mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-05 15:10:20 +08:00
8d9d767051
* feat(eval): add report quality evaluation module Addresses issue #773 - How to evaluate generated report quality objectively. This module provides two evaluation approaches: 1. Automated metrics (no LLM required): - Citation count and source diversity - Word count compliance per report style - Section structure validation - Image inclusion tracking 2. LLM-as-Judge evaluation: - Factual accuracy scoring - Completeness assessment - Coherence evaluation - Relevance and citation quality checks The combined evaluator provides a final score (1-10) and letter grade (A+ to F). Files added: - src/eval/__init__.py - src/eval/metrics.py - src/eval/llm_judge.py - src/eval/evaluator.py - tests/unit/eval/test_metrics.py - tests/unit/eval/test_evaluator.py * feat(eval): integrate report evaluation with web UI This commit adds the web UI integration for the evaluation module: Backend: - Add EvaluateReportRequest/Response models in src/server/eval_request.py - Add /api/report/evaluate endpoint to src/server/app.py Frontend: - Add evaluateReport API function in web/src/core/api/evaluate.ts - Create EvaluationDialog component with grade badge, metrics display, and optional LLM deep evaluation - Add evaluation button (graduation cap icon) to research-block.tsx toolbar - Add i18n translations for English and Chinese The evaluation UI allows users to: 1. View quick metrics-only evaluation (instant) 2. Optionally run deep LLM-based evaluation for detailed analysis 3. See grade (A+ to F), score (1-10), and metric breakdown * feat(eval): improve evaluation reliability and add LLM judge tests - Extract MAX_REPORT_LENGTH constant in llm_judge.py for maintainability - Add comprehensive unit tests for LLMJudge class (parse_response, calculate_weighted_score, evaluate with mocked LLM) - Pass reportStyle prop to EvaluationDialog for accurate evaluation criteria - Add researchQueries store map to reliably associate queries with research - Add getResearchQuery helper to retrieve query by researchId - Remove unused imports in test_metrics.py * fix(eval): use resolveServiceURL for evaluate API endpoint The evaluateReport function was using a relative URL '/api/report/evaluate' which sent requests to the Next.js server instead of the FastAPI backend. Changed to use resolveServiceURL() consistent with other API functions. * fix: improve type accuracy and React hooks in evaluation components - Fix get_word_count_target return type from Optional[Dict] to Dict since it always returns a value via default fallback - Fix useEffect dependency issue in EvaluationDialog using useRef to prevent unwanted re-evaluations - Add aria-label to GradeBadge for screen reader accessibility
286 lines
13 KiB
JSON
286 lines
13 KiB
JSON
{
|
|
"common": {
|
|
"cancel": "Cancel",
|
|
"save": "Save",
|
|
"settings": "Settings",
|
|
"getStarted": "Get Started",
|
|
"learnMore": "Learn More",
|
|
"starOnGitHub": "Star on GitHub",
|
|
"send": "Send",
|
|
"stop": "Stop",
|
|
"linkNotReliable": "This link might be a hallucination from AI model and may not be reliable.",
|
|
"noResult": "No result"
|
|
},
|
|
"messageInput": {
|
|
"placeholder": "What can I do for you?",
|
|
"placeholderWithRag": "What can I do for you? \nYou may refer to RAG resources by using @."
|
|
},
|
|
"header": {
|
|
"title": "DeerFlow"
|
|
},
|
|
"hero": {
|
|
"title": "Deep Research",
|
|
"subtitle": "at Your Fingertips",
|
|
"description": "Meet DeerFlow, your personal Deep Research assistant. With powerful tools like search engines, web crawlers, Python and MCP services, it delivers instant insights, comprehensive reports, and even captivating podcasts.",
|
|
"footnote": "* DEER stands for Deep Exploration and Efficient Research."
