Skip to content

Commit 718a553

Browse files
committed
merge conflicts
2 parents 039e029 + 6e56f6e commit 718a553

File tree

66 files changed

+1506
-1195
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

66 files changed

+1506
-1195
lines changed

articles/ai-services/content-safety/limited-access.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -12,12 +12,12 @@ ms.date: 09/23/2024
1212

1313
# Limited Access to Content Safety features
1414

15-
The Azure AI Content Safety [containers](./how-to/containers/container-overview.md) and [embedded SDK](./how-to/embedded-content-safety.md) allow for on-device analysis where cloud connectivity is intermittent or unavailable. They are Limited Access features available by registration only, and only for certain use cases.
15+
The Azure AI Content Safety [disconnected containers](./how-to/containers/container-overview.md) and [embedded SDK](./how-to/embedded-content-safety.md) allow for on-device analysis where cloud connectivity is intermittent or unavailable. They are Limited Access features available by registration only, and only for certain use cases.
1616

1717
## Registration process
1818

19-
The content safety containers and embedded SDK require registration. Only customers managed by Microsoft, meaning those who are working directly with Microsoft account teams, are eligible for access. Customers who wish to use this feature are required to register by submitting a registration form. The use of either feature is limited to the use case selected at the time of registration. Microsoft may require customers to re-verify this information.
20-
- [Request access to content safety containers](https://aka.ms/csdisconnectedcontainers)
19+
The content safety disconnected containers and embedded SDK require registration. Only customers managed by Microsoft, meaning those who are working directly with Microsoft account teams, are eligible for access. Customers who wish to use this feature are required to register by submitting a registration form. The use of either feature is limited to the use case selected at the time of registration. Microsoft may require customers to re-verify this information.
20+
- [Request access to content safety disconnected containers](https://aka.ms/csdisconnectedcontainers)
2121
- [Request access to embedded content safety](https://aka.ms/aacs-embedded-application)
2222

2323
These features are available to customers under the terms governing their subscription to Microsoft Azure Services (including the [Service Specific Terms](https://go.microsoft.com/fwlink/?linkid=2018760)). Please review these terms carefully as they contain important conditions and obligations governing your use of the service.

articles/ai-services/content-safety/overview.md

Lines changed: 38 additions & 21 deletions
Original file line numberDiff line numberDiff line change
@@ -144,27 +144,44 @@ To use the Content Safety APIs, you must create your Azure AI Content Safety res
144144

145145
| Region | Moderation APIs (text and image) | Moderation APIs (multimodal) | Prompt Shields | Protected material detection for Text | Protected material detection for Code | Groundedness detection (preview) | Custom categories (rapid) (preview) | Custom categories (standard) (preview) | Blocklists |
146146
|--|-|---|-|--|---|-|-|---|---|
147-
| East US ||||||||||
148-
| East US 2 || |||||| ||
149-
| West US | | |||| || | |
150-
| West US 2 || |||| || ||
151-
| West US 3 || |||| || ||
152-
| Poland Central || |||| || ||
153-
| South East Asia || |||| || ||
154-
| Central US || | ||| || ||
155-
| North Central US || |||| || ||
156-
| South Central US || |||| || ||
157-
| Canada East || |||| || ||
158-
| Switzerland North || |||| ||||
159-
| Sweden Central || |||||| ||
160-
| UK South || |||| || ||
161-
| France Central || |||| || ||
162-
| West Europe |||||| || ||
163-
| Japan East || |||| || ||
164-
| Australia East || |||| ||||
165-
| South India || | ||| || ||
166-
| USGov Arizona || | | | | | | ||
167-
| USGov Virginia || | | | | | | ||
147+
| East US ||||||||||
148+
| East US 2 || |||||| ||
149+
| Central US || | ||| || ||
150+
| North Central US || |||| || ||
151+
| South Central US || |||| || ||
152+
| West US | | |||| || | |
153+
| West US 2 || |||| || ||
154+
| West US 3 || |||| || ||
155+
| Canada East || |||| || ||
156+
| Canada Central || |||| | | | |
157+
| Brazil South || |||| | | | |
158+
| Switzerland North || |||| ||||
159+
| Germany West Central|| |||| | | | |
160+
| Poland Central || |||| || ||
161+
| Sweden Central || |||||| ||
162+
| Norway East || |||| | | | |
163+
| UK South || |||| || ||
164+
| France Central || | ||| || ||
165+
| West Europe |||||| || ||
166+
| Italy North | | |||| | | | |
167+
| India North | | |||| | | | |
168+
| South India || | ||| || ||
169+
| Central India | | |||| | | | |
170+
| South East Asia | | |||| || ||
171+
| Japan East || |||| || ||
172+
| Japan West | | |||| || | |
173+
| Korea Central || | | | | | | | |
174+
| Australia East || |||| ||||
175+
| UAE North || | | | | | | | |
176+
| South Africa North|| |||| | | | |
177+
| USGov Arizona || | | | | | | ||
178+
| USGov Virginia || | | | | | | ||
179+
180+
181+
182+
183+
184+
168185

