> ## Documentation Index > Fetch the complete documentation index at: https://docs.streamkap.com/llms.txt > Use this file to discover all available pages before exploring further. # Create Knowledge Base > Create a knowledge base pipeline, optionally deploying it. Set deploy=false to save as draft without deploying to Flink. ## OpenAPI ````yaml /openapi/openapi.json post /knowledge-bases/config openapi: 3.1.0 info: title: Streamkap REST API description: >- The Streamkap REST API allows you to programmatically manage your CDC pipelines, sources, destinations, transforms, and more. Authenticate using a bearer token obtained from the [Access Token](/api-reference/auth/access-token) endpoint with your API client credentials. contact: name: Streamkap Support url: https://streamkap.com/ email: support@streamkap.com license: name: Proprietary version: 2.0.0 servers: - url: https://api.streamkap.com description: Production security: [] tags: - name: Agents description: Create, deploy, and manage Flink-based AI agents. - name: Agents Observability description: >- Read-only views over the MCP audit log: agent rollup, sessions, spans, histograms, external-agent verify. - name: Alerts description: Manage alert subscribers, preferences, and notification credentials. - name: Authentication description: Obtain and refresh access tokens, manage client credentials and roles. - name: Billing description: Retrieve usage metrics, summaries, and export billing data. - name: Consumer Groups description: List, inspect, and reset Kafka consumer group offsets. - name: Dashboard description: Retrieve organisation-level statistics and overview data. - name: Destinations description: Create, configure, and manage data destinations and their lifecycle. - name: Kafka Access description: Manage Kafka users and their access permissions. - name: Logs description: Query and summarise system logs. - name: Pipelines description: Create, configure, and manage CDC pipelines and their lifecycle. - name: Project Keys description: Manage project keys that bundle API credentials and optional Kafka access. - name: Schema Registry description: Browse schema subjects, versions, and retrieve schema definitions. - name: Services description: View and switch service metadata. - name: Sources description: >- Create, configure, and manage data sources, snapshots, and their lifecycle. - name: Tags description: Create, update, and manage resource tags for organisation. - name: Topics description: Browse topic details, statistics, configurations, metrics, and messages. - name: Transforms description: >- Create, deploy, and manage data transforms, unit tests, and implementation details. paths: /knowledge-bases/config: post: tags: - Knowledge Bases summary: Create Knowledge Base description: |- Create a knowledge base pipeline, optionally deploying it. Set deploy=false to save as draft without deploying to Flink. operationId: createKnowledgeBase parameters: - name: deploy in: query required: false schema: type: boolean default: true title: Deploy requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateKnowledgeBaseRequest' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/KnowledgeBaseResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - FronteggHTTPAuthentication: [] components: schemas: CreateKnowledgeBaseRequest: properties: name: type: string maxLength: 200 minLength: 1 title: Name description: Knowledge base display name description: anyOf: - type: string maxLength: 500 - type: 'null' title: Description description: Human-readable context source: $ref: '#/components/schemas/KBSourceConfig' text: $ref: '#/components/schemas/KBTextConfig' description: Text template configuration embedding: $ref: '#/components/schemas/KBEmbeddingConfig' vectorStore: $ref: '#/components/schemas/KBVectorStoreConfig' processing: $ref: '#/components/schemas/KBProcessingConfig' additionalProperties: false type: object required: - name - source - embedding - vectorStore title: CreateKnowledgeBaseRequest description: >- Request body for POST /knowledge-bases/config — create a knowledge base pipeline. KnowledgeBaseResponse: properties: _id: type: string title: Id name: type: string title: Name job_type: $ref: >- #/components/schemas/app__models__api__agents_api_models__flink_jobs__FlinkJobTypeEnum status: $ref: '#/components/schemas/FlinkJobStatusEnum' desired_status: anyOf: - $ref: '#/components/schemas/FlinkJobStatusEnum' - type: 'null' flink_job_name: type: string title: Flink Job Name flink_job_id: anyOf: - type: string - type: 'null' title: Flink Job Id parallelism: type: integer title: Parallelism default: 1 error_message: anyOf: - type: string - type: 'null' title: Error Message agent_config: anyOf: - additionalProperties: true type: object - type: 'null' title: Agent Config description: KB config (secrets masked) created_by: anyOf: - type: string - type: 'null' title: Created By created_timestamp: anyOf: - type: string format: date-time - type: 'null' title: Created Timestamp updated_timestamp: anyOf: - type: string format: date-time - type: 'null' title: Updated Timestamp additionalProperties: true type: object required: - _id - name - job_type - status - flink_job_name title: KnowledgeBaseResponse description: >- Response model for knowledge base entities. Mirrors FlinkJobResponse shape. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError KBSourceConfig: properties: topic: anyOf: - type: string maxLength: 249 - type: 'null' title: Topic description: >- Exact Kafka topic name (Kafka's own limit is 249). Mutually exclusive with ``topicPattern``. The deploy-time builder turns this into ``^re.escape(topic)$`` for the Java runtime. topicPattern: anyOf: - type: string maxLength: 1024 - type: 'null' title: Topicpattern description: >- Regex pattern for input topics, e.g. ``^source_.