",
"temperature": 0.1,
"temperatureEnabled": false,
"tools": [],
"topPEnabled": false,
"top_p": 0.3,
"user_prompt": "",
"visual_files_var": ""
}
},
"upstream": [
"Retrieval:HappyTiesFilm",
"Retrieval:SmartNewsHammer",
"Retrieval:SweetDancersAppear"
]
},
"ExeSQL:TiredShirtsPull": {
"downstream": [
"Message:ShaggyMasksAttend"
],
"obj": {
"component_name": "ExeSQL",
"params": {
"database": "",
"db_type": "mysql",
"host": "",
"max_records": 1024,
"outputs": {
"formalized_content": {
"type": "string",
"value": ""
},
"json": {
"type": "Array<Object>",
"value": []
}
},
"password": "20010812Yy!",
"port": 3306,
"sql": "{Agent:WickedGoatsDivide@content}",
"username": "13637682833@163.com"
}
},
"upstream": [
"Agent:WickedGoatsDivide"
]
},
"Message:ShaggyMasksAttend": {
"downstream": [],
"obj": {
"component_name": "Message",
"params": {
"content": [
"{ExeSQL:TiredShirtsPull@formalized_content}"
]
}
},
"upstream": [
"ExeSQL:TiredShirtsPull"
]
},
"Retrieval:HappyTiesFilm": {
"downstream": [
"Agent:WickedGoatsDivide"
],
"obj": {
"component_name": "Retrieval",
"params": {
"cross_languages": [],
"empty_response": "",
"kb_ids": [],
"keywords_similarity_weight": 0.7,
"outputs": {
"formalized_content": {
"type": "string",
"value": ""
}
},
"query": "{sys.query}",
"rerank_id": "",
"similarity_threshold": 0.2,
"top_k": 1024,
"top_n": 8,
"use_kg": false
}
},
"upstream": [
"begin"
]
},
"Retrieval:SmartNewsHammer": {
"downstream": [
"Agent:WickedGoatsDivide"
],
"obj": {
"component_name": "Retrieval",
"params": {
"cross_languages": [],
"empty_response": "",
"kb_ids": [],
"keywords_similarity_weight": 0.7,
"outputs": {
"formalized_content": {
"type": "string",
"value": ""
}
},
"query": "{sys.query}",
"rerank_id": "",
"similarity_threshold": 0.2,
"top_k": 1024,
"top_n": 8,
"use_kg": false
}
},
"upstream": [
"begin"
]
},
"Retrieval:SweetDancersAppear": {
"downstream": [
"Agent:WickedGoatsDivide"
],
"obj": {
"component_name": "Retrieval",
"params": {
"cross_languages": [],
"empty_response": "",
"kb_ids": [],
"keywords_similarity_weight": 0.7,
"outputs": {
"formalized_content": {
"type": "string",
"value": ""
}
},
"query": "{sys.query}",
"rerank_id": "",
"similarity_threshold": 0.2,
"top_k": 1024,
"top_n": 8,
"use_kg": false
}
},
"upstream": [
"begin"
]
},
"begin": {
"downstream": [
"Retrieval:HappyTiesFilm",
"Retrieval:SmartNewsHammer",
"Retrieval:SweetDancersAppear"
],
"obj": {
"component_name": "Begin",
"params": {
"enablePrologue": true,
"inputs": {},
"mode": "conversational",
"prologue": "Hi! I'm your SQL assistant. What can I do for you?"
