POST
/
v1
/
artifacts
/
ingest
{
  "object": "list",
  "model": "private-gpt",
  "data": [
    {
      "object": "ingest.document",
      "artifact": "quarterly_report",
      "doc_metadata": {
        "file_name": "Q3_Report.pdf",
        "page_number": 1,
        "total_pages": 10
      }
    }
  ]
}

Body

application/json

JSON request body supporting multiple input types

Request body for ingesting content into the system for AI context.

​
artifact
string
required

Unique identifier for the text being ingested within the collection

Required string length: 1 - 255
Examples:

"user_manual_chapter_1"

"policy_document_2024"

​
input
object
required

Raw input data to be processed and ingested into the system. Can be a file (base64), URI, or plain text Input for base64 encoded files.

​
collection
string
default:pgpt_collection

Collection name to group related documents for better organization and filtering

Required string length: 1 - 255
Examples:

"corporate_docs"

"user_manuals"

"financial_reports"

​
metadata
object | null

Optional metadata dictionary containing additional document information. If provided, must include 'file_name' with a valid file extension

Examples:
{
  "author": "John Doe",
  "department": "HR",
  "file_name": "company_policy.txt"
}
{
  "file_name": "manual_section.txt",
  "last_updated": "2024-01-15",
  "version": "2.1"
}

Response

Content successfully ingested and processed

Response model for successful document ingestion operations.

​
object
string
required

Response object type, always 'list' for ingestion responses

Allowed value: "list"
​
model
string
required

Model identifier, always 'private-gpt'

Allowed value: "private-gpt"
​
data
IngestedDoc · object[]
required

List of ingested documents with their metadata and processing information