diff --git a/agent/templates/choose_your_knowledge_base_agent.json b/agent/templates/choose_your_knowledge_base_agent.json index 1d201f550..e55cd8249 100644 --- a/agent/templates/choose_your_knowledge_base_agent.json +++ b/agent/templates/choose_your_knowledge_base_agent.json @@ -1,8 +1,12 @@ { "id": 19, - "title": "Choose Your Knowledge Base Agent", - "description": "Select your desired knowledge base from the dropdown menu. The Agent will only retrieve from the selected knowledge base and use this content to generate responses.", - "canvas_type": "Agent", + "title": { + "en": "Choose Your Knowledge Base Agent", + "zh": "选择知识库智能体"}, + "description": { + "en": "Select your desired knowledge base from the dropdown menu. The Agent will only retrieve from the selected knowledge base and use this content to generate responses.", + "zh": "从下拉菜单中选择知识库，智能体将仅根据所选知识库内容生成回答。"}, + "canvas_type": "Agent", "dsl": { "components": { "Agent:BraveParksJoke": { diff --git a/agent/templates/choose_your_knowledge_base_workflow.json b/agent/templates/choose_your_knowledge_base_workflow.json index 3bd04e982..0a5b8d887 100644 --- a/agent/templates/choose_your_knowledge_base_workflow.json +++ b/agent/templates/choose_your_knowledge_base_workflow.json @@ -1,8 +1,12 @@ { "id": 18, - "title": "Choose Your Knowledge Base Workflow", - "description": "Select your desired knowledge base from the dropdown menu. The retrieval assistant will only use data from your selected knowledge base to generate responses.", - "canvas_type": "Other", + "title": { + "en": "Choose Your Knowledge Base Workflow", + "zh": "选择知识库工作流"}, + "description": { + "en": "Select your desired knowledge base from the dropdown menu. The retrieval assistant will only use data from your selected knowledge base to generate responses.", + "zh": "从下拉菜单中选择知识库，工作流将仅根据所选知识库内容生成回答。"}, + "canvas_type": "Other", "dsl": { "components": { "Agent:ProudDingosShout": { diff --git a/agent/templates/customer_review_analysis.json b/agent/templates/customer_review_analysis.json index 52b365878..3e10f6d0c 100644 --- a/agent/templates/customer_review_analysis.json +++ b/agent/templates/customer_review_analysis.json @@ -1,9 +1,13 @@ { "id": 11, - "title": "Customer Review Analysis", - "description": "Automatically classify customer reviews using LLM (Large Language Model) and route them via email to the relevant departments.", - "canvas_type": "Customer Support", + "title": { + "en": "Customer Review Analysis", + "zh": "客户评价分析"}, + "description": { + "en": "Automatically classify customer reviews using LLM (Large Language Model) and route them via email to the relevant departments.", + "zh": "大模型将自动分类客户评价，并通过电子邮件将结果发送到相关部门。"}, + "canvas_type": "Customer Support", "dsl": { "components": { "Categorize:FourTeamsFold": { diff --git a/agent/templates/customer_service.json b/agent/templates/customer_service.json index d9333561c..7b50c09e2 100644 --- a/agent/templates/customer_service.json +++ b/agent/templates/customer_service.json @@ -1,8 +1,12 @@ { "id": 2, - "title": "Multi-Agent Customer Support", - "description": "This is a multi-agent system for intelligent customer service processing based on user intent classification. It uses the lead-agent to identify the type of user needs, assign tasks to sub-agents for processing.", + "title": { + "en": "Multi-Agent Customer Support", + "zh": "多智能体客服"}, + "description": { + "en": "This is a multi-agent system for intelligent customer service processing based on user intent classification. It uses the lead-agent to identify the type of user needs, assign tasks to sub-agents for processing.", + "zh": "多智能体系统，用于智能客服场景。基于用户意图分类，使用主智能体识别用户需求类型，并将任务分配给子智能体进行处理。"