From b9a99eeaae82ee822f66cfcb33091b37a500c70a Mon Sep 17 00:00:00 2001 From: Adi Eldar Date: Thu, 7 May 2026 21:32:48 +0300 Subject: [PATCH] Update SLM embeddings Python image prerequisite --- data-explorer/kusto/includes/slm-embeddings-fl-adx.md | 6 ++++-- data-explorer/kusto/includes/slm-embeddings-fl-fabric.md | 6 ++++-- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/data-explorer/kusto/includes/slm-embeddings-fl-adx.md b/data-explorer/kusto/includes/slm-embeddings-fl-adx.md index c7bd768424..acfa4146ec 100644 --- a/data-explorer/kusto/includes/slm-embeddings-fl-adx.md +++ b/data-explorer/kusto/includes/slm-embeddings-fl-adx.md @@ -1,12 +1,14 @@ --- ms.topic: include -ms.date: 04/27/2026 +ms.date: 05/07/2026 --- The function `slm_embeddings_fl()` is a [UDF (user-defined function)](../query/functions/user-defined-functions.md) that generates text embeddings using local Small Language Models (SLM). This function converts text into numerical vector representations that can be used for semantic search, similarity analysis, and other natural language processing tasks. Currently the function supports [harrier-v1-270m](https://huggingface.co/microsoft/harrier-oss-v1-270m), [jina-v2-small](https://huggingface.co/jinaai/jina-embeddings-v2-small-en), and [e5-small-v2](https://huggingface.co/intfloat/e5-small-v2) models. -[!INCLUDE [python-zone-pivot-fabric](../includes/python-zone-pivot-fabric.md)] +## Prerequisites + +* The `python()` plugin must be [enabled on the cluster](/azure/data-explorer/language-extensions#enable-language-extensions-on-your-cluster) with either the `3.11.7` or `3.11.7 DL` Python sandbox image. This is required for the inline Python used in the function. To review the package contents for these images, see [Python package reference](../query/python-package-reference.md). * Alter the cluster's [callout policy](../management/callout-policy.md) to allow access to the external artifacts (which are referenced in the KQL code below): ```kusto diff --git a/data-explorer/kusto/includes/slm-embeddings-fl-fabric.md b/data-explorer/kusto/includes/slm-embeddings-fl-fabric.md index 647863ead1..d4a39bc7be 100644 --- a/data-explorer/kusto/includes/slm-embeddings-fl-fabric.md +++ b/data-explorer/kusto/includes/slm-embeddings-fl-fabric.md @@ -1,12 +1,14 @@ --- ms.topic: include -ms.date: 04/27/2026 +ms.date: 05/07/2026 --- The function `slm_embeddings_fl()` is a [UDF (user-defined function)](../query/functions/user-defined-functions.md) that generates text embeddings using local Small Language Models (SLM). This function converts text into numerical vector representations that can be used for semantic search, similarity analysis, and other natural language processing tasks. Currently the function supports [harrier-v1-270m](https://huggingface.co/microsoft/harrier-oss-v1-270m), [jina-v2-small](https://huggingface.co/jinaai/jina-embeddings-v2-small-en), and [e5-small-v2](https://huggingface.co/intfloat/e5-small-v2) models. -[!INCLUDE [python-zone-pivot-fabric](../includes/python-zone-pivot-fabric.md)] +## Prerequisites + +* The `python()` plugin must be [enabled on the database](/fabric/real-time-analytics/python-plugin) with either the `3.11.7` or `3.11.7 DL` Python sandbox image. This is required for the inline Python used in the function. To review the package contents for these images, see [Python package reference](../query/python-package-reference.md). * Create a lakehouse to host the external artifacts (which are referenced in the KQL code below), preferably in the same workspace as your eventhouse. ## Syntax