> ## 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. # Search knowledge base > Search a Knowledge Base and return the most similar chunks, along with their search and rerank scores. Note that all configuration changes made in the API will override the settings in the UI. **Related guide**: Knowledge bases guide. See the [Knowledge bases guide](/docs/ai-studio/ai-engineering/knowledge-bases) for a walkthrough with examples. ## OpenAPI ````yaml post /v2/knowledge/{knowledge_id}/search openapi: 3.1.0 info: title: orq.ai API version: '2.0' description: orq.ai API documentation servers: - url: https://my.orq.ai security: - ApiKey: [] tags: - name: Chunking description: Split text into smaller chunks for retrieval and generation workflows. - name: File Systems description: >- Create and manage persistent file systems that agents and MCP clients read from and write to. - name: Knowledge Bases description: Create and manage knowledge bases used by agents and retrieval workflows. - name: Memory Stores description: Create and manage memory stores, memories, and memory documents. - name: Evals description: Run an evaluator against a conversation and its result - description: List models available through the AI Router. name: Models - name: Policies - name: Alerts description: >- Alerts evaluate a Reporting API metric on a fixed interval and fire notifications through notifiers when the value breaches a threshold. Each breach opens a trigger that tracks the incident until the value recovers. - name: Annotation Queues description: Annotation queues collect spans for human review. - name: API keys description: >- API keys authenticate programmatic access to the workspace. They expose opaque tokens, per-domain access grants, and budget and rate-limit constraints. - name: Audit Logs description: Audit logs record workspace entity changes and access-relevant events. - name: Budgets description: >- Budgets govern spend, token usage, and request rate across six scopes: workspace, project, identity, API key, provider, and model. Every applicable budget is enforced, and the most restrictive limit applies per dimension. - name: Files description: File upload and retrieval operations. - name: Guardrail Rules description: >- Guardrail Rules conditionally enforce evaluators and plugins for AI Gateway traffic. Rules may be scoped to a project or the whole workspace. - name: Identities description: >- Identities represent end users from your system for usage and engagement tracking. - name: Management keys description: >- Management keys are workspace-scoped credentials that authenticate programmatic access to workspace administration surfaces (API keys, budgets). Unlike project-scoped API keys, a management key always operates at the workspace level. - name: MCP Gateway description: >- Register upstream MCP servers, discover and sync their tools, and assemble gateways that expose a curated tool surface to MCP clients. - name: Model Catalog description: >- Browse the orq.ai model catalog: every model orq offers, across every provider, with pricing, capabilities and benchmark data. List endpoints only return models that are not deprecated. This API is public, requires no authentication, and is rate limited to 120 requests per minute per IP. Responses carry a 5-minute cache-control max-age. - name: Notifiers description: Notifier destinations used to send delivery and workflow notifications. - name: Projects description: Projects organize resources within a workspace - name: Routing Rules description: >- Routing Rules conditionally select models and enforce request plugins for AI Gateway traffic. Rules are evaluated by ascending priority and may be scoped to a project or the whole workspace. - name: Skills description: >- Skills are modular instructions you can use to codify processes and conventions - name: Smart Routers description: >- Create and manage workspace Smart Routers. A Smart Router selects a model from an eligible pool for each request according to a quality, balanced, or cost profile. - name: Webhooks description: >- Create and manage webhooks that deliver workspace events to external HTTPS endpoints. - name: Workspace Security description: >- Workspace-level domain verification and IP allowlist controls. These operations are restricted to workspace administrators. - name: Workspace Settings description: >- Workspace-level settings managed with a workspace credential. A workspace is the tenant, so these settings are a singleton — there is nothing to create or delete, only read and update. - name: Responses - description: Run agents on a cron cadence. Minimum firing interval is 1 hour. name: Agent Schedules - name: Embeddings - name: Logs description: >- OpenTelemetry log query API. Search, filter, aggregate, and facet log records ingested via OTLP. - 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: Traces description: >- Query and inspect ingested trace data: search trace summaries, aggregate metrics, and read individual traces and their spans. externalDocs: url: https://docs.orq.ai description: orq.ai Documentation paths: /v2/knowledge/{knowledge_id}/search: post: tags: - Knowledge Bases summary: Search knowledge base description: >- Search a Knowledge Base and return the most similar chunks, along with their search and rerank scores. Note that all configuration