}, "canvas_type": "Agent", "dsl": { "components": { @@ -708,4 +712,4 @@ "retrieval": [] }, "avatar": "data:image/png;base64,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" -} \ No newline at end of file +} diff --git a/agent/templates/customer_support.json b/agent/templates/customer_support.json index b77bb5ec2..34280e00c 100644 --- a/agent/templates/customer_support.json +++ b/agent/templates/customer_support.json @@ -1,8 +1,12 @@ { "id": 10, - "title": "Customer Support", - "description": "This is an intelligent customer service processing system workflow based on user intent classification. It uses LLM to identify user demand types and transfers them to the corresponding professional agent for processing.", + "title": { + "en":"Customer Support", + "zh": "客户支持"}, + "description": { + "en": "This is an intelligent customer service processing system workflow based on user intent classification. It uses LLM to identify user demand types and transfers them to the corresponding professional agent for processing.", + "zh": "工作流系统，用于智能客服场景。基于用户意图分类。使用大模型识别用户需求类型，并将需求转移给相应的智能体进行处理。"}, "canvas_type": "Customer Support", "dsl": { "components": { diff --git a/agent/templates/cv_analysis_and_candidate_evaluation.json b/agent/templates/cv_analysis_and_candidate_evaluation.json index f1ec9d648..ad5d5ad33 100644 --- a/agent/templates/cv_analysis_and_candidate_evaluation.json +++ b/agent/templates/cv_analysis_and_candidate_evaluation.json @@ -1,8 +1,12 @@ { "id": 15, - "title": "CV Analysis and Candidate Evaluation", - "description": "This is a workflow that helps companies evaluate resumes, HR uploads a job description first, then submits multiple resumes via the chat window for evaluation.", + "title": { + "en": "CV Analysis and Candidate Evaluation", + "zh": "简历分析和候选人评估"}, + "description": { + "en": "This is a workflow that helps companies evaluate resumes, HR uploads a job description first, then submits multiple resumes via the chat window for evaluation.", + "zh": "帮助公司评估简历的工作流。HR首先上传职位描述，通过聊天窗口提交多份简历进行评估。"}, "canvas_type": "Other", "dsl": { "components": { diff --git a/agent/templates/cv_evaluation.json b/agent/templates/cv_evaluation.json deleted file mode 100644 index fa3fd3c91..000000000 --- a/agent/templates/cv_evaluation.json +++ /dev/null @@ -1,917 +0,0 @@ - -{ - "id": 4, - "title": "Generate SEO Blog", - "description": "This workflow automatically generates a complete SEO-optimized blog article based on a simple user input. You don’t need any writing experience. Just provide a topic or short request — the system will handle the rest.", - "canvas_type": "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", - "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", - "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", - "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", - "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/png;base64,iVBORw0KGgoAAAANSUhEUgAAADAAAAAwCAYAAABXAvmHAAAACXBIWXMAABYlAAAWJQFJUiTwAAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAABhDSURBVHgBXZp5kKVVecbf797v7mvvPd3Ts7AKOEFZBFF2ZQkFggTFiAFiRUGjUEaiYoxjCkL5hwYrWpZLRLBETIwZC2QrUqDBUtkc1gEGmO7pnl7vvu83v+e0WiZd0zXdfb97znm3533e51zP/t/Xp6+64KzA0HtPpz+8NOQHdkT9gNW7favV25ZNRIy/WbPdNc8LWCTsmQ0D1uoOrN/rWSoR5vehDVlnNJUwzwLWHQys2WpZNBKxfr9v0XDI+jzj8d3tD1gjZJVa3bxAwDqswePW7Aysp2dDQQsEg5aMh/d63nDvoG1f2v39PfN/el7vDz/8y42XZteL7S9mY4kb+8OB1ZsNqzT7HDpskUjINkp1mxlNW75St+nRFG/0LBJi80bTYtGQrRerFo9GbGYsbX6Q38tV63R6FuBgEd+3Uq3CITFi0LF2u4fRfWt0ujYYehbjoIlo0KqtrkWDvuVqTYuH2dcP8voQw/rWwrjJTNzCIe/2kEVkSOmPBlxz6VnZmXT80dfXSm8ZSUQtFvatjRf6g6FVmy2L4T2PJ31v02NpjFrN121qLIHncbrxLG4P6CcONJaKYUTQwqxTb3RwRMOtIae0Op51+h0bTcQsGDDrsQdntLFM0tYLFctVW+69PhvGYj7P90wxzfK8nBbw9ZrtHfa8s2VEUAac99ajbovGwpeOJkLmB3yL4bGB1zOfdJnKJvE0/48kLJOIOy+kYhFLEJXBoG+d7tBFIBry3QbdftcdKl9qmKwOYUQgELRut2v1Vp/X+1bGqEK1wc/m3hfmFEEiFeXZ7VNZC3hD9orqoJaJR0k9pdTA8kTGI8e6ve50f9iL/ur51x/ybrvuSvJ8eKDR6bhwOXfwbxSPNMjdNAsEyPdKo2UblYbVWm3+3rVg0LPRZNwt3CIV4tGwJfnW4fsY0ewMiZbv6kWHlhPGqYs2zxfKrNNu46ggB42x5cBWyw3n7ZDShjVa3Y6lIjEbS0csjCUp0rNB6ml9nUFfE6nw2f4zB+a/mAzHrMMig94Ab/pWoWBHE1Xs8FyYaxwwg9dDeGtiJGMxPDaKh0ZSKQxruHwd4m2f14vUiNZo4e1YJGjtnlKk98fNM0R3AkNy5QoRIuIcrkf+zVFPTaJUa/Vs20TGObHWbNuInESkdZaoIkp6jY8miehQ9Xipd9Nfnv+7Zrv3Fnm0xqY4ShltuVKTNDJLqoArTdLAo4iTVq63XG3MjKTxUtfK1EiWKLXxnoydzlAXbDYg1Cq+yWyCVAhavl7HCVGiFCUVaraF94cxuFKpWDcQMsEPPrRoLGRlnNBhD8DNFfuA9eIUeoM9/JBnI9GYc0okHJ73Ljv7bUNtNnSHDbtF89Umi/UoxoSDMqWHUmU0FubAeIUiLdbaeMMDRYcG2BGJtivANXJ/huLuchqf1PPwmiDzmK3jtrBRthkMSlFLKSA57rMu6KKcjyaS5HfPwWeImunxfnyGswY2v16yJIWyUevYeqlGOoXt5ZWCg2Tv6oveMczG4uS0Qh0gF2vgdg+kIM/JR4Ws1em732dGUiAU6eIKqW9N4TaGNXk9HiE1snFTKVfJ+zBg0AaighhRqDVcD6m3+87QdDyEoTWbHUux5xCsD9nOybTtW8q5+sqk4pwBR8UjNk7K1vlZgDGRjAImafYKk0IdoDfCfhx6qVhR3lixTpVzYBXeFKkQIxp93uhj/SQLtTlogoPKey022rZl1Aqlqi3mqniNtCGXi+2OQ5lGt+/+1qeutnDQ9Wrd5saydtqxczbCASoUsXJfBfzCwZyru3cctdXmWSseFgSPuVRVnwnwTGcQsB5OeYNodHFciH5R4jXv4jNOHCpWhXIHLO85j0+ko7yIpyhcIUkEOF0q1CzCax5po7xUkclDW6gLpViOtJvJxFwUi/UG4Q27lDliOou36yY0rzY2EUxIpNpKsH44EHA9ZoMojVAfuMFirNsl37NEastoRr6lnzRJb4AE45TO66y5RN/wLj/3FDnBVOcp8Hxxo0S6BBw2AyCuS8bJtVhYbT3Azz4bc7i1skMVnzRrAsHKdVmlZ9V5W/xtNJ101KPTA2ZJk6BDnIGjC+orVQ4ZJt8rzaaFqKM375w2pcJKvgpYNF09KlU7oEkTJKzxHDjhmqKMn0zSYN91yq5hl266bSrjQqavHPkZ5BBUn3mEWVRC3vMwIMrf66RYn4JTjxAnmqYwhVJlCjsKP1I3rlLsNbzdAUpmRmPOGesUeAwDhV4jFPLRW8eoEc/t06LuZOAa/UB1EibaUSBRHXjX3Lg1QDsPZ+m987m66zmFct38nVvGXErIw6vFum2Um67Ky+Skmo+8LGMy5H2ZA2kBdWPxmOVczXaQIvNErU2BxsH/AQ04FQ65ZqROmsrGXa4LTrPAqI+hGTwnnlSoVOFMTUfuprIp2UGKdVyddbUv0Xl9tQDyNUnRtiN/Y0koiDd0tEZn8j7+F+cMC3jmEF4fT8ddAevADYpRVKmLcfKucq/RhITRkHzqIBENuzoI6JRqOo0e0QCdumqGQVAt4Dp4gJSIciAy3ZKkXpvUEhopckkMHgeSBcer9Jo8TpvFkCTPN0mLGHvEFH3guTvEQaRUjNTRGXW+WhNWfOX5bx8KCifw0OJGxTHAEJsrtwccvgUu13hYeRvHgwql0kJ9Q6mn03MW59UizW80G+X9ITptw5GwJHWlPBYPikYCrnjXYK7yeJv1/UjQGT2JZ+sgU4OfRT0EICJ1daKeSoZxBnWgbs6mUZwp7qSU9y4+8+Rhtd50hCseDmw2B5eX5rpp2PddBJSXWiAWUQ304DtDRwOU7+IwKk6FVIumiMDLBzcsQJ20ZTwYND02CnOI2TFHbLOjd8zYTx74BVAZd0Xp+UOH7Vq/0+25zu4Y7kB/D7kaFKFLE8Ex9Qie0XmEZv4WPH8kTUQen9o6a8/sfdFqlTKdj5YUCoMgeARoFFcX0SvyxiwwV6Yrkg0cgv6RW7Xts1OOrxxxxKxtn5uzc88ftV1H7bSpmS02sWUbPH9g8XTKdWWDe01Of8Nuvf1Om5iAfYLKeWpBiJWFY1XYv1DW/BB2wJGmkAPgVHckTp1WNwcd6InIoHf9ZWcPa8W8fWfPQ+b3W7hjYMV8wZYOHrTC6pI999LL9j9PPmflQs5eml8jt8OOCuzcknWzwZD8+cEP7qI4iRaeE2i3YbEb1NSrr71qjz611147uGhf/dTHIIO/n9g0zUF/TjrrYpscnwTN6CPFhikjD61t2K03f8JOO+F4O8gZ3ji4bMsrh2zfa4u2upazcrVmIa+LOZ6FSU/vi5efPrzwQ9fYrlNOsyYkS2PfOF6jPKzd7Fh6cotZp2atYsHWVlZs/2uv2zPP7bOX9r1iv336WXvvee+wW/71m1Z8ff/m4fDORrVix5xwrk0evsN++8BPLJsdszRpsrq84iKt50anJ+1D11xvT7+wn/RKOfoi1Gvw3qeefcKKB+YBDnJfDU+RS0I7SNVapWh51slv5GxtbR2WkEnbKRdcbLnFBdcDUhC4iz74EdvPi28/8c/stYUle/eJb7XPX3c1r6XtbSefbKefdYaFkxn7xc/vtX/8p9voFXU3OvaomT78501HHmFH8t6FhVW7/Xt32uLquo2kE/btz3+GQafkZuZyvmTXXft+O/eK6yn0nZYFjQQiJ/zZsW5oEd9qtWG6pPh3fnCP3fPIL23btkkbi6fsC5/8CKAzQqpuM//qG26yEiFSlUNP7Z6H/9sevPche9clF9iX//6zNjM3a3fdfafDbUeRxWHorA1qoLX8or26nLfm0oIF4xnrMhsIOBulin3wsots9z/cZm8+Yod9ZfctFgQCawdfdexSPVtQ/M4zz7Cp6XEr1CF/eH9nNmSXn3+Oi/aA14OgzdSu0/F6zZ7/zQMQvkn70YMP28jMLvv5T++w0447zgKzRx/DINNzUBfF+9deeYXdd++dLkVmdx5jn7jpJrvqwvMZTHpOIZCnAX/Lz79gq4fmba3QsldeeNqi8aRzgr6kQlx9+UVupPz0P3/Nrv3UJ+28D7zf7rr/QSKRpodE7b5fPG5D6ulv3n8xUak5BCqVynbuOadbldkhmUzYLd/6Ps7dsJs/8zGbGxm1fK5gV73nIstsnbH3XnODRWmogcLSopM0JifG7cy/+qhddu3f2vHHHm9LLzxr4zvm7OvfvMMaosU6uBCEQwkB9j31iL2Rb8iX9qsnnnHMMxDY5P+KVBakObT/t7bwq/vt21+62R7+t2/Yhy+9mImNXkM/+dbdP7Ef3vOfdt2HP2TtRtm97/AdszayZasFgegG5O36D1ymUFmdBhfLjNr45IQ98bu9Vl5asW2HbbUwYOA7aYI35/J5e/zHd9hP73/YPveVr9rKRt6uuOzP7Qsf/2vz2psGaNgIMIQceuVJW1tds/ufX7YQY+Uz+5cI+yqQysxLisF/3bMR1u0yvHcwvPb76IToK2Wo9X3f/TpSTMmmDzvK3n36Sfb0vgU79YTjnJYkSgGyMt0xBL34S7vko39n137mZorct+9/79/t8mveZ3fd+nlbz5UECtJeBq7rFZbXKNiT7OIzTif/wnRi5XrNFlZXwOaaHXfk4Y63PPnYA7a/0LZXXy/ZUdMpW2E6Ki3P29gxb4MG0xxYKxhSNIIuYps8dehStd9mVO20gOU6xKdqS4/vh6l2rVAo2nlnn2XNQt5E74MaJzt4njWe3nM3dKJiNSD067s/awEkn1wuh9ZUk4qiqT/osHnAPACUWBPyNCQPhQRZUuvC91xpP/rKLTS2iM0/8Yi9DLo88FKe+TS4qTh4feph2UaPHjrK3WKzdrMCLFetxSHb/N9sAMUtpBQOJX4lNhsKRZnKklaEY2GZnXHumTb0QyBc0O2tZ5SORSDTsQJqr7SWd1Pc9NyMbdt+vPm5/c/CR6J4HA6DjBGMJcBfWCOFJpLTpgPfd8c37E1AVgcS9fBD99pSdWBvrFTsSPB7MhNxHl5k4Z145eXfPGjrG+sOUkXYNJhL6ettMnXmZyKCh8N+jEYUdcAgmSTGzz7RKSwecGkahMj5ODcU3RTJApGoi6a+ZUCHqe97t99K8w1GN9U1mhX0ji2KFCMp5cCGISQcsblExjW5px7+se07WLBfHyjZKPOoETEaunXp3r9+9iW78JIrnN5Tb+MtunRbsAtvkeQSYEHN2B6joMaOEuPpMuPhb14p2gpj5AmHTTEDBFyjUpQcQ9Q3qSeeJtbrexjGukF4k4y85NSTzW8Q2omJUYo07sa4NhvKoI7muB4LNerWrJSsTz288OLLttEe2qGNpk2h4o3QBE998w5bWMlbqE0zSyQsAW/RpFWE6uYYcHL0hAqOKTN8NBhyrAeHguD5RCUM1k8wtZ133BwUIkf0odLJJJQ76oRe9ZuBdFFqRuwy4LUdEmrAV7qvSvW46py3DiNQ121zwFIybTsgYtu2TtvM1LSlU0kWIgXYtMWg8egD99iX/uNJy8JI58ZTlqBQTz32cFsDDZbA6BQtf4nZogrKSLhOQwPGURI06IQRrsRkhcYRopoEURRhLLIlZucqBidQA0N0eO07NzNlGdbL8HMMj0uCVBYOHN3uOUTXl3/isUeyqNQ4Ciy/bnueehY1jE1RxDbw4GHbZ2zr1u12zFE77PHX1iFddTvisAmLaAaIxezF1w6iVkMxjppzY+BxaJsl1pKuGmRdFV8fT4r41YDjBPNshFqbx2jR+DocqNhoOiVimlSJILVbwbd9C68zB0ObmfzKDEBt5uKx0az7Hh3J2sz4GApd1rwffeHDQ3H5ICYl4Tr5UtGNjbX6pi764sFVx01CYDtDFypyFNmkj/4fVnYiYmVJqZKbGUTUSnhfaZHFCauFquXqHVe0B1ZLm2qG9R2ej6BwT+FxR40Dm/PvJEOOT3QWAIRCpeWi1QA40hR0JCQ1YlOe1FDTxrCmUvGl+WVoBBMZKkGSP3SARY1r0+hAcWS8Xdun3SLMOs4jy+S0BvE8MoyQpk7oNU+v51v2pp1TLtyPPL/gYFDSYgLPJ/jbLKKYdIIBnhR9lo6YSkSd+vbGatmJAN5iwaVditelWviaDHlAdRlXb+EQMqw0oCYwOsizvhpTBF69hrfqsZYjY0027rpbkq67K/BxRRms7rLQlqkxDltlo7At5ctWYXQs1Fqme4XHXpynUBHFpIeCGpNMT0oNpzxwkDjeXUFE03gawrADsE9JhfjJxgGEcfQouT0T21T/pI7HQC0N8wsIaOVGb1Pk5Q3qkeJv/jpS4lBvwpoG0CYqILg7lMsT0ihiaxS22HYKdZVCXmb41jCtoT3CIVEk7eQjt5BaCFAUex8IlLjlrpb42ecADbiN+slzjJnNrtJxk5aMUWfbAYN4RHP0wAloGhVrw75jB7XmwF4hpZukToba2cHkuIjAtozM36IuRqVKvPrDLw/bbWgwG66sr+OhqstnyeE6hBRhiUo9sVVQREUoJUx/71Ar6XjcjYLykrQjpXmRQjx86xScp+FGUYlcRZS3FM1qkrFQxZ7EMfly2aGJk8/7nltDEr5StY4zS7xH11mqlf3LOVuvtZ0ikQbVUqjY4mfe+845aThC0ekmRJcLOliPmkhyvaP5QIZJXlRXlQK3QcQiEUmAuoQL44muU/XSpIoH6gQoRt0ziH5H1aLZJIyB0lw3cXBTvu/glEqj6w4tMJAyUmF9Hd7JNuxZ4+ffza+7a6WJeMylo5RCpbTvnIawcMauw5xIJUFLBaNLPVW3mhlUhQdDwGLTSRnSdo6eHafQaeW60eH/0dEE+Tp0yCVFQ6EPk+sBjw6NZ9tuEIL7oCZLwpRGkaDm1Kj0Hq0RVJqpiQ6k+QOnmZSTVR58/g0iHnW5Lkoo+/WcK6mu5/b1Pn752cMU8rrCJS+LNSpMuveKSSWQvukNHNkTF9J1UgXEUMSEXjJM2o0uN3SRIamdsKEkRN39wCy3LWQjxd1wwrGkyQ0uMJSKrW7bUQUpd7ooUU9Q/eRwWBfyNDkSQ83AWBzwzAL8CmBxgIAxIdWfFDpZmNekj/eiTkgShMZdaBeRDp1BnU1NRsggAUz5q9lcuo0aFOoiv4ed3E1rcTAogbfdH7obmRrIMzs+4kCiw6ETGL9SKLsiloArOBbvScZEyhgjIYjKCgLkLj90U3QC+qguTZSCVTIk7G/eYHrfvPEDB3rd/g7BUkj0mE2cyAqs+rT/IjxG4pUuGRQhVZ0ogRqJLuaUdiHdF0PBky6FzOG3BClprFWUjYj7mZri74peVpwp5rsb0VXgsQqz3DaZYqgvk14xJxBLa9W1lwRjOUkzeY+9W72uqxORxEw8ttdPhkI/W2+1blhcKaM6xLh5jFqx2HL3tgW6qvTIDLJfuxvZPCxRkooW5H8JsXnCXeP/c47b7lBK053kR6GPNtZFxAJELUQkpugLo0RWF4FtLummJxJgf8JFNg4tOfnwnczTTdONaYU1los1m55NuFqZnZowj1oQLZcRa7zWHvT3etdc8M6zIjH/0SAh6FFEmjPV8DWgZ9xltOduaYo14AsGGpEmCYbreqfT77mPGGxy/iHIEXT5vlZ2k5KDR3VRUYcUUdAVlDcYuguLDoeWAq73RKObgm1QeBT0XC04iRGDJ/gWkRM46O5hkdQrooiovrLR6E43qF532Tm3490bxD1qTdEJmGRcs2uXNJKKHOE2BrqAeCtytQWvhWFzupyIgxYreWqIFHS1AWea5ValyL2yUkJd2Q0t/K5LwCmUBDfCgm5b4D7qOW8gobuZwd0X152ELrQK4m597KDe3dRi0wCLUlI3+IN+4Gt3P/T4jd4fPicx7PiPcgPyFuVup6vbdLqoyAuLKpRSjZXDah6SwdM0km3jGYfXo+mY2yCsS46GtHyaFkVfg37oQNFQyF1FKT1VI0orXeeKKwnz06RPjdQRza5Sax08GJIih1dmcIZeW8yV3V5qnJVWa6/fb5597e17Sn/8sMfuay7NTo/EdpPfN4xls3TJirsJ1GHEhwrcgakYhc/qxLpJySDyqjcMSSlNWn0nDnCPyyZCbjUwwa7IoD6soU+8SFnWSNikbtSM1DQTsdCmUOsp/VpOYlS3FtroXlqR1UcYAp5u/ltfa3Zju/c89ljp/3xa5Q9f/7X7uh35anl3qdE6Pl9pvkUbSu/Rhy+E+7q0GIMjpdWs8GKUgha9Vc4WdGsIYjUpMkUkqo8IgDiiFlMMJ/oog24Y9VkLUWx1Jt2MCm3UQzpwoKgfci1LNaaJrYShvU5vnrf+DFje87nv7nnsT8/7v0z4/4GgBTU9AAAAAElFTkSuQmCC" -} - diff --git a/agent/templates/deep_research.json b/agent/templates/deep_research.json index 49bbda8ac..4e53bfd28 100644 --- a/agent/templates/deep_research.json +++ b/agent/templates/deep_research.json @@ -1,8 +1,12 @@ { "id": 1, - "title": "Deep Research", - "description": "For professionals in sales, marketing, policy, or consulting, the Multi-Agent Deep Research Agent conducts structured, multi-step investigations across diverse sources and delivers consulting-style reports with clear citations.", + "title": { + "en": "Deep Research", + "zh": "深度研究"}, + "description": { + "en": "For professionals in sales, marketing, policy, or consulting, the Multi-Agent Deep Research Agent conducts structured, multi-step investigations across diverse sources and delivers consulting-style reports with clear citations.", + "zh": "专为销售、市场、政策或咨询领域的专业人士设计，多智能体的深度研究会结合多源信息进行结构化、多步骤地回答问题，并附带有清晰的引用。"