The Knowledge Retrieval node is a core capability in the XpertAI agent workflow, providing highly relevant information support for user queries. It automatically retrieves content snippets semantically related to the query from a pre-built knowledge base, serving as contextual input for downstream agents to understand, analyze, and generate responses.
Main Capabilities
Function
Description
🔍 Semantic Matching
Automatically identifies the core intent of user input and retrieves the most semantically relevant knowledge snippets
📂 Content Support
Supports retrieval of structured and unstructured document content, such as policy documents, FAQs, product manuals, etc.
🎯 Precise Recall
Supports recall of multiple relevant content items, enabling comprehensive judgment by downstream nodes
🧭 Intelligent Filtering
Enforces a fixed business boundary and lets the agent narrow retrieval with registered system and metadata fields
🔄 Composability
Can be flexibly combined with any language model node (e.g., reasoning models) to form complex task flows
🔗 Multi-Knowledge Source Support
Configurable to access multiple knowledge bases for cross-business or multi-domain information retrieval
Usage
1. Input Parameters
The Knowledge Retrieval node accepts input from upstream nodes, typically a user’s natural language question or a standardized query processed by an agent.
{ "question": "What are the company's rules for compensatory leave?"}
2. Retrieval and filter configuration
Each Knowledge Retrieval node stores an independent configuration for every bound knowledge base:
Retrieval mode: intelligent filtering currently applies to Vector mode;
Fixed filter: configured by the workflow designer with constants or workflow variables and cannot be changed by the agent at runtime;
Allow agent automatic filtering: lets the agent add valid request-specific conditions inferred from the question;
Multiple knowledge bases: each binding retains its own fixed filter and agent-filter switch.
Fixed, caller, and agent-generated filters are always combined with AND. A missing or mistyped fixed variable stops retrieval. An invalid dynamic filter is discarded as a whole, and retrieval continues with the fixed filter.See Intelligent Retrieval Filtering for fields, operators, zero-hit behavior, and the support matrix.
3. Output Structure
The Knowledge Retrieval node returns a list of documents in the format of Langchain’s Document object. Each document contains two parts:
page_content: The actual retrieved text content
metadata: Metadata related to the content (e.g., source, document name, segment index, etc.)
** 📄 Output Example **:
[ { "pageContent": "According to company policy, employees may apply for compensatory leave within 5 working days after overtime.", "id": "123", "metadata": { "source": "HR_Employee_Policy_v3.pdf", "section": "Compensatory Leave Policy", "page": 12 } }, { "pageContent": "Compensatory leave applications require approval from the direct supervisor and must not exceed the actual overtime hours.", "id": "456", "metadata": { "source": "HR_Employee_Policy_v3.pdf", "section": "Compensatory Leave Policy", "page": 12 } }]
This structure facilitates downstream language model nodes (e.g., Deepseek R1) to use the raw content and contextual information for high-quality question answering, summarization, or logical reasoning.
Typical Use Cases
Enterprise Internal Q&A Assistant: For policies, IT support, expense reimbursement processes, etc.
Customer Service Intelligent Assistant: Product feature explanations, troubleshooting guides
Project Knowledge Support: Helps team members quickly understand background information or past experiences
Legal/Compliance Consulting Bot: Extracts explanatory content from regulatory documents
Recommended Companion Nodes
The Knowledge Retrieval node is typically used with the following nodes to form a complete agent task chain:
Companion Node
Role
🎯 Reasoning Model Node (e.g., Deepseek R1)
Performs deep understanding and logical judgment on retrieved content to generate professional responses
🧠 Prompt Generation Node
Rewrites user input to improve retrieval accuracy
📝 Formatting Node
Enhances output readability and clarity
🚀 Output Node
Sends results to user interfaces, such as Feishu or web chat windows
Notes
Ensure the relevant knowledge base is populated and available
For multilingual content, pre-configure support for the corresponding language in the knowledge base
The amount of retrieved content can be customized in node settings (e.g., return top 3 or top 5 results)
When fixed or agent filtering is configured, use Vector mode with PGVector or Milvus
Conclusion
The Knowledge Retrieval node serves as a bridge between “user questions” and “intelligent answers.”
It not only provides factual evidence but also offers reliable semantic support for the agent’s understanding and expression. In the XpertAI workflow, Knowledge Retrieval enhances your agent’s contextual awareness and business expertise.For more details on building and maintaining a knowledge base, see Knowledge Base Overview.