changes made in the API will override the settings in the UI. operationId: SearchKnowledge parameters: - name: knowledge_id in: path description: The unique identifier or key of the knowledge base. required: true schema: type: string requestBody: description: A search request for chunks in a knowledge base content: application/json: schema: $ref: '#/components/schemas/SearchKnowledgeRequest' required: true responses: '200': description: Search knowledge base content: application/json: schema: $ref: '#/components/schemas/SearchKnowledgeResponse' x-code-samples: - lang: curl label: Core source: |- curl --request POST \ --url "https://my.orq.ai/v2/knowledge/$KNOWLEDGE_ID/search" \ --header "Authorization: Bearer $ORQ_API_KEY" \ --header 'Content-Type: application/json' \ --data '{ "query": "What is our refund policy?", "top_k": 10, "search_type": "hybrid_search", "search_options": { "include_vectors": false, "include_metadata": true, "include_scores": true } }' - lang: typescript label: Node.js source: |- import { Orq } from "@orq-ai/node"; const orq = new Orq({ apiKey: process.env["ORQ_API_KEY"] }); const result = await orq.knowledge.search({ knowledgeId: process.env["KNOWLEDGE_ID"], requestBody: { query: "What is our refund policy?", topK: 10, searchType: "hybrid_search", searchOptions: { includeVectors: false, includeMetadata: true, includeScores: true } } }); console.log(result.matches); - lang: python label: Python source: |- import os from orq_ai_sdk import Orq orq = Orq(api_key=os.getenv("ORQ_API_KEY")) result = orq.knowledge.search( knowledge_id=os.getenv("KNOWLEDGE_ID"), query="What is our refund policy?", top_k=10, search_type="hybrid_search", search_options={ "include_vectors": False, "include_metadata": True, "include_scores": True, }, ) print(result.matches) components: schemas: SearchKnowledgeRequest: required: - query type: object properties: query: minLength: 1 type: string description: The query to use to search the knowledge base top_k: maximum: 100 minimum: 1 type: integer description: >- The number of results to return. If not provided, will default to the knowledge base configured `top_k`. format: int32 threshold: maximum: 1 type: number description: >- The threshold to apply to the search. If not provided, will default to the knowledge base configured `threshold` format: double minimum: 0 search_type: $ref: '#/components/schemas/SearchType' default: hybrid_search description: >- The type of search to perform. If not provided, will default to the knowledge base configured `retrieval_type` filter_by: description: >- The metadata filter to apply to the search. Check the [Searching a Knowledge Base](https://docs.orq.ai/docs/knowledge/api#knowledge-base-search) for more information. anyOf: - type: object additionalProperties: anyOf: - type: object properties: eq: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - eq title: eq description: Equal to - type: object properties: ne: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - ne title: ne description: Not equal to - type: object properties: gt: type: number required: - gt title: gt description: Greater than - type: object properties: gte: type: number required: - gte title: gte description: Greater than or equal to - type: object properties: lt: type: number required: - lt title: lt description: Less than - type: object properties: lte: type: number required: - lte title: lte description: Less than or equal to - type: object properties: in: type: array items: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - in title: in description: In - type: object properties: nin: type: array items: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - nin title: nin description: Not in - type: object properties: exists: type: boolean required: - exists title: exists description: Exists title: Search operator - type: object properties: and: type: array items: type: object additionalProperties: anyOf: - type: object properties: eq: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - eq title: eq description: Equal to - type: object properties: ne: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - ne title: ne description: Not equal to - type: object properties: gt: type: number required: - gt title: gt description: Greater than - type: object properties: gte: type: number required: - gte title: gte description: Greater than or equal to - type: object properties: lt: type: number required: - lt title: lt description: Less than - type: object properties: lte: type: number required: - lte title: lte description: Less than or equal to - type: object properties: in: type: array items: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - in title: in description: In - type: object properties: nin: type: array items: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - nin title: nin description: Not in - type: object properties: exists: type: boolean required: - exists title: exists description: Exists required: - and title: and description: And - type: object properties: or: type: array items: type: object additionalProperties: anyOf: - type: object properties: eq: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - eq title: eq description: Equal to - type: object properties: ne: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - ne title: ne description: Not equal to - type: object