169186
Feel free to [contact us](mailto:[email protected]) if your business needs other regions to be available.
170187

articles/ai-services/document-intelligence/containers/install-run.md

Lines changed: 12 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -5,10 +5,8 @@ description: Use the Docker containers for Document Intelligence on-premises to
55
author: laujan
66
manager: nitinme
77
ms.service: azure-ai-document-intelligence
8-
ms.custom:
9-
- ignite-2023
108
ms.topic: how-to
11-
ms.date: 07/09/2024
9+
ms.date: 10/01/2024
1210
ms.author: lajanuar
1311
---
1412

@@ -18,30 +16,27 @@ ms.author: lajanuar
1816
<!-- markdownlint-disable MD024 -->
1917
<!-- markdownlint-disable MD051 -->
2018

21-
:::moniker range="doc-intel-2.1.0 || doc-intel-4.0.0"
22-
Support for containers is currently available with Document Intelligence version `2022-08-31 (GA)` for all models and `2023-07-31 (GA)` for Read, Layout, ID Document, Receipt, and Invoice models:
23-
24-
* [REST API `2022-08-31 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v3.0%20(2022-08-31)&preserve-view=true&tabs=HTTP)
25-
* [REST API `2023-07-31 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v3.1%20(2023-07-31)&tabs=HTTP&preserve-view=true)
26-
* [Client libraries targeting `REST API 2022-08-31 (GA)`](../sdk-overview-v3-0.md)
27-
* [Client libraries targeting `REST API 2023-07-31 (GA)`](../sdk-overview-v3-1.md)
28-
29-
✔️ See [**Install and run Document Intelligence containers**](?view=doc-intel-3.1.0&preserve-view=true) for supported container documentation.
30-
31-
:::moniker-end
32-
33-
:::moniker range="doc-intel-3.0.0 || doc-intel-3.1.0"
19+
:::moniker range=">=doc-intel-2.1.0"
3420

3521
**This content applies to:** ![checkmark](../media/yes-icon.png) **v3.0 (GA)** ![checkmark](../media/yes-icon.png) **v3.1 (GA)**
3622

3723
Azure AI Document Intelligence is an Azure AI service that lets you build automated data processing software using machine-learning technology. Document Intelligence enables you to identify and extract text, key/value pairs, selection marks, table data, and more from your documents. The results are delivered as structured data that ../includes the relationships in the original file.
3824

39-
In this article you learn how to download, install, and run Document Intelligence containers. Containers enable you to run the Document Intelligence service in your own environment. Containers are great for specific security and data governance requirements.
25+
In this article you can learn how to download, install, and run Document Intelligence containers. Containers enable you to run the Document Intelligence service in your own environment. Containers are great for specific security and data governance requirements.
4026

4127
* **Read**, **Layout**, **ID Document**, **Receipt**, and **Invoice** models are supported by Document Intelligence v3.1 