}, "canvas_type": "Recommended", "dsl": { "components": { diff --git a/agent/templates/deep_search_r.json b/agent/templates/deep_search_r.json index acce322da..4c34b63c8 100644 --- a/agent/templates/deep_search_r.json +++ b/agent/templates/deep_search_r.json @@ -1,8 +1,12 @@ { "id": 6, - "title": "Deep Research", - "description": "For professionals in sales, marketing, policy, or consulting, the Multi-Agent Deep Research Agent conducts structured, multi-step investigations across diverse sources and delivers consulting-style reports with clear citations.", + "title": { + "en": "Deep Research", + "zh": "深度研究"}, + "description": { + "en": "For professionals in sales, marketing, policy, or consulting, the Multi-Agent Deep Research Agent conducts structured, multi-step investigations across diverse sources and delivers consulting-style reports with clear citations.", + "zh": "专为销售、市场、政策或咨询领域的专业人士设计，多智能体的深度研究会结合多源信息进行结构化、多步骤地回答问题，并附带有清晰的引用。"}, "canvas_type": "Agent", "dsl": { "components": { diff --git a/agent/templates/generate_SEO_blog.json b/agent/templates/generate_SEO_blog.json index 9d8c062b1..2107e5050 100644 --- a/agent/templates/generate_SEO_blog.json +++ b/agent/templates/generate_SEO_blog.json @@ -1,7 +1,11 @@ { "id": 8, - "title": "Generate SEO Blog", - "description": "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.", + "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": { diff --git a/agent/templates/image_lingo.json b/agent/templates/image_lingo.json index 22b089403..0f874d75c 100644 --- a/agent/templates/image_lingo.json +++ b/agent/templates/image_lingo.json @@ -1,7 +1,11 @@ { "id": 13, - "title": "ImageLingo", - "description": "ImageLingo lets you snap any photo containing text—menus, signs, or documents—and instantly recognize and translate it into your language of choice using advanced AI-powered translation technology.", + "title": { + "en": "ImageLingo", + "zh": "图片解析"}, + "description": { + "en": "ImageLingo lets you snap any photo containing text—menus, signs, or documents—and instantly recognize and translate it into your language of choice using advanced AI-powered translation technology.", + "zh": "多模态大模型允许您拍摄任何包含文本的照片——菜单、标志或文档——立即识别并转换成您选择的语言。"}, "canvas_type": "Consumer App", "dsl": { "components": { diff --git a/agent/templates/knowledge_base_report.json b/agent/templates/knowledge_base_report.json index d22e76da2..581b5e2f1 100644 --- a/agent/templates/knowledge_base_report.json +++ b/agent/templates/knowledge_base_report.json @@ -1,7 +1,11 @@ { "id": 20, - "title": "Report Agent Using Knowledge Base", - "description": "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", + "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": { diff --git a/agent/templates/knowledge_base_report_r.json b/agent/templates/knowledge_base_report_r.json new file mode 100644 index 000000000..d237000ec --- /dev/null +++ b/agent/templates/knowledge_base_report_r.json @@ -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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" +} \ No newline at end of file diff --git a/agent/templates/market_generate_seo_blog.json b/agent/templates/market_generate_seo_blog.json index 905eeea53..4c437a560 100644 --- a/agent/templates/market_generate_seo_blog.json +++ b/agent/templates/market_generate_seo_blog.json @@ -1,7 +1,11 @@ { "id": 12, - "title": "Generate SEO Blog", - "description": "This workflow automatically generates a complete SEO-optimized blog article based on a simple user input. You don’t need any writing experience. Just provide a topic or short request — the system will handle the rest.", + "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": { diff --git a/agent/templates/seo_blog.json b/agent/templates/seo_blog.json index 861e6200e..fb9e4bb86 100644 --- a/agent/templates/seo_blog.json +++ b/agent/templates/seo_blog.json @@ -1,7 +1,11 @@ { "id": 4, - "title": "Generate SEO Blog", - "description": "This workflow automatically generates a complete SEO-optimized blog article based on a simple user input. You don’t need any writing experience. Just provide a topic or short request — the system will handle the rest.", + "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": { diff --git a/agent/templates/sql_assistant.json b/agent/templates/sql_assistant.json index 810f1a1f6..d11de2363 100644 --- a/agent/templates/sql_assistant.json +++ b/agent/templates/sql_assistant.json @@ -1,7 +1,11 @@ { "id": 17, - "title": "SQL