mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-08-04 23:00:30 +08:00
Fix: The tool icon for the agent operator created from the template is not clickable. (#17794)
This commit is contained in:
balibabu
@@ -1,306 +1,308 @@
|
||||
{
|
||||
"id": "41",
|
||||
"title": {
|
||||
"en": "CAJAL scientific paper agent",
|
||||
"de": "CAJAL-Agent für wissenschaftliche Arbeiten",
|
||||
"zh": "CAJAL 科学论文助手"
|
||||
},
|
||||
"description": {
|
||||
"en": "A local-first scientific paper generation agent for RAGFlow. It is preconfigured for Agnuxo/CAJAL-4B-P2PCLAW through Ollama, retrieves knowledge-base evidence, and drafts citation-grounded LaTeX-ready academic sections.",
|
||||
"de": "Ein lokal ausgerichteter Agent zur Erstellung wissenschaftlicher Arbeiten in RAGFlow. Er ist für Agnuxo/CAJAL-4B-P2PCLAW über Ollama vorkonfiguriert, ruft Evidenz aus der Wissensdatenbank ab und erstellt zitationsgestützte, LaTeX-fähige akademische Abschnitte.",
|
||||
"zh": "面向 RAGFlow 的本地优先科学论文生成助手。该模板预配置 Agnuxo/CAJAL-4B-P2PCLAW（Ollama），可检索知识库证据，并生成带引用依据、适合 LaTeX 的学术章节。"
|
||||
},
|
||||
"canvas_type": "Agent",
|
||||
"canvas_types": [
|
||||
"Agent",
|
||||
"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": "agnuxo/cajal-4b-p2pclaw@Ollama",
|
||||
"maxTokensEnabled": true,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 3,
|
||||
"max_tokens": 32768,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
}
|
||||
},
|
||||
"parameter": "Precise",
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.5,
|
||||
"prompts": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "# Research request\n{sys.query}\n\nUse the configured knowledge base retrieval tool before drafting. If no evidence is retrieved, state that limitation clearly."
|
||||
}
|
||||
],
|
||||
"sys_prompt": "## Role & Task\nYou are **CAJAL**, a local-first scientific writing agent specialized in citation-grounded paper generation.\n\nUse RAGFlow retrieval results as the source of truth. Write precise academic content that can be pasted into a paper draft, technical report, or LaTeX manuscript. You are optimized for the local GGUF model `Agnuxo/CAJAL-4B-P2PCLAW` served through Ollama as `agnuxo/cajal-4b-p2pclaw`.\n\n## Operating Rules\n1. Decompose the user request into research goals, target section type, expected citation style, and missing evidence.\n2. Retrieve relevant knowledge-base passages before drafting factual claims.\n3. Ground every substantive claim in retrieved evidence. If evidence is missing, mark it as a limitation instead of inventing a citation.\n4. Prefer structured scientific writing: abstract, introduction, related work, methodology, experiments, results, limitations, and conclusion.\n5. Use LaTeX formatting for equations, symbols, algorithms, tables, and section headings when it helps the manuscript.\n6. Preserve traceability: cite source titles, document names, page numbers, or chunk identifiers when available in retrieved context.\n7. Keep language technical, concise, and reproducible. Avoid marketing language and vague generalizations.\n\n## Output Contract\nReturn one of the following, depending on the user request:\n- A complete paper section with citation markers and a short evidence map.\n- A literature review organized by themes, methods, findings, and gaps.\n- A methodology or experiment section with reproducible steps, assumptions, and limitations.\n- A LaTeX-ready abstract, introduction, or conclusion.\n\nAlways include:\n- **Draft**: the requested scientific content.\n- **Evidence used**: concise bullets mapping claims to retrieved sources.\n- **Limitations**: missing evidence, weak support, or assumptions that require verification.\n",
|
||||
"temperature": 0.2,
|
||||
"temperatureEnabled": true,
|
||||
"tools": [
|
||||
{
|
||||
"component_name": "Retrieval",
|
||||
"name": "Retrieval",
|
||||
"params": {
|
||||
"cross_languages": [],
|
||||
"description": "Retrieve papers, reports, datasets, and notes that ground CAJAL scientific writing outputs.",
|
||||
"empty_response": "",
|
||||
"kb_ids": [],
|
||||
"retrieval_from": "dataset",
|
||||
"keywords_similarity_weight": 0.7,
|
||||
"outputs": {
|
||||
"formalized_content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
"id": "41",
|
||||
"title": {
|
||||
"en": "CAJAL scientific paper agent",
|
||||
"de": "CAJAL-Agent für wissenschaftliche Arbeiten",
|
||||
"zh": "CAJAL 科学论文助手"
|
||||
},
|
||||
"description": {
|
||||
"en": "A local-first scientific paper generation agent for RAGFlow. It is preconfigured for Agnuxo/CAJAL-4B-P2PCLAW through Ollama, retrieves knowledge-base evidence, and drafts citation-grounded LaTeX-ready academic sections.",
|
||||
"de": "Ein lokal ausgerichteter Agent zur Erstellung wissenschaftlicher Arbeiten in RAGFlow. Er ist für Agnuxo/CAJAL-4B-P2PCLAW über Ollama vorkonfiguriert, ruft Evidenz aus der Wissensdatenbank ab und erstellt zitationsgestützte, LaTeX-fähige akademische Abschnitte.",
|
||||
"zh": "面向 RAGFlow 的本地优先科学论文生成助手。该模板预配置 Agnuxo/CAJAL-4B-P2PCLAW（Ollama），可检索知识库证据，并生成带引用依据、适合 LaTeX 的学术章节。"
|
||||
},
|
||||
"canvas_type": "Agent",
|
||||
"canvas_types": [
|
||||
"Agent",
|
||||
"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": "agnuxo/cajal-4b-p2pclaw@Ollama",
|
||||
"maxTokensEnabled": true,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 3,
|
||||
"max_tokens": 32768,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
}
|
||||
},
|
||||
"parameter": "Precise",
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.5,
|
||||
"prompts": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "# Research request\n{sys.query}\n\nUse the configured knowledge base retrieval tool before drafting. If no evidence is retrieved, state that limitation clearly."
|
||||
}
|
||||
],
|
||||
"sys_prompt": "## Role & Task\nYou are **CAJAL**, a local-first scientific writing agent specialized in citation-grounded paper generation.\n\nUse RAGFlow retrieval results as the source of truth. Write precise academic content that can be pasted into a paper draft, technical report, or LaTeX manuscript. You are optimized for the local GGUF model `Agnuxo/CAJAL-4B-P2PCLAW` served through Ollama as `agnuxo/cajal-4b-p2pclaw`.\n\n## Operating Rules\n1. Decompose the user request into research goals, target section type, expected citation style, and missing evidence.\n2. Retrieve relevant knowledge-base passages before drafting factual claims.\n3. Ground every substantive claim in retrieved evidence. If evidence is missing, mark it as a limitation instead of inventing a citation.\n4. Prefer structured scientific writing: abstract, introduction, related work, methodology, experiments, results, limitations, and conclusion.\n5. Use LaTeX formatting for equations, symbols, algorithms, tables, and section headings when it helps the manuscript.\n6. Preserve traceability: cite source titles, document names, page numbers, or chunk identifiers when available in retrieved context.\n7. Keep language technical, concise, and reproducible. Avoid marketing language and vague generalizations.\n\n## Output Contract\nReturn one of the following, depending on the user request:\n- A complete paper section with citation markers and a short evidence map.\n- A literature review organized by themes, methods, findings, and gaps.\n- A methodology or experiment section with reproducible steps, assumptions, and limitations.\n- A LaTeX-ready abstract, introduction, or conclusion.\n\nAlways include:\n- **Draft**: the requested scientific content.\n- **Evidence used**: concise bullets mapping claims to retrieved sources.\n- **Limitations**: missing evidence, weak support, or assumptions that require verification.\n",
|
||||
"temperature": 0.2,
|
||||
"temperatureEnabled": true,
|
||||
"tools": [
|
||||
{
|
||||
"component_name": "Retrieval",
|
||||
"name": "Retrieval",
|
||||
"params": {
|
||||
"cross_languages": [],
|
||||
"description": "Retrieve papers, reports, datasets, and notes that ground CAJAL scientific writing outputs.",
|
||||
"empty_response": "",
|
||||
"kb_ids": [],
|
||||
"retrieval_from": "dataset",
|
||||
"keywords_similarity_weight": 0.7,
|
||||
"outputs": {
|
||||
"formalized_content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
}
|
||||
},
|
||||
"rerank_id": "",
|
||||
"similarity_threshold": 0.2,
|
||||
"top_k": 1024,
|
||||
"top_n": 10,
|
||||
"use_kg": false
|
||||
},
|
||||
"id": "Retrieval:FairBoatsBurn"
|
||||
}
|
||||
],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.75,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
}
|
||||
},
|
||||
"rerank_id": "",
|
||||
"similarity_threshold": 0.2,
|
||||
"top_k": 1024,
|
||||
"top_n": 10,
|
||||
"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": "Hi, I am CAJAL in RAGFlow. Add research papers or datasets to your knowledge base, then ask me to draft a citation-grounded paper section, literature review, methodology, or LaTeX-ready abstract."
|
||||
}
|
||||
},
|
||||
"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
|
||||
}
|
||||
],
|
||||
"nodes": [
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"enablePrologue": true,
|
||||
"inputs": {},
|
||||
"mode": "conversational",
|
||||
"prologue": "Hi, I am CAJAL in RAGFlow. Add research papers or datasets to your knowledge base, then ask me to draft a citation-grounded paper section, literature review, methodology, or LaTeX-ready abstract."
|
||||
},
|
||||
"upstream": [
|
||||
"begin"
|
||||
]
|
||||
},
|
||||
"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}"
|
||||
]
|
||||
"Message:OrangeYearsShine": {
|
||||
"downstream": [],
|
||||
"obj": {
|
||||
"component_name": "Message",
|
||||
"params": {
|
||||
"content": [
|
||||
"{Agent:NewPumasLick@content}"
|
||||
]
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"Agent:NewPumasLick"
|
||||
]
|
||||
},
|
||||
"label": "Message",
|
||||
"name": "Scientific Draft"
|
||||
},
|
||||
"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"
|
||||
"begin": {
|
||||
"downstream": [
|
||||
"Agent:NewPumasLick"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Begin",
|
||||
"params": {
|
||||
"enablePrologue": true,
|
||||
"inputs": {},
|
||||
"mode": "conversational",
|
||||
"prologue": "Hi, I am CAJAL in RAGFlow. Add research papers or datasets to your knowledge base, then ask me to draft a citation-grounded paper section, literature review, methodology, or LaTeX-ready abstract."
|
||||
}
|
||||
},
|
||||
"upstream": []
|
||||
}
|
||||
},
|
||||
{
|
||||
"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": "agnuxo/cajal-4b-p2pclaw@Ollama",
|
||||
"maxTokensEnabled": true,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 3,
|
||||
"max_tokens": 32768,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
}
|
||||
},
|
||||
"parameter": "Precise",
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.5,
|
||||
"prompts": [
|
||||
"globals": {
|
||||
"sys.conversation_turns": 0,
|
||||
"sys.files": [],
|
||||
"sys.query": "",
|
||||
"sys.user_id": ""
|
||||
},
|
||||
"graph": {
|
||||
"edges": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "# Research request\n{sys.query}\n\nUse the configured knowledge base retrieval tool before drafting. If no evidence is retrieved, state that limitation clearly."
