> ## Documentation Index > Fetch the complete documentation index at: https://manual.seahorse.dnotitia.ai/llms.txt > Use this file to discover all available pages before exploring further. # Insert Data with Embedding > Embed the data using inference endpoints and then insert the data into the table. The embedding is generated from the embedding source and stored in the embedding target column. ## OpenAPI ````yaml POST /v2/data/embedding openapi: 3.1.0 info: title: Seahorse API Gateway description: >- Seahorse API Gateway is an API gateway that integrates vector database, AI inference, and storage services. It provides features such as vector search, embedding generation, text generation, and object storage. license: name: '' version: 2.0.0-rc1 servers: - url: https://{resource_uuid}.api.seahorse.dnotitia.ai description: >- 리소스(스토리지/테이블/인퍼런스 endpoint)별 UUID 서브도메인. UUID 는 콘솔 → 리소스 상세 페이지 "API URL" 항목에서 확인 variables: resource_uuid: default: your-resource-uuid-here description: '대시 제거된 32자리 UUID (예: b0348a15cf0e48079e290fe03901247b)' security: [] tags: - name: TABLE_V2 description: Table operations v2 - name: STORAGE description: Storage Object operations paths: /v2/data/embedding: post: tags: - TABLE_V2 summary: Insert Data with Embedding description: >- Embed the data using inference endpoints and then insert the data into the table. The embedding is generated from the embedding source and stored in the embedding target column. operationId: insert_data_with_embedding_handler_v2 requestBody: description: >- If you provide the data to insert into the table in the 'data' field, and set the embedding source and target (using embedding_source and embedding_config), the gateway will automatically generate embeddings for your data and insert the data with the embeddings into the table. Input limits: - Max rows in data: 50 - Max bytes for embedding_source text per row: 32KB Primary Key Generation Rules: - Format: {Document Id: String}{Record Separator: \RS, ASCII 30}{Chunk Id: Int} - Document Id: A hash value for duplicate data detection. Recommended length is around 128 characters. - Record Separator: ASCII 30 character (\u001E) - Chunk Id: 4-byte unsigned integer (maximum: 2^32-1). Sequential numbers are recommended. - Do NOT assign the same primary key value (pk) to different chunks. Each pk must be unique per chunk. content: application/json: schema: $ref: '#/components/schemas/DataInsertWithEmbeddingRequest' example: data: - id: random1\u001E1 metadata: A text: hello - id: random1\u001E2 metadata: B text: world embedding_config: - embedding_target: dense_vector embedding_type: dense - embedding_target: sparse_vector embedding_type: sparse embedding_source: text required: true responses: '200': description: Success to insert data with embedding content: application/json: schema: $ref: '#/components/schemas/CoralResponse_DataInsertResult' example: code: 200 data: elapsed_time: 1 inserted_record_batches: 1 inserted_row_count: 1 exception: null success: true '400': description: Invalid input provided. content: application/json: schema: $ref: '#/components/schemas/CoralResponse_ErrorBody' example: code: 400 data: null exception: error_code: 400001 error_message: 'Bad Request: ' success: false '500': description: Error occurred while inserting data with embedding. content: application/json: schema: $ref: '#/components/schemas/CoralResponse_ErrorBody' example: code: 500 data: null exception: error_code: 500001 error_message: 'Arrow error: ' success: false security: - bearerAuth: - WRITE - apiKeyAuth: - WRITE components: schemas: DataInsertWithEmbeddingRequest: type: object required: - data - embedding_source properties: data: type: array items: {} description: List of Data that will be inserted into the table. embedding_config: type: - array - 'null' items: $ref: '#/components/schemas/EmbeddingConfig' description: Embedding type to use. "dense" or "sparse". embedding_source: type: string description: >- Name of the column to get text for embedding. ex) text, metadata, etc. embedding_target: type: - string - 'null' description: >- Name of the column to store the embedding vector. The embedding vector generated from the embedding source will be added to the column specified by the embedding target. The embedding target column must be a vector column. ex) feature, embedding, etc. CoralResponse_DataInsertResult: type: object required: - success - code properties: code: type: integer format: int32 description: HTTP status code. minimum: 0 data: type: object required: - inserted_record_batches - inserted_row_count properties: elapsed_time: type: - number - 'null' format: float description: >- Elapsed time in seconds for reading the file and inserting the data into the table. This measures the time taken by the underlying data insertion process, but does not include the full duration of the API request. inserted_record_batches: type: integer description: Number of total record batches inserted. minimum: 0 inserted_row_count: type: integer description: Number of total rows inserted. minimum: 0 exception: type: object required: - inserted_record_batches - inserted_row_count properties: elapsed_time: type: - number - 'null' format: float description: >- Elapsed time in seconds for reading the file and inserting the data into the table. This measures the time taken by the underlying data insertion process, but does not include the full duration of the API request. inserted_record_batches: type: integer description: Number of total record batches inserted. minimum: 0 inserted_row_count: type: integer description: Number of total rows inserted. minimum: 0 success: type: boolean description: Whether the request was successful. CoralResponse_ErrorBody: type: object required: - success - code properties: code: type: integer format: int32 description: HTTP status code. minimum: 0 data: type: object required: - error_code - error_message properties: error_code: type: integer format: int32 minimum: 0 error_message: type: string exception: type: object required: - error_code - error_message properties: error_code: type: integer format: int32 minimum: 0 error_message: type: string success: type: boolean description: Whether the request was successful. EmbeddingConfig: type: object required: - embedding_type - embedding_target properties: embedding_target: type: string description: >- Name of the column to store the embedding vector. The embedding vector generated from the embedding source will be added to the column specified by the embedding target. The embedding target column must be a vector column. ex) feature, embedding, etc. embedding_type: $ref: '#/components/schemas/EmbeddingType' description: Embedding type to use. "dense" or "sparse". EmbeddingType: type: string enum: - Dense - Sparse securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT description: >- Bearer token authentication. Include the token in the Authorization header as 'Bearer ' apiKeyAuth: type: apiKey in: header name: api-key description: API key authentication. Include the key in the api-key header ````