Put the right result first
Superlinked gives your agent one API to rescore retrieved documents against the full question and put the best evidence first.
Which passage shows that the bearing was visibly on fire at Salem while the detector alert went to the Wayside Help Desk instead of the crew?
The Wayside Help Desk in Atlanta, Georgia, monitors alerts from NS’s HBDs. Critical alarms broadcast straight to the train crew. For noncritical alerts, the analyst monitors the train over HBDs it crosses later, paying attention to temperature trends. The single analyst on duty did not notice the Salem noncritical alert, as he dealt with higher-priority alerts.
At 8:13 p.m., at the Salem HBD, the reading for the L1 bearing was 103°F above ambient. This reading was high enough to trigger a noncritical alert to the Wayside Help Desk (see box), but not to the crew. A surveillance camera picture from Salem showed fire near the bearing (right). Surveillance cameras in Sebring also captured images of the train, and no anomalies were noted.
Reranking separates complete evidence from close matches
Which passage says a court must decide which contract governs when the parties agreed to two contracts?
In cases where parties have agreed to only one contract, and that contract contains an arbitration clause with a delegation provision, then, absent a successful challenge to the delegation provision, courts must send all arbitrability disputes to arbitration.
One contract, not twoBut, where, as here, parties have agreed to two contracts—one sending arbitrability disputes to arbitration, and the other either explicitly or implicitly sending arbitrability disputes to the courts—a court must decide which contract governs.
Complete query evidenceWhat did the doctor fail to document within 6 months of proof of delivery in the published L1851 claim example?
Proof of delivery with face-to-face encounter 7 months ago
The evidence alone does not name the documentation errorThe doctor didn’t document the face-to-face encounter within 6 months of proof of delivery.
Complete query evidenceWhich passage records the Audit Committee’s non-reliance conclusion and defines the affected annual and interim reporting periods?
Pathward Financial, Inc. (the "Company") is filing this Amendment No. 1 on Form 10-K/A (this “Form 10-K/A”) to amend and restate its audited financial statements and related footnote information as of September 30, 2024 and September 30, 2023, and for the years ended September 30, 2024, 2023 and 2022, previously included in its Annual Report on Form 10-K filed with the Securities and Exchange Commission (the “SEC”) on November 26, 2024 (the “Original Report”). Additionally, it includes the restated unaudited interim condensed consolidated financial statements for the Affected Periods (as defined below). This Form 10-K/A also amends certain other Items in the Original Report, as listed in “Items Amended in this Form 10-K/A” below.
No Audit Committee non-reliance conclusionAs described in the Company’s Current Report on Form 8-K filed with the SEC on July 2, 2025, on June 26, 2025, the Audit Committee of our Board of Directors, after discussion with management and our independent registered public accounting firm, Crowe LLP, concluded that our audited consolidated financial statements as of the fiscal years ended September 30, 2024 and 2023, and for each year in the three fiscal year periods ended September 30, 2024 contained in our Annual Reports on Form 10-K, and our unaudited consolidated financial statements as of and for the interim periods ended December 31, 2024, 2023, 2022, and 2021, March 31, 2024, 2023, and 2022, June 30, 2024, 2023, and 2022, and September 30, 2024, 2023, and 2022 contained in our Quarterly Reports on Form 10-Q (collectively, but excluding the interim period ended December 31, 2024, the “Affected Periods”) should no longer be relied upon and should be restated because of errors identified in such financial statements, as described below.
Complete query evidenceRun reranking with one score call
from sie_sdk import SIEClientclient = SIEClient( api_key="sk-sie-…", base_url="https://api.superlinked.com",)query = "queryWhich passage shows that the bearing was visibly on fire at Salem while the detector alert went to the Wayside Help Desk instead of the crew?"documents = [ "document 1At 7:37 p.m., at the Sebring HBD, the reading for the L1 bearing was only 38°F above ambient—not high enough to trigger an alert. The R1 bearing measured 20°F above ambient. But the L1 bearing was hotter.", "document 2At 8:13 p.m., at the Salem HBD, the reading for the L1 bearing was 103°F above ambient. This reading was high enough to trigger a noncritical alert to the Wayside Help Desk (see box), but not to the crew. A surveillance camera picture from Salem showed fire near the bearing (right). Surveillance cameras in Sebring also captured images of the train, and no anomalies were noted.", "document 3About 8:52 p.m., the train went over the East Palestine HBD. Less than a minute later, the HBD recorded a temperature of 253°F above ambient at the L1 bearing; bearing R1 remained at 20°F above ambient. The HBD immediately transmitted a critical alarm, which was broadcast in the locomotive cab.", "document 4The Wayside Help Desk in Atlanta, Georgia, monitors alerts from NS’s HBDs. Critical alarms broadcast straight to the train crew. For noncritical alerts, the analyst monitors the train over HBDs it crosses later, paying attention to temperature trends. The single analyst on duty did not notice the Salem noncritical alert, as he dealt with higher-priority alerts.",]items = [{"id": str(i), "text": d} for i, d in enumerate(documents)]ranked = client.score("modelQwen/Qwen3-Reranker-4B", {"text": query}, items)for r in ranked["scores"]: print(r["score"], documents[int(r["item_id"])])import { SIEClient } from '@superlinked/sie-sdk';
