UI updates (#6290)

### What problem does this PR solve?



### Type of change


- [x] Documentation Update

docs/guides/agent/agent_component_reference/retrieval.mdx

@@ -53,23 +53,31 @@ Using a rerank model will *significantly* increase the system's response time.
 
 ### Tavily API key
 
-If an API key is correctly set here, Tavily-based web searches will be used to supplement knowledge base retrieval.
+*Optional*
+
+Enter your Tavily API key here to enable Tavily web search during retrieval. See [here](https://app.tavily.com/home) for instructions on getting a Tavily API key.
 
 ### Use knowledge graph
 
-It will retrieve descriptions of relevant entities,relations and community reports, which will enhance inference of multi-hop and complex question.
+Whether to use knowledge graph(s) in the specified knowledge base(s) during retrieval for multi-hop question answering. When enabled, this would involve iterative searches across entity, relationship, and community report chunks, greatly increasing retrieval time.
 
 ### Knowledge bases 
 
+*Optional*
+
 Select the knowledge base(s) to retrieve data from.
 
-:::danger IMPORTANT 
-If you select multiple knowledge bases, you must ensure that the knowledge bases (datasets) you select use the same embedding model; otherwise, an error message would occur.
-:::
+- If no knowledge base is selected, meaning conversations with the agent will not be based on any knowledge base, ensure that the **Empty response** field is left blank to avoid an error.
+- If you select multiple knowledge bases, you must ensure that the knowledge bases (datasets) you select use the same embedding model; otherwise, an error message would occur.
 
 ### Empty response
 
-Set this as a response if no results are retrieved from the knowledge bases for your query, or leave this field blank to allow the LLM to improvise when nothing is found.
+- Set this as a response if no results are retrieved from the knowledge base(s) for your query, or 
+- Leave this field blank to allow the chat model to improvise when nothing is found.
+
+:::caution WARNING
+If you do not specify a knowledge base, you must leave this field blank; otherwise, an error would occur.
+:::
 
 ## Examples
 

docs/guides/chat/start_chat.md

@@ -37,6 +37,8 @@ You start an AI conversation by creating an assistant.
      - If **Rerank model** is selected, the hybrid score system uses keyword similarity and reranker score, and the default weight assigned to the reranker score is 1-0.7=0.3.
    - **Top N** determines the *maximum* number of chunks to feed to the LLM. In other words, even if more chunks are retrieved, only the top N chunks are provided as input.
    - **Multi-turn optimization** enhances user queries using existing context in a multi-round conversation. It is enabled by default. When enabled, it will consume additional LLM tokens and significantly increase the time to generate answers.
+   - **Use knowledge graph** indicates whether to use knowledge graph(s) in the specified knowledge base(s) during retrieval for multi-hop question answering. When enabled, this would involve iterative searches across entity, relationship, and community report chunks, greatly increasing retrieval time.
+   - **Reasoning** indicates whether to generate answers through reasoning processes like Deepseek-R1/OpenAI o1. Once enabled, the chat model autonomously integrates Deep Research during question answering when encountering an unknown topic. This involves the chat model dynamically searching external knowledge and generating final answers through reasoning.
    - **Rerank model** sets the reranker model to use. It is left empty by default.
      - If **Rerank model** is left empty, the hybrid score system uses keyword similarity and vector similarity, and the default weight assigned to the vector similarity component is 1-0.7=0.3.
      - If **Rerank model** is selected, the hybrid score system uses keyword similarity and reranker score, and the default weight assigned to the reranker score is 1-0.7=0.3.

docs/guides/dataset/use_tag_sets.md

@@ -13,7 +13,7 @@ Retrieval accuracy is the touchstone for a production-ready RAG framework. In ad
 
 To use this feature, ensure you have at least one properly configured tag set, specify the tag set(s) on the **Configuration** page of your knowledge base (dataset), and then re-parse your documents to initiate the auto-tag process. During this process, each chunk in your dataset is compared with every entry in the specified tag set(s), and tags are automatically applied based on similarity.
 
-:::danger IMPORTANT
+:::caution NOTE
 The auto-tagging feature is *unavailable* on the [Infinity](https://github.com/infiniflow/infinity) document engine.
 :::
 

web/src/locales/de.ts

@@ -541,7 +541,7 @@ export default {
       descriptionPlaceholder: 'z.B. Ein Chat-Assistent für Lebensläufe.',
       useKnowledgeGraph: 'Wissensgraph verwenden',
       useKnowledgeGraphTip:
-        'Es werden Beschreibungen relevanter Entitäten, Beziehungen und Gemeinschaftsberichte abgerufen, was die Inferenz von mehrschrittigen und komplexen Fragen verbessert.',
+        'Ob ein Wissensgraph im angegebenen Wissensspeicher während der Wiederherstellung für die Beantwortung von Fragen mit mehreren Schritten verwendet werden soll. Wenn aktiviert, beinhaltet dies iterative Suchen über Entitäten-, Beziehungs- und Gemeinschaftsberichtssegmente, was die Wiederherstellungszeit erheblich verlängert.',
       keyword: 'Schlüsselwortanalyse',
       keywordTip:
         'LLM anwenden, um die Fragen des Benutzers zu analysieren und Schlüsselwörter zu extrahieren, die während der Relevanzberechnung hervorgehoben werden.',
@@ -552,7 +552,7 @@ export default {
       selectLanguage: 'Sprache auswählen',
       reasoning: 'Schlussfolgerung',
       reasoningTip:
-        'Es wird ein Schlussfolgerungsprozess wie bei Deepseek-R1/OpenAI o1 ausgelöst. Integriert einen agentischen Suchprozess in den Schlussfolgerungsworkflow, der es Modellen ermöglicht, dynamisch externes Wissen abzurufen, wenn sie auf unsichere Informationen stoßen.',
+        'Ob Antworten durch Denkprozesse wie DeepSeek-R1/OpenAI o1 generiert werden sollen. Wenn aktiviert, integriert das Chat-Modell Deep Research autonom während der Beantwortung von Fragen, wenn es auf ein unbekanntes Thema trifft. Dies beinhaltet, dass das Chat-Modell dynamisch externe Kenntnisse durchsucht und endgültige Antworten durch Denkprozesse generiert.',
       tavilyApiKeyTip:
         'Wenn hier ein API-Schlüssel korrekt eingestellt ist, werden Tavily-basierte Websuchen verwendet, um den Abruf aus der Wissensdatenbank zu ergänzen.',
       tavilyApiKeyMessage: 'Bitte geben Sie Ihren Tavily-API-Schlüssel ein',