|
||||
}
|
||||
],
|
||||
"sys_prompt": "## Role & Task\nYou are **CAJAL**, a local-first scientific writing agent specialized in citation-grounded paper generation.\n\nUse RAGFlow retrieval results as the source of truth. Write precise academic content that can be pasted into a paper draft, technical report, or LaTeX manuscript. You are optimized for the local GGUF model `Agnuxo/CAJAL-4B-P2PCLAW` served through Ollama as `agnuxo/cajal-4b-p2pclaw`.\n\n## Operating Rules\n1. Decompose the user request into research goals, target section type, expected citation style, and missing evidence.\n2. Retrieve relevant knowledge-base passages before drafting factual claims.\n3. Ground every substantive claim in retrieved evidence. If evidence is missing, mark it as a limitation instead of inventing a citation.\n4. Prefer structured scientific writing: abstract, introduction, related work, methodology, experiments, results, limitations, and conclusion.\n5. Use LaTeX formatting for equations, symbols, algorithms, tables, and section headings when it helps the manuscript.\n6. Preserve traceability: cite source titles, document names, page numbers, or chunk identifiers when available in retrieved context.\n7. Keep language technical, concise, and reproducible. Avoid marketing language and vague generalizations.\n\n## Output Contract\nReturn one of the following, depending on the user request:\n- A complete paper section with citation markers and a short evidence map.\n- A literature review organized by themes, methods, findings, and gaps.\n- A methodology or experiment section with reproducible steps, assumptions, and limitations.\n- A LaTeX-ready abstract, introduction, or conclusion.\n\nAlways include:\n- **Draft**: the requested scientific content.\n- **Evidence used**: concise bullets mapping claims to retrieved sources.\n- **Limitations**: missing evidence, weak support, or assumptions that require verification.\n",
|
||||
"temperature": 0.2,
|
||||
"temperatureEnabled": true,
|
||||
"tools": [
|
||||
{
|
||||
"component_name": "Retrieval",
|
||||
"name": "Retrieval",
|
||||
"params": {
|
||||
"cross_languages": [],
|
||||
"description": "Retrieve papers, reports, datasets, and notes that ground CAJAL scientific writing outputs.",
|
||||
"empty_response": "",
|
||||
"kb_ids": [],
|
||||
"retrieval_from": "dataset",
|
||||
"keywords_similarity_weight": 0.7,
|
||||
"outputs": {
|
||||
"formalized_content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
}
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"rerank_id": "",
|
||||
"similarity_threshold": 0.2,
|
||||
"top_k": 1024,
|
||||
"top_n": 10,
|
||||
"use_kg": 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
|
||||
}
|
||||
],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.75,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
},
|
||||
"label": "Agent",
|
||||
"name": "CAJAL Writer"
|
||||
},
|
||||
"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"
|
||||
}
|
||||
]
|
||||
],
|
||||
"nodes": [
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"enablePrologue": true,
|
||||
"inputs": {},
|
||||
"mode": "conversational",
|
||||
"prologue": "Hi, I am CAJAL in RAGFlow. Add research papers or datasets to your knowledge base, then ask me to draft a citation-grounded paper section, literature review, methodology, or LaTeX-ready abstract."
|
||||
},
|
||||
"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": "Scientific Draft"
|
||||
},
|
||||
"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": "agnuxo/cajal-4b-p2pclaw@Ollama",
|
||||
"maxTokensEnabled": true,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 3,
|
||||
"max_tokens": 32768,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
}
|
||||
},
|
||||
"parameter": "Precise",
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.5,
|
||||
"prompts": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "# Research request\n{sys.query}\n\nUse the configured knowledge base retrieval tool before drafting. If no evidence is retrieved, state that limitation clearly."
|
||||
}
|
||||
],
|
||||
"sys_prompt": "## Role & Task\nYou are **CAJAL**, a local-first scientific writing agent specialized in citation-grounded paper generation.\n\nUse RAGFlow retrieval results as the source of truth. Write precise academic content that can be pasted into a paper draft, technical report, or LaTeX manuscript. You are optimized for the local GGUF model `Agnuxo/CAJAL-4B-P2PCLAW` served through Ollama as `agnuxo/cajal-4b-p2pclaw`.\n\n## Operating Rules\n1. Decompose the user request into research goals, target section type, expected citation style, and missing evidence.\n2. Retrieve relevant knowledge-base passages before drafting factual claims.\n3. Ground every substantive claim in retrieved evidence. If evidence is missing, mark it as a limitation instead of inventing a citation.\n4. Prefer structured scientific writing: abstract, introduction, related work, methodology, experiments, results, limitations, and conclusion.\n5. Use LaTeX formatting for equations, symbols, algorithms, tables, and section headings when it helps the manuscript.\n6. Preserve traceability: cite source titles, document names, page numbers, or chunk identifiers when available in retrieved context.\n7. Keep language technical, concise, and reproducible. Avoid marketing language and vague generalizations.\n\n## Output Contract\nReturn one of the following, depending on the user request:\n- A complete paper section with citation markers and a short evidence map.\n- A literature review organized by themes, methods, findings, and gaps.\n- A methodology or experiment section with reproducible steps, assumptions, and limitations.\n- A LaTeX-ready abstract, introduction, or conclusion.\n\nAlways include:\n- **Draft**: the requested scientific content.\n- **Evidence used**: concise bullets mapping claims to retrieved sources.\n- **Limitations**: missing evidence, weak support, or assumptions that require verification.\n",
|
||||
"temperature": 0.2,
|
||||
"temperatureEnabled": true,
|
||||
"tools": [
|
||||
{
|
||||
"component_name": "Retrieval",
|
||||
"name": "Retrieval",
|
||||
"params": {
|
||||
"cross_languages": [],
|
||||
"description": "Retrieve papers, reports, datasets, and notes that ground CAJAL scientific writing outputs.",
|
||||
"empty_response": "",
|
||||
"kb_ids": [],
|
||||
"retrieval_from": "dataset",
|
||||
"keywords_similarity_weight": 0.7,
|
||||
"outputs": {
|
||||
"formalized_content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
}
|
||||
},
|
||||
"rerank_id": "",
|
||||
"similarity_threshold": 0.2,
|
||||
"top_k": 1024,
|
||||
"top_n": 10,
|
||||
"use_kg": false
|
||||
},
|
||||
"id": "Retrieval:GrandLionsJump"
|
||||
}
|
||||
],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.75,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
},
|
||||
"label": "Agent",
|
||||
"name": "CAJAL Writer"
|
||||
},
|
||||
"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"
|
||||
}
|
||||
]
|
||||
},
|
||||
"history": [],
|
||||
"memory": [],
|
||||
"messages": [],
|
||||
"path": [],
|
||||
"retrieval": []
|
||||
},
|
||||
"history": [],
|
||||
"memory": [],
|
||||
"messages": [],
|
||||
"path": [],
|
||||
"retrieval": []
|
||||
},
|
||||
"avatar": "data:image/png;base64,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"
|
||||
}
|
||||
"avatar": "data:image/png;base64,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"
|
||||
}
|
||||
@@ -96,6 +96,7 @@
|
||||
{
|
||||
"component_name": "TavilySearch",
|
||||
"name": "TavilySearch",
|
||||
"id": "TavilySearch:FairToolsLive",
|
||||
"params": {
|
||||
"api_key": "",
|
||||
"days": 7,
|
||||
@@ -170,6 +171,7 @@
|
||||
{
|
||||
"component_name": "TavilyExtract",
|
||||
"name": "TavilyExtract",
|
||||
"id": "TavilyExtract:SlickYearsCough",
|
||||
"params": {
|
||||
"api_key": ""
|
||||
}
|
||||
@@ -489,6 +491,7 @@
|
||||
{
|
||||
"component_name": "TavilySearch",
|
||||
"name": "TavilySearch",
|
||||
"id": "TavilySearch:FairToolsLive",
|
||||
"params": {
|
||||
"api_key": "",
|
||||
"days": 7,
|
||||
@@ -578,6 +581,7 @@
|
||||
{
|
||||
"component_name": "TavilyExtract",
|
||||
"name": "TavilyExtract",
|
||||
"id": "TavilyExtract:SlickYearsCough",
|
||||
"params": {
|
||||
"api_key": ""
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -3,13 +3,18 @@
|
||||
"title": {
|
||||
"en": "Reflective academic paper generator",
|
||||
"de": "Schreibhilfe für Reflexionspapiere",
|
||||
"zh": "学术论文生成助手"},
|
||||
"zh": "学术论文生成助手"
|
||||
},
|
||||
"description": {
|
||||
"en": "A reflective academic paper generator using local knowledge base, with advanced capabilities in task planning, reasoning, and reflective analysis. Recommended for academic research paper Q&A",
|
||||
"de": "Ein Berichtsgenerierungsassistent, der eine lokale Wissensdatenbank nutzt, mit erweiterten Fähigkeiten in Aufgabenplanung, Schlussfolgerung und reflektierender Analyse. Empfohlen für akademische Forschungspapier-Fragen und -Antworten.",
|
||||
"zh": "一个使用本地知识库的学术论文生成助手，具备高级能力，包括任务规划、推理和反思性分析。推荐用于学术研究论文问答。"},
|
||||
"zh": "一个使用本地知识库的学术论文生成助手，具备高级能力，包括任务规划、推理和反思性分析。推荐用于学术研究论文问答。"
|
||||
},
|
||||
"canvas_type": "Agent",
|
||||
"canvas_types": ["Agent", "Recommended"],
|
||||
"canvas_types": [
|
||||
"Agent",
|
||||
"Recommended"
|
||||
],
|
||||
"dsl": {
|
||||
"components": {
|
||||
"Agent:NewPumasLick": {
|
||||
@@ -49,7 +54,7 @@
|
||||
"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",
|
||||
"sys_prompt": "## Role & Task\nYou are a **“Knowledge Base Retrieval Q\\&A Agent”** whose goal is to break down the user’s 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 5–20 depending on question complexity).\n2. **Query Type Determination (Rule-Based)**\n * Example rules:\n * If the question involves a single issue but requests “method comparison/multiple explanations” → use **depth-first**.\n * If the question can naturally be split into ≥3 independent sub-questions → use **breadth-first**.\n * If the question can be answered by a single fact/specification/definition → use **simple query**.\n3. **Research Plan Formulation**\n * Depth-first: define 3–5 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 ≤3 times, or flag as requiring external search.\n5. **Integration & Reasoning**\n * Build the answer using a **fact–evidence–reasoning** chain. For each conclusion, attach 1–2 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’s preferred language\n",
|
||||
"temperature": "0.1",
|
||||
"temperatureEnabled": true,
|
||||
"tools": [
|
||||
@@ -74,7 +79,8 @@
|
||||
"top_k": 1024,
|
||||
"top_n": 8,
|
||||
"use_kg": false
|
||||
}
|
||||
},
|
||||
"id": "Retrieval:NewPumasLick"
|
||||
}
|
||||
],
|
||||
"topPEnabled": false,
|
||||
@@ -111,7 +117,7 @@
|
||||
"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"
|
||||
"prologue": "你好！ 我是你的助理，有什么可以帮到你的吗？"
|
||||
}
|
||||
},
|
||||
"upstream": []
|
||||
@@ -171,7 +177,7 @@
|
||||
"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"
|
||||