}
},
"upstream": []
}
},
"globals": {
"sys.conversation_turns": 0,
"sys.files": [],
"sys.query": "",
"sys.user_id": ""
},
"graph": {
"edges": [
{
"data": {
"isHovered": false
},
"id": "xy-edge__beginstart-Retrieval:HappyTiesFilmend",
"source": "begin",
"sourceHandle": "start",
"target": "Retrieval:HappyTiesFilm",
"targetHandle": "end"
},
{
"id": "xy-edge__beginstart-Retrieval:SmartNewsHammerend",
"source": "begin",
"sourceHandle": "start",
"target": "Retrieval:SmartNewsHammer",
"targetHandle": "end"
},
{
"data": {
"isHovered": false
},
"id": "xy-edge__beginstart-Retrieval:SweetDancersAppearend",
"source": "begin",
"sourceHandle": "start",
"target": "Retrieval:SweetDancersAppear",
"targetHandle": "end"
},
{
"data": {
"isHovered": false
},
"id": "xy-edge__Retrieval:HappyTiesFilmstart-Agent:WickedGoatsDivideend",
"source": "Retrieval:HappyTiesFilm",
"sourceHandle": "start",
"target": "Agent:WickedGoatsDivide",
"targetHandle": "end"
},
{
"data": {
"isHovered": false
},
"id": "xy-edge__Retrieval:SmartNewsHammerstart-Agent:WickedGoatsDivideend",
"markerEnd": "logo",
"source": "Retrieval:SmartNewsHammer",
"sourceHandle": "start",
"style": {
"stroke": "rgba(91, 93, 106, 1)",
"strokeWidth": 1
},
"target": "Agent:WickedGoatsDivide",
"targetHandle": "end",
"type": "buttonEdge",
"zIndex": 1001
},
{
"data": {
"isHovered": false
},
"id": "xy-edge__Retrieval:SweetDancersAppearstart-Agent:WickedGoatsDivideend",
"markerEnd": "logo",
"source": "Retrieval:SweetDancersAppear",
"sourceHandle": "start",
"style": {
"stroke": "rgba(91, 93, 106, 1)",
"strokeWidth": 1
},
"target": "Agent:WickedGoatsDivide",
"targetHandle": "end",
"type": "buttonEdge",
"zIndex": 1001
},
{
"data": {
"isHovered": false
},
"id": "xy-edge__Agent:WickedGoatsDividestart-ExeSQL:TiredShirtsPullend",
"source": "Agent:WickedGoatsDivide",
"sourceHandle": "start",
"target": "ExeSQL:TiredShirtsPull",
"targetHandle": "end"
},
{
"data": {
"isHovered": false
},
"id": "xy-edge__ExeSQL:TiredShirtsPullstart-Message:ShaggyMasksAttendend",
"source": "ExeSQL:TiredShirtsPull",
"sourceHandle": "start",
"target": "Message:ShaggyMasksAttend",
"targetHandle": "end"
}
],
"nodes": [
{
"data": {
"form": {
"enablePrologue": true,
"inputs": {},
"mode": "conversational",
"prologue": "Hi! I'm your SQL assistant. What can I do for you?"
},
"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": {
"cross_languages": [],
"empty_response": "",
"kb_ids": [],
"keywords_similarity_weight": 0.7,
"outputs": {
"formalized_content": {
"type": "string",
"value": ""
}
},
"query": "{sys.query}",
"rerank_id": "",
"similarity_threshold": 0.2,
"top_k": 1024,
"top_n": 8,
"use_kg": false
},
"label": "Retrieval",
"name": "Schema"
},
"dragging": false,
"id": "Retrieval:HappyTiesFilm",
"measured": {
"height": 96,
"width": 200
},
"position": {
"x": 414,
"y": 20.5
},
"selected": false,
"sourcePosition": "right",
"targetPosition": "left",
"type": "retrievalNode"
},
{
"data": {
"form": {
"cross_languages": [],
"empty_response": "",
"kb_ids": [],
"keywords_similarity_weight": 0.7,
"outputs": {
"formalized_content": {
"type": "string",
"value": ""
}
},
"query": "{sys.query}",
"rerank_id": "",
"similarity_threshold": 0.2,
"top_k": 1024,
"top_n": 8,
"use_kg": false
},
"label": "Retrieval",
"name": "Question to SQL"
},
"dragging": false,
"id": "Retrieval:SmartNewsHammer",
"measured": {
"height": 96,
"width": 200
},
"position": {
"x": 406.5,
"y": 175.5
},
"selected": false,
"sourcePosition": "right",
"targetPosition": "left",
"type": "retrievalNode"
},
{
"data": {
"form": {
"cross_languages": [],
"empty_response": "",
"kb_ids": [],
"keywords_similarity_weight": 0.7,
"outputs": {
"formalized_content": {
"type": "string",
"value": ""
}
},
"query": "{sys.query}",
"rerank_id": "",
"similarity_threshold": 0.2,
"top_k": 1024,
"top_n": 8,
"use_kg": false
},
"label": "Retrieval",
"name": "Database Description"
},
"dragging": false,
"id": "Retrieval:SweetDancersAppear",
"measured": {
"height": 96,
"width": 200
},
"position": {
"x": 403.5,
"y": 328
},
"selected": false,
"sourcePosition": "right",
"targetPosition": "left",