{"docsConfig":{"theme":"mint","$schema":"https://mintlify.com/docs.json","name":"Xpert AI","colors":{"primary":"#FF0000","light":"#07C983","dark":"#15803D"},"logo":{"light":"https://mintcdn.com/xpertai/2jKsBNCoQ3CSMXtA/logo/light.svg?fit=max\u0026auto=format\u0026n=2jKsBNCoQ3CSMXtA\u0026q=85\u0026s=e4c3777e44d9b5b2e80e8ea4f9a6d9f6","dark":"https://mintcdn.com/xpertai/2jKsBNCoQ3CSMXtA/logo/dark.svg?fit=max\u0026auto=format\u0026n=2jKsBNCoQ3CSMXtA\u0026q=85\u0026s=dad304490ba7841404252de1fd7943b8"},"favicon":"https://mintcdn.com/xpertai/2jKsBNCoQ3CSMXtA/favicon.svg?fit=max\u0026auto=format\u0026n=2jKsBNCoQ3CSMXtA\u0026q=85\u0026s=617c77252b632e710a4d3597f3189347","appearance":{"default":"light"},"navbar":{"links":[{"href":"https://github.com/xpert-ai/xpert","label":"GitHub"},{"href":"https://data.xpertai.cn/","label":"Ontology"},{"href":"mailto:service@xpertai.cn","label":"Support"}],"primary":{"type":"button","label":"Try XpertAI","href":"https://app.xpertai.cn/"}},"footer":{"socials":{"x":"https://xpertai.cn/","github":"https://github.com/xpert-ai/xpert"}},"fonts":{"family":"Inter"},"contextual":{"options":["copy","view","chatgpt","claude","perplexity","mcp","cursor","vscode"],"display":"header"},"styling":{"latex":false},"navigation":{"global":{"anchors":[{"anchor":"Blog","icon":"newspaper","href":"https://xpertai.cn/blog/"}]},"languages":[{"language":"en","default":true,"navbar":{"links":[{"href":"https://github.com/xpert-ai/xpert","label":"GitHub"},{"href":"https://data.xpertai.cn/","label":"Ontology"},{"href":"mailto:service@xpertai.cn","label":"Support"}],"primary":{"type":"button","label":"Try XpertAI","href":"https://app.xpertai.cn/"}},"href":"en/ai/getting-started"},{"language":"zh-Hans","navbar":{"links":[{"href":"https://github.com/xpert-ai/xpert","label":"GitHub"},{"href":"https://data.xpertai.cn/","label":"进入本体"},{"href":"mailto:service@xpertai.cn","label":"支持"}],"primary":{"type":"button","label":"试用 XpertAI","href":"https://app.xpertai.cn/"}},"href":"zh-Hans/ai/getting-started"}]}},"deployment":{"deploymentMetadataValue":{"subdomain":"xpertai","hasAudioNarration":false,"actualSubdomain":"xpertai","customDomains":["docs.xpertai.cn"],"gitSource":{"type":"github","owner":"xpert-ai","repo":"docs","deployBranch":"main","contentDirectory":"","isPrivate":true,"mountPath":"","label":""},"entitlements":{},"buildId":"6af197020da5396f96328d23","clientVersion":"0.0.4270","searchFilterCounts":[{"language":"en","tag":"AI","count":406},{"language":"zh-Hans","tag":"AI","count":406},{"language":"zh-Hans","tag":"默认","count":124},{"language":"en","tag":"Default","count":122},{"language":"en","tag":"Ontology","count":91},{"language":"zh-Hans","tag":"本体","count":91},{"language":"en","tag":"Agent","count":70},{"language":"zh-Hans","tag":"智能体","count":68},{"language":"en","tag":"OpenAPI (Unmaintained)","count":59},{"language":"zh-Hans","tag":"OpenAPI(不再维护)","count":59},{"language":"en","tag":"Plugin","count":47},{"language":"zh-Hans","tag":"插件","count":47},{"language":"zh-Hans","tag":"工作流","count":33},{"language":"en","tag":"Tutorial","count":31},{"language":"en","tag":"Workflow","count":31},{"language":"zh-Hans","tag":"教程","count":30},{"language":"en","tag":"Toolset","count":28},{"language":"zh-Hans","tag":"工具集","count":26},{"language":"en","tag":"Data and Analytics","count":23},{"language":"zh-Hans","tag":"数据分析","count":23}]},"assistantConfig":{"enableAskAiButton":false,"enableStarterQuestions":false,"enableAskAiSearchBar":true},"basePath":"","hasChatPermissions":false,"hasWebMcpPermissions":false,"toggles":[{"name":"kill-isr","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"custom-rbac-roles","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"agent-mintlify-slack","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"agent-integrations-settings","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"rbac-expansion","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automations-pr-grouping","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"custom-prefix","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"analytics-v7","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"user-flows-analytics","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"no-publish-flow","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-onboarding","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"snapshot-serving-live","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"stripTemperatureMiddleware","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"support-platform-pylon-zendesk","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"snapshot-serving","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"instant-rollback","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