---
title: Overview
description: End-to-end applications built with SIE.
canonical_url: https://superlinked.com/docs/examples
last_updated: 2026-08-08
---

Full applications built on SIE, with the pipelines, models, and evaluation results documented in each one. Every project is self-contained: clone it, run it, learn from it.

<CardGrid>
  <LinkCard title="Find the best retrieval strategy for your RAG" description="Head-to-head retrieval ablation across six conditions and eight encoder, reranker, and multi-vector models on 1,854 SEC 10-K queries, ranked by NDCG@10." href="/docs/examples/benchmark" />
  <LinkCard title="Private fine-tuned compliance RAG" description="Domain-tuned LoRA encoder and a custom cross-encoder that reranks and prunes context in one forward pass, all served from one SIE cluster." href="/docs/examples/regulatory-intelligence-rag" />
  <LinkCard title="Self-hosted product search in 5 min" description="A full Amazon-style product search engine running on a laptop in 5 minutes. Uses all three SIE primitives (extract, encode, score) through three SDK calls." href="/docs/examples/ecommerce-product-search" />
  <LinkCard title="Build a multimodal wine recommender with OCR" description="A demo app that pairs preference-based wine retrieval with OCR-based label detection. Shows extract, encode, and score wired into one user-facing flow." href="/docs/examples/wine-recommender" />
  <LinkCard title="Find SOTA embedding models by MTEB task" description="Describe your task in plain language and search across ~14K Hugging Face embedding models, ranked by task-specific MTEB scores." href="/docs/examples/semantic-hf-model-search" />
  <LinkCard title="Build a multi-modal product classifier with embeddings" description="A structured evaluation of NLI, text retrieval, image retrieval, and cross-encoder reranking on Shopify's hierarchical product taxonomy." href="/docs/examples/taxonomy-classification" />
  <LinkCard title="Swap an OCR model with one identifier change" description="A multi-model OCR demo: recognition VLM, end-to-end document model, and zero-shot NER all driven by the same extract call. Only the model ID changes between calls." href="/docs/examples/document-ocr" />
  <LinkCard title="A Stripe Link checkout with an SIE fraud-risk gate" description="Three SIE primitives (extract, encode, score) score every order against a corpus of past fraud patterns before the Stripe PaymentIntent is created. The risk band annotates the Stripe Link payment button, in the same UI, in the same request." href="/docs/examples/stripe-link-fraud" />
</CardGrid>

## More examples on GitHub

Newer gallery projects that have not been written up as docs pages yet. Each card links to the full README and runnable code in the [sie repo](https://github.com/superlinked/sie/tree/main/examples).

<CardGrid>
  <LinkCard title="A behavioural gate that catches hijacked AI agents" description="Judges a proposed AI agent action against that agent's own learned baseline in real time, before it reaches a downstream system. Docker Compose with a self-hosted SIE, n8n, and a mock downstream." href="https://github.com/superlinked/sie/tree/main/examples/agent-action-monitor" />
  <LinkCard title="Multi-model contract review with the OpenAI Agents SDK" description="An agent whose every model call (triage, orchestration, vision, OCR, embeddings, rerank, entity extraction, text-to-SQL, reasoning, and a safety guardrail) is served by one SIE cluster, each step on the right catalog model." href="https://github.com/superlinked/sie/tree/main/examples/contract-review-agent" />
  <LinkCard title="Vision-first document RAG" description="Retrieves and answers questions over a multi-tenant page corpus by looking at page images, including scanned drawings, with OCR kept out of the score path." href="https://github.com/superlinked/sie/tree/main/examples/vision-doc-rag" />
  <LinkCard title="Turn difficult PDFs into Markdown" description="Preserves tables, reading order, headings, and form labels across real financial, academic, and government PDFs with docling behind the extract call." href="https://github.com/superlinked/sie/tree/main/examples/document-to-markdown" />
  <LinkCard title="Rank exact primary-source passages" description="Tests a reranker on verbatim SEC, CMS, NTSB, and Supreme Court excerpts against an SIE endpoint running Qwen3 Reranker." href="https://github.com/superlinked/sie/tree/main/examples/rerank" />
  <LinkCard title="Extract custom entities from primary sources" description="Changes zero-shot GLiNER labels across financial, healthcare, rail-safety, and legal text without retraining anything." href="https://github.com/superlinked/sie/tree/main/examples/named-entity-extraction" />
  <LinkCard title="Search licensed images with text" description="Recomputes a six-image hard-negative ranking from full SigLIP vectors served by the encode endpoint." href="https://github.com/superlinked/sie/tree/main/examples/multimodal-search" />
  <LinkCard title="Review a published flood-insurance appeal" description="Separates FEMA's covered stone-removal scope from excluded barge, handling, disposal, and yard costs, using the bundled public FEMA appeal and policy." href="https://github.com/superlinked/sie/tree/main/examples/insurance-claims-agent" />
  <LinkCard title="Trace a restated filing figure" description="Follows one reported figure through an original filing, corrective notice, and restatement while preserving source status, on public SEC facts." href="https://github.com/superlinked/sie/tree/main/examples/financial-filing-agent" />
  <LinkCard title="Reproduce CMS's L1851 documentation finding" description="Traces a published six-month requirement against a seven-month face-to-face encounter and CMS's recoupment result, on the exact CMS published example." href="https://github.com/superlinked/sie/tree/main/examples/prior-authorization-review-agent" />
  <LinkCard title="Reconstruct a bearing failure" description="Turns the NTSB's three East Palestine detector readings into a cited temperature and alert sequence without adding a new causal claim." href="https://github.com/superlinked/sie/tree/main/examples/maintenance-triage-agent" />
  <LinkCard title="Make a shelf gap auditable" description="Detects one empty facing, derives its notice and shelf-label crops by geometry, then preserves OCR evidence from a CC0 supermarket shelf image." href="https://github.com/superlinked/sie/tree/main/examples/retail-shelf-audit" />
</CardGrid>

## Submit your project

We welcome community examples. To add yours:

1. Create a subdirectory in [`examples/`](https://github.com/superlinked/sie/tree/main/examples) with a short name (e.g. `wikipedia-search/`, `pdf-rag/`).
2. Include a README covering what it does, how to run it, and which SIE features it uses.
3. Keep it self-contained: include `requirements.txt` or `package.json`, a docker-compose if needed, and sample data or instructions to fetch it.
4. Open a PR against `main`.

Projects can be anything: a search engine, a RAG pipeline, a benchmark, a migration guide, a CLI tool. If it uses SIE, it belongs here.