List Datastores

List Datastores

curl --request GET \
  --url https://api.contextual.ai/v1/datastores \
  --header 'Authorization: Bearer <token>'

{
  "total_count": 123,
  "datastores": [
    {
      "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
      "name": "<string>",
      "datastore_type": "<string>",
      "created_at": "2023-11-07T05:31:56Z",
      "configuration": {}
    }
  ],
  "next_cursor": "<string>"
}

GET

datastores

List Datastores

curl --request GET \
  --url https://api.contextual.ai/v1/datastores \
  --header 'Authorization: Bearer <token>'

{
  "total_count": 123,
  "datastores": [
    {
      "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
      "name": "<string>",
      "datastore_type": "<string>",
      "created_at": "2023-11-07T05:31:56Z",
      "configuration": {}
    }
  ],
  "next_cursor": "<string>"
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Query Parameters

agent_id

string<uuid>

ID of the agent used to filter datastores. If provided, only datastores linked to this agent will be returned.

limit

integer

default:1000

Maximum number of datastores to return

Required range: 1 <= x <= 1000

cursor

string

Cursor from the previous call to list datastores, used to retrieve the next set of results

Response

Successful Response

total_count

integer

required

Total number of available datastores

datastores

DatastoreOutputEntry · object[]

required

List of all datastores

Show child attributes

datastores.id

string<uuid>

required

ID of the datastore

datastores.name

string

required

Name of the datastore

datastores.datastore_type

string

required

Type of the datastore

Allowed value: "UNSTRUCTURED"

datastores.created_at

string<date-time>

required

Timestamp of when the datastore was created, in ISO format

datastores.configuration

Configuration · object

Configuration of the datastore

Show child attributes

datastores.configuration.parsing

DatastoreParseConfiguration · object

Configuration for document parsing

Show child attributes

datastores.configuration.parsing.figure_captioning_prompt

string

Prompt to use for generating image captions. Must be non-empty if figure_caption_mode is custom. Otherwise, must be null.

datastores.configuration.parsing.figure_caption_mode

enum<string>

default:default

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.

Available options:

default,

custom,

ignore

datastores.configuration.parsing.enable_split_tables

boolean

default:true

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.

datastores.configuration.parsing.max_split_table_cells

integer

default:100

Maximum number of cells for split tables. Ignored if enable_split_tables is False.

datastores.configuration.chunking

ChunkingConfiguration · object

Configuration for document chunking

Show child attributes

datastores.configuration.chunking.chunking_mode

enum<string>

default:hierarchy_depth

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.

Available options:

hierarchy_depth,

hierarchy_heading,

static_length,

page_level

datastores.configuration.chunking.max_chunk_length_tokens

integer

default:768

Target maximum length of text tokens chunks for chunking. Chunk length may exceed this value in some edge cases.

Required range: 512 <= x <= 4096

datastores.configuration.chunking.min_chunk_length_tokens

integer

default:384

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.

Required range: 128 <= x <= 3712

datastores.configuration.chunking.enable_hierarchy_based_contextualization

boolean

default:true

Whether to enable section-based contextualization for chunking

datastores.configuration.html_config

HtmlConfiguration · object

Configuration for HTML Extraction

Show child attributes

datastores.configuration.html_config.max_chunk_length_tokens

integer

default:768

Target maximum length of text tokens chunks for chunking. Chunk length may exceed this value in some edge cases.

Required range: 512 <= x <= 4096

next_cursor

string

Next cursor to continue pagination. Omitted if there are no more datastores to retrieve.

Create Datastore

⌘I

/datastores

/datastores/{id}/documents

/agents

/contents

/agents/{id}/query

/lmunit

/users

/generate

/rerank

/parse

/workspaces

/billing

Authorizations

Query Parameters

Response