"granular-notifications-server","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"granular-notifications","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automations-fable","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"fixed-ai-action-pricing","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"site-roles","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automation-resolve-merge-conflict","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"scoped-publishing","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"mintql","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"page-level-analytics","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"editor-version-history-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"billing-page-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"full-page-search","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workspace-projects","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"assistant-v5","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"fork-pr-previews","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"revalidation-jwt","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-sso-scim","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"hobby-abuse-scan","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"dashboard-inbox","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-signup","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"turbopuffer-dual-write","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-enabled","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"approve-review-flow","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"editor-metadata","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"sso-setup-deadline-banner","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"turbopuffer-serve","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"live-agents","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"starter-pricing","enabled":true,"variant":{"name":"control","enabled":true,"payload":{"type":"string","value":"control"},"feature_enabled":true},"impressionData":false},{"name":"llms-txt-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"wildcard-email-auth","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false}],"googleFontsInlined":false},"customCss":[{"filePath":"public/styles.css","content":""}]}
{"page":{"pagePath":"en/ai/workflow/knowledge","slug":"/en/ai/workflow/knowledge","pageMetadata":{"title":"Knowledge Retrieval","sidebar_position":21,"description":null,"href":"/en/ai/workflow/knowledge"},"pageType":"default","mdx":{"mdxSource":{"compiledSource":"\"use strict\";const{Fragment:_Fragment,jsx:_jsx,jsxs:_jsxs}=arguments[0];const{useMDXComponents:_provideComponents}=arguments[0];function _createMdxContent(props){const _components={a:`a`,code:`code`,hr:`hr`,li:`li`,p:`p`,pre:`pre`,span:`span`,strong:`strong`,tbody:`tbody`,td:`td`,th:`th`,thead:`thead`,tr:`tr`,ul:`ul`,..._provideComponents(),...props.components},{CodeBlock,Heading,Table,Tip}=_components;if(!CodeBlock)_missingMdxReference(`CodeBlock`,true);if(!Heading)_missingMdxReference(`Heading`,true);if(!Table)_missingMdxReference(`Table`,true);if(!Tip)_missingMdxReference(`Tip`,true);return _jsxs(_Fragment,{children:[_jsxs(_components.p,{children:[`The `,_jsx(_components.strong,{children:`Knowledge Retrieval`}),` node is a core capability in the XpertAI agent workflow, providing highly relevant information support for user queries. It automatically retrieves content snippets semantically related to the query from a pre-built knowledge base, serving as contextual input for downstream agents to understand, analyze, and generate responses.`]}),`\n`,_jsx(Heading,{level:`2`,id:`main-capabilities`,children:`Main Capabilities`}),`\n`,_jsxs(Table,{children:[_jsx(_components.thead,{children:_jsxs(_components.tr,{children:[_jsx(_components.th,{children:`Function`}),_jsx(_components.th,{children:`Description`})]})}),_jsxs(_components.tbody,{children:[_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`🔍 Semantic Matching`}),_jsx(_components.td,{children:`Automatically identifies the core intent of user input and retrieves the most semantically relevant knowledge snippets`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`📂 Content Support`}),_jsx(_components.td,{children:`Supports retrieval of structured and unstructured document content, such as policy documents, FAQs, product manuals, etc.