const client = new SIEClient('https://api.superlinked.com', {
apiKey: 'sk-sie-…',
});
const query = "Which passage shows that the bearing was visibly on fire at Salem while the detector alert went to the Wayside Help Desk instead of the crew?";
const documents = [
"At 7:37 p.m., at the Sebring HBD, the reading for the L1 bearing was only 38°F above ambient—not high enough to trigger an alert. The R1 bearing measured 20°F above ambient. But the L1 bearing was hotter.",
"At 8:13 p.m., at the Salem HBD, the reading for the L1 bearing was 103°F above ambient. This reading was high enough to trigger a noncritical alert to the Wayside Help Desk (see box), but not to the crew. A surveillance camera picture from Salem showed fire near the bearing (right). Surveillance cameras in Sebring also captured images of the train, and no anomalies were noted.",
"About 8:52 p.m., the train went over the East Palestine HBD. Less than a minute later, the HBD recorded a temperature of 253°F above ambient at the L1 bearing; bearing R1 remained at 20°F above ambient. The HBD immediately transmitted a critical alarm, which was broadcast in the locomotive cab.",
"The Wayside Help Desk in Atlanta, Georgia, monitors alerts from NS’s HBDs. Critical alarms broadcast straight to the train crew. For noncritical alerts, the analyst monitors the train over HBDs it crosses later, paying attention to temperature trends. The single analyst on duty did not notice the Salem noncritical alert, as he dealt with higher-priority alerts.",
];
const items = documents.map((text, i) => ({ id: String(i), text }));
const ranked = await client.score('Qwen/Qwen3-Reranker-4B', { text: query }, items);
console.log(ranked.scores.map(({ itemId, score }) => ({ document: documents[Number(itemId)], score })));curl https://api.superlinked.com/v1/score/Qwen%2FQwen3-Reranker-4B \
-H "Authorization: Bearer sk-sie-…" \
-H "Content-Type: application/json" \
-d "{\"query\":{\"text\":\"Which passage shows that the bearing was visibly on fire at Salem while the detector alert went to the Wayside Help Desk instead of the crew?\"},\"items\":[{\"id\":\"0\",\"text\":\"At 7:37 p.m., at the Sebring HBD, the reading for the L1 bearing was only 38°F above ambient—not high enough to trigger an alert. The R1 bearing measured 20°F above ambient. But the L1 bearing was hotter.\"},{\"id\":\"1\",\"text\":\"At 8:13 p.m., at the Salem HBD, the reading for the L1 bearing was 103°F above ambient. This reading was high enough to trigger a noncritical alert to the Wayside Help Desk (see box), but not to the crew. A surveillance camera picture from Salem showed fire near the bearing (right). Surveillance cameras in Sebring also captured images of the train, and no anomalies were noted.\"},{\"id\":\"2\",\"text\":\"About 8:52 p.m., the train went over the East Palestine HBD. Less than a minute later, the HBD recorded a temperature of 253°F above ambient at the L1 bearing; bearing R1 remained at 20°F above ambient. The HBD immediately transmitted a critical alarm, which was broadcast in the locomotive cab.\"},{\"id\":\"3\",\"text\":\"The Wayside Help Desk in Atlanta, Georgia, monitors alerts from NS’s HBDs. Critical alarms broadcast straight to the train crew. For noncritical alerts, the analyst monitors the train over HBDs it crosses later, paying attention to temperature trends. The single analyst on duty did not notice the Salem noncritical alert, as he dealt with higher-priority alerts.\"}]}"Build the "Rerank" capability into my app using the Superlinked Inference Engine (SIE).
Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: https://api.superlinked.com (or my regional endpoint). Auth: Bearer key from env `SIE_API_KEY` (never hard-code it).
- Model: Qwen/Qwen3-Reranker-4B (SIE primitive: /score). Keep the model id configurable.
Task
- Input: a query string plus a list of candidate documents.
- Behaviour: reorder the candidates by true relevance to the query using the cross-encoder
- Call the selected SIE primitive once per request and map the response into your domain type.
Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.- Reorders by true relevance
- Scored by meaning, keyword-free
Task-level rerank quality and latency
Deploy your way
Managed Cloud
Full compute toolkit for your agents with zero ops.
- No idle GPUs, pay for what you use
- Fits your stack: SDK, API, CLI, MCP
- Zero lock-in, self-host the same stack
- SOC 2 Type 2, US or EU data residency
no credit card required
Self-host with K8s
Easy & scalable deployment in your own cloud.
- Terraform to your cloud in minutes
- Apache-2.0, same engine as Cloud
- Scales to zero, no bill between jobs
- Per-tenant pools, no noisy neighbors
Deploy SIE to our AWS account with the superlinked/sie/aws Terraform module. Docs: superlinked.com/docs/deploymentDeploy SIE to our GCP project with the superlinked/sie/google Terraform module. Docs: superlinked.com/docs/deploymentDeploy SIE to our Azure AKS cluster via helm install. Requirements: superlinked.com/docs/deployment Run locally
Run the same models on your own machine.
- Runs on NVIDIA GPU or Apple Silicon
- One command, no Docker or cluster
- All 100+ Cloud models, fully offline
- Same SDK and IDs, no code changes
pip install "sie-server[local]" && sie-server servepip install "sie-server[local]" && sie-server serve --device cuda