Skip to main content
POST
/
knowledge
Python
from datagrid_ai import Datagrid

client = Datagrid(
    api_key="My API Key",
)
knowledge = client.knowledge.create(
    files=[b"raw file contents"],
)
print(knowledge.id)
{
  "object": "knowledge",
  "id": "<string>",
  "name": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "status": "pending",
  "row_counts": {
    "total": 123,
    "completed": 123,
    "failed": 123
  },
  "credits": {
    "consumed": 123
  }
}

Authorizations

​
Authorization
string
header
required

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

Body

multipart/form-data
​
files
file[]
required

The files to be uploaded and learned. Supported media types are pdf, json, csv, text, png, jpeg, excel, google sheets.

​
name
string | null

The name of the knowledge.

Response

201 - application/json

Successfully created knowledge

The knowledge object represents knowledge that an agent may leverage to respond.

​
object
enum<string>
required

The object type, which is always knowledge.

Available options:
knowledge
​
id
string
required

The knowledge identifier, which can be referenced in the API endpoints.

​
name
string
required

The name of the knowledge

​
created_at
string<date-time>
required

The ISO string for when the knowledge was created.

​
status
enum<string>
required

The current knowledge status can be one of three values: pending, partial, or ready. pending indicates that the knowledge is awaiting learning and will not be used by the agent when responding. partial indicates that the knowledge is partially learned. The agent may use some aspects of it when responding. ready indicates that the knowledge is fully learned and will be completely utilized in responses.

Available options:
pending,
partial,
ready
​
row_counts
object
required

Row count statistics for the knowledge.

​
updated_at
string<date-time>

The ISO string for when the knowledge was last updated.

​
credits
object