fabric-ai-functionslisted

Use for Microsoft Fabric AI Functions (Data Science) — one-line LLM transformations on pandas and PySpark DataFrames in Fabric notebooks: `ai.analyze_sentiment`, `ai.classify`, `ai.extract`, `ai.embed`, `ai.summarize`, `ai.translate`, `ai.fix_grammar`, `ai.generate_response`, `ai.similarity`. Covers the two import paths (`synapse.ml.aifunc` pandas single-node vs `synapse.ml.spark.aifunc` PySpark distributed), pandas Series-accessor vs PySpark `df.ai` DataFrame-accessor shapes, GA defaults (`gpt-5-mini` + `reasoning_effort=low`, `openai` no longer required), pandas `aifunc.Conf` vs PySpark `OpenAIDefaults` config (concurrency, temperature/top_p/verbosity/seed), `gpt-5.1` opt-in and gpt-4.1→gpt-5.1 migration, custom Azure OpenAI/Foundry endpoints, `ExtractLabel` schema extract, PySpark chaining, `ai.stats` + Exception/Filter/CapacityExceeded results, multimodal `column_type=path`, prerequisites (F2+, Runtime 1.3+, Copilot tenant switch), and Copilot-&-AI billing. Also in SQL/Warehouse and Dataflow Gen2.
wardawgmalvicious/claude-config · ★ 2 · AI & Automation · score 75

Install: claude install-skill wardawgmalvicious/claude-config

# Fabric AI Functions One-line, LLM-powered transformations applied to whole pandas or PySpark DataFrames in Fabric notebooks. Fabric handles the model endpoint, auth, request orchestration, batching, and retries — you call a DataFrame method and get an enriched column back. Nine prebuilt functions cover sentiment, classification, extraction, embeddings, grammar, custom prompts, similarity, summarization, and translation. ## When to use vs not Use AI Functions to enrich, classify, extract, summarize, translate, or embed **tabular data at scale** — thousands to millions of rows — with minimal code, letting Fabric manage concurrency (200 rows in parallel by default) and the built-in endpoint. This is the fastest path to apply an LLM across a column. Skip them when you need **low-level control** over a single prompt/response, custom orchestration, function-calling loops, or a conversational agent — use the [Azure OpenAI Python SDK](https://learn.microsoft.com/fabric/data-science/ai-services/how-to-use-openai-python-sdk) or [SynapseML](https://learn.microsoft.com/fabric/data-science/ai-services/how-to-use-openai-synapse-ml) instead. For a governed natural-language-to-data experience over your semantic models/lakehouses, that's a Data Agent (`fabric-data-agent`), not AI Functions. ## Prerequisites - **Paid capacity** — F2 or higher, or any P edition. Not available on trial/Free. - **Fabric Runtime 1.3+** — earlier runtimes can't run AI Functions. - **Tenant switch** — an adm