Assistant", - "description": "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. ", + "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": { diff --git a/agent/templates/technical_docs.json b/agent/templates/technical_docs.json deleted file mode 100644 index 83d4f8422..000000000 --- a/agent/templates/technical_docs.json +++ /dev/null @@ -1,331 +0,0 @@ - -{ - "id": 3, - "title": "Technical Docs QA", - "description": "This is a document question-and-answer system based on a knowledge base. When a user asks a question, it retrieves relevant document content to provide accurate answers.", - "canvas_type": "Recommended", - "dsl": { - "components": { - "Agent:StalePandasDream": { - "downstream": [ - "Message:BrownPugsStick" - ], - "obj": { - "component_name": "Agent", - "params": { - "delay_after_error": 1, - "description": "", - "exception_comment": "", - "exception_default_value": "", - "exception_goto": [], - "exception_method": null, - "frequencyPenaltyEnabled": false, - "frequency_penalty": 0.7, - "llm_id": "deepseek-chat@DeepSeek", - "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": "The user query is {sys.query}", - "role": "user" - } - ], - "sys_prompt": "# Role\n\nYou are the **Docs QA Agent**, a specialized knowledge base assistant responsible for providing accurate answers based strictly on the connected documentation repository.\n\n# Core Principles\n\n1. **Knowledge Base Only**: Answer questions EXCLUSIVELY based on information retrieved from the connected knowledge base.\n\n2. **No Content Creation**: Never generate, infer, or create information that is not explicitly present in the retrieved documents.\n\n3. **Source Transparency**: Always indicate when information comes from the knowledge base vs. when it's unavailable.\n\n4. **Accuracy Over Completeness**: Prefer incomplete but accurate answers over complete but potentially inaccurate ones.\n\n# Response Guidelines\n\n## When Information is Available\n\n- Provide direct answers based on retrieved content\n\n- Quote relevant sections when helpful\n\n- Cite the source document/section if available\n\n- Use phrases like: \"According to the documentation...\" or \"Based on the knowledge base...\"\n\n## When Information is Unavailable\n\n- Clearly state: \"I cannot find this information in the current knowledge base.\"\n\n- Do NOT attempt to fill gaps with general knowledge\n\n- Suggest alternative questions that might be covered in the docs\n\n- Use phrases like: \"The documentation does not cover...\" or \"This information is not available in the knowledge base.\"\n\n# Response Format\n\n```markdown\n\n## Answer\n\n[Your response based strictly on knowledge base content]\n\n**Always do these:**\n\n- Use the Retrieval tool for every question\n\n- Be transparent about information availability\n\n- Stick to documented facts only\n\n- Acknowledge knowledge base limitations\n\n", - "temperature": 0.1, - "temperatureEnabled": true, - "tools": [ - { - "component_name": "Retrieval", - "name": "Retrieval", - "params": { - "cross_languages": [], - "description": "This is a technical docs knowledge bases.", - "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": 0.3, - "user_prompt": "", - "visual_files_var": "" - } - }, - "upstream": [ - "begin" - ] - }, - "Message:BrownPugsStick": { - "downstream": [], - "obj": { - "component_name": "Message", - "params": { - "content": [ - "{Agent:StalePandasDream@content}" - ] - } - }, - "upstream": [ - "Agent:StalePandasDream" - ] - }, - "begin": { - "downstream": [ - "Agent:StalePandasDream" - ], - "obj": { - "component_name": "Begin", - "params": {} - }, - "upstream": [] - } - }, - "globals": { - "sys.conversation_turns": 0, - "sys.files": [], - "sys.query": "", - "sys.user_id": "" - }, - "graph": { - "edges": [ - { - "data": { - "isHovered": false - }, - "id": "xy-edge__beginstart-Agent:StalePandasDreamend", - "source": "begin", - "sourceHandle": "start", - "target": "Agent:StalePandasDream", - "targetHandle": "end" - }, - { - "data": { - "isHovered": false - }, - "id": "xy-edge__Agent:StalePandasDreamstart-Message:BrownPugsStickend", - "source": "Agent:StalePandasDream", - "sourceHandle": "start", - "target": "Message:BrownPugsStick", - "targetHandle": "end" - }, - { - "id": "xy-edge__Agent:StalePandasDreamtool-Tool:PrettyMasksFloatend", - "source": "Agent:StalePandasDream", - "sourceHandle": "tool", - "target": "Tool:PrettyMasksFloat", - "targetHandle": "end" - } - ], - "nodes": [ - { - "data": { - "label": "Begin", - "name": "begin" - }, - "dragging": false, - "id": "begin", - "measured": { - "height": 48, - "width": 200 - }, - "position": { - "x": 47.500000000000014, - "y": 199.5 - }, - "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": 0.7, - "llm_id": "deepseek-chat@DeepSeek", - "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": "The user query is {sys.query}", - "role": "user" - } - ], - "sys_prompt": "# Role\n\nYou are the **Docs QA Agent**, a specialized knowledge base assistant responsible for providing accurate answers based strictly on the connected documentation repository.\n\n# Core Principles\n\n1. **Knowledge Base Only**: Answer questions EXCLUSIVELY based on information retrieved from the connected knowledge base.\n\n2. **No Content Creation**: Never generate, infer, or create information that is not explicitly present in the retrieved documents.\n\n3. **Source Transparency**: Always indicate when information comes from the knowledge base vs. when it's unavailable.\n\n4. **Accuracy Over Completeness**: Prefer incomplete but accurate answers over complete but potentially inaccurate ones.\n\n# Response Guidelines\n\n## When Information is Available\n\n- Provide direct answers based on retrieved content\n\n- Quote relevant sections when helpful\n\n- Cite the source document/section if available\n\n- Use phrases like: \"According to the documentation...\" or \"Based on the knowledge base...\"\n\n## When Information is Unavailable\n\n- Clearly state: \"I cannot find this information in the current knowledge base.\"\n\n- Do NOT attempt to fill gaps with general knowledge\n\n- Suggest alternative questions that might be covered in the docs\n\n- Use phrases like: \"The documentation does not cover...\" or \"This information is not available in the knowledge base.\"\n\n# Response Format\n\n```markdown\n\n## Answer\n\n[Your response based strictly on knowledge base content]\n\n**Always do these:**\n\n- Use the Retrieval tool for every question\n\n- Be transparent about information availability\n\n- Stick to documented facts only\n\n- Acknowledge knowledge base limitations\n\n", - "temperature": 0.1, - "temperatureEnabled": true, - "tools": [ - { - "component_name": "Retrieval", - "name": "Retrieval", - "params": { - "cross_languages": [], - "description": "This is a technical docs knowledge bases.", - "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": 0.3, - "user_prompt": "", - "visual_files_var": "" - }, - "label": "Agent", - "name": "Docs QA Agent" - }, - "dragging": false, - "id": "Agent:StalePandasDream", - "measured": { - "height": 87, - "width": 200 - }, - "position": { - "x": 351.5, - "y": 231 - }, - "selected": true, - "sourcePosition": "right", - "targetPosition": "left", - "type": "agentNode" - }, - { - "data": { - "form": { - "content": [ - "{Agent:StalePandasDream@content}" - ] - }, - "label": "Message", - "name": "Message_0" - }, - "dragging": false, - "id": "Message:BrownPugsStick", - "measured": { - "height": 56, - "width": 200 - }, - "position": { - "x": 671.5, - "y": 192.5 - }, - "selected": false, - "sourcePosition": "right", - "targetPosition": "left", - "type": "messageNode" - }, - { - "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:PrettyMasksFloat", - "measured": { - "height": 48, - "width": 200 - }, - "position": { - "x": 234.5, - "y": 370.5 - }, - "selected": false, - "sourcePosition": "right", - "targetPosition": "left", - "type": "toolNode" - }, - { - "data": { - "form": { - "text": "This is a document question-and-answer system based on a knowledge base. When a user asks a question, it retrieves relevant document content to provide accurate answers.