"type": "retrievalNode"
},
{
"data": {
"form": {
"delay_after_error": 1,
"description": "",
"exception_default_value": "",
"exception_goto": [],
"exception_method": "",
"frequencyPenaltyEnabled": false,
"frequency_penalty": 0.7,
"llm_id": "qwen-max@Tongyi-Qianwen",
"maxTokensEnabled": false,
"max_retries": 3,
"max_rounds": 5,
"max_tokens": 256,
"mcp": [],
"message_history_window_size": 12,
"outputs": {
"content": {
"type": "string",
"value": ""
}
},
"presencePenaltyEnabled": false,
"presence_penalty": 0.4,
"prompts": [
{
"content": "User's query: {sys.query}\n\nSchema: {Retrieval:HappyTiesFilm@formalized_content}\n\nSamples about question to SQL: {Retrieval:SmartNewsHammer@formalized_content}\n\nDescription about meanings of tables and files: {Retrieval:SweetDancersAppear@formalized_content}",
"role": "user"
}
],
"sys_prompt": "### ROLE\nYou are a Text-to-SQL assistant. \nGiven a relational database schema and a natural-language request, you must produce a **single, syntactically-correct MySQL query** that answers the request. \nReturn **nothing except the SQL statement itself**\u2014no code fences, no commentary, no explanations, no comments, no trailing semicolon if not required.\n\n\n### EXAMPLES \n-- Example 1 \nUser: List every product name and its unit price. \nSQL:\nSELECT name, unit_price FROM Products;\n\n-- Example 2 \nUser: Show the names and emails of customers who placed orders in January 2025. \nSQL:\nSELECT DISTINCT c.name, c.email\nFROM Customers c\nJOIN Orders o ON o.customer_id = c.id\nWHERE o.order_date BETWEEN '2025-01-01' AND '2025-01-31';\n\n-- Example 3 \nUser: How many orders have a status of \"Completed\" for each month in 2024? \nSQL:\nSELECT DATE_FORMAT(order_date, '%Y-%m') AS month,\n COUNT(*) AS completed_orders\nFROM Orders\nWHERE status = 'Completed'\n AND YEAR(order_date) = 2024\nGROUP BY month\nORDER BY month;\n\n-- Example 4 \nUser: Which products generated at least \\$10 000 in total revenue? \nSQL:\nSELECT p.id, p.name, SUM(oi.quantity * oi.unit_price) AS revenue\nFROM Products p\nJOIN OrderItems oi ON oi.product_id = p.id\nGROUP BY p.id, p.name\nHAVING revenue >= 10000\nORDER BY revenue DESC;\n\n\n### OUTPUT GUIDELINES\n1. Think through the schema and the request. \n2. Write **only** the final MySQL query. \n3. Do **not** wrap the query in back-ticks or markdown fences. \n4. Do **not** add explanations, comments, or additional text\u2014just the SQL.",
"temperature": 0.1,
"temperatureEnabled": false,
"tools": [],
"topPEnabled": false,
"top_p": 0.3,
"user_prompt": "",
"visual_files_var": ""
},
"label": "Agent",
"name": "SQL Generator "
},
"dragging": false,
"id": "Agent:WickedGoatsDivide",
"measured": {
"height": 84,
"width": 200
},
"position": {
"x": 981,
"y": 174
},
"selected": false,
"sourcePosition": "right",
"targetPosition": "left",
"type": "agentNode"
},
{
"data": {
"form": {
"database": "",
"db_type": "mysql",
"host": "",
"max_records": 1024,
"outputs": {
"formalized_content": {
"type": "string",
"value": ""
},
"json": {
"type": "Array<Object>",
"value": []
}
},
"password": "20010812Yy!",
"port": 3306,
"sql": "{Agent:WickedGoatsDivide@content}",
"username": "13637682833@163.com"
},
"label": "ExeSQL",
"name": "ExeSQL"
},
"dragging": false,
"id": "ExeSQL:TiredShirtsPull",
"measured": {
"height": 56,
"width": 200
},
"position": {
"x": 1211.5,
"y": 212.5
},
"selected": false,
"sourcePosition": "right",
"targetPosition": "left",
"type": "ragNode"
},
{
"data": {
"form": {
"content": [
"{ExeSQL:TiredShirtsPull@formalized_content}"
]
},
"label": "Message",
"name": "Message"
},
"dragging": false,
"id": "Message:ShaggyMasksAttend",
"measured": {
"height": 56,
"width": 200
},
"position": {
"x": 1447.3125,
"y": 181.5
},
"selected": false,
"sourcePosition": "right",
"targetPosition": "left",
"type": "messageNode"
},
{
"data": {
"form": {
"text": "Searches for relevant database creation statements.\n\nIt should label with a knowledgebase to which the schema is dumped in. You could use \" General \" as parsing method, \" 2 \" as chunk size and \" ; \" as delimiter."