web/src/locales/en.ts

@@ -524,7 +524,7 @@ This auto-tag feature enhances retrieval by adding another layer of domain-speci
       descriptionPlaceholder: 'e.g. A chat assistant for resume.',
       useKnowledgeGraph: 'Use knowledge graph',
       useKnowledgeGraphTip:
-        'It will retrieve descriptions of relevant entities,relations and community reports, which will enhance inference of multi-hop and complex question.',
+        'Whether to use knowledge graph(s) in the specified knowledge base(s) during retrieval for multi-hop question answering. When enabled, this would involve iterative searches across entity, relationship, and community report chunks, greatly increasing retrieval time.',
       keyword: 'Keyword analysis',
       keywordTip: `Apply LLM to analyze user's questions, extract keywords which will be emphasize during the relevance computation.`,
       languageTip:

web/src/locales/vi.ts

@@ -494,7 +494,7 @@ export default {
       betaError: `"Beta API Token" không được để trống!`,
       useKnowledgeGraph: 'Sử dụng đồ thị tri thức',
       useKnowledgeGraphTip:
-        'Nó sẽ truy xuất các mô tả về các thực thể, quan hệ và cộng đồng liên quan, điều này sẽ tăng cường khả năng suy luận các câu hỏi phức tạp và nhiều bước.',
+        'Có nên sử dụng đồ thị tri thức trong cơ sở tri thức được chỉ định trong quá trình thu hồi để trả lời câu hỏi đa bước hay không. Khi được kích hoạt, điều này sẽ liên quan đến các tìm kiếm lặp lại trên các đoạn thực thể, mối quan hệ và báo cáo cộng đồng, làm tăng đáng kể thời gian thu hồi.',
       keyword: 'Phân tích từ khóa',
       keywordTip:
         'Áp dụng LLM (Mô hình ngôn ngữ lớn) để phân tích câu hỏi của người dùng, trích xuất các từ khóa sẽ được nhấn mạnh trong quá trình tính toán độ liên quan.',

web/src/locales/zh-traditional.ts

@@ -515,7 +515,7 @@ export default {
       keywordTip: `應用LLM分析使用者的問題，提取在相關性計算中需要強調的關鍵字。`,
       reasoning: '推理',
       reasoningTip:
-        '它將觸發類似Deepseek-R1/OpenAI o1的推理過程。將代理搜尋過程整合到推理工作流程中，使得模型本身能夠在遇到不確定資訊時動態地檢索外部知識。',
+        '是否像 DeepSeek-R1 / OpenAI o1 一樣通過推理產生答案。啟用後，允許模型在遇到未知情況時將代理搜索過程整合到推理工作流中，自行動態檢索外部知識，並通過推理生成最終答案。',
       tavilyApiKeyTip:
         '如果 API 金鑰設定正確，它將利用 Tavily 進行網路搜尋作為知識庫的補充。',
       tavilyApiKeyMessage: '請輸入你的 Tavily API Key',

web/src/locales/zh.ts

@@ -527,12 +527,12 @@ General：实体和关系提取提示来自 GitHub - microsoft/graphrag：基于
         '例如 你是一个专业的简历助手，只能回答简历的问题。',
       useKnowledgeGraph: '使用知识图谱',
       useKnowledgeGraphTip:
-        '它将检索相关实体、关系和社区报告的描述，这将增强多跳和复杂问题的推理。',
+        '是否检索与所选知识库对应的知识图谱相关文本块，以处理复杂的多跳问题？这一过程将涉及对实体、关系和社区报告文本块的多次检索，会显著延长检索时间。',
       keyword: '关键词分析',
       keywordTip: `应用 LLM 分析用户的问题，提取在相关性计算中要强调的关键词。`,
       reasoning: '推理',
       reasoningTip:
-        '它将像Deepseek-R1 / OpenAI o1一样触发推理过程。将代理搜索过程集成到推理工作流中，允许模型本身在遇到不确定信息时动态地检索外部知识。',
+        '是否像 Deepseek-R1 / OpenAI o1一样通过推理产生答案。启用后，允许模型在遇到未知情况时将代理搜索过程集成到推理工作流中，自行动态检索外部知识，并通过推理生成最终答案。',
       tavilyApiKeyTip:
         '如果 API 密钥设置正确，它将利用 Tavily 进行网络搜索作为知识库的补充。',
       tavilyApiKeyMessage: '请输入你的 Tavily API Key',