`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`🎯 Precise Recall`}),_jsx(_components.td,{children:`Supports recall of multiple relevant content items, enabling comprehensive judgment by downstream nodes`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`🧭 Intelligent Filtering`}),_jsx(_components.td,{children:`Enforces a fixed business boundary and lets the agent narrow retrieval with registered system and metadata fields`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`🔄 Composability`}),_jsx(_components.td,{children:`Can be flexibly combined with any language model node (e.g., reasoning models) to form complex task flows`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`🔗 Multi-Knowledge Source Support`}),_jsx(_components.td,{children:`Configurable to access multiple knowledge bases for cross-business or multi-domain information retrieval`})]})]})]}),`\n`,_jsx(Heading,{level:`2`,id:`usage`,children:`Usage`}),`\n`,_jsx(Heading,{level:`3`,id:`1-input-parameters`,children:`1. Input Parameters`}),`\n`,_jsx(_components.p,{children:`The Knowledge Retrieval node accepts input from upstream nodes, typically a user’s natural language question or a standardized query processed by an agent.`}),`\n`,_jsx(CodeBlock,{filename:``,numberOfLines:`3`,language:`json`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`json`,children:_jsxs(_components.code,{language:`json`,numberOfLines:`3`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`{`})}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#116329`,\"--shiki-dark\":`#9CDCFE`},children:` \"question\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`: `}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:`\"What are the company's rules for compensatory leave?\"`})]}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`}`})}),`\n`]})})}),`\n`,_jsx(Heading,{level:`3`,id:`2-retrieval-and-filter-configuration`,children:`2. Retrieval and filter configuration`}),`\n`,_jsx(_components.p,{children:`Each Knowledge Retrieval node stores an independent configuration for every bound knowledge base:`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Retrieval mode`}),`: intelligent filtering currently applies to Vector mode;`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Fixed filter`}),`: configured by the workflow designer with constants or workflow variables and cannot be changed by the agent at runtime;`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Allow agent automatic filtering`}),`: lets the agent add valid request-specific conditions inferred from the question;`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Multiple knowledge bases`}),`: each binding retains its own fixed filter and agent-filter switch.`]}),`\n`]}),`\n`,_jsxs(_components.p,{children:[`Fixed, caller, and agent-generated filters are always combined with `,_jsx(_components.code,{children:`AND`}),`. A missing or mistyped fixed variable stops retrieval. An invalid dynamic filter is discarded as a whole, and retrieval continues with the fixed filter.`]}),`\n`,_jsxs(_components.p,{children:[`See `,_jsx(_components.a,{href:`/en/ai/knowledge-base/intelligent-filtering`,children:`Intelligent Retrieval Filtering`}),` for fields, operators, zero-hit behavior, and the support matrix.`]}),`\n`,_jsx(Heading,{level:`3`,id:`3-output-structure`,children:`3. Output Structure`}),`\n`,_jsxs(_components.p,{children:[`The Knowledge Retrieval node returns a list of documents in the format of Langchain’s `,_jsx(_components.code,{children:`Document`}),` object. Each document contains two parts:`]}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.code,{children:`page_content`}),`: The actual retrieved text content`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.code,{children:`metadata`}),`: Metadata related to the content (e.g., source, document name, segment index, etc.)`]}),`\n`]}),`\n`,_jsx(_components.p,{children:`** 📄 Output Example **:`}),`\n`,_jsx(CodeBlock,{filename:``,numberOfLines:`20`,language:`json`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`json`,children:_jsxs(_components.code,{language:`json`,numberOfLines:`20`,children:[_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`[`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:` {`})}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#116329`,\"--shiki-dark\":`#9CDCFE`},children:` \"pageContent\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`: `}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:`\"According to company policy, employees may apply for compensatory leave within 5 working days after overtime.