Serverless AI Context Database Creator

AI service that loads and processes text data into vector embeddings for semantic search and retrieval.

Endpoint

Upload and process content data into vector embeddings for a specified collection. PUT will overwrite existing data.

POST | PUThttps://api.xtartapp.com/data/memory

You must use a Bearer token provided by the dashboard to use for authentication. Add the token to the Authorization header.

Name	Type	Required	Max	Description
collection	string	Yes	-	The name of the collection to store the data in. This will be used as part of the collection identifier.
document	string	Yes	200	Unique identifier for the document. Must be less than 200 characters and contain only letters, numbers, underscores, and hyphens.
content	string	Yes	50000	The text content to process and store. Will be automatically chunked into smaller pieces for vector embedding.

Name	Type	Description
data	object	The data of the upload process
data.size	number	Number of document chunks created and stored from the uploaded content
data.document	string	The document identifier used for storage
data.collection	string	The name of the collection where the data was stored
metadata	object	Metadata about the data loader upload process
metadata.cost	number	The cost of the data loader upload request (approximately $0.000001 per document chunk)

{
   "error": "string", 
   "code": "string"
}

HTTP Status	Error Code	Message
400	INVALID_PAYLOAD	Occurs when the payload is invalid.
400	INVALID_REQUEST	Ex.: The request is invalid.
400	DATA_LOADER_ERROR	Ex: could not load data \| parsing error
400	HARM_CONTENT	Ex.: The content is harmful and cannot be processed.
400	INSUFFICIENT_BALANCE	The user has insufficient balance
401	UNAUTHORIZED	Ex.: The token is invalid.
429	TOO_MANY_REQUESTS	Ex.: The request limit has been reached.