*\.orders$``. Mutually exclusive with ``topic`` — set this only for programmatic multi-topic fan-in. inputSerialization: $ref: '#/components/schemas/AgentSerializationEnum' description: Input deserialization format default: JsonConfluent fields: anyOf: - items: type: string type: array - type: 'null' title: Fields description: Column-level filter — only these fields processed textFields: anyOf: - items: type: string type: array - type: 'null' title: Textfields description: Fields to include in the embedded text (if not using textTemplate) metadataFields: anyOf: - items: type: string type: array - type: 'null' title: Metadatafields description: Fields to store as vector metadata (filterable at query time) additionalProperties: false type: object title: KBSourceConfig description: |- Kafka source configuration for the knowledge base pipeline. Exactly one of ``topic`` or ``topicPattern`` must be set: - ``topic`` — exact Kafka topic name (the FE wizard's single-topic picker emits this). The service layer composes ``^re.escape(topic)$`` for the Java ``--topicMatcherRegex`` CLI arg, so the Java side keeps the regex-only contract. - ``topicPattern`` — escape hatch for tenants who genuinely need a multi-topic regex (e.g. fan-in of a sharded topic family). Not exposed by the FE wizard today — programmatic API callers only. The XOR rule is enforced by ``_topic_xor`` below: empty payload (neither set) and over-specified payload (both set) both 422. KBTextConfig: properties: textTemplate: type: string maxLength: 8000 title: Texttemplate description: >- Template with ${field} placeholders, e.g. 'Customer ${customer_id} ordered ${product}' default: '' additionalProperties: false type: object title: KBTextConfig description: >- Text template configuration for composing the embedding input from record fields. KBEmbeddingConfig: properties: embeddingConnectionId: type: string maxLength: 64 minLength: 1 title: Embeddingconnectionid description: >- Reference to a saved AgentLlmConnection. The connection must advertise the 'embedding' capability. model: anyOf: - type: string maxLength: 200 - type: 'null' title: Model description: >- Per-KB embedding-model override. ``None`` = use the connection's default embedding model (``embedding.model`` on the saved row). dimensions: anyOf: - type: integer maximum: 65536 minimum: 1 - type: 'null' title: Dimensions description: >- Per-KB dimensions override. ``None`` = use the connection's default (``embedding.dimensions`` on the saved row), or the provider default when neither is set. batchSize: anyOf: - type: integer maximum: 2048 minimum: 1 - type: 'null' title: Batchsize description: >- Per-KB batchSize override. ``None`` = use the connection's default (``embedding.batchSize`` on the saved row, falls back to 100). additionalProperties: false type: object required: - embeddingConnectionId title: KBEmbeddingConfig description: |- Embedding-side configuration for a knowledge base. Carries a reference to a saved ``AgentLlmConnection`` plus optional per-KB overrides of the connection's defaults. Credentials, provider, and the default model live on the connection — there is no inline apiKey / baseUrl path on a KB. The deploy-time resolver (``resolve_kb_connections``) reads the referenced connection's ``embedding`` defaults block, applies any per-KB overrides, and stamps the resulting bundle into the Flink CLI JSON. The referenced connection must carry ``'embedding'`` in its ``capabilities`` list and have a non-empty ``embedding.model`` — the validator inside ``resolve_saved_embedding_credentials`` raises 422 at deploy time otherwise so the FE error surfaces the cause without waiting for a Java runtime 4xx. KBVectorStoreConfig: properties: vectorStoreConnectionId: type: string maxLength: 64 minLength: 1 title: Vectorstoreconnectionid description: >- Reference to a saved AgentVectorStoreConnection. BE resolves credentials at deploy time. indexName: type: string maxLength: 200 minLength: 1 title: Indexname description: Index or collection name in the vector store namespace: anyOf: - type: string maxLength: 200 - type: 'null' title: Namespace description: Namespace or partition within the index metric: type: string enum: - cosine - dot_product - euclidean title: Metric description: Distance metric default: cosine additionalProperties: false type: object required: - vectorStoreConnectionId - indexName title: KBVectorStoreConfig description: |- Vector store configuration for the knowledge base. References a lightweight ``AgentVectorStoreConnection`` by id. The BE resolves the connection's credentials (apiKey + endpoint) at deploy time. There is no inline-credentials path — KBs must reference a saved connection (the FE picker is the only authoring surface). KBProcessingConfig: properties: parallelism: type: integer maximum: 128 minimum: 1 title: Parallelism description: Flink parallelism default: 1 checkpointIntervalMin: type: integer maximum: 60 minimum: 1 title: Checkpointintervalmin description: Checkpoint interval in minutes default: 5 chunkSize: type: integer maximum: 8192 minimum: 1 title: Chunksize description: Text chunk size in tokens default: 512 chunkOverlap: type: integer maximum: 4096 minimum: 0 title: Chunkoverlap description: Overlap tokens between chunks default: 50 additionalProperties: false type: object title: KBProcessingConfig description: Processing configuration for the knowledge base pipeline. app__models__api__agents_api_models__flink_jobs__FlinkJobTypeEnum: type: string enum: - pyflink - jar - agent_config - knowledge_base title: FlinkJobTypeEnum FlinkJobStatusEnum: type: string enum: - CREATED - DEPLOYING - RUNNING - CANCELLING - CANCELLED - FAILED - FINISHED title: FlinkJobStatusEnum ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError AgentSerializationEnum: type: string enum: - JsonConfluent - AvroConfluent title: AgentSerializationEnum securitySchemes: FronteggHTTPAuthentication: type: http scheme: bearer ````