\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`,`})]}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#116329`,\"--shiki-dark\":`#9CDCFE`},children:` \"id\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`: `}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:`\"123\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`,`})]}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#116329`,\"--shiki-dark\":`#9CDCFE`},children:` \"metadata\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`: {`})]}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#116329`,\"--shiki-dark\":`#9CDCFE`},children:` \"source\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`: `}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:`\"HR_Employee_Policy_v3.pdf\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`,`})]}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#116329`,\"--shiki-dark\":`#9CDCFE`},children:` \"section\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`: `}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:`\"Compensatory Leave Policy\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`,`})]}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#116329`,\"--shiki-dark\":`#9CDCFE`},children:` \"page\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`: `}),_jsx(_components.span,{style:{color:`#0550AE`,\"--shiki-dark\":`#B5CEA8`},children:`12`})]}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:` }`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:` },`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:` {`})}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#116329`,\"--shiki-dark\":`#9CDCFE`},children:` \"pageContent\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`: `}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:`\"Compensatory leave applications require approval from the direct supervisor and must not exceed the actual overtime hours.\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`,`})]}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#116329`,\"--shiki-dark\":`#9CDCFE`},children:` \"id\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`: `}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:`\"456\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`,`})]}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#116329`,\"--shiki-dark\":`#9CDCFE`},children:` \"metadata\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`: {`})]}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#116329`,\"--shiki-dark\":`#9CDCFE`},children:` \"source\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`: `}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:`\"HR_Employee_Policy_v3.pdf\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`,`})]}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#116329`,\"--shiki-dark\":`#9CDCFE`},children:` \"section\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`: `}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:`\"Compensatory Leave Policy\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`,`})]}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#116329`,\"--shiki-dark\":`#9CDCFE`},children:` \"page\"`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`: `}),_jsx(_components.span,{style:{color:`#0550AE`,\"--shiki-dark\":`#B5CEA8`},children:`12`})]}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:` }`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:` }`})}),`\n`,_jsx(_components.span,{className:`line`,children:_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`]`})}),`\n`]})})}),`\n`,_jsx(_components.p,{children:`This structure facilitates downstream language model nodes (e.g., Deepseek R1) to use the raw content and contextual information for high-quality question answering, summarization, or logical reasoning.`}),`\n`,_jsx(Heading,{level:`2`,id:`typical-use-cases`,children:`Typical Use Cases`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Enterprise Internal Q\u0026A Assistant`}),`: For policies, IT support, expense reimbursement processes, etc.`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Customer Service Intelligent Assistant`}),`: Product feature explanations, troubleshooting guides`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Project Knowledge Support`}),`: Helps team members quickly understand background information or past experiences`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.strong,{children:`Legal/Compliance Consulting Bot`}),`: Extracts explanatory content from regulatory documents`]}),`\n`]}),`\n`,_jsx(Heading,{level:`2`,id:`recommended-companion-nodes`,children:`Recommended Companion Nodes`}),`\n`,_jsx(_components.p,{children:`The Knowledge Retrieval node is typically used with the following nodes to form a complete agent task chain:`}),`\n`,_jsxs(Table,{children:[_jsx(_components.thead,{children:_jsxs(_components.tr,{children:[_jsx(_components.th,{children:`Companion Node`}),_jsx(_components.th,{children:`Role`})]})}),_jsxs(_components.tbody,{children:[_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`🎯 Reasoning Model Node (e.g., Deepseek R1)`}),_jsx(_components.td,{children:`Performs deep understanding and logical