properties: gt: type: number required: - gt title: gt description: Greater than - type: object properties: gte: type: number required: - gte title: gte description: Greater than or equal to - type: object properties: lt: type: number required: - lt title: lt description: Less than - type: object properties: lte: type: number required: - lte title: lte description: Less than or equal to - type: object properties: in: type: array items: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - in title: in description: In - type: object properties: nin: type: array items: anyOf: - type: string title: string description: String - type: number title: number description: Number - type: boolean title: boolean description: Boolean required: - nin title: nin description: Not in - type: object properties: exists: type: boolean required: - exists title: exists description: Exists required: - or title: or description: Or search_options: allOf: - $ref: '#/components/schemas/SearchOptions' description: Additional search options rerank_config: allOf: - $ref: '#/components/schemas/SearchRerankConfig' description: >- Override the rerank configuration for this search. If not provided, will use the knowledge base configured rerank settings. agentic_rag_config: description: >- Override the agentic RAG configuration for this search. If not provided, will use the knowledge base configured agentic RAG settings. anyOf: - type: object allOf: - $ref: '#/components/schemas/GoogleProtobufValue' anyOf: - required: - model - required: - model_db_id - provider properties: model: type: string description: >- The name of the model for the Agent to use. Refer to the [model list](https://docs.orq.ai/docs/proxy#/chat-models). model_db_id: type: string description: Identifier of the stored model configuration to use. provider: type: string description: Provider identifier for the stored model configuration. integration_id: type: - string - 'null' description: >- Optional integration identifier for the stored model configuration. - type: 'null' retrieval_config: allOf: - $ref: '#/components/schemas/SearchRetrievalConfig' description: >- Override the stored retrieval configuration for this search. If not provided, the knowledge base configuration is used. description: >- Search request. Sets the knowledge base and query, plus optional retrieval settings. SearchKnowledgeResponse: required: - matches type: object properties: matches: type: array items: $ref: '#/components/schemas/SearchKnowledgeMatch' description: >- Matching chunks. The response codec must emit this field even when empty. SearchType: type: string enum: - vector_search - keyword_search - hybrid_search SearchOptions: type: object properties: include_vectors: type: boolean description: Whether to include the vector in the chunk include_metadata: type: boolean description: Whether to include the metadata in the chunk include_scores: type: boolean description: Whether to include the scores in the chunk SearchRerankConfig: required: - model type: object properties: model: example: cohere/rerank-multilingual-v3.0 type: string description: >- The name of the rerank model to use. Refer to the [model list](https://docs.orq.ai/docs/proxy#/rerank-models). threshold: maximum: 1 type: number default: 0 description: >- The threshold value used to filter the rerank results, only documents with a relevance score greater than the threshold will be returned format: double minimum: 0 top_k: maximum: 100 minimum: 1 type: integer default: 10 description: >- The number of top results to return after reranking. If not provided, will default to the knowledge base configured `top_k`. format: int32 GoogleProtobufValue: description: >- Represents a dynamically typed value which can be either null, a number, a string, a boolean, a recursive struct value, or a list of values. SearchRetrievalConfig: type: object properties: type: $ref: '#/components/schemas/SearchType' top_k: type: integer format: int32 threshold: type: number format: double rerank_config: type: - object - 'null' description: >- Override reranking for this retrieval configuration. Omit to inherit stored settings or set to null to disable reranking. properties: enabled: type: boolean provider: type: string top_k: type: integer format: int32 minimum: 1 maximum: 100 model: type: string model_db_id: type: string model_type: type: string enum: - rerank model_parameters: type: object properties: threshold: type: number integration_id: type: - string - 'null' description: >- SearchRetrievalConfig is the retrieval strategy configuration. Type remains optional because external knowledge bases use the same base configuration without a retrieval strategy discriminator. SearchKnowledgeMatch: required: - id - text type: object properties: id: type: string text: type: string vector: type: array items: type: number format: double description: Embedding vector of the chunk, returned only when requested. metadata: type: object description: Arbitrary chunk metadata, omitted unless requested. scores: allOf: - $ref: '#/components/schemas/SearchKnowledgeScores' description: Search and rerank scores, omitted unless requested. SearchKnowledgeScores: type: object properties: rerank_score: type: number format: double search_score: type: number format: double securitySchemes: ApiKey: type: http scheme: bearer bearerFormat: JWT ````