Files
deer-flow/web/messages/en.json
jimmyuconn1982 2510cc61de feat: Add intelligent clarification feature in coordinate step for research queries (#613)
* fix: support local models by making thought field optional in Plan model

- Make thought field optional in Plan model to fix Pydantic validation errors with local models
- Add Ollama configuration example to conf.yaml.example
- Update documentation to include local model support
- Improve planner prompt with better JSON format requirements

Fixes local model integration issues where models like qwen3:14b would fail
due to missing thought field in JSON output.

* feat: Add intelligent clarification feature for research queries

- Add multi-turn clarification process to refine vague research questions
- Implement three-dimension clarification standard (Tech/App, Focus, Scope)
- Add clarification state management in coordinator node
- Update coordinator prompt with detailed clarification guidelines
- Add UI settings to enable/disable clarification feature (disabled by default)
- Update workflow to handle clarification rounds recursively
- Add comprehensive test coverage for clarification functionality
- Update documentation with clarification feature usage guide

Key components:
- src/graph/nodes.py: Core clarification logic and state management
- src/prompts/coordinator.md: Detailed clarification guidelines
- src/workflow.py: Recursive clarification handling
- web/: UI settings integration
- tests/: Comprehensive test coverage
- docs/: Updated configuration guide

* fix: Improve clarification conversation continuity

- Add comprehensive conversation history to clarification context
- Include previous exchanges summary in system messages
- Add explicit guidelines for continuing rounds in coordinator prompt
- Prevent LLM from starting new topics during clarification
- Ensure topic continuity across clarification rounds

Fixes issue where LLM would restart clarification instead of building upon previous exchanges.

* fix: Add conversation history to clarification context

* fix: resolve clarification feature message to planer, prompt, test issues

- Optimize coordinator.md prompt template for better clarification flow
- Simplify final message sent to planner after clarification
- Fix API key assertion issues in test_search.py

* fix: Add configurable max_clarification_rounds and comprehensive tests

- Add max_clarification_rounds parameter for external configuration
- Add comprehensive test cases for clarification feature in test_app.py
- Fixes issues found during interactive mode testing where:
  - Recursive call failed due to missing initial_state parameter
  - Clarification exited prematurely at max rounds
  - Incorrect logging of max rounds reached

* Move clarification tests to test_nodes.py and add max_clarification_rounds to zh.json
2025-10-14 13:35:57 +08:00

235 lines
10 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.",
"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."
},
"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",
"disabled": "Disabled",
"new": "New"
},
"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 as markdown",
"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"
},
"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"
}
}
}