judgment on retrieved content to generate professional responses`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`🧠 Prompt Generation Node`}),_jsx(_components.td,{children:`Rewrites user input to improve retrieval accuracy`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`📝 Formatting Node`}),_jsx(_components.td,{children:`Enhances output readability and clarity`})]}),_jsxs(_components.tr,{children:[_jsx(_components.td,{children:`🚀 Output Node`}),_jsx(_components.td,{children:`Sends results to user interfaces, such as Feishu or web chat windows`})]})]})]}),`\n`,_jsx(Heading,{level:`2`,id:`notes`,children:`Notes`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsx(_components.li,{children:`Ensure the relevant knowledge base is populated and available`}),`\n`,_jsx(_components.li,{children:`For multilingual content, pre-configure support for the corresponding language in the knowledge base`}),`\n`,_jsx(_components.li,{children:`The amount of retrieved content can be customized in node settings (e.g., return top 3 or top 5 results)`}),`\n`,_jsx(_components.li,{children:`When fixed or agent filtering is configured, use Vector mode with PGVector or Milvus`}),`\n`]}),`\n`,_jsx(_components.hr,{}),`\n`,_jsx(Heading,{level:`2`,id:`conclusion`,children:`Conclusion`}),`\n`,_jsx(Tip,{children:_jsxs(_components.p,{children:[`The `,_jsx(_components.strong,{children:`Knowledge Retrieval`}),` node serves as a bridge between “user questions” and “intelligent answers.”`]})}),`\n`,_jsx(_components.p,{children:`It not only provides factual evidence but also offers reliable semantic support for the agent’s understanding and expression. In the XpertAI workflow, Knowledge Retrieval enhances your agent’s contextual awareness and business expertise.`}),`\n`,_jsxs(_components.p,{children:[`For more details on building and maintaining a knowledge base, see `,_jsx(_components.a,{href:`/en/ai/knowledge-base/index`,children:`Knowledge Base Overview`}),`.`]})]})}function MDXContent(props={}){const{wrapper:MDXLayout}={..._provideComponents(),...props.components};return MDXLayout?_jsx(MDXLayout,{...props,children:_jsx(_createMdxContent,{...props})}):_createMdxContent(props)}return{default:MDXContent};function _missingMdxReference(id,component){throw new Error(`Expected `+(component?`component`:`object`)+\" `\"+id+\"` to be defined: you likely forgot to import, pass, or provide it.\")}","frontmatter":{},"scope":{"config":{},"pageMetadata":{"title":"Knowledge Retrieval","sidebar_position":21,"description":null,"href":"/en/ai/workflow/knowledge"}}},"mdxSourceWithNoJs":null},"mdxExtracts":{"tableOfContents":[{"title":"Main Capabilities","slug":"main-capabilities","depth":2,"children":[]},{"title":"Usage","slug":"usage","depth":2,"children":[{"title":"1. Input Parameters","slug":"1-input-parameters","depth":3,"children":[]},{"title":"2. Retrieval and filter configuration","slug":"2-retrieval-and-filter-configuration","depth":3,"children":[]},{"title":"3. Output Structure","slug":"3-output-structure","depth":3,"children":[]}]},{"title":"Typical Use Cases","slug":"typical-use-cases","depth":2,"children":[]},{"title":"Recommended Companion Nodes","slug":"recommended-companion-nodes","depth":2,"children":[]},{"title":"Notes","slug":"notes","depth":2,"children":[]},{"title":"Conclusion","slug":"conclusion","depth":2,"children":[]}],"codeExamples":{}},"jsLinks":[],"subdomain":"xpertai","siteName":"Xpert AI","title":"Knowledge Retrieval - Xpert AI","navMaps":{"firstHrefInVersion":{},"firstHrefInLanguage":{"en":{"href":"/en/ai/workflow/knowledge","matchLevel":0},"zh-Hans":{"href":"/zh-Hans/ai/getting-started","matchLevel":4}}},"lastModified":"2026-10-20T09:41:32.164Z","originalFileLocation":"en/ai/workflow/knowledge.md","locale":"en"},"headHtml":"\u003cscript data-mint-head>(function(){var d=document.documentElement,p=null;if(!p){try{p=localStorage.getItem(\"isDarkMode\")}catch(e){}if(p==='true')p='dark';else if(p==='false')p='light';if(p!=='light'\u0026\u0026p!=='dark'\u0026\u0026p!=='system')p=\"light\"}var r=p==='system'?(matchMedia(\"(prefers-color-scheme: dark)\").matches?'dark':'light'):p;d.classList.remove(r==='dark'?'light':'dark');d.classList.add(r);d.setAttribute(\"data-theme-preference\",p)})();\u003c/script>\u003cmeta data-mint-head name=\"application-name\" content=\"Xpert AI\">\u003cmeta data-mint-head name=\"generator\" content=\"Mintlify\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/xpertai/-IgJ8RS8fLVB5p0L/_generated/favicon/android-chrome-192x192.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"apple-touch-icon\" type=\"image/png\" sizes=\"180x180\" href=\"/mintlify-assets/_mintlify/favicons/xpertai/-IgJ8RS8fLVB5p0L/_generated/favicon/apple-touch-icon.png\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/xpertai/-IgJ8RS8fLVB5p0L/_generated/favicon/favicon-16x16.