> ## Documentation Index > Fetch the complete documentation index at: https://docs.orq.ai/llms.txt > Use this file to discover all available pages before exploring further. > Create a new knowledge base for retrieval-augmented generation. Configure chunking, embedding, and search settings for your RAG application. # Create a knowledge ## OpenAPI ````yaml post /v2/knowledge openapi: 3.1.0 info: title: orq.ai API version: '2.0' description: orq.ai API documentation servers: - url: https://api.orq.ai security: - ApiKey: [] tags: - name: Guardrail Rules - name: Policies - name: Routing Rules - name: Files description: File upload and retrieval operations. - name: FilesService - name: Projects description: Projects organize resources within a workspace - name: ProjectsService - name: Skills description: >- Skills are modular instructions you can use to codify processes and conventions - name: SkillsService - name: Responses - description: >- Run agents on a cadence — cron, interval, or one-off. Minimum firing interval is 1 hour. name: Agent Schedules - name: Reporting description: >- GenAI reporting API over canonical analytics rollups. Accepts a metric name, time range, grain, group-by, and filters; returns a typed time series and optional totals. - name: ReportingService description: |- ReportingService exposes a single QueryReport RPC that maps allowlisted analytics payloads onto safe rollup queries. Callers never send SQL; the backend picks the rollup family and grain from the metric catalogue, the requested range, and the requested grouping. externalDocs: url: https://docs.orq.ai description: orq.ai Documentation paths: /v2/knowledge: post: tags: - Knowledge Bases summary: Create a knowledge operationId: CreateKnowledge requestBody: required: true content: application/json: schema: oneOf: - type: object properties: type: type: string enum: - internal default: internal key: type: string description: type: string embedding_model: type: string description: >- The embeddings model to use for the knowledge base in the format "provider/model" for public models or "workspaceKey@provider/model" for private workspace models. This model will be used to embed the chunks when they are added to the knowledge base. retrieval_settings: type: object properties: retrieval_type: type: string enum: - vector_search - keyword_search - hybrid_search default: hybrid_search description: >- The retrieval type to use for the knowledge base. If not provided, Hybrid Search will be used as a default query strategy. top_k: type: integer exclusiveMinimum: 0 default: 5 description: The number of results to return from the search. threshold: type: number minimum: 0 maximum: 1 default: 0 description: >- The threshold value used to filter the search results, only documents with a relevance score greater than the threshold will be returned rerank_config: type: - object - 'null' properties: top_k: type: integer minimum: 1 maximum: 100 default: 5 description: >- The number of results to return by the reranking model rerank_threshold: type: number minimum: 0 maximum: 1 default: 0.5 description: >- The threshold value used to filter the rerank results, only documents with a relevance score greater than the threshold will be returned rerank_model: type: string description: The rerank model to use for the knowledge base. required: - rerank_model description: >- The rerank configuration for the knowledge base. In case the model is provided it will be used to enhance the search precision. agentic_rag_config: type: - object - 'null' properties: model: type: string description: The model to use for the Agentic RAG required: - model description: >- The Agentic RAG configuration for the knowledge base. If `null` is provided, Agentic RAG will be disabled. description: >- The retrieval settings for the knowledge base. If not provider, Hybrid Search will be used as a default query strategy. path: type: string description: >- Entity storage path. With workspace-level API keys, use the format `project/folder/subfolder/...`. The first element identifies the project, followed by nested folders (auto-created as needed). Example: `Default/agents`. With project-level API keys, the project is predetermined by the API key, so the path is relative to that project. Example: `agents`. For backward compatibility, a leading project name is ignored when it matches the scoped project. example: Default required: - key - embedding_model - path - type: object properties: type: type: string enum: - external default: external key: type: string description: type: string external_config: type: object properties: name: type: string description: The name of the external knowledge base. api_url: type: string format: uri description: The API URL of the external knowledge base. api_key: type: string description: The API key to access the external knowledge base. required: - name - api_url - api_key required: - key - external_config responses: '200': description: Knowledge successfully created content: application/json: schema: oneOf: - type: object properties: _id: type: string description: The unique identifier of the knowledge base. created: type: string description: The creation date of the knowledge base. description: type: string description: The description of the knowledge base. key: type: string description: The unique key of the knowledge base. domain_id: type: string description: The project/domain ID of the knowledge base. path: type: string description: >- Entity storage path. With workspace-level API keys, use the format `project/folder/subfolder/...