Ingest Content | PrivateGPT

Unified endpoint to ingest files, text, URIs, or already processed content

JSON request body supporting multiple input types

artifactstringRequired1-255 characters

Unique identifier for the text being ingested within the collection

inputobjectRequired

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

collectionstringOptional1-255 charactersDefaults to pgpt_collection

Collection name to group related documents for better organization and filtering

metadatamap from strings to any or nullOptional

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

Content successfully ingested and processed

datalist of objects

List of ingested documents with their metadata and processing information

object"list"Defaults to list

Response object type, always 'list' for ingestion responses

model"private-gpt"Defaults to private-gpt

Model identifier, always ‘private-gpt’

401

Unauthorized Error

$	curl -X POST /v1/artifacts/ingest \
>	-H "Content-Type: application/json" \
>	-d '{
>	"artifact": "company_profile",
>	"input": {
>	"type": "text",
>	"value": "Our company was founded in 2020..."
>	},
>	"collection": "corporate_docs",
>	"metadata": {
>	"author": "Marketing Team",
>	"file_name": "company_profile.txt"
>	}
>	}'

1	{
2	"data": [
3	{
4	"artifact": "company_profile",
5	"object": "ingest.document",
6	"doc_metadata": {
7	"author": "Marketing Team",
8	"file_name": "company_profile.txt"
9	}
10	}
11	],
12	"object": "list",
13	"model": "private-gpt"
14	}