Documentation Index
Fetch the complete documentation index at: https://docs.engramme.com/llms.txt
Use this file to discover all available pages before exploring further.
This page collects operational details that apply across the Engramme API.
Rate Limits
Requests are subject to gateway and application-level limits. The public gateway currently enforces:
| Limit | Value |
|---|
| Requests per minute | 1,000 per project |
429 Too Many Requests, retry with exponential backoff. Response bodies can vary by which layer returns the limit. Application-level limits may return:
{
"detail": "RATE_LIMIT_EXCEEDED"
}
Request Limits
| Limit | Value |
|---|
| Text/file uploads | 10MB |
| PDF uploads | 20MB |
| Recall query text | 1,000 characters |
item_id length | 500 characters |
Pre-extracted memory_json | 256KB default |
item_id may contain word characters plus -, _, =, !, and :.
Status Codes
| Status | Meaning |
|---|
400 | Invalid request parameters or malformed input |
401 | Missing or invalid API key |
402 | Billing or usage check failed, such as INSUFFICIENT_FUNDS |
403 | The API key does not have access to the requested source or endpoint |
404 | Resource not found |
409 | Conflict, such as an item_id that is currently being processed |
429 | Rate limit exceeded |
500 | Internal server error |
503 | Service temporarily unavailable |
Upload Conflicts
If you provide your own item_id, /v1/memorize may return 409 when the item is already being processed.
Use generated IDs for simple uploads. Use stable unique item_id values when you want deduplication or idempotent behavior.
Async Processing
/v1/memorize returns after upload is accepted and processing has started. Memories may not be immediately available through /v1/memories/recall.
If recall returns no results right after upload, retry after a short delay.
