| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
feat: Common Crawl x Daft tutorial using Qwen3 (#5472) Added a new tutorial for the new Common Crawl dataset. The notebook explores the crawl data, gives some motivation and exposition around text embeddings, provides a sentence splitting UDF using Spacy, and shows off the new daft.functions.ai.embed_text expression using a locally-running Qwen3 0.6B model. Adds a new example card for this new tutorial, complete with an AI-generated cover image. ## Checklist - [x] Documented in API Docs (if applicable) - [x] Documented in User Guide (if applicable) - [x] If adding a new documentation page, doc is added to docs/mkdocs.yml navigation - [x] Documentation builds and is formatted properly | 11 个月前 |