"prologue": "你好！ 我是你的助理，有什么可以帮到你的吗？"
|
||||
},
|
||||
"label": "Begin",
|
||||
"name": "begin"
|
||||
@@ -249,7 +255,7 @@
|
||||
"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",
|
||||
"sys_prompt": "## Role & Task\nYou are a **“Knowledge Base Retrieval Q\\&A Agent”** whose goal is to break down the user’s 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 5–20 depending on question complexity).\n2. **Query Type Determination (Rule-Based)**\n * Example rules:\n * If the question involves a single issue but requests “method comparison/multiple explanations” → use **depth-first**.\n * If the question can naturally be split into ≥3 independent sub-questions → use **breadth-first**.\n * If the question can be answered by a single fact/specification/definition → use **simple query**.\n3. **Research Plan Formulation**\n * Depth-first: define 3–5 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 ≤3 times, or flag as requiring external search.\n5. **Integration & Reasoning**\n * Build the answer using a **fact–evidence–reasoning** chain. For each conclusion, attach 1–2 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’s preferred language\n",
|
||||
"temperature": "0.1",
|
||||
"temperatureEnabled": true,
|
||||
"tools": [
|
||||
@@ -274,7 +280,8 @@
|
||||
"top_k": 1024,
|
||||
"top_n": 8,
|
||||
"use_kg": false
|
||||
}
|
||||
},
|
||||
"id": "Retrieval:NewPumasLick"
|
||||
}
|
||||
],
|
||||
"topPEnabled": false,
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -14,190 +14,191 @@
|
||||
"dsl": {
|
||||
"components": {
|
||||
"Agent:LargeFliesMelt": {
|
||||
"downstream": [
|
||||
"UserFillUp:GoldBroomsRelate"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Agent",
|
||||
"params": {
|
||||
"cite": true,
|
||||
"delay_after_error": 1,
|
||||
"description": "",
|
||||
"exception_default_value": "",
|
||||
"exception_goto": [],
|
||||
"exception_method": "",
|
||||
"frequencyPenaltyEnabled": false,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "qwen-turbo@Tongyi-Qianwen",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 1,
|
||||
"max_tokens": 256,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
},
|
||||
"structured": {}
|
||||
},
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "User query:{sys.query}",
|
||||
"role": "user"
|
||||
}
|
||||
"downstream": [
|
||||
"UserFillUp:GoldBroomsRelate"
|
||||
],
|
||||
"sys_prompt": "<role>\nYou are the Planning Agent in a multi-agent RAG workflow.\nYour sole job is to design a crisp, executable Search Plan for the next agent. Do not search or answer the user’s question.\n</role>\n<objectives>\nUnderstand the user’s task and decompose it into evidence-seeking steps.\nProduce high-quality queries and retrieval settings tailored to the task type (fact lookup, multi-hop reasoning, comparison, statistics, how-to, etc.).\nIdentify missing information that would materially change the plan (≤3 concise questions).\nOptimize for source trustworthiness, diversity, and recency; define stopping criteria to avoid over-searching.\nAnswer in 150 words.\n<objectives>",
|
||||
"temperature": 0.1,
|
||||
"temperatureEnabled": false,
|
||||
"tools": [],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.3,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"begin"
|
||||
]
|
||||
"obj": {
|
||||
"component_name": "Agent",
|
||||
"params": {
|
||||
"cite": true,
|
||||
"delay_after_error": 1,
|
||||
"description": "",
|
||||
"exception_default_value": "",
|
||||
"exception_goto": [],
|
||||
"exception_method": "",
|
||||
"frequencyPenaltyEnabled": false,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "qwen-turbo@Tongyi-Qianwen",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 1,
|
||||
"max_tokens": 256,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
},
|
||||
"structured": {}
|
||||
},
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "User query:{sys.query}",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "<role>\nYou are the Planning Agent in a multi-agent RAG workflow.\nYour sole job is to design a crisp, executable Search Plan for the next agent. Do not search or answer the user’s question.\n</role>\n<objectives>\nUnderstand the user’s task and decompose it into evidence-seeking steps.\nProduce high-quality queries and retrieval settings tailored to the task type (fact lookup, multi-hop reasoning, comparison, statistics, how-to, etc.).\nIdentify missing information that would materially change the plan (≤3 concise questions).\nOptimize for source trustworthiness, diversity, and recency; define stopping criteria to avoid over-searching.\nAnswer in 150 words.\n<objectives>",
|
||||
"temperature": 0.1,
|
||||
"temperatureEnabled": false,
|
||||
"tools": [],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.3,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"begin"
|
||||
]
|
||||
},
|
||||
"Agent:TangyWordsType": {
|
||||
"downstream": [
|
||||
"Message:FreshWallsStudy"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Agent",
|
||||
"params": {
|
||||
"cite": true,
|
||||
"delay_after_error": 1,
|
||||
"description": "",
|
||||
"exception_default_value": "",
|
||||
"exception_goto": [],
|
||||
"exception_method": "",
|
||||
"frequencyPenaltyEnabled": false,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "qwen-turbo@Tongyi-Qianwen",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 1,
|
||||
"max_tokens": 256,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
},
|
||||
"structured": {}
|
||||
},
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "Search Plan: {Agent:LargeFliesMelt@content}\n\n\n\nAwait Response feedback:{UserFillUp:GoldBroomsRelate@instructions}\n",
|
||||
"role": "user"
|
||||
}
|
||||
"downstream": [
|
||||
"Message:FreshWallsStudy"
|
||||
],
|
||||
"sys_prompt": "<role>\nYou are the Search Agent.\nYour job is to execute the approved Search Plan, integrate the Await Response feedback, retrieve evidence, and produce a well-grounded answer.\n</role>\n<objectives>\nTranslate the plan + feedback into concrete searches.\nCollect diverse, trustworthy, and recent evidence meeting the plan’s evidence bar.\nSynthesize a concise answer; include citations next to claims they support.\nIf evidence is insufficient or conflicting, clearly state limitations and propose next steps.\n</objectives>\n <tools>\nRetrieval: You must use Retrieval to do the search.\n </tools>\n",
|
||||
"temperature": 0.1,
|
||||
"temperatureEnabled": false,
|
||||
"tools": [
|
||||
{
|
||||
"component_name": "Retrieval",
|
||||
"name": "Retrieval",
|
||||
"obj": {
|
||||
"component_name": "Agent",
|
||||
"params": {
|
||||
"cross_languages": [],
|
||||
"cite": true,
|
||||
"delay_after_error": 1,
|
||||
"description": "",
|
||||
"empty_response": "",
|
||||
"kb_ids": [],
|
||||
"retrieval_from": "dataset",
|
||||
"keywords_similarity_weight": 0.7,
|
||||
"exception_default_value": "",
|
||||
"exception_goto": [],
|
||||
"exception_method": "",
|
||||
"frequencyPenaltyEnabled": false,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "qwen-turbo@Tongyi-Qianwen",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 1,
|
||||
"max_tokens": 256,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"formalized_content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
},
|
||||
"structured": {}
|
||||
},
|
||||
"json": {
|
||||
"type": "Array<Object>",
|
||||
"value": []
|
||||
}
|
||||
},
|
||||
"rerank_id": "",
|
||||
"similarity_threshold": 0.2,
|
||||
"toc_enhance": false,
|
||||
"top_k": 1024,
|
||||
"top_n": 8,
|
||||
"use_kg": false
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "Search Plan: {Agent:LargeFliesMelt@content}\n\n\n\nAwait Response feedback:{UserFillUp:GoldBroomsRelate@instructions}\n",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "<role>\nYou are the Search Agent.\nYour job is to execute the approved Search Plan, integrate the Await Response feedback, retrieve evidence, and produce a well-grounded answer.\n</role>\n<objectives>\nTranslate the plan + feedback into concrete searches.\nCollect diverse, trustworthy, and recent evidence meeting the plan’s evidence bar.\nSynthesize a concise answer; include citations next to claims they support.\nIf evidence is insufficient or conflicting, clearly state limitations and propose next steps.\n</objectives>\n <tools>\nRetrieval: You must use Retrieval to do the search.\n </tools>\n",
|
||||
"temperature": 0.1,
|
||||
"temperatureEnabled": false,
|
||||
"tools": [
|
||||
{
|
||||
"component_name": "Retrieval",
|
||||
"name": "Retrieval",
|
||||
"params": {
|
||||
"cross_languages": [],
|
||||
"description": "",
|
||||
"empty_response": "",
|
||||
"kb_ids": [],
|
||||
"retrieval_from": "dataset",
|
||||
"keywords_similarity_weight": 0.7,
|
||||
"outputs": {
|
||||
"formalized_content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
},
|
||||
"json": {
|
||||
"type": "Array<Object>",
|
||||
"value": []
|
||||
}
|
||||
},
|
||||
"rerank_id": "",
|
||||
"similarity_threshold": 0.2,
|
||||
"toc_enhance": false,
|
||||
"top_k": 1024,
|
||||
"top_n": 8,
|
||||
"use_kg": false
|
||||
},
|
||||
"id": "Retrieval:WarmRiversMarch"
|
||||
}
|
||||
],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.3,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
}
|
||||
}
|
||||
],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.3,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"UserFillUp:GoldBroomsRelate"
|
||||
]
|
||||
},
|
||||
"upstream": [
|
||||
"UserFillUp:GoldBroomsRelate"
|
||||
]
|
||||
},
|
||||
"Message:FreshWallsStudy": {
|
||||
"downstream": [],
|
||||
"obj": {
|
||||
"component_name": "Message",
|
||||
"params": {
|
||||
"content": [
|
||||
"{Agent:TangyWordsType@content}"
|
||||
"downstream": [],
|
||||
"obj": {
|
||||
"component_name": "Message",
|
||||
"params": {
|
||||
"content": [
|
||||
"{Agent:TangyWordsType@content}"
|
||||
]
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"Agent:TangyWordsType"
|
||||
]
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"Agent:TangyWordsType"
|
||||
]
|
||||
},
|
||||
"UserFillUp:GoldBroomsRelate": {
|
||||
"downstream": [
|
||||
"Agent:TangyWordsType"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "UserFillUp",
|
||||
"params": {
|
||||
"enable_tips": true,
|
||||
"inputs": {
|
||||
"instructions": {
|
||||
"name": "instructions",
|
||||
"optional": false,
|
||||
"options": [],
|
||||
"type": "paragraph"
|
||||
"downstream": [
|
||||
"Agent:TangyWordsType"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "UserFillUp",
|
||||
"params": {
|
||||
"enable_tips": true,
|
||||
"inputs": {
|
||||
"instructions": {
|
||||
"name": "instructions",
|
||||
"optional": false,
|
||||
"options": [],
|
||||
"type": "paragraph"
|
||||
}
|
||||
},
|
||||
"outputs": {
|
||||
"instructions": {
|
||||
"name": "instructions",
|
||||
"optional": false,
|
||||
"options": [],
|
||||
"type": "paragraph"
|
||||
}
|
||||
},
|
||||
"tips": "Here is my search plan:\n{Agent:LargeFliesMelt@content}\nAre you okay with it?"