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/xpertai/-IgJ8RS8fLVB5p0L/_generated/favicon/favicon-32x32.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/xpertai/-IgJ8RS8fLVB5p0L/_generated/favicon/favicon.ico\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/xpertai/-IgJ8RS8fLVB5p0L/_generated/favicon-dark/android-chrome-192x192.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/xpertai/-IgJ8RS8fLVB5p0L/_generated/favicon-dark/favicon-16x16.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/xpertai/-IgJ8RS8fLVB5p0L/_generated/favicon-dark/favicon-32x32.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/xpertai/-IgJ8RS8fLVB5p0L/_generated/favicon-dark/favicon.ico\" media=\"(prefers-color-scheme: dark)\">\u003cmeta data-mint-head property=\"og:title\" content=\"Knowledge Retrieval - Xpert AI\">\u003cmeta data-mint-head property=\"og:site_name\" content=\"Xpert AI\">\u003cmeta data-mint-head property=\"og:url\" content=\"https://docs.xpertai.cn/en/ai/workflow/knowledge\">\u003cmeta data-mint-head property=\"og:type\" content=\"website\">\u003cmeta data-mint-head property=\"og:image\" content=\"https://xpertai.mintlify.site/_mintlify/api/og/v2?division=Default\u0026amp;title=Knowledge+Retrieval\u0026amp;theme=ea705b00189439c1b6512356\u0026amp;signature=4ad15f102ff16964687c1edd55864a4e1b685074add7b54b47705a9836a88720\">\u003cmeta data-mint-head property=\"og:image:width\" content=\"1200\">\u003cmeta data-mint-head property=\"og:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"twitter:card\" content=\"summary_large_image\">\u003cmeta data-mint-head name=\"twitter:title\" content=\"Knowledge Retrieval - Xpert AI\">\u003cmeta data-mint-head name=\"twitter:image\" content=\"https://xpertai.mintlify.site/_mintlify/api/og/v2?division=Default\u0026amp;title=Knowledge+Retrieval\u0026amp;theme=ea705b00189439c1b6512356\u0026amp;signature=4ad15f102ff16964687c1edd55864a4e1b685074add7b54b47705a9836a88720\">\u003cmeta data-mint-head name=\"twitter:image:width\" content=\"1200\">\u003cmeta data-mint-head name=\"twitter:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"msapplication-config\" content=\"/mintlify-assets/_mintlify/favicons/xpertai/-IgJ8RS8fLVB5p0L/_generated/favicon/browserconfig.xml\">\u003cmeta data-mint-head name=\"apple-mobile-web-app-title\" content=\"Xpert AI\">\u003cmeta data-mint-head name=\"msapplication-TileColor\" content=\"#FF0000\">\u003clink data-mint-head rel=\"canonical\" href=\"https://docs.xpertai.cn/en/ai/workflow/knowledge\">\u003clink data-mint-head rel=\"alternate\" type=\"application/xml\" href=\"/sitemap.xml\">\u003clink data-mint-head rel=\"alternate\" type=\"text/markdown\" href=\"/en/ai/workflow/knowledge.md\">\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@graph\":[{\"@type\":\"Organization\",\"@id\":\"https://docs.xpertai.cn/#organization\",\"name\":\"Xpert AI\",\"url\":\"https://docs.xpertai.cn\",\"logo\":{\"@type\":\"ImageObject\",\"url\":\"https://mintcdn.com/xpertai/2jKsBNCoQ3CSMXtA/logo/light.svg?fit=max\u0026auto=format\u0026n=2jKsBNCoQ3CSMXtA\u0026q=85\u0026s=e4c3777e44d9b5b2e80e8ea4f9a6d9f6\"}},{\"@type\":\"WebSite\",\"@id\":\"https://docs.xpertai.cn#website\",\"name\":\"Xpert AI\",\"url\":\"https://docs.xpertai.cn\",\"publisher\":{\"@id\":\"https://docs.xpertai.cn/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https://docs.xpertai.cn/en/ai/workflow/knowledge#webpage\",\"url\":\"https://docs.xpertai.cn/en/ai/workflow/knowledge\",\"name\":\"Knowledge Retrieval\",\"dateModified\":\"2026-10-20T09:41:32.164Z\",\"isPartOf\":{\"@id\":\"https://docs.xpertai.cn#website\"},\"breadcrumb\":{\"@id\":\"https://docs.xpertai.cn/en/ai/workflow/knowledge#breadcrumb\"}},{\"@type\":\"BreadcrumbList\",\"@id\":\"https://docs.xpertai.cn/en/ai/workflow/knowledge#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Default\",\"item\":\"https://docs.xpertai.cn/en/ai/workflow\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Knowledge Retrieval\",\"item\":\"https://docs.xpertai.cn/en/ai/workflow/knowledge\"}]},{\"@type\":[\"Article\",\"TechArticle\"],\"@id\":\"https://docs.xpertai.cn/en/ai/workflow/knowledge#article\",\"headline\":\"Knowledge Retrieval\",\"name\":\"Knowledge Retrieval\",\"url\":\"https://docs.xpertai.cn/en/ai/workflow/knowledge\",\"mainEntityOfPage\":{\"@id\":\"https://docs.xpertai.cn/en/ai/workflow/knowledge#webpage\"},\"dateModified\":\"2026-10-20T09:41:32.164Z\",\"publisher\":{\"@id\":\"https://docs.xpertai.cn/#organization\"},\"isPartOf\":{\"@id\":\"https://docs.xpertai.cn#website\"}}]}\u003c/script>\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@type\":\"WebSite\",\"name\":\"Xpert