|
|
},
|
|
"settings": {
|
|
"title": "DeerFlow Settings",
|
|
"description": "Manage your DeerFlow settings here.",
|
|
"addServers": "Add Servers",
|
|
"cancel": "Cancel",
|
|
"addNewMCPServers": "Add New MCP Servers",
|
|
"mcpConfigDescription": "DeerFlow uses the standard JSON MCP config to create a new server.",
|
|
"pasteConfigBelow": "Paste your config below and click \"Add\" to add new servers.",
|
|
"rag": {
|
|
"title": "Resources",
|
|
"description": "Manage your knowledge base resources here. Upload markdown or text files to be indexed for retrieval.",
|
|
"upload": "Upload",
|
|
"uploading": "Uploading...",
|
|
"uploadSuccess": "File uploaded successfully",
|
|
"uploadFailed": "Failed to upload file",
|
|
"emptyFile": "Cannot upload an empty file",
|
|
"loading": "Loading resources...",
|
|
"noResources": "No resources found. Upload a file to get started."
|
|
},
|
|
"add": "Add",
|
|
"general": {
|
|
"title": "General",
|
|
"autoAcceptPlan": "Allow automatic acceptance of plans",
|
|
"enableClarification": "Allow clarification",
|
|
"maxClarificationRounds": "Max clarification rounds",
|
|
"maxClarificationRoundsDescription": "Maximum number of clarification rounds when clarification is enabled (default: 3).",
|
|
"maxPlanIterations": "Max plan iterations",
|
|
"maxPlanIterationsDescription": "Set to 1 for single-step planning. Set to 2 or more to enable re-planning.",
|
|
"maxStepsOfPlan": "Max steps of a research plan",
|
|
"maxStepsDescription": "By default, each research plan has 3 steps.",
|
|
"maxSearchResults": "Max search results",
|
|
"maxSearchResultsDescription": "By default, each search step has 3 results.",
|
|
"enableWebSearch": "Enable web search",
|
|
"enableWebSearchDescription": "When disabled, only local RAG knowledge base will be used. Useful for environments without internet access."
|
|
},
|
|
"mcp": {
|
|
"title": "MCP Servers",
|
|
"description": "The Model Context Protocol boosts DeerFlow by integrating external tools for tasks like private domain searches, web browsing, food ordering, and more. Click here to",
|
|
"learnMore": "learn more about MCP.",
|
|
"enableDisable": "Enable/disable server",
|
|
"deleteServer": "Delete server",
|
|
"editServer": "Edit server",
|
|
"refreshServer": "Refresh server",
|
|
"editServerDescription": "Edit the MCP server configuration",
|
|
"editServerNote": "Update the server configuration in JSON format",
|
|
"disabled": "Disabled",
|
|
"new": "New",
|
|
"invalidJson": "Invalid JSON format",
|
|
"validationFailed": "Validation failed",
|
|
"missingServerName": "Missing server name"
|
|
},
|
|
"about": {
|
|
"title": "About"
|
|
},
|
|
"reportStyle": {
|
|
"writingStyle": "Writing Style",
|
|
"chooseTitle": "Choose Writing Style",
|
|
"chooseDesc": "Select the writing style for your research reports. Different styles are optimized for different audiences and purposes.",
|
|
"academic": "Academic",
|
|
"academicDesc": "Formal, objective, and analytical with precise terminology",
|
|
"popularScience": "Popular Science",
|
|
"popularScienceDesc": "Engaging and accessible for general audience",
|
|
"news": "News",
|
|
"newsDesc": "Factual, concise, and impartial journalistic style",
|
|
"socialMedia": "Social Media",
|
|
"socialMediaDesc": "Concise, attention-grabbing, and shareable",
|
|
"strategicInvestment": "Strategic Investment",
|
|
"strategicInvestmentDesc": "Deep, comprehensive analysis for strategic investment institutions with actionable insights"
|
|
}
|
|
},
|
|
"footer": {
|
|
"quote": "Originated from Open Source, give back to Open Source.",
|
|
"license": "Licensed under MIT License",
|
|
"copyright": "DeerFlow"
|
|
},
|
|
"chat": {
|
|
"page": {
|
|
"loading": "Loading DeerFlow...",
|
|
"welcomeUser": "Welcome, {username}",
|
|
"starOnGitHub": "Star DeerFlow on GitHub"
|
|
},
|
|
"welcome": {
|
|
"greeting": "👋 Hello, there!",
|
|
"description": "Welcome to 🦌 DeerFlow, a deep research assistant built on cutting-edge language models, helps you search on web, browse information, and handle complex tasks."