|
||||
}
|
||||
},
|
||||
"outputs": {
|
||||
"instructions": {
|
||||
"name": "instructions",
|
||||
"optional": false,
|
||||
"options": [],
|
||||
"type": "paragraph"
|
||||
}
|
||||
},
|
||||
"tips": "Here is my search plan:\n{Agent:LargeFliesMelt@content}\nAre you okay with it?"
|
||||
}
|
||||
},
|
||||
"upstream": [
|
||||
"Agent:LargeFliesMelt"
|
||||
]
|
||||
"upstream": [
|
||||
"Agent:LargeFliesMelt"
|
||||
]
|
||||
},
|
||||
"begin": {
|
||||
"downstream": [
|
||||
"Agent:LargeFliesMelt"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Begin",
|
||||
"params": {}
|
||||
},
|
||||
"upstream": []
|
||||
"downstream": [
|
||||
"Agent:LargeFliesMelt"
|
||||
],
|
||||
"obj": {
|
||||
"component_name": "Begin",
|
||||
"params": {}
|
||||
},
|
||||
"upstream": []
|
||||
}
|
||||
},
|
||||
"globals": {
|
||||
@@ -208,308 +209,309 @@
|
||||
},
|
||||
"graph": {
|
||||
"edges": [
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__beginstart-Agent:LargeFliesMeltend",
|
||||
"source": "begin",
|
||||
"sourceHandle": "start",
|
||||
"target": "Agent:LargeFliesMelt",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
"id": "xy-edge__beginstart-Agent:LargeFliesMeltend",
|
||||
"source": "begin",
|
||||
"sourceHandle": "start",
|
||||
"target": "Agent:LargeFliesMelt",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__Agent:LargeFliesMeltstart-UserFillUp:GoldBroomsRelateend",
|
||||
"source": "Agent:LargeFliesMelt",
|
||||
"sourceHandle": "start",
|
||||
"target": "UserFillUp:GoldBroomsRelate",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
"id": "xy-edge__Agent:LargeFliesMeltstart-UserFillUp:GoldBroomsRelateend",
|
||||
"source": "Agent:LargeFliesMelt",
|
||||
"sourceHandle": "start",
|
||||
"target": "UserFillUp:GoldBroomsRelate",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
{
|
||||
"data": {
|
||||
"isHovered": false
|
||||
},
|
||||
"id": "xy-edge__UserFillUp:GoldBroomsRelatestart-Agent:TangyWordsTypeend",
|
||||
"source": "UserFillUp:GoldBroomsRelate",
|
||||
"sourceHandle": "start",
|
||||
"target": "Agent:TangyWordsType",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
"id": "xy-edge__UserFillUp:GoldBroomsRelatestart-Agent:TangyWordsTypeend",
|
||||
"source": "UserFillUp:GoldBroomsRelate",
|
||||
"sourceHandle": "start",
|
||||
"target": "Agent:TangyWordsType",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"id": "xy-edge__Agent:TangyWordsTypetool-Tool:NastyBatsGoend",
|
||||
"source": "Agent:TangyWordsType",
|
||||
"sourceHandle": "tool",
|
||||
"target": "Tool:NastyBatsGo",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"id": "xy-edge__Agent:TangyWordsTypestart-Message:FreshWallsStudyend",
|
||||
"source": "Agent:TangyWordsType",
|
||||
"sourceHandle": "start",
|
||||
"target": "Message:FreshWallsStudy",
|
||||
"targetHandle": "end"
|
||||
}
|
||||
{
|
||||
"id": "xy-edge__Agent:TangyWordsTypetool-Tool:NastyBatsGoend",
|
||||
"source": "Agent:TangyWordsType",
|
||||
"sourceHandle": "tool",
|
||||
"target": "Tool:NastyBatsGo",
|
||||
"targetHandle": "end"
|
||||
},
|
||||
{
|
||||
"id": "xy-edge__Agent:TangyWordsTypestart-Message:FreshWallsStudyend",
|
||||
"source": "Agent:TangyWordsType",
|
||||
"sourceHandle": "start",
|
||||
"target": "Message:FreshWallsStudy",
|
||||
"targetHandle": "end"
|
||||
}
|
||||
],
|
||||
"nodes": [
|
||||
{
|
||||
"data": {
|
||||
"label": "Begin",
|
||||
"name": "begin"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "begin",
|
||||
"measured": {
|
||||
"height": 50,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 154.9008789064451,
|
||||
"y": 119.51001744285344
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "left",
|
||||
"targetPosition": "right",
|
||||
"type": "beginNode"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"cite": true,
|
||||
"delay_after_error": 1,
|
||||
"description": "",
|
||||
"exception_default_value": "",
|
||||
"exception_goto": [],
|
||||
"exception_method": "",
|
||||
"frequencyPenaltyEnabled": false,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "qwen-turbo@Tongyi-Qianwen",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 1,
|
||||
"max_tokens": 256,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
{
|
||||
"data": {
|
||||
"label": "Begin",
|
||||
"name": "begin"
|
||||
},
|
||||
"structured": {}
|
||||
"dragging": false,
|
||||
"id": "begin",
|
||||
"measured": {
|
||||
"height": 50,
|
||||
"width": 200
|
||||
},
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "User query:{sys.query}",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "<role>\nYou are the Planning Agent in a multi-agent RAG workflow.\nYour sole job is to design a crisp, executable Search Plan for the next agent. Do not search or answer the user’s question.\n</role>\n<objectives>\nUnderstand the user’s task and decompose it into evidence-seeking steps.\nProduce high-quality queries and retrieval settings tailored to the task type (fact lookup, multi-hop reasoning, comparison, statistics, how-to, etc.).\nIdentify missing information that would materially change the plan (≤3 concise questions).\nOptimize for source trustworthiness, diversity, and recency; define stopping criteria to avoid over-searching.\nAnswer in 150 words.\n<objectives>",
|
||||
"temperature": 0.1,
|
||||
"temperatureEnabled": false,
|
||||
"tools": [],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.3,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
},
|
||||
"label": "Agent",
|
||||
"name": "Planning Agent"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Agent:LargeFliesMelt",
|
||||
"measured": {
|
||||
"height": 90,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 443.96309330796714,
|
||||
"y": 104.61370811205677
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "agentNode"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"enable_tips": true,
|
||||
"inputs": {
|
||||
"instructions": {
|
||||
"name": "instructions",
|
||||
"optional": false,
|
||||
"options": [],
|
||||
"type": "paragraph"
|
||||
}
|
||||
"position": {
|
||||
"x": 154.9008789064451,
|
||||
"y": 119.51001744285344
|
||||
},
|
||||
"outputs": {
|
||||
"instructions": {
|
||||
"name": "instructions",
|
||||
"optional": false,
|
||||
"options": [],
|
||||
"type": "paragraph"
|
||||
}
|
||||
},
|
||||
"tips": "Here is my search plan:\n{Agent:LargeFliesMelt@content}\nAre you okay with it?"
|
||||
"selected": false,
|
||||
"sourcePosition": "left",
|
||||
"targetPosition": "right",
|
||||
"type": "beginNode"
|
||||
},
|
||||
"label": "UserFillUp",
|
||||
"name": "Await Response"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "UserFillUp:GoldBroomsRelate",
|
||||
"measured": {
|
||||
"height": 50,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 683.3409492927474,
|
||||
"y": 116.76274137645598
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "ragNode"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"cite": true,
|
||||
"delay_after_error": 1,
|
||||
"description": "",
|
||||
"exception_default_value": "",
|
||||
"exception_goto": [],
|
||||
"exception_method": "",
|
||||
"frequencyPenaltyEnabled": false,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "qwen-turbo@Tongyi-Qianwen",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 1,
|
||||
"max_tokens": 256,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
},
|
||||
"structured": {}
|
||||
},
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "Search Plan: {Agent:LargeFliesMelt@content}\n\n\n\nAwait Response feedback:{UserFillUp:GoldBroomsRelate@instructions}\n",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "<role>\nYou are the Search Agent.\nYour job is to execute the approved Search Plan, integrate the Await Response feedback, retrieve evidence, and produce a well-grounded answer.\n</role>\n<objectives>\nTranslate the plan + feedback into concrete searches.\nCollect diverse, trustworthy, and recent evidence meeting the plan’s evidence bar.\nSynthesize a concise answer; include citations next to claims they support.\nIf evidence is insufficient or conflicting, clearly state limitations and propose next steps.\n</objectives>\n <tools>\nRetrieval: You must use Retrieval to do the search.\n </tools>\n",
|
||||
"temperature": 0.1,
|
||||
"temperatureEnabled": false,
|
||||
"tools": [
|
||||
{
|
||||
"component_name": "Retrieval",
|
||||
"name": "Retrieval",
|
||||
"params": {
|
||||
"cross_languages": [],
|
||||
"description": "",
|
||||
"empty_response": "",
|
||||
"kb_ids": [],
|
||||
"retrieval_from": "dataset",
|
||||
"keywords_similarity_weight": 0.7,
|
||||
"outputs": {
|
||||
"formalized_content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"cite": true,
|
||||
"delay_after_error": 1,
|
||||
"description": "",
|
||||
"exception_default_value": "",
|
||||
"exception_goto": [],
|
||||
"exception_method": "",
|
||||
"frequencyPenaltyEnabled": false,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "qwen-turbo@Tongyi-Qianwen",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 1,
|
||||
"max_tokens": 256,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
},
|
||||
"structured": {}
|
||||
},
|
||||
"json": {
|
||||
"type": "Array<Object>",
|
||||
"value": []
|
||||
}
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "User query:{sys.query}",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "<role>\nYou are the Planning Agent in a multi-agent RAG workflow.\nYour sole job is to design a crisp, executable Search Plan for the next agent. Do not search or answer the user’s question.\n</role>\n<objectives>\nUnderstand the user’s task and decompose it into evidence-seeking steps.\nProduce high-quality queries and retrieval settings tailored to the task type (fact lookup, multi-hop reasoning, comparison, statistics, how-to, etc.).\nIdentify missing information that would materially change the plan (≤3 concise questions).\nOptimize for source trustworthiness, diversity, and recency; define stopping criteria to avoid over-searching.\nAnswer in 150 words.\n<objectives>",
|
||||
"temperature": 0.1,
|
||||
"temperatureEnabled": false,
|
||||
"tools": [],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.3,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
},
|
||||
"rerank_id": "",
|
||||
"similarity_threshold": 0.2,
|
||||
"toc_enhance": false,
|
||||
"top_k": 1024,
|
||||
"top_n": 8,
|
||||
"use_kg": false
|
||||
}
|
||||
}
|
||||
],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.3,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
"label": "Agent",
|
||||
"name": "Planning Agent"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Agent:LargeFliesMelt",
|
||||
"measured": {
|
||||
"height": 90,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 443.96309330796714,
|
||||
"y": 104.61370811205677
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "agentNode"
|
||||
},
|
||||
"label": "Agent",
|
||||
"name": "Search Agent"
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"enable_tips": true,
|
||||
"inputs": {
|
||||
"instructions": {
|
||||
"name": "instructions",
|
||||
"optional": false,
|
||||
"options": [],
|
||||
"type": "paragraph"
|
||||
}
|
||||
},
|
||||
"outputs": {
|
||||
"instructions": {
|
||||
"name": "instructions",
|
||||
"optional": false,
|
||||
"options": [],
|
||||
"type": "paragraph"
|
||||
}
|
||||
},
|
||||
"tips": "Here is my search plan:\n{Agent:LargeFliesMelt@content}\nAre you okay with it?"
