Skip to main content
POST
/
index-document
Index Document
curl --request POST \
  --url https://api.agentbase.sh/index-document \
  --header 'Content-Type: multipart/form-data' \
  --form 'datastore_id=<string>' \
  --form file='@example-file'
{
  "document_id": "<string>",
  "datastore_id": "<string>",
  "filename": "<string>",
  "status": "<string>",
  "indexed_at": "<string>"
}

Documentation Index

Fetch the complete documentation index at: https://docs.agentbase.sh/llms.txt

Use this file to discover all available pages before exploring further.

​
Body Parameters

​
file
file
required
The document file to upload and index. Supported formats include PDF, TXT, PNG, JPG, and more.
​
datastore_id
string
required
The ID of the datastore where the document will be indexed. You can get this ID from the Create Datastore endpoint.

​
Example Request

curl -X POST https://api.agentbase.sh/index-document \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F "file=@./Trends_Artificial_Intelligence.pdf" \
  -F "datastore_id=ds_1234567890abcdef"

​
Response

Returns information about the indexed document. 
{
  "document_id": "doc_abcdef1234567890",
  "datastore_id": "ds_1234567890abcdef",
  "filename": "Trends_Artificial_Intelligence.pdf",
  "status": "indexed",
  "indexed_at": "2025-10-01T12:00:00Z"
}

​
Response Fields

​
document_id
string
The unique identifier for the indexed document
​
datastore_id
string
The ID of the datastore containing the document
​
filename
string
The name of the uploaded file
​
status
string
The indexing status of the document (e.g., indexed, processing)
​
indexed_at
string
Timestamp of when the document was successfully indexed