> ## Documentation Index > Fetch the complete documentation index at: https://docs.contextual.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create Datastore > Create a new `Datastore`. A `Datastore` is a collection of documents. Documents can be ingested into and deleted from a `Datastore`. A `Datastore` can be linked to one or more `Agents`, and conversely, an `Agent` can be associated with one or more `Datastores` to ground its responses with relevant data. This flexible many-to-many relationship allows `Agents` to draw from multiple sources of information. This linkage of `Datastore` to `Agent` is done through the `Create Agent` or `Edit Agent` APIs. > Note that self-serve users are currently required to create datastores through our UI. Otherwise, they will receive the following message: "This endpoint is disabled as you need to go through checkout. Please use the UI to make this request." ## OpenAPI ````yaml api-reference/openapi.json post /datastores openapi: 3.1.0 info: title: Endpoints version: '1.0' servers: - url: https://api.contextual.ai/v1 security: - BearerAuth: [] paths: /datastores: post: tags: - /datastores summary: Create Datastore description: >- Create a new `Datastore`. A `Datastore` is a collection of documents. Documents can be ingested into and deleted from a `Datastore`. A `Datastore` can be linked to one or more `Agents`, and conversely, an `Agent` can be associated with one or more `Datastores` to ground its responses with relevant data. This flexible many-to-many relationship allows `Agents` to draw from multiple sources of information. This linkage of `Datastore` to `Agent` is done through the `Create Agent` or `Edit Agent` APIs. > Note that self-serve users are currently required to create datastores through our UI. Otherwise, they will receive the following message: "This endpoint is disabled as you need to go through checkout. Please use the UI to make this request." operationId: create_datastore_datastores_post requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/DatastoreInput' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/CreateDatastoreOutput' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: DatastoreInput: properties: name: type: string title: Name description: Name of the datastore configuration: $ref: '#/components/schemas/UnstructuredDatastoreConfigModel' title: Configuration description: >- Configuration of the datastore. If not provided, default configuration is used. default: {} type: object required: - name title: DatastoreInput description: >- DatastoreInput for creating a new datastore. If no type is provided, we default to unstructured. CreateDatastoreOutput: properties: id: type: string format: uuid title: Id description: ID of the datastore type: object required: - id title: CreateDatastoreOutput HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError UnstructuredDatastoreConfigModel: properties: parsing: $ref: '#/components/schemas/DatastoreParseConfiguration' description: Configuration for document parsing chunking: $ref: '#/components/schemas/ChunkingConfiguration' description: Configuration for document chunking html_config: $ref: '#/components/schemas/HtmlConfiguration' description: Configuration for HTML Extraction additionalProperties: false type: object title: UnstructuredDatastoreConfigModel description: Configuration for unstructured datastores. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError DatastoreParseConfiguration: properties: figure_captioning_prompt: type: string title: Figure Captioning Prompt description: >- Prompt to use for generating image captions. Must be non-empty if `figure_caption_mode` is `custom`. Otherwise, must be null. figure_caption_mode: $ref: '#/components/schemas/DatastoreFigureCaptionMode' title: Figure Caption Mode description: >- Mode for figure captioning. Options are `default`, `custom`, or `ignore`. Set to `ignore` to disable figure captioning. Set to `default` to use the default figure prompt, which generates a detailed caption for each figure. Set to `custom` to use a custom prompt. default: default enable_split_tables: type: boolean title: Enable Split Tables description: >- Whether to enable table splitting, which splits large tables into smaller tables with at most `max_split_table_cells` cells each. In each split table, the table headers are reproduced as the first row(s). This is useful for preserving context when tables are too large to fit into one chunk. default: false max_split_table_cells: type: integer title: Max Split Table Cells description: >- Maximum number of cells for split tables. Ignored if `enable_split_tables` is False. default: 100 ingestion_tier: anyOf: - $ref: '#/components/schemas/IngestionTier' - type: 'null' description: >- Ingestion tier for preset extraction configurations. Options: STANDARD, ADVANCED, PREMIUM, or None. When None (default), uses explicit config values or system defaults. When set, applies tier-based presets that can be overridden by explicit config. type: object title: DatastoreParseConfiguration description: >- Configuration for data extraction settings from documents at datastore level. Controls settings for document parsing. Includes those from `/parse` API along with some extra ingestion-only ones. ChunkingConfiguration: properties: chunking_mode: $ref: '#/components/schemas/ChunkingMode' title: Chunking Mode description: >- Chunking mode to use. Options are: `hierarchy_depth`, `hierarchy_heading`, `static_length`, `page_level`. `hierarchy_depth` groups chunks of the same hierarchy level or below, additionally merging or splitting based on length constraints. `hierarchy_heading` splits chunks at every heading in the document hierarchy, additionally merging or splitting based on length constraints. `static_length` creates chunks of a fixed length. `page_level` creates chunks that cannot run over page boundaries. default: hierarchy_depth max_chunk_length_tokens: type: integer maximum: 4096 minimum: 512 title: Max Chunk Length Tokens description: >- Target maximum length of text tokens chunks for chunking. Chunk length may exceed this value in some edge cases. default: 768 min_chunk_length_tokens: type: integer maximum: 3712 minimum: 128 title: Min Chunk Length Tokens description: >- Target minimum length of chunks in tokens. Must be at least 384 tokens less than `max_chunk_length_tokens`. Chunk length may be shorter than this value in some edge cases. Ignored if `chunking_mode` is `page_level`. default: 384 enable_hierarchy_based_contextualization: type: boolean title: Enable Hierarchy Based Contextualization description: Whether to enable section-based contextualization for chunking default: true type: object title: ChunkingConfiguration description: Configuration for document chunking settings. HtmlConfiguration: properties: max_chunk_length_tokens: type: integer maximum: 4096 minimum: 512 title: Max Chunk Length Tokens description: >- Target maximum length of text tokens chunks for chunking. Chunk length may exceed this value in some edge cases. default: 768 type: object title: HtmlConfiguration description: Configuration for HTML document ingestion settings. DatastoreFigureCaptionMode: type: string enum: - default - custom - ignore title: DatastoreFigureCaptionMode description: >- Mode for figure captioning. - `default`: Use the default figure prompt, which generates a detailed caption for each figure. - `custom`: Use a custom prompt. - `ignore`: Disable figure captioning. IngestionTier: type: string enum: - STANDARD - ADVANCED - PREMIUM title: IngestionTier description: Ingestion tier levels that determine extraction quality and cost. ChunkingMode: type: string enum: - hierarchy_depth - hierarchy_heading - static_length - page_level title: ChunkingMode description: >- Defines available chunking strategies. - `hierarchy_depth`: Creates a new chunk whenever a higher-level section heading is encountered. - `hierarchy_heading`: Creates a new chunk whenever any section heading is encountered. - `static_length`: Creates chunks of a fixed length. - `page_level`: Creates chunks that cannot run over page boundaries. securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: API Key ````