CoralDashboardDocumentationPlaygroundCommunity

Bulk Embedding (might be redundant)

Suggest Edits

If you have a large collection of text rather than a single file, bulk embedding may be more efficient for you. This endpoint returns a JSONL file of text embeddings with their respective text. The JSONL will be available for 2 months and downloadable via the download_file().

Example Requests

Create A Bulk Embed

Request

# Request
co.bulk_embed(
	model: "string",
	url: "string"(url to gcp file)
  file_id: "string" (id to uploaded file)
	text_field: "string" (column to get text from)
	truncate:"string" {LEFT:DEFAULT,RIGHT}
)

Response

{
	job_id:"string"
}

Retrieve A Bulk Embed

Request

co.get_bulk_embed(
	job_id: "string"
)

Response

# Response of co.get_bulk_embed():
{
	job_id: "string",
  status: "string", (COMPLETE, QUEUED, FAILED or RUNNING)
  created_at: "string", (timestamp)
  updated_at: "string", (timestamp)
  input_url: "string",
  input_file_id: "string",
  output_file_id: "string",
  model: "string",
  truncate: "string", (LEFT or RIGHT)
  percent_complete: float
}

List a Bulk Embed

Request

co.list_bulk_embed()

Response

# Response of co.list_bulk_embeds():
{bulk_embed : [{
	job_id: "string",
  status: "string", (COMPLETE, QUEUED, FAILED or RUNNING)
  created_at: "string", (timestamp)
  updated_at: "string", (timestamp)
  input_url: "string",
  input_file_id: "string",
  output_file_id: "string",
  model: "string",
  truncate: "string", (LEFT or RIGHT)
  percent_complete: float
}, ...]}

Next Steps

Updated about 2 months ago