|
|
},
|
|
"conversationStarters": [
|
|
"How many times taller is the Eiffel Tower than the tallest building in the world?",
|
|
"How many years does an average Tesla battery last compared to a gasoline engine?",
|
|
"How many liters of water are required to produce 1 kg of beef?",
|
|
"How many times faster is the speed of light compared to the speed of sound?"
|
|
],
|
|
"inputBox": {
|
|
"deepThinking": "Deep Thinking",
|
|
"deepThinkingTooltip": {
|
|
"title": "Deep Thinking Mode: {status}",
|
|
"description": "When enabled, DeerFlow will use reasoning model ({model}) to generate more thoughtful plans."
|
|
},
|
|
"investigation": "Investigation",
|
|
"investigationTooltip": {
|
|
"title": "Investigation Mode: {status}",
|
|
"description": "When enabled, DeerFlow will perform a quick search before planning. This is useful for researches related to ongoing events and news."
|
|
},
|
|
"enhancePrompt": "Enhance prompt with AI",
|
|
"on": "On",
|
|
"off": "Off"
|
|
},
|
|
"research": {
|
|
"deepResearch": "Deep Research",
|
|
"researching": "Researching...",
|
|
"generatingReport": "Generating report...",
|
|
"reportGenerated": "Report generated",
|
|
"open": "Open",
|
|
"close": "Close",
|
|
"deepThinking": "Deep Thinking",
|
|
"report": "Report",
|
|
"activities": "Activities",
|
|
"generatePodcast": "Generate podcast",
|
|
"edit": "Edit",
|
|
"copy": "Copy",
|
|
"downloadReport": "Download report",
|
|
"downloadMarkdown": "Markdown (.md)",
|
|
"downloadHTML": "HTML (.html)",
|
|
"downloadPDF": "PDF (.pdf)",
|
|
"downloadWord": "Word (.docx)",
|
|
"downloadImage": "Image (.png)",
|
|
"exportFailed": "Export failed, please try again",
|
|
"evaluateReport": "Evaluate report quality",
|
|
"searchingFor": "Searching for",
|
|
"reading": "Reading",
|
|
"runningPythonCode": "Running Python code",
|
|
"errorExecutingCode": "Error when executing the above code",
|
|
"executionOutput": "Execution output",
|
|
"retrievingDocuments": "Retrieving documents from RAG",
|
|
"running": "Running",
|
|
"generatingPodcast": "Generating podcast...",
|
|
"nowPlayingPodcast": "Now playing podcast...",
|
|
"podcast": "Podcast",
|
|
"errorGeneratingPodcast": "Error when generating podcast. Please try again.",
|
|
"downloadPodcast": "Download podcast"
|
|
},
|
|
"evaluation": {
|
|
"title": "Report Quality Evaluation",
|
|
"description": "Evaluate your report using automated metrics and AI analysis.",
|
|
"evaluating": "Evaluating report...",
|
|
"analyzing": "Running deep analysis...",
|
|
"overallScore": "Overall Score",
|
|
"metrics": "Report Metrics",
|
|
"wordCount": "Word Count",
|
|
"citations": "Citations",
|
|
"sources": "Unique Sources",
|
|
"images": "Images",
|
|
"sectionCoverage": "Section Coverage",
|
|
"detailedAnalysis": "Detailed Analysis",
|
|
"deepEvaluation": "Deep Evaluation (AI)",
|
|
"strengths": "Strengths",
|
|
"weaknesses": "Areas for Improvement",
|
|
"scores": {
|
|
"factual_accuracy": "Factual Accuracy",
|
|
"completeness": "Completeness",
|
|
"coherence": "Coherence",
|
|
"relevance": "Relevance",
|
|
"citation_quality": "Citation Quality",
|
|
"writing_quality": "Writing Quality"
|
|
}
|
|
},
|
|
"messages": {
|
|
"replaying": "Replaying",
|
|
"replayDescription": "DeerFlow is now replaying the conversation...",
|
|
"replayHasStopped": "The replay has been stopped.",
|
|
"replayModeDescription": "You're now in DeerFlow's replay mode. Click the \"Play\" button on the right to start.",
|
|
"play": "Play",
|
|
"fastForward": "Fast Forward",
|
|
"demoNotice": "* This site is for demo purposes only. If you want to try your own question, please",
|
|
"clickHere": "click here",
|
|
"cloneLocally": "to clone it locally and run it."
