Add files to vector store
Add parsed files to a vector store for indexing and search.
This endpoint initiates an asynchronous process to add files to a vector store:
- Creates a background job to track the operation
- Starts a Temporal workflow to process the files
- Files are parsed, chunked, and embedded into the vector store
- Job status can be monitored via the jobs API
Authentication:
- Credentials can be provided either through project-level credentials or request-level credentials
- For SGP Knowledge Base, SGP credentials are required
Process:
- The operation runs asynchronously in the background
- Use the returned job entity to monitor progress
- Files must be previously parsed (have parse_result_ids)
Returns:
- Job entity with ID, status, and metadata for tracking the operation progress
Example Request:
{
"parse_result_ids": ["parse_123", "parse_456"],
"credentials": {
"sgp": {
"api_key": "your-api-key",
"account_id": "your-account-id"
}
}
}
Example Response:
{
"id": "job_123456789",
"operation": "VECTOR_STORE",
"status": "PENDING",
"parameters": {
"parse_result_ids": ["parse_123", "parse_456"]
},
"source_id": null,
"project_id": "proj_987654321",
"created_at": "2024-01-15T10:30:00Z",
"updated_at": "2024-01-15T10:30:00Z"
}
Documentation Index
Fetch the complete documentation index at: https://docs.gp.scale.com/llms.txt
Use this file to discover all available pages before exploring further.
Authorizations
API key for authentication
Selected Account ID
Body
IDs of the parse results
Response
Files added to vector store successfully. Job entity returned for tracking progress.
Job response model representing an asynchronous operation.
ID of the entity
ID of the project
Operation type (e.g., 'parse')
parse, batch_parse, extract, research, vector_store, chunk, summarization, create_index, update_index Current job status
pending, running, succeeded, partially_succeeded, failed, cancelled When the job was created
"job"Source document/file ID
Request correlation ID for tracing
When the job started processing
When the job completed
Job result payload when completed
Live progress payload (used by batch jobs)
Error message if job failed
Timeline of job execution events