AI\",\"publisher\":{\"@type\":\"Organization\",\"name\":\"Xpert AI\"},\"provider\":{\"@type\":\"Organization\",\"name\":\"Mintlify\",\"url\":\"https://mintlify.com\"}}\u003c/script>","agentPointerHref":"/en/ai/workflow/knowledge.md","siteName":"Xpert AI","nav":{"global":{"anchors":[{"anchor":"Blog","icon":"newspaper","href":"https://xpertai.cn/blog/"}]},"languages":[{"language":"en","default":true,"navbar":{"links":[{"href":"https://github.com/xpert-ai/xpert","label":"GitHub"},{"href":"https://data.xpertai.cn/","label":"Ontology"},{"href":"mailto:service@xpertai.cn","label":"Support"}],"primary":{"type":"button","label":"Try XpertAI","href":"https://app.xpertai.cn/"}},"products":[{"product":"AI","tabs":[{"tab":"Getting Started","pages":[{"title":"Getting Started","href":"/en/ai/getting-started"}]},{"tab":"Bosi App","pages":[{"title":"Bosi App","href":"/en/ai/bosi"}]},{"tab":"Plugin Apps","pages":[{"title":"Plugin Apps","href":"/en/ai/applications"}]},{"tab":"Agent","pages":[{"title":"Agent","href":"/en/ai/agent/agent"}]},{"tab":"Projects \u0026 Tasks","pages":[{"title":"Projects \u0026 Tasks","href":"/en/ai/projects"}]},{"tab":"Live Dashboard","pages":[{"title":"Live Dashboard","href":"/en/ai/live-dashboard"}]},{"tab":"Knowledge Base","pages":[{"title":"Knowledge Base","href":"/en/ai/knowledge-base"}]},{"tab":"Workflow","groups":[{"group":"Default","pages":[{"title":"🔀 Workflow","href":"/en/ai/workflow"},{"title":"Agent","href":"/en/ai/workflow/agent"},{"title":"External Digital Experts","href":"/en/ai/workflow/external"},{"title":"Conversation Variables","href":"/en/ai/workflow/variables"},{"title":"Error Handling","href":"/en/ai/workflow/error-handling"},{"title":"Execution Endpoint","href":"/en/ai/workflow/terminal"},{"title":"Trigger","href":"/en/ai/workflow/trigger"},{"title":"DingTalk Trigger","href":"/en/ai/workflow/dingtalk-trigger"},{"title":"Logical Router","href":"/en/ai/workflow/if-else"},{"title":"Answer","href":"/en/ai/workflow/answer"},{"title":"Variable Assigner","href":"/en/ai/workflow/assigner"},{"title":"Subflow","href":"/en/ai/workflow/subflow"},{"title":"Iterating","href":"/en/ai/workflow/iterating"},{"title":"List Operator","href":"/en/ai/workflow/list-operator"},{"title":"Variable Aggregator","description":null,"href":"/en/ai/workflow/variable-aggregator"},{"title":"Knowledge Retrieval","href":"/en/ai/workflow/knowledge"},{"title":"HTTP Request","description":null,"href":"/en/ai/workflow/http"},{"title":"Note","href":"/en/ai/workflow/note"},{"title":"Code Execution","href":"/en/ai/workflow/code"},{"title":"Template Transformation","href":"/en/ai/workflow/template"},{"title":"Question Classifier","href":"/en/ai/workflow/classifier"},{"title":"Toolset","href":"/en/ai/workflow/toolset"},{"title":"Tool Invocation","href":"/en/ai/workflow/tool"},{"title":"Agent Workflow","href":"/en/ai/workflow/agent-workflow"},{"title":"Task Handover","href":"/en/ai/workflow/task"},{"title":"Document Source","href":"/en/ai/workflow/source"},{"title":"Document Transformer","href":"/en/ai/workflow/processor"},{"title":"Document Chunker","href":"/en/ai/workflow/chunker"},{"title":"Document Image Understanding","href":"/en/ai/workflow/understanding"},{"title":"Document Knowledge Base","href":"/en/ai/workflow/knowledgebase"},{"title":"Agent Middleware","href":"/en/ai/workflow/middleware"}]}]},{"tab":"Agent Middleware","pages":[{"title":"Agent Middleware","href":"/en/ai/middleware"}]},{"tab":"Plugin","pages":[{"title":"Plugin","href":"/en/ai/plugin/overview"}]},{"tab":"Chatkit","pages":[{"title":"Chatkit","href":"/en/ai/chatkit"}]},{"tab":"Troubleshooting","pages":[{"title":"Troubleshooting","href":"/en/ai/troubleshooting/errors/recursion-limit"}]},{"tab":"Tutorial","pages":[{"title":"Tutorial","href":"/en/ai/tutorial/assistant-everyday-chat"}]},{"tab":"System","pages":[{"title":"System","href":"/en/ai/system/membership-plan"}]},{"tab":"OpenAPI (Unmaintained)","pages":[{"title":"OpenAPI (Unmaintained)","href":"/en/api-reference/aiv1/chat-with-an-agent"}]},{"tab":"SDK","pages":[{"title":"SDK","href":"/en/ai/agent/development-api"}]}]},{"product":"Ontology","pages":[{"title":"Ontology","href":"/en/data/getting-started"}]},{"product":"Code","pages":[{"title":"Code","href":"/en/code/web"}]}]},{"language":"zh-Hans","navbar":{"links":[{"href":"https://github.com/xpert-ai/xpert","label":"GitHub"},{"href":"https://data.xpertai.cn/","label":"进入本体"},{"href":"mailto:service@xpertai.cn","label":"支持"}],"primary":{"type":"button","label":"试用 XpertAI","href":"https://app.xpertai.cn/"}},"pages":[{"title":"zh-Hans","href":"/zh-Hans/ai/getting-started"}]}]},"basePath":"","title":"Knowledge Retrieval - Xpert AI","deploymentId":"dpl_DyXGnKeCjZyA3sUdfMJ7FjkdBefg","buildId":"dpl_DyXGnKeCjZyA3sUdfMJ7FjkdBefg","dynamics":[],"chunks":[]}