|
|
},
|
|
"multiAgent": {
|
|
"moveToPrevious": "Move to the previous step",
|
|
"playPause": "Play / Pause",
|
|
"moveToNext": "Move to the next step",
|
|
"toggleFullscreen": "Toggle fullscreen"
|
|
}
|
|
},
|
|
"landing": {
|
|
"caseStudies": {
|
|
"title": "Case Studies",
|
|
"description": "See DeerFlow in action through replays.",
|
|
"clickToWatch": "Click to watch replay",
|
|
"cases": [
|
|
{
|
|
"title": "How tall is Eiffel Tower compared to tallest building?",
|
|
"description": "The research compares the heights and global significance of the Eiffel Tower and Burj Khalifa, and uses Python code to calculate the multiples."
|
|
},
|
|
{
|
|
"title": "What are the top trending repositories on GitHub?",
|
|
"description": "The research utilized MCP services to identify the most popular GitHub repositories and documented them in detail using search engines."
|
|
},
|
|
{
|
|
"title": "Write an article about Nanjing's traditional dishes",
|
|
"description": "The study vividly showcases Nanjing's famous dishes through rich content and imagery, uncovering their hidden histories and cultural significance."
|
|
},
|
|
{
|
|
"title": "How to decorate a small rental apartment?",
|
|
"description": "The study provides readers with practical and straightforward methods for decorating apartments, accompanied by inspiring images."
|
|
},
|
|
{
|
|
"title": "Introduce the movie 'Léon: The Professional'",
|
|
"description": "The research provides a comprehensive introduction to the movie 'Léon: The Professional', including its plot, characters, and themes."
|
|
},
|
|
{
|
|
"title": "How do you view the takeaway war in China? (in Chinese)",
|
|
"description": "The research analyzes the intensifying competition between JD and Meituan, highlighting their strategies, technological innovations, and challenges."
|
|
},
|
|
{
|
|
"title": "Are ultra-processed foods linked to health?",
|
|
"description": "The research examines the health risks of rising ultra-processed food consumption, urging more research on long-term effects and individual differences."
|
|
},
|
|
{
|
|
"title": "Write an article on \"Would you insure your AI twin?\"",
|
|
"description": "The research explores the concept of insuring AI twins, highlighting their benefits, risks, ethical considerations, and the evolving regulatory."
|
|
}
|
|
]
|
|
},
|
|
"coreFeatures": {
|
|
"title": "Core Features",
|
|
"description": "Find out what makes DeerFlow effective.",
|
|
"features": [
|
|
{
|
|
"name": "Dive Deeper and Reach Wider",
|
|
"description": "Unlock deeper insights with advanced tools. Our powerful search + crawling and Python tools gathers comprehensive data, delivering in-depth reports to enhance your study."
|
|
},
|
|
{
|
|
"name": "Human-in-the-loop",
|
|
"description": "Refine your research plan, or adjust focus areas all through simple natural language."
|
|
},
|
|
{
|
|
"name": "Lang Stack",
|
|
"description": "Build with confidence using the LangChain and LangGraph frameworks."
|
|
},
|
|
{
|
|
"name": "MCP Integrations",
|
|
"description": "Supercharge your research workflow and expand your toolkit with seamless MCP integrations."
|
|
},
|
|
{
|
|
"name": "Podcast Generation",
|
|
"description": "Instantly generate podcasts from reports. Perfect for on-the-go learning or sharing findings effortlessly."
|
|
}
|
|
]
|
|
},
|
|
"multiAgent": {
|
|
"title": "Multi-Agent Architecture",
|
|
"description": "Experience the agent teamwork with our Supervisor + Handoffs design pattern."
|
|
},
|
|
"joinCommunity": {
|
|
"title": "Join the DeerFlow Community",
|
|
"description": "Contribute brilliant ideas to shape the future of DeerFlow. Collaborate, innovate, and make impacts.",
|
|
"contributeNow": "Contribute Now"
|
|
}
|
|
}
|
|
} |