# ML, Embeddings & Search

Examples for GPU embeddings, batch inference, vector search, and multimodal analysis.

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th><th data-hidden data-card-cover data-type="files"></th></tr></thead><tbody><tr><td><strong>Embed 50K Wikipedia articles</strong></td><td>Embed 50,000 Wikipedia articles with a CUDA image, CPU download stage, GPU embedding stage, and shared vector artifacts.</td><td><a href="/pages/5IISUkHLuDTCQDeJSSBn">/pages/5IISUkHLuDTCQDeJSSBn</a></td><td><a href="/files/tOspuUdq6AMLN0WdznQs">/files/tOspuUdq6AMLN0WdznQs</a></td></tr><tr><td><strong>Tune XGBoost on 1,000 CPUs</strong></td><td>Train 36 XGBoost models across 1,000 CPUs and pick the best flight-delay model.</td><td><a href="/pages/2ojprBaXQZns21MOse2C">/pages/2ojprBaXQZns21MOse2C</a></td><td><a href="/files/HQDmNvHnQiqyKErwnXDl">/files/HQDmNvHnQiqyKErwnXDl</a></td></tr><tr><td><strong>Run batch LLM inference</strong></td><td>Load a Hugging Face model once per worker and score Parquet batches without building an endpoint.</td><td><a href="/pages/48J3KTplQcuADx1KeFH2">/pages/48J3KTplQcuADx1KeFH2</a></td><td><a href="/files/2DH1VsjAxv1TPprljFki">/files/2DH1VsjAxv1TPprljFki</a></td></tr><tr><td><strong>Cluster arXiv abstracts</strong></td><td>Shard metadata, embed every abstract, then cluster and search after the corpus is visible.</td><td><a href="/pages/jiq6hCRLePtSuPvnondx">/pages/jiq6hCRLePtSuPvnondx</a></td><td><a href="/files/UfdaEdoAK5IWrdFPBLqb">/files/UfdaEdoAK5IWrdFPBLqb</a></td></tr><tr><td><strong>Search 192K artworks with CLIP</strong></td><td>Fetch and embed Open Access museum images, then use FAISS to find visual matches without labels.</td><td><a href="/pages/WxhBk9CUk9N5ytBCuAYD">/pages/WxhBk9CUk9N5ytBCuAYD</a></td><td><a href="/files/4a2IARHzx8PyWfCBgjXg">/files/4a2IARHzx8PyWfCBgjXg</a></td></tr><tr><td><strong>Test Airbnb hypotheses</strong></td><td>Run listings, photos, CLIP, Haiku Vision, reviews, and bootstrap confidence intervals across the public corpus.</td><td><a href="/pages/i35wX3WrdVZR8DWNc6pB">/pages/i35wX3WrdVZR8DWNc6pB</a></td><td><a href="/files/oFjSy5bB4lqnpT8nzsZe">/files/oFjSy5bB4lqnpT8nzsZe</a></td></tr></tbody></table>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.burla.dev/all-examples/ml-embeddings-and-search.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.