mirror of
https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git
synced 2025-08-14 02:45:54 +08:00
### What problem does this PR solve? Feat: Add reasoning item to chat configuration modal #5173 ### Type of change - [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
parent
39b96849a9
commit
f52970b038
@ -527,6 +527,9 @@ This procedure will improve precision of retrieval by adding more information to
|
|||||||
'Allows sentence rewriting with the specified language or defaults to the latest question if not selected.',
|
'Allows sentence rewriting with the specified language or defaults to the latest question if not selected.',
|
||||||
avatarHidden: 'Hide avatar',
|
avatarHidden: 'Hide avatar',
|
||||||
locale: 'Locale',
|
locale: 'Locale',
|
||||||
|
reasoning: 'Reasoning',
|
||||||
|
reasoningTip:
|
||||||
|
'It will trigger reasoning process like Deepseek-R1/OpenAI o1. Integrates an agentic search process into the reasoning workflow, allowing models itself to dynamically retrieve external knowledge whenever they encounter uncertain information.',
|
||||||
},
|
},
|
||||||
setting: {
|
setting: {
|
||||||
profile: 'Profile',
|
profile: 'Profile',
|
||||||
|
@ -506,6 +506,9 @@ export default {
|
|||||||
'它將檢索相關實體、關係和社區報告的描述,這將增強多跳和複雜問題的推理。',
|
'它將檢索相關實體、關係和社區報告的描述,這將增強多跳和複雜問題的推理。',
|
||||||
keyword: '關鍵字分析',
|
keyword: '關鍵字分析',
|
||||||
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。`,
|
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。',
|
||||||
},
|
},
|
||||||
setting: {
|
setting: {
|
||||||
profile: '概述',
|
profile: '概述',
|
||||||
|
@ -523,6 +523,9 @@ General:实体和关系提取提示来自 GitHub - microsoft/graphrag:基于
|
|||||||
'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。',
|
'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。',
|
||||||
keyword: '关键词分析',
|
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。`,
|
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。',
|
||||||
},
|
},
|
||||||
setting: {
|
setting: {
|
||||||
profile: '概要',
|
profile: '概要',
|
||||||
|
@ -172,6 +172,14 @@ const PromptEngine = (
|
|||||||
<UseKnowledgeGraphItem
|
<UseKnowledgeGraphItem
|
||||||
filedName={['prompt_config', 'use_kg']}
|
filedName={['prompt_config', 'use_kg']}
|
||||||
></UseKnowledgeGraphItem>
|
></UseKnowledgeGraphItem>
|
||||||
|
<Form.Item
|
||||||
|
label={t('reasoning')}
|
||||||
|
tooltip={t('reasoningTip')}
|
||||||
|
name={['prompt_config', 'reasoning']}
|
||||||
|
initialValue={false}
|
||||||
|
>
|
||||||
|
<Switch></Switch>
|
||||||
|
</Form.Item>
|
||||||
<Rerank></Rerank>
|
<Rerank></Rerank>
|
||||||
<section className={classNames(styles.variableContainer)}>
|
<section className={classNames(styles.variableContainer)}>
|
||||||
<Row align={'middle'} justify="end">
|
<Row align={'middle'} justify="end">
|
||||||
|
Loading…
x
Reference in New Issue
Block a user