From 023f35623ff70f2407e94e0885fb25b28dc74175 Mon Sep 17 00:00:00 2001 From: chienyuanchang Date: Fri, 1 May 2026 14:45:59 -0700 Subject: [PATCH 1/3] Add preview disclaimer for to_llm_input in README --- .../azure-ai-contentunderstanding/README.md | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/sdk/contentunderstanding/azure-ai-contentunderstanding/README.md b/sdk/contentunderstanding/azure-ai-contentunderstanding/README.md index 1c6e8588f5d1..811f9616afd9 100644 --- a/sdk/contentunderstanding/azure-ai-contentunderstanding/README.md +++ b/sdk/contentunderstanding/azure-ai-contentunderstanding/README.md @@ -520,6 +520,12 @@ asyncio.run(analyze_invoice()) #### Convert results to LLM-ready text +> [!NOTE] +> **Preview feature**: `to_llm_input()` is currently in preview and may change in +> future releases. We welcome feedback — please file suggestions or issues on +> [GitHub Issues](https://github.com/Azure/azure-sdk-for-python/issues) with the +> `Cognitive - Content Understanding` label. + Use the `to_llm_input()` helper to convert any analysis result into a text format that LLMs can consume directly — YAML front matter with extracted fields followed by the markdown body. This works with all content types (documents, images, audio, video) and handles multi-segment From 285702012d3f594645580b9072274b95b5a3fb63 Mon Sep 17 00:00:00 2001 From: chienyuanchang Date: Fri, 1 May 2026 15:13:10 -0700 Subject: [PATCH 2/3] Add file-issue link to README header and preview disclaimer --- .../azure-ai-contentunderstanding/README.md | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/sdk/contentunderstanding/azure-ai-contentunderstanding/README.md b/sdk/contentunderstanding/azure-ai-contentunderstanding/README.md index 811f9616afd9..2aeee6641762 100644 --- a/sdk/contentunderstanding/azure-ai-contentunderstanding/README.md +++ b/sdk/contentunderstanding/azure-ai-contentunderstanding/README.md @@ -11,6 +11,8 @@ Use the client library for Azure AI Content Understanding to: * **Create custom analyzers** - Build domain-specific analyzers for specialized content extraction needs across all four modalities (documents, video, audio, and images) * **Classify documents and video** - Automatically categorize and extract information from documents and video by type +If you have encountered issues or want to suggest features, please [file an issue][file_issue]. + [Source code][python_cu_src] | [Package (PyPI)][python_cu_pypi] | [Product documentation][python_cu_product_docs] | [Samples][python_cu_samples] ## Table of Contents @@ -522,9 +524,8 @@ asyncio.run(analyze_invoice()) > [!NOTE] > **Preview feature**: `to_llm_input()` is currently in preview and may change in -> future releases. We welcome feedback — please file suggestions or issues on -> [GitHub Issues](https://github.com/Azure/azure-sdk-for-python/issues) with the -> `Cognitive - Content Understanding` label. +> future releases. We welcome feedback — please +> [file an issue][file_issue]. Use the `to_llm_input()` helper to convert any analysis result into a text format that LLMs can consume directly — YAML front matter with extracted fields followed by the markdown body. @@ -701,6 +702,7 @@ This project has adopted the [Microsoft Open Source Code of Conduct][code_of_con [pip]: https://pypi.org/project/pip/ [cla]: https://cla.microsoft.com [code_of_conduct]: https://opensource.microsoft.com/codeofconduct/ +[file_issue]: https://github.com/Azure/azure-sdk-for-python/issues/new?labels=Cognitive%20-%20Content%20Understanding&title=[ContentUnderstanding]%20&body=%23%23%20Library%20Version%0A%0A%23%23%20Repro%20Steps%0A%0A%23%23%20Expected%20Result%0A%0A%23%23%20Actual%20Result [code_of_conduct_faq]: https://opensource.microsoft.com/codeofconduct/faq/ [opencode_email]: mailto:opencode@microsoft.com [aiohttp]: https://pypi.org/project/aiohttp/ From ce88476e47e1d0659a6b78e23c53396ee2df9f9c Mon Sep 17 00:00:00 2001 From: chienyuanchang Date: Fri, 1 May 2026 15:49:44 -0700 Subject: [PATCH 3/3] update Note --- .../azure-ai-contentunderstanding/README.md | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/sdk/contentunderstanding/azure-ai-contentunderstanding/README.md b/sdk/contentunderstanding/azure-ai-contentunderstanding/README.md index 2aeee6641762..a50a10002bf4 100644 --- a/sdk/contentunderstanding/azure-ai-contentunderstanding/README.md +++ b/sdk/contentunderstanding/azure-ai-contentunderstanding/README.md @@ -522,10 +522,8 @@ asyncio.run(analyze_invoice()) #### Convert results to LLM-ready text -> [!NOTE] -> **Preview feature**: `to_llm_input()` is currently in preview and may change in -> future releases. We welcome feedback — please -> [file an issue][file_issue]. +> **Note:** `to_llm_input()` is currently in preview and may change in future +> releases. We welcome feedback — please [file an issue][file_issue]. Use the `to_llm_input()` helper to convert any analysis result into a text format that LLMs can consume directly — YAML front matter with extracted fields followed by the markdown body.