|
||||
},
|
||||
"label": "UserFillUp",
|
||||
"name": "Await Response"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "UserFillUp:GoldBroomsRelate",
|
||||
"measured": {
|
||||
"height": 50,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 683.3409492927474,
|
||||
"y": 116.76274137645598
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "ragNode"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Agent:TangyWordsType",
|
||||
"measured": {
|
||||
"height": 90,
|
||||
"width": 200
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"cite": true,
|
||||
"delay_after_error": 1,
|
||||
"description": "",
|
||||
"exception_default_value": "",
|
||||
"exception_goto": [],
|
||||
"exception_method": "",
|
||||
"frequencyPenaltyEnabled": false,
|
||||
"frequency_penalty": 0.7,
|
||||
"llm_id": "qwen-turbo@Tongyi-Qianwen",
|
||||
"maxTokensEnabled": false,
|
||||
"max_retries": 3,
|
||||
"max_rounds": 1,
|
||||
"max_tokens": 256,
|
||||
"mcp": [],
|
||||
"message_history_window_size": 12,
|
||||
"outputs": {
|
||||
"content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
},
|
||||
"structured": {}
|
||||
},
|
||||
"presencePenaltyEnabled": false,
|
||||
"presence_penalty": 0.4,
|
||||
"prompts": [
|
||||
{
|
||||
"content": "Search Plan: {Agent:LargeFliesMelt@content}\n\n\n\nAwait Response feedback:{UserFillUp:GoldBroomsRelate@instructions}\n",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
"sys_prompt": "<role>\nYou are the Search Agent.\nYour job is to execute the approved Search Plan, integrate the Await Response feedback, retrieve evidence, and produce a well-grounded answer.\n</role>\n<objectives>\nTranslate the plan + feedback into concrete searches.\nCollect diverse, trustworthy, and recent evidence meeting the plan’s evidence bar.\nSynthesize a concise answer; include citations next to claims they support.\nIf evidence is insufficient or conflicting, clearly state limitations and propose next steps.\n</objectives>\n <tools>\nRetrieval: You must use Retrieval to do the search.\n </tools>\n",
|
||||
"temperature": 0.1,
|
||||
"temperatureEnabled": false,
|
||||
"tools": [
|
||||
{
|
||||
"component_name": "Retrieval",
|
||||
"name": "Retrieval",
|
||||
"params": {
|
||||
"cross_languages": [],
|
||||
"description": "",
|
||||
"empty_response": "",
|
||||
"kb_ids": [],
|
||||
"retrieval_from": "dataset",
|
||||
"keywords_similarity_weight": 0.7,
|
||||
"outputs": {
|
||||
"formalized_content": {
|
||||
"type": "string",
|
||||
"value": ""
|
||||
},
|
||||
"json": {
|
||||
"type": "Array<Object>",
|
||||
"value": []
|
||||
}
|
||||
},
|
||||
"rerank_id": "",
|
||||
"similarity_threshold": 0.2,
|
||||
"toc_enhance": false,
|
||||
"top_k": 1024,
|
||||
"top_n": 8,
|
||||
"use_kg": false
|
||||
},
|
||||
"id": "Retrieval:BrightMoonsGlow"
|
||||
}
|
||||
],
|
||||
"topPEnabled": false,
|
||||
"top_p": 0.3,
|
||||
"user_prompt": "",
|
||||
"visual_files_var": ""
|
||||
},
|
||||
"label": "Agent",
|
||||
"name": "Search Agent"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Agent:TangyWordsType",
|
||||
"measured": {
|
||||
"height": 90,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 944.6411255659472,
|
||||
"y": 99.84499066368488
|
||||
},
|
||||
"selected": true,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "agentNode"
|
||||
},
|
||||
"position": {
|
||||
"x": 944.6411255659472,
|
||||
"y": 99.84499066368488
|
||||
{
|
||||
"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"
|
||||
},
|
||||
"id": "Tool:NastyBatsGo",
|
||||
"measured": {
|
||||
"height": 50,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 862.6411255659472,
|
||||
"y": 239.84499066368488
|
||||
},
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "toolNode"
|
||||
},
|
||||
"selected": true,
|
||||
"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"
|
||||
},
|
||||
"id": "Tool:NastyBatsGo",
|
||||
"measured": {
|
||||
"height": 50,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 862.6411255659472,
|
||||
"y": 239.84499066368488
|
||||
},
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "toolNode"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"content": [
|
||||
"{Agent:TangyWordsType@content}"
|
||||
]
|
||||
},
|
||||
"label": "Message",
|
||||
"name": "Message"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Message:FreshWallsStudy",
|
||||
"measured": {
|
||||
"height": 50,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 1216.7057997987163,
|
||||
"y": 120.48541298149814
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "messageNode"
|
||||
}
|
||||
{
|
||||
"data": {
|
||||
"form": {
|
||||
"content": [
|
||||
"{Agent:TangyWordsType@content}"
|
||||
]
|
||||
},
|
||||
"label": "Message",
|
||||
"name": "Message"
|
||||
},
|
||||
"dragging": false,
|
||||
"id": "Message:FreshWallsStudy",
|
||||
"measured": {
|
||||
"height": 50,
|
||||
"width": 200
|
||||
},
|
||||
"position": {
|
||||
"x": 1216.7057997987163,
|
||||
"y": 120.48541298149814
|
||||
},
|
||||
"selected": false,
|
||||
"sourcePosition": "right",
|
||||
"targetPosition": "left",
|
||||
"type": "messageNode"
|
||||
}
|
||||
]
|
||||
},
|
||||
"history": [],
|
||||
@@ -517,7 +519,6 @@
|
||||
"path": [],
|
||||
"retrieval": [],
|
||||
"variables": {}
|
||||
},
|
||||
"avatar":
|
||||
"data:image/png;base64,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"
|
||||
},
|
||||
"avatar": "data:image/png;base64,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"
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
@@ -74,7 +74,8 @@
|
||||
"top_k": 1024,
|
||||
"top_n": 8,
|
||||
"use_kg": false
|
||||
}
|
||||
},
|
||||
"id": "Retrieval:WarmOwlsCough"
|
||||
}
|
||||
],
|
||||
"topPEnabled": false,
|
||||
@@ -226,7 +227,8 @@
|
||||
"top_k": 1024,
|
||||
"top_n": 8,
|
||||
"use_kg": false
|
||||
}
|
||||
},
|
||||
"id": "Retrieval:WarmWeeksRead"
|
||||
}
|
||||
],
|
||||
"topPEnabled": false,
|
||||
|
||||
@@ -4,7 +4,7 @@ import {
|
||||
} from '@/constants/knowledge';
|
||||
import { useTranslate } from '@/hooks/common-hooks';
|
||||
import { camelCase, isEqual } from 'lodash';
|
||||
import React, { useCallback } from 'react';
|
||||
import { useCallback } from 'react';
|
||||
import { useFormContext } from 'react-hook-form';
|
||||
import { z } from 'zod';
|
||||
import { Collapse } from '../collapse';
|
||||
@@ -92,13 +92,6 @@ export function LlmSettingFieldItems({
|
||||
const form = useFormContext();
|
||||
const { t } = useTranslate('chat');
|
||||
|
||||
const CollapseComponent = showCollapse ? Collapse : React.Fragment;
|
||||
const collapseProps = showCollapse
|
||||
? {
|
||||
title: t('modelSetting'),
|
||||
}
|
||||
: {};
|
||||
|
||||
const getFieldWithPrefix = useCallback(
|
||||
(name: string) => {
|
||||
return prefix ? `${prefix}.${name}` : name;
|
||||
@@ -149,6 +142,141 @@ export function LlmSettingFieldItems({
|
||||
}
|
||||
};
|
||||
|
||||
const settingFields = (
|
||||
<section className="space-y-5">
|
||||
<FormField
|
||||
control={form.control}
|
||||
name={getFieldWithPrefix('parameter')}
|
||||
render={({ field }) => (
|
||||
<FormItem className="flex justify-between items-center">
|
||||
<FormLabel className="flex-1">{t('freedom')}</FormLabel>
|
||||
<FormControl>
|
||||
<Select
|
||||
value={field.value}
|
||||
onValueChange={(val) => {
|
||||
handleChange(val);
|
||||
field.onChange(val);
|
||||
}}
|
||||
>
|
||||
<SelectTrigger className="flex-1 !m-0">
|
||||
<SelectValue />
|
||||
</SelectTrigger>
|
||||
<SelectContent>
|
||||
{parameterOptions.map((x) => (
|
||||
<SelectItem value={x.value} key={x.value}>
|
||||
{x.label}
|
||||
</SelectItem>
|
||||
))}
|
||||
</SelectContent>
|
||||
</Select>
|
||||
</FormControl>
|
||||
<FormMessage />
|
||||
</FormItem>
|
||||
)}
|
||||
/>
|
||||
{showFields.some((item) => item === 'temperature') && (
|
||||
<SliderInputSwitchFormField
|
||||
name={getFieldWithPrefix('temperature')}
|
||||
checkName="temperatureEnabled"
|
||||
label="temperature"
|
||||
max={1}
|
||||
step={0.01}
|
||||
min={0}
|
||||
onChange={() => {
|
||||
checkParameterIsEqual();
|
||||
}}
|
||||
></SliderInputSwitchFormField>
|
||||
)}
|
||||
{showFields.some((item) => item === 'top_p') && (
|
||||
<SliderInputSwitchFormField
|
||||
name={getFieldWithPrefix('top_p')}
|
||||
checkName="topPEnabled"
|
||||
label="topP"
|
||||
max={1}
|
||||
step={0.01}
|
||||
min={0}
|
||||
onChange={() => {
|
||||
checkParameterIsEqual();
|
||||
}}
|
||||
></SliderInputSwitchFormField>
|
||||
)}
|
||||
{showFields.some((item) => item === 'presence_penalty') && (
|
||||
<SliderInputSwitchFormField
|
||||