\nProcess Steps\n\n#Begin\n\nWorkflow entry: Receive user questions\n\nDocs QA Agent\n\nAI Model: deepseek-chat\n\nFunction: Analyze user questions and understand query intent\n\nRetrieval\n\nFunction: Search for relevant information from connected document knowledge bases\n\nFeature: Ensures answers are based on actual document content\n\nMessage_0 (Output Response)\n\nReturns accurate answers to the user based on the knowledge base\n\n#Core Features\n\nAccuracy: Answers are strictly based on knowledge base content\n\nReliability: Avoid AI illusions and only provide information that is verifiable\n\nSimplicity: Linear process with fast response\n\n#Applicable Scenarios\n\nProduct Documentation Query\n\nTechnical Support Q&A\n\nInternal Enterprise Knowledge Base Search\n\nUser Manual Consultation" - }, - "label": "Note", - "name": "Workflow Overall Description" - }, - "dragHandle": ".note-drag-handle", - "dragging": false, - "height": 154, - "id": "Note:SwiftSuitsFlow", - "measured": { - "height": 154, - "width": 374 - }, - "position": { - "x": 349.65276636527506, - "y": 28.869446726944993 - }, - "resizing": false, - "selected": false, - "sourcePosition": "right", - "targetPosition": "left", - "type": "noteNode", - "width": 374 - } - ] - }, - "history": [], - "messages": [], - "path": [], - "retrieval": [] - }, - "avatar": "data:image/png;base64,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" -} - diff --git a/agent/templates/technical_docs_qa.json b/agent/templates/technical_docs_qa.json index 6889d17b9..101d850b6 100644 --- a/agent/templates/technical_docs_qa.json +++ b/agent/templates/technical_docs_qa.json @@ -1,8 +1,12 @@ { "id": 9, - "title": "Technical Docs QA", - "description": "This is a document question-and-answer system based on a knowledge base. When a user asks a question, it retrieves relevant document content to provide accurate answers.", + "title": { + "en": "Technical Docs QA", + "zh": "技术文档问答"}, + "description": { + "en": "This is a document question-and-answer system based on a knowledge base. When a user asks a question, it retrieves relevant document content to provide accurate answers.", + "zh": "基于知识库的文档问答系统，当用户提出问题时，会检索相关本地文档并提供准确回答。"}, "canvas_type": "Customer Support", "dsl": { "components": { diff --git a/agent/templates/trip_planner.json b/agent/templates/trip_planner.json index 7e043570b..322cf7be0 100644 --- a/agent/templates/trip_planner.json +++ b/agent/templates/trip_planner.json @@ -1,9 +1,13 @@ { "id": 14, - "title": "Trip Planner", - "description": "This smart trip planner utilizes LLM technology to automatically generate customized travel itineraries, with optional tool integration for enhanced reliability.", - "canvas_type": "Consumer App", + "title": { + "en": "Trip Planner", + "zh": "旅行规划"}, + "description": + "en": "This smart trip planner utilizes LLM technology to automatically generate customized travel itineraries, with optional tool integration for enhanced reliability.", + "zh": "智能旅行规划将利用大模型自动生成定制化的旅行行程，附带可选工具集成，以增强可靠性。"}, + "canvas_type": "Consumer App", "dsl": { "components": { "Agent:OddGuestsPump": { diff --git a/agent/templates/web_search_assistant.json b/agent/templates/web_search_assistant.json index 08d550abe..0e532d1d6 100644 --- a/agent/templates/web_search_assistant.json +++ b/agent/templates/web_search_assistant.json @@ -1,9 +1,13 @@ { "id": 16, - "title": "WebSearch Assistant", - "description": "A chat assistant template that integrates information extracted from a knowledge base and web searches to respond to queries. Let's start by setting up your knowledge base in 'Retrieval'!", - "canvas_type": "Other", + "title": { + "en": "WebSearch Assistant", + "zh": "网页搜索助手"}, + "description": { + "en": "A chat assistant template that integrates information extracted from a knowledge base and web searches to respond to queries. Let's start by setting up your knowledge base in 'Retrieval'!", + "zh": "集成了从知识库和网络搜索中提取的信息回答用户问题。让我们从设置您的知识库开始检索！"}, + "canvas_type": "Other", "dsl": { "components": { "Agent:SmartSchoolsCross": {