`. The first element identifies the project, followed by nested folders (auto-created as needed). Example: `Default/agents`. With project-level API keys, the project is predetermined by the API key, so the path is relative to that project. Example: `agents`. For backward compatibility, a leading project name is ignored when it matches the scoped project. example: Default created_by_id: type: - string - 'null' format: uuid updated_by_id: type: - string - 'null' format: uuid updated: type: string description: The last update date of the knowledge base. type: type: string enum: - internal default: internal retrieval_settings: type: object properties: retrieval_type: type: string enum: - vector_search - keyword_search - hybrid_search default: hybrid_search description: >- The retrieval type to use for the knowledge base. If not provided, Hybrid Search will be used as a default query strategy. top_k: type: integer exclusiveMinimum: 0 default: 5 description: The number of results to return from the search. threshold: type: number minimum: 0 maximum: 1 default: 0 description: >- The threshold value used to filter the search results, only documents with a relevance score greater than the threshold will be returned rerank_config: type: - object - 'null' properties: top_k: type: integer minimum: 1 maximum: 100 default: 5 description: >- The number of results to return by the reranking model rerank_threshold: type: number minimum: 0 maximum: 1 default: 0.5 description: >- The threshold value used to filter the rerank results, only documents with a relevance score greater than the threshold will be returned rerank_model: type: string description: >- The rerank model to use for the knowledge base. required: - rerank_model description: >- The rerank configuration for the knowledge base. In case the model is provided it will be used to enhance the search precision. agentic_rag_config: type: - object - 'null' properties: model: type: string description: The model to use for the Agentic RAG required: - model description: >- The Agentic RAG configuration for the knowledge base. If `null` is provided, Agentic RAG will be disabled. description: >- The retrieval settings for the knowledge base. If not provider, Hybrid Search will be used as a default query strategy. model: type: string description: The embeddings model used for the knowledge base. required: - _id - created - key - domain_id - updated - model - type: object properties: _id: type: string description: The unique identifier of the knowledge base. created: type: string description: The creation date of the knowledge base. description: type: string description: The description of the knowledge base. key: type: string description: The unique key of the knowledge base. domain_id: type: string description: The project/domain ID of the knowledge base. path: type: string description: >- Entity storage path. With workspace-level API keys, use the format `project/folder/subfolder/...`. The first element identifies the project, followed by nested folders (auto-created as needed). Example: `Default/agents`. With project-level API keys, the project is predetermined by the API key, so the path is relative to that project. Example: `agents`. For backward compatibility, a leading project name is ignored when it matches the scoped project. example: Default created_by_id: type: - string - 'null' format: uuid updated_by_id: type: - string - 'null' format: uuid updated: type: string description: The last update date of the knowledge base. type: type: string enum: - external default: external retrieval_settings: type: object properties: top_k: type: integer exclusiveMinimum: 0 default: 5 description: The number of results to return from the search. threshold: type: number minimum: 0 maximum: 1 default: 0 description: >- The threshold value used to filter the search results, only documents with a relevance score greater than the threshold will be returned rerank_config: type: - object - 'null' properties: top_k: type: integer minimum: 1 maximum: 100 default: 5 description: >- The number of results to return by the reranking model rerank_threshold: type: number minimum: 0 maximum: 1 default: 0.5 description: >- The threshold value used to filter the rerank results, only documents with a relevance score greater than the threshold will be returned rerank_model: type: string description: >- The rerank model to use for the knowledge base. required: - rerank_model description: >- The rerank configuration for the knowledge base. In case the model is provided it will be used to enhance the search precision. agentic_rag_config: type: - object - 'null' properties: model: type: string description: The model to use for the Agentic RAG required: - model description: >- The Agentic RAG configuration for the knowledge base. If `null` is provided, Agentic RAG will be disabled. description: The retrieval settings for the knowledge base. external_config: type: object properties: name: type: string description: The name of the external knowledge base. api_url: type: string format: uri description: The API URL of the external knowledge base. required: - name - api_url required: - _id - created - key - domain_id - updated - external_config components: securitySchemes: ApiKey: type: http scheme: bearer bearerFormat: JWT ````