name={getFieldWithPrefix('presence_penalty')}
|
||||
checkName="presencePenaltyEnabled"
|
||||
label="presencePenalty"
|
||||
max={1}
|
||||
step={0.01}
|
||||
min={0}
|
||||
onChange={() => {
|
||||
checkParameterIsEqual();
|
||||
}}
|
||||
></SliderInputSwitchFormField>
|
||||
)}
|
||||
{showFields.some((item) => item === 'frequency_penalty') && (
|
||||
<SliderInputSwitchFormField
|
||||
name={getFieldWithPrefix('frequency_penalty')}
|
||||
checkName="frequencyPenaltyEnabled"
|
||||
label="frequencyPenalty"
|
||||
max={1}
|
||||
step={0.01}
|
||||
min={0}
|
||||
onChange={() => {
|
||||
checkParameterIsEqual();
|
||||
}}
|
||||
></SliderInputSwitchFormField>
|
||||
)}
|
||||
{showFields.some((item) => item === 'max_tokens') && (
|
||||
<SliderInputSwitchFormField
|
||||
name={getFieldWithPrefix('max_tokens')}
|
||||
checkName="maxTokensEnabled"
|
||||
numberInputClassName="w-20"
|
||||
label="maxTokens"
|
||||
max={128000}
|
||||
min={0}
|
||||
onChange={() => {
|
||||
checkParameterIsEqual();
|
||||
}}
|
||||
></SliderInputSwitchFormField>
|
||||
)}
|
||||
{showFields.some((item) => item === 'thinking') && (
|
||||
<FormField
|
||||
control={form.control}
|
||||
name={getFieldWithPrefix('thinking')}
|
||||
render={({ field }) => (
|
||||
<FormItem className="flex justify-between items-center">
|
||||
<FormLabel className="flex-1" tooltip={t('thinkingTip')}>
|
||||
{t('thinking')}
|
||||
</FormLabel>
|
||||
<FormControl>
|
||||
<Select
|
||||
value={field.value ?? 'default'}
|
||||
onValueChange={field.onChange}
|
||||
>
|
||||
<SelectTrigger className="flex-1 !m-0">
|
||||
<SelectValue />
|
||||
</SelectTrigger>
|
||||
<SelectContent>
|
||||
<SelectItem value="default">
|
||||
{t('thinkingDefault')}
|
||||
</SelectItem>
|
||||
<SelectItem value="enabled">
|
||||
{t('thinkingEnabled')}
|
||||
</SelectItem>
|
||||
<SelectItem value="disabled">
|
||||
{t('thinkingDisabled')}
|
||||
</SelectItem>
|
||||
</SelectContent>
|
||||
</Select>
|
||||
</FormControl>
|
||||
<FormMessage />
|
||||
</FormItem>
|
||||
)}
|
||||
/>
|
||||
)}
|
||||
</section>
|
||||
);
|
||||
|
||||
return (
|
||||
<div className="space-y-5">
|
||||
<LLMFormField
|
||||
@@ -158,140 +286,11 @@ export function LlmSettingFieldItems({
|
||||
optionTestIdPrefix={llmOptionTestIdPrefix}
|
||||
ownerTenantId={ownerTenantId}
|
||||
></LLMFormField>
|
||||
<CollapseComponent {...collapseProps}>
|
||||
<section className="space-y-5">
|
||||
<FormField
|
||||
control={form.control}
|
||||
name={getFieldWithPrefix('parameter')}
|
||||
render={({ field }) => (
|
||||
<FormItem className="flex justify-between items-center">
|
||||
<FormLabel className="flex-1">{t('freedom')}</FormLabel>
|
||||
<FormControl>
|
||||
<Select
|
||||
value={field.value}
|
||||
onValueChange={(val) => {
|
||||
handleChange(val);
|
||||
field.onChange(val);
|
||||
}}
|
||||
>
|
||||
<SelectTrigger className="flex-1 !m-0">
|
||||
<SelectValue />
|
||||
</SelectTrigger>
|
||||
<SelectContent>
|
||||
{parameterOptions.map((x) => (
|
||||
<SelectItem value={x.value} key={x.value}>
|
||||
{x.label}
|
||||
</SelectItem>
|
||||
))}
|
||||
</SelectContent>
|
||||
</Select>
|
||||
</FormControl>
|
||||
<FormMessage />
|
||||
</FormItem>
|
||||
)}
|
||||
/>
|
||||
{showFields.some((item) => item === 'temperature') && (
|
||||
<SliderInputSwitchFormField
|
||||
name={getFieldWithPrefix('temperature')}
|
||||
checkName="temperatureEnabled"
|
||||
label="temperature"
|
||||
max={1}
|
||||
step={0.01}
|
||||
min={0}
|
||||
onChange={() => {
|
||||
checkParameterIsEqual();
|
||||
}}
|
||||
></SliderInputSwitchFormField>
|
||||
)}
|
||||
{showFields.some((item) => item === 'top_p') && (
|
||||
<SliderInputSwitchFormField
|
||||
name={getFieldWithPrefix('top_p')}
|
||||
checkName="topPEnabled"
|
||||
label="topP"
|
||||
max={1}
|
||||
step={0.01}
|
||||
min={0}
|
||||
onChange={() => {
|
||||
checkParameterIsEqual();
|
||||
}}
|
||||
></SliderInputSwitchFormField>
|
||||
)}
|
||||
{showFields.some((item) => item === 'presence_penalty') && (
|
||||
<SliderInputSwitchFormField
|
||||
name={getFieldWithPrefix('presence_penalty')}
|
||||
checkName="presencePenaltyEnabled"
|
||||
label="presencePenalty"
|
||||
max={1}
|
||||
step={0.01}
|
||||
min={0}
|
||||
onChange={() => {
|
||||
checkParameterIsEqual();
|
||||
}}
|
||||
></SliderInputSwitchFormField>
|
||||
)}
|
||||
{showFields.some((item) => item === 'frequency_penalty') && (
|
||||
<SliderInputSwitchFormField
|
||||
name={getFieldWithPrefix('frequency_penalty')}
|
||||
checkName="frequencyPenaltyEnabled"
|
||||
label="frequencyPenalty"
|
||||
max={1}
|
||||
step={0.01}
|
||||
min={0}
|
||||
onChange={() => {
|
||||
checkParameterIsEqual();
|
||||
}}
|
||||
></SliderInputSwitchFormField>
|
||||
)}
|
||||
{showFields.some((item) => item === 'max_tokens') && (
|
||||
<SliderInputSwitchFormField
|
||||
name={getFieldWithPrefix('max_tokens')}
|
||||
checkName="maxTokensEnabled"
|
||||
numberInputClassName="w-20"
|
||||
label="maxTokens"
|
||||
max={128000}
|
||||
min={0}
|
||||
onChange={() => {
|
||||
checkParameterIsEqual();
|
||||
}}
|
||||
></SliderInputSwitchFormField>
|
||||
)}
|
||||
{showFields.some((item) => item === 'thinking') && (
|
||||
<FormField
|
||||
control={form.control}
|
||||
name={getFieldWithPrefix('thinking')}
|
||||
render={({ field }) => (
|
||||
<FormItem className="flex justify-between items-center">
|
||||
<FormLabel className="flex-1" tooltip={t('thinkingTip')}>
|
||||
{t('thinking')}
|
||||
</FormLabel>
|
||||
<FormControl>
|
||||
<Select
|
||||
value={field.value ?? 'default'}
|
||||
onValueChange={field.onChange}
|
||||
>
|
||||
<SelectTrigger className="flex-1 !m-0">
|
||||
<SelectValue />
|
||||
</SelectTrigger>
|
||||
<SelectContent>
|
||||
<SelectItem value="default">
|
||||
{t('thinkingDefault')}
|
||||
</SelectItem>
|
||||
<SelectItem value="enabled">
|
||||
{t('thinkingEnabled')}
|
||||
</SelectItem>
|
||||
<SelectItem value="disabled">
|
||||
{t('thinkingDisabled')}
|
||||
</SelectItem>
|
||||
</SelectContent>
|
||||
</Select>
|
||||
</FormControl>
|
||||
<FormMessage />
|
||||
</FormItem>
|
||||
)}
|
||||
/>
|
||||
)}
|
||||
</section>
|
||||
</CollapseComponent>
|
||||
{showCollapse ? (
|
||||
<Collapse title={t('modelSetting')}>{settingFields}</Collapse>
|
||||
) : (
|
||||
settingFields
|
||||
)}
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
@@ -10,7 +10,7 @@ import {
|
||||
import { useFetchAllAddedModels } from '@/hooks/use-llm-request';
|
||||
import { IAddedModel } from '@/interfaces/database/llm';
|
||||
import { buildModelValue, getRealModelName } from '@/utils/llm-util';
|
||||
import { useCallback, useMemo } from 'react';
|
||||
import { forwardRef, useCallback, useMemo } from 'react';
|
||||
import { useFormContext } from 'react-hook-form';
|
||||
import { useTranslation } from 'react-i18next';
|
||||
import { TreeSelect, TreeSelectNode } from './tree-select';
|
||||
@@ -116,19 +116,25 @@ export interface ModelTreeSelectProps {
|
||||
ownerTenantId?: string;
|
||||
}
|
||||
|
||||
export function ModelTreeSelect({
|
||||
modelTypes = ModelTypeMap.llm_id,
|
||||
value,
|
||||
onChange,
|
||||
disabled,
|
||||
placeholder,
|
||||
showSearch = true,
|
||||
allowClear = false,
|
||||
className,
|
||||
renderSelected,
|
||||
testId,
|
||||
ownerTenantId,
|
||||
}: ModelTreeSelectProps) {
|
||||
export const ModelTreeSelect = forwardRef<
|
||||
HTMLButtonElement,
|
||||
ModelTreeSelectProps
|
||||
>(function ModelTreeSelect(
|
||||
{
|
||||
modelTypes = ModelTypeMap.llm_id,
|
||||
value,
|
||||
onChange,
|
||||
disabled,
|
||||
placeholder,
|
||||
showSearch = true,
|
||||
allowClear = false,
|
||||
className,
|
||||
renderSelected,
|
||||
testId,
|
||||
ownerTenantId,
|
||||
},
|
||||
ref,
|
||||
) {
|
||||
const { data: allAddedModels } = useFetchAllAddedModels(
|
||||
undefined,
|
||||
ownerTenantId,
|
||||
@@ -185,6 +191,7 @@ export function ModelTreeSelect({
|
||||
|
||||
return (
|
||||
<TreeSelect
|
||||
ref={ref}
|
||||
data={treeData}
|
||||
value={normalizedValue}
|
||||
onChange={onChange}
|
||||
@@ -198,7 +205,7 @@ export function ModelTreeSelect({
|
||||
testId={testId}
|
||||
/>
|
||||
);
|
||||
}
|
||||
});
|
||||
|
||||
export interface ModelTreeSelectFormFieldProps extends ModelTreeSelectProps {
|
||||
name?: string;
|
||||
|
||||
@@ -5,7 +5,7 @@ import {
|
||||
} from '@/components/ui/popover';
|
||||
import { cn } from '@/lib/utils';
|
||||
import { ChevronDown, ChevronRight, Search, X } from 'lucide-react';
|
||||
import { useCallback, useEffect, useMemo, useState } from 'react';
|
||||
import { forwardRef, useCallback, useEffect, useMemo, useState } from 'react';
