Limits & Quotas

All numerical limits are enforced server-side.

---

File Upload (Web UI)

Limit	Value	Notes
Max file size	5 MB	Browser sessionStorage also caps at ~5 MB
Max rows	2,048	Client-side display cap
Max columns	100	Across all rows in the file
File format	.csv only	Must be valid CSV with headers

---

Predict API

Applies to POST /api/predict regardless of input mode (inline or remote data source). The underlying model is SAP-RPT-1.6.

Row Limits

Limit	Value
Min query rows	1
Max query rows	512
Min context rows	2
Max context rows	100,000

• Query rows: rows containing the [PREDICT] placeholder.
• Context rows: rows without [PREDICT] — used as examples for the model.
• Context rows beyond 2,048 are randomly downsampled before being sent to the model.

Column & Cell Limits

Limit	Value	Notes
Max columns total	100	Applies to sap-rpt-1.6; exceeding requires sap-rpt-1.6-large (256 columns)
Max target columns	10
Max cell string length	1,000 characters	Values exceeding ~500 subword tokens are compressed or truncated by the model
Max column name length	100 characters
Max target classes (recommendation)	256

---

Remote Data Source

Additional limits when using dataSource.type: "url" to reference an external CSV file. Standard API row/column limits above still apply.

Limit	Value
Max file size	100 MB
Fetch timeout	30 seconds
Protocol	HTTPS only
URL length	8,192 characters

---

Rate Limits

Rate limiting is per-user. Exceeding the limit returns HTTP 429 with headers:

• X-RateLimit-Limit — total allowed requests
• X-RateLimit-Remaining — remaining requests in window
• X-RateLimit-Reset — Unix timestamp when window resets
• Retry-After — seconds until next request is allowed

A 429 has two causes: the burst limit (requests sent too quickly — wait a few seconds) or the hourly budget (window exhausted — resets within the hour). The Retry-After header tells you how long to wait in either case.

Predict API

Limit	Value
Requests per window	1000
Window duration	3,600 seconds (1 hour)
Burst allowance	5 requests per 18s window
Average pace	~1 request every 3.6 seconds

You can send up to 5 requests in any 18-second window. All burst tokens reset together at the end of each window. This caps instantaneous load while still allowing short bursts for batch workflows (e.g. notebooks). The burst limit is checked first; if it rejects, your hourly budget is preserved.

Planning sustained load: to avoid burst rejections, keep continuous requests at roughly 1 every 3.6 seconds (5 per 18s). Batches larger than 5 should be spread across multiple windows.

Chat API

Limit	Value
Requests per window	20
Window duration	60 seconds

SQL Execute API

Limit	Value
Requests per window	40
Window duration	60 seconds

---

Explainability

Parameter	Range	Default
top_column_scores	1–20	4
top_relevant_context_rows	1–20	3

---

Context Downsampling

Requests with more than 2,048 context rows are randomly downsampled (Fisher-Yates) to 2,048 rows before being sent to RPT-1. Query rows (rows containing [PREDICT]) are never downsampled. The response's samplingMetadata reports what happened.

Reproducibility: Pass sampler_options.seed to make the random selection deterministic. Repeated requests with the same context rows and seed produce the same downsampled subset.

What's not affected: UI uploads remain capped at 2,048 rows and never trigger downsampling. The downsampler only kicks in for direct API consumers calling /api/predict with more than 2,048 context rows.

Limit	Value
Max context rows accepted (input)	100,000
Max context rows forwarded to model	2,048
Strategy	random (Fisher-Yates)