},
"label": "Note",
"name": "Note Schema"
},
"dragHandle": ".note-drag-handle",
"dragging": false,
"height": 188,
"id": "Note:ThickClubsFloat",
"measured": {
"height": 188,
"width": 392
},
"position": {
"x": 689,
"y": -180.31251144409183
},
"resizing": false,
"selected": false,
"sourcePosition": "right",
"targetPosition": "left",
"type": "noteNode",
"width": 392
},
{
"data": {
"form": {
"text": "Searches for samples about question to SQL. \n\nYou could use \" Q&A \" as parsing method.\n\nPlease check this dataset:\nhttps://huggingface.co/datasets/InfiniFlow/text2sql"
},
"label": "Note",
"name": "Note: Question to SQL"
},
"dragHandle": ".note-drag-handle",
"dragging": false,
"height": 154,
"id": "Note:ElevenLionsJoke",
"measured": {
"height": 154,
"width": 345
},
"position": {
"x": 693.5,
"y": 138
},
"resizing": false,
"selected": false,
"sourcePosition": "right",
"targetPosition": "left",
"type": "noteNode",
"width": 345
},
{
"data": {
"form": {
"text": "Searches for description about meanings of tables and fields.\n\nYou could use \" General \" as parsing method, \" 2 \" as chunk size and \" ### \" as delimiter."
},
"label": "Note",
"name": "Note: Database Description"
},
"dragHandle": ".note-drag-handle",
"dragging": false,
"height": 158,
"id": "Note:ManyRosesTrade",
"measured": {
"height": 158,
"width": 408
},
"position": {
"x": 691.5,
"y": 435.69736389555317
},
"resizing": false,
"selected": false,
"sourcePosition": "right",
"targetPosition": "left",
"type": "noteNode",
"width": 408
},
{
"data": {
"form": {
"text": "The Agent learns which tables may be available based on the responses from three knowledge bases and converts the user's input into SQL statements."
},
"label": "Note",
"name": "Note: SQL Generator"
},
"dragHandle": ".note-drag-handle",
"dragging": false,
"height": 132,
"id": "Note:RudeHousesInvite",
"measured": {
"height": 132,
"width": 383
},
"position": {
"x": 1106.9254833678003,
"y": 290.5891036507015
},
"resizing": false,
"selected": false,
"sourcePosition": "right",
"targetPosition": "left",
"type": "noteNode",
"width": 383
},
{
"data": {
"form": {
"text": "Connect to your database to execute SQL statements."
},
"label": "Note",
"name": "Note: SQL Executor"
},
"dragHandle": ".note-drag-handle",
"dragging": false,
"id": "Note:HungryBatsLay",
"measured": {
"height": 136,
"width": 255
},
"position": {
"x": 1185,
"y": -30
},
"selected": false,
"sourcePosition": "right",
"targetPosition": "left",
"type": "noteNode"
}
]
},
"history": [],
"messages": [],
"path": [],
"retrieval": []
},
"avatar": "data:image/jpeg;base64,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"
}

335
agent/templates/technical_docs_qa.json Normal file
View File

File diff suppressed because one or more lines are too long

689
agent/templates/trip_planner.json Normal file
View File

File diff suppressed because one or more lines are too long

875
agent/templates/web_search_assistant.json Normal file
View File

File diff suppressed because one or more lines are too long