|
||||
import { useTranslation } from 'react-i18next';
|
||||
|
||||
export interface TreeSelectNode {
|
||||
@@ -31,239 +31,247 @@ interface TreeSelectProps {
|
||||
testId?: string;
|
||||
}
|
||||
|
||||
export function TreeSelect({
|
||||
data,
|
||||
value,
|
||||
onChange,
|
||||
placeholder,
|
||||
disabled,
|
||||
allowClear,
|
||||
showSearch,
|
||||
className,
|
||||
defaultExpandAll,
|
||||
renderSelected,
|
||||
testId,
|
||||
}: TreeSelectProps) {
|
||||
const [open, setOpen] = useState(false);
|
||||
const [searchTerm, setSearchTerm] = useState('');
|
||||
const [expandedIds, setExpandedIds] = useState<Set<string>>(new Set());
|
||||
const { t } = useTranslation();
|
||||
|
||||
useEffect(() => {
|
||||
if (!defaultExpandAll) return;
|
||||
const ids = new Set<string>();
|
||||
const walk = (nodes: TreeSelectNode[]) => {
|
||||
for (const node of nodes) {
|
||||
if (node.children?.length) {
|
||||
ids.add(node.id);
|
||||
walk(node.children);
|
||||
}
|
||||
}
|
||||
};
|
||||
walk(data);
|
||||
setExpandedIds(ids);
|
||||
}, [data, defaultExpandAll]);
|
||||
|
||||
const selectedNode = useMemo(() => {
|
||||
const find = (nodes: TreeSelectNode[]): TreeSelectNode | undefined => {
|
||||
for (const node of nodes) {
|
||||
if (node.id === value && value) return node;
|
||||
if (node.children) {
|
||||
const found = find(node.children);
|
||||
if (found) return found;
|
||||
}
|
||||
}
|
||||
};
|
||||
return find(data);
|
||||
}, [data, value]);
|
||||
|
||||
const isLeaf = useCallback(
|
||||
(node: TreeSelectNode) => !node.children?.length,
|
||||
[],
|
||||
);
|
||||
|
||||
const handleToggle = useCallback((id: string) => {
|
||||
setExpandedIds((prev) => {
|
||||
const next = new Set(prev);
|
||||
if (next.has(id)) {
|
||||
next.delete(id);
|
||||
} else {
|
||||
next.add(id);
|
||||
}
|
||||
return next;
|
||||
});
|
||||
}, []);
|
||||
|
||||
const handleSelect = useCallback(
|
||||
(node: TreeSelectNode) => {
|
||||
if (node.disabled) return;
|
||||
if (isLeaf(node)) {
|
||||
onChange?.(node.id);
|
||||
setOpen(false);
|
||||
setSearchTerm('');
|
||||
} else {
|
||||
handleToggle(node.id);
|
||||
}
|
||||
export const TreeSelect = forwardRef<HTMLButtonElement, TreeSelectProps>(
|
||||
function TreeSelect(
|
||||
{
|
||||
data,
|
||||
value,
|
||||
onChange,
|
||||
placeholder,
|
||||
disabled,
|
||||
allowClear,
|
||||
showSearch,
|
||||
className,
|
||||
defaultExpandAll,
|
||||
renderSelected,
|
||||
testId,
|
||||
},
|
||||
[isLeaf, onChange, handleToggle],
|
||||
);
|
||||
ref,
|
||||
) {
|
||||
const [open, setOpen] = useState(false);
|
||||
const [searchTerm, setSearchTerm] = useState('');
|
||||
const [expandedIds, setExpandedIds] = useState<Set<string>>(new Set());
|
||||
const { t } = useTranslation();
|
||||
|
||||
const handleClear = useCallback(
|
||||
(e: React.MouseEvent) => {
|
||||
e.stopPropagation();
|
||||
onChange?.('');
|
||||
},
|
||||
[onChange],
|
||||
);
|
||||
|
||||
const filterTree = useCallback(
|
||||
(nodes: TreeSelectNode[], term: string): TreeSelectNode[] => {
|
||||
if (!term) return nodes;
|
||||
return nodes.reduce<TreeSelectNode[]>((acc, node) => {
|
||||
const titleMatch = node.title
|
||||
.toLowerCase()
|
||||
.includes(term.toLowerCase());
|
||||
const filteredChildren = node.children
|
||||
? filterTree(node.children, term)
|
||||
: undefined;
|
||||
if (titleMatch || filteredChildren?.length) {
|
||||
acc.push({ ...node, children: filteredChildren ?? node.children });
|
||||
useEffect(() => {
|
||||
if (!defaultExpandAll) return;
|
||||
const ids = new Set<string>();
|
||||
const walk = (nodes: TreeSelectNode[]) => {
|
||||
for (const node of nodes) {
|
||||
if (node.children?.length) {
|
||||
ids.add(node.id);
|
||||
walk(node.children);
|
||||
}
|
||||
}
|
||||
return acc;
|
||||
}, []);
|
||||
},
|
||||
[],
|
||||
);
|
||||
};
|
||||
walk(data);
|
||||
setExpandedIds(ids);
|
||||
}, [data, defaultExpandAll]);
|
||||
|
||||
const filteredData = useMemo(
|
||||
() => filterTree(data, searchTerm),
|
||||
[data, searchTerm, filterTree],
|
||||
);
|
||||
|
||||
const visibleExpandedIds = useMemo(() => {
|
||||
if (!searchTerm) return expandedIds;
|
||||
const ids = new Set<string>();
|
||||
const walk = (nodes: TreeSelectNode[]) => {
|
||||
for (const node of nodes) {
|
||||
if (node.children?.length) {
|
||||
ids.add(node.id);
|
||||
walk(node.children);
|
||||
const selectedNode = useMemo(() => {
|
||||
const find = (nodes: TreeSelectNode[]): TreeSelectNode | undefined => {
|
||||
for (const node of nodes) {
|
||||
if (node.id === value && value) return node;
|
||||
if (node.children) {
|
||||
const found = find(node.children);
|
||||
if (found) return found;
|
||||
}
|
||||
}
|
||||
}
|
||||
};
|
||||
walk(filteredData);
|
||||
return ids;
|
||||
}, [searchTerm, expandedIds, filteredData]);
|
||||
};
|
||||
return find(data);
|
||||
}, [data, value]);
|
||||
|
||||
const renderTree = useCallback(
|
||||
(nodes: TreeSelectNode[], level = 0): React.ReactNode => {
|
||||
return nodes.map((node) => {
|
||||
const leaf = isLeaf(node);
|
||||
const expanded = visibleExpandedIds.has(node.id);
|
||||
const selected = value === node.id;
|
||||
const isLeaf = useCallback(
|
||||
(node: TreeSelectNode) => !node.children?.length,
|
||||
[],
|
||||
);
|
||||
|
||||
return (
|
||||
<div key={node.id}>
|
||||
<div
|
||||
className={cn(
|
||||
'flex items-center rounded-sm cursor-pointer text-sm',
|
||||
'hover:bg-accent transition-colors',
|
||||
!leaf && 'text-text-primary font-medium',
|
||||
selected && 'bg-accent text-accent-foreground',
|
||||
node.disabled && 'opacity-50 pointer-events-none',
|
||||
)}
|
||||
style={{
|
||||
paddingLeft: `${level * 20 + 4}px`,
|
||||
paddingRight: '8px',
|
||||
paddingTop: '6px',
|
||||
paddingBottom: '6px',
|
||||
}}
|
||||
onClick={() => handleSelect(node)}
|
||||
>
|
||||
<span className="w-4 h-4 mr-0.5 flex-shrink-0 flex items-center justify-center">
|
||||
{!leaf && (
|
||||
<>
|
||||
{expanded ? (
|
||||
<ChevronDown className="h-3.5 w-3.5 text-text-secondary" />
|
||||
) : (
|
||||
<ChevronRight className="h-3.5 w-3.5 text-text-secondary" />
|
||||
)}
|
||||
</>
|
||||
)}
|
||||
</span>
|
||||
<span className="truncate">{node.label ?? node.title}</span>
|
||||
</div>
|
||||
{!leaf && expanded && node.children && (
|
||||
<div>{renderTree(node.children, level + 1)}</div>
|
||||
)}
|
||||
</div>
|
||||
);
|
||||
const handleToggle = useCallback((id: string) => {
|
||||
setExpandedIds((prev) => {
|
||||
const next = new Set(prev);
|
||||
if (next.has(id)) {
|
||||
next.delete(id);
|
||||
} else {
|
||||
next.add(id);
|
||||
}
|
||||
return next;
|
||||
});
|
||||
},
|
||||
[isLeaf, visibleExpandedIds, value, handleSelect],
|
||||
);
|
||||
}, []);
|
||||
|
||||
return (
|
||||
<Popover open={open} onOpenChange={setOpen}>
|
||||
<PopoverTrigger asChild disabled={disabled}>
|
||||
<button
|
||||
type="button"
|
||||
data-testid={testId}
|
||||
className={cn(
|
||||
'flex items-center justify-between border border-border-button rounded-md px-3 py-1.5 w-full',
|
||||
'bg-bg-input text-sm',
|
||||
'hover:bg-border-button transition-colors',
|
||||
disabled && 'opacity-50 cursor-not-allowed',
|
||||
className,
|
||||
)}
|
||||
>
|
||||
<span className={cn('truncate', !selectedNode && 'text-slate-400')}>
|
||||
{renderSelected
|
||||
? renderSelected(selectedNode)
|
||||
: selectedNode?.title || placeholder || t('common.pleaseSelect')}
|
||||
</span>
|
||||
<div className="flex items-center ml-2 flex-shrink-0">
|
||||
{allowClear && value ? (
|
||||
<X
|
||||
className="h-4 w-4 opacity-50 hover:opacity-100"
|
||||
onClick={handleClear}
|
||||
/>
|
||||
) : (
|
||||
<ChevronDown className="h-4 w-4 opacity-50" />
|
||||
const handleSelect = useCallback(
|
||||
(node: TreeSelectNode) => {
|
||||
if (node.disabled) return;
|
||||
if (isLeaf(node)) {
|
||||
onChange?.(node.id);
|
||||
setOpen(false);
|
||||
setSearchTerm('');
|
||||
} else {
|
||||
handleToggle(node.id);
|
||||
}
|
||||
},
|
||||
[isLeaf, onChange, handleToggle],
|
||||
);
|
||||
|
||||
const handleClear = useCallback(
|
||||
(e: React.MouseEvent) => {
|
||||
e.stopPropagation();
|
||||
onChange?.('');
|
||||
},
|
||||
[onChange],
|
||||
);
|
||||
|
||||
const filterTree = useCallback(
|
||||
(nodes: TreeSelectNode[], term: string): TreeSelectNode[] => {
|
||||
if (!term) return nodes;
|
||||
return nodes.reduce<TreeSelectNode[]>((acc, node) => {
|
||||
const titleMatch = node.title
|
||||
.toLowerCase()
|
||||
.includes(term.toLowerCase());
|
||||
const filteredChildren = node.children
|
||||
? filterTree(node.children, term)
|
||||
: undefined;
|
||||
if (titleMatch || filteredChildren?.length) {
|
||||
acc.push({ ...node, children: filteredChildren ?? node.children });
|
||||
}
|
||||
return acc;
|
||||
}, []);
|
||||
},
|
||||
[],
|
||||
);
|
||||
|
||||
const filteredData = useMemo(
|
||||
() => filterTree(data, searchTerm),
|
||||
[data, searchTerm, filterTree],
|
||||
);
|
||||
|
||||
const visibleExpandedIds = useMemo(() => {
|
||||
if (!searchTerm) return expandedIds;
|
||||
const ids = new Set<string>();
|
||||
const walk = (nodes: TreeSelectNode[]) => {
|
||||
for (const node of nodes) {
|
||||
if (node.children?.length) {
|
||||
ids.add(node.id);
|
||||
walk(node.children);
|
||||
}
|
||||
}
|
||||
};
|
||||
walk(filteredData);
|
||||
return ids;
|
||||
}, [searchTerm, expandedIds, filteredData]);
|
||||
|
||||
const renderTree = useCallback(
|
||||
(nodes: TreeSelectNode[], level = 0): React.ReactNode => {
|
||||
return nodes.map((node) => {
|
||||
const leaf = isLeaf(node);
|
||||
const expanded = visibleExpandedIds.has(node.id);
|
||||
const selected = value === node.id;
|
||||
|
||||
return (
|
||||
<div key={node.id}>
|
||||
<div
|
||||
className={cn(
|
||||
'flex items-center rounded-sm cursor-pointer text-sm',
|
||||
'hover:bg-accent transition-colors',
|
||||
!leaf && 'text-text-primary font-medium',
|
||||
selected && 'bg-accent text-accent-foreground',
|
||||
node.disabled && 'opacity-50 pointer-events-none',
|
||||
)}
|
||||
style={{
|
||||
paddingLeft: `${level * 20 + 4}px`,
|
||||
paddingRight: '8px',
|
||||
paddingTop: '6px',
|
||||
paddingBottom: '6px',
|
||||
}}
|
||||
onClick={() => handleSelect(node)}
|
||||
>
|
||||
<span className="w-4 h-4 mr-0.5 flex-shrink-0 flex items-center justify-center">
|
||||
{!leaf && (
|
||||
<>
|
||||
{expanded ? (
|
||||
<ChevronDown className="h-3.5 w-3.5 text-text-secondary" />
|
||||
) : (
|
||||
<ChevronRight className="h-3.5 w-3.5 text-text-secondary" />
|
||||
)}
|
||||
</>
|
||||
)}
|
||||
</span>
|
||||
<span className="truncate">{node.label ?? node.title}</span>
|
||||
</div>
|
||||
{!leaf && expanded && node.children && (
|
||||
<div>{renderTree(node.children, level + 1)}</div>
|
||||
)}
|
||||
</div>
|
||||
);
|
||||
});
|
||||
},
|
||||
[isLeaf, visibleExpandedIds, value, handleSelect],
|
||||
);
|
||||
|
||||
return (
|
||||
<Popover open={open} onOpenChange={setOpen}>
|
||||
<PopoverTrigger asChild disabled={disabled}>
|
||||
<button
|
||||
ref={ref}
|
||||
type="button"
|
||||
data-testid={testId}
|
||||
className={cn(
|
||||
'flex items-center justify-between border border-border-button rounded-md px-3 py-1.5 w-full',
|
||||
'bg-bg-input text-sm',
|
||||
'hover:bg-border-button transition-colors',
|
||||
disabled && 'opacity-50 cursor-not-allowed',
|
||||
className,
|
||||
)}
|
||||
</div>
|
||||
</button>
|
||||
</PopoverTrigger>
|
||||
<PopoverContent
|
||||
className="p-0 w-auto min-w-[var(--radix-popover-trigger-width)]"
|
||||
align="start"
|
||||
sideOffset={4}
|
||||
>
|
||||
{showSearch && (
|
||||
<div className="flex items-center border-b px-3 py-2">
|
||||
<Search className="h-4 w-4 text-slate-400 mr-2 flex-shrink-0" />
|
||||
<input
|
||||
type="text"
|
||||
className="flex-1 bg-transparent text-sm outline-none placeholder:text-slate-400"
|
||||
placeholder={t('common.search')}
|
||||
value={searchTerm}
|
||||
onChange={(e) => setSearchTerm(e.target.value)}
|
||||
/>
|
||||
</div>
|
||||
)}
|
||||
<div
|
||||
className="max-h-60 overflow-auto p-1"
|
||||
onWheel={(e) => e.stopPropagation()}
|
||||
>
|
||||
<span className={cn('truncate', !selectedNode && 'text-slate-400')}>
|
||||
{renderSelected
|
||||
? renderSelected(selectedNode)
|
||||
: selectedNode?.title ||
|
||||
placeholder ||
|
||||
t('common.pleaseSelect')}
|
||||
</span>
|
||||
<div className="flex items-center ml-2 flex-shrink-0">
|
||||
{allowClear && value ? (
|
||||
<X
|
||||
className="h-4 w-4 opacity-50 hover:opacity-100"
|
||||
onClick={handleClear}
|
||||
/>
|
||||
) : (
|
||||
<ChevronDown className="h-4 w-4 opacity-50" />
|
||||
)}
|
||||
</div>
|
||||
</button>
|
||||
</PopoverTrigger>
|
||||
<PopoverContent
|
||||
className="p-0 w-auto min-w-[var(--radix-popover-trigger-width)]"
|
||||
align="start"
|
||||
sideOffset={4}
|
||||
>
|
||||
{filteredData.length > 0 ? (
|
||||
renderTree(filteredData)
|
||||
) : (
|
||||
<div className="py-6 text-center text-sm text-slate-400">
|
||||
{t('common.noData')}
|
||||
{showSearch && (
|
||||
<div className="flex items-center border-b px-3 py-2">
|
||||
<Search className="h-4 w-4 text-slate-400 mr-2 flex-shrink-0" />
|
||||
<input
|
||||
type="text"
|
||||
className="flex-1 bg-transparent text-sm outline-none placeholder:text-slate-400"
|
||||
placeholder={t('common.search')}
|
||||
value={searchTerm}
|
||||
onChange={(e) => setSearchTerm(e.target.value)}
|
||||
/>
|
||||
</div>
|
||||
)}
|
||||
</div>
|
||||
</PopoverContent>
|
||||
</Popover>
|
||||
);
|
||||
}
|
||||
<div
|
||||
className="max-h-60 overflow-auto p-1"
|
||||
onWheel={(e) => e.stopPropagation()}
|
||||
>
|
||||
{filteredData.length > 0 ? (
|
||||
renderTree(filteredData)
|
||||
) : (
|
||||
<div className="py-6 text-center text-sm text-slate-400">
|
||||
{t('common.noData')}
|
||||
</div>
|
||||
)}
|
||||
</div>
|
||||
</PopoverContent>
|
||||
</Popover>
|
||||
);
|
||||
},
|
||||
);
|
||||
|
||||
@@ -54,13 +54,13 @@ function InnerToolNode({
|
||||
/>
|
||||
|
||||
<NodeCollapsible items={[tools, mcpList]}>
|
||||
{(x) => {
|
||||
{(x, idx) => {
|
||||
if (Reflect.has(x, 'mcp_id')) {
|
||||
const mcp = x as unknown as IAgentForm['mcp'][number];
|
||||
|
||||
return (
|
||||
<ToolCard
|
||||
key={mcp.mcp_id}
|
||||
key={mcp.mcp_id || `mcp-${idx}`}
|
||||
onClick={(e) => {
|
||||
if (mcp.mcp_id === Operator.Code) {
|
||||
e.preventDefault();
|
||||
@@ -79,7 +79,7 @@ function InnerToolNode({
|
||||
|
||||
return (
|
||||
<ToolCard
|
||||
key={tool.id}
|
||||
key={tool.id || `tool-${idx}`}
|
||||
onClick={(e) => {
|
||||
if (tool.component_name === Operator.Code) {
|
||||
e.preventDefault();
|
||||
|
||||
@@ -39,25 +39,21 @@ export function ToolCard({
|
||||
isNodeTool = true,
|
||||
...props
|
||||
}: ToolCardProps) {
|
||||
const element = useMemo(() => {
|
||||
return (
|
||||
<LabelCard
|
||||
{...props}
|
||||
className={cn(
|
||||
'flex justify-between ',
|
||||
{ 'p-2.5 text-text-primary text-sm': !isNodeTool },
|
||||
className,
|
||||
)}
|
||||
>
|
||||
{children}
|
||||
</LabelCard>
|
||||
);
|
||||
}, [children, className, isNodeTool, props]);
|
||||
|
||||
if (children === Operator.Code) {
|
||||
return (
|
||||
<Tooltip>
|
||||
<TooltipTrigger asChild>{element}</TooltipTrigger>
|
||||
<TooltipTrigger asChild>
|
||||
<LabelCard
|
||||
{...props}
|
||||
className={cn(
|
||||
'flex justify-between ',
|
||||
{ 'p-2.5 text-text-primary text-sm': !isNodeTool },
|
||||
className,
|
||||
)}
|
||||
>
|
||||
{children}
|
||||
</LabelCard>
|
||||
</TooltipTrigger>
|
||||
<TooltipContent>
|
||||
<p>It doesn't have any config.</p>
|
||||
</TooltipContent>
|
||||
@@ -65,7 +61,18 @@ export function ToolCard({
|
||||
);
|
||||
}
|
||||
|
||||
return element;
|
||||
return (
|
||||
<LabelCard
|
||||
{...props}
|
||||
className={cn(
|
||||
'flex justify-between ',
|
||||
{ 'p-2.5 text-text-primary text-sm': !isNodeTool },
|
||||
className,
|
||||
)}
|
||||
>
|
||||
{children}
|
||||
</LabelCard>
|
||||
);
|
||||
}
|
||||
|
||||
type ActionButtonProps<T> = {
|
||||
@@ -131,22 +138,22 @@ export function AgentTools() {
|
||||
<section className="space-y-2.5">
|
||||
<span className="text-text-secondary text-sm">{t('flow.tools')}</span>
|
||||
<ul className="space-y-2.5">
|
||||
{tools.map(({ id, component_name, name }) => (
|
||||
<ToolCard key={id} isNodeTool={false}>
|
||||
{tools.map(({ id, component_name, name }, idx) => (
|
||||
<ToolCard key={id || `tool-${idx}`} isNodeTool={false}>
|
||||
<div className="flex gap-2 items-center">
|
||||
<OperatorIcon name={component_name as Operator}></OperatorIcon>
|
||||
{component_name === Operator.Retrieval ? name : component_name}
|
||||
</div>
|
||||
<ActionButton
|
||||
record={id}
|
||||
record={id || component_name}
|
||||
deleteRecord={deleteNodeTool(id)}
|
||||
edit={handleEdit}
|
||||
/>
|
||||
</ToolCard>
|
||||
))}
|
||||
|
||||
{mcpIds.map((id) => (
|
||||
<ToolCard key={id} isNodeTool={false}>
|
||||
{mcpIds.map((id, idx) => (
|
||||
<ToolCard key={id || `mcp-${idx}`} isNodeTool={false}>
|
||||
{findMcpById(id)?.name}
|
||||
<ActionButton
|
||||
record={id}
|
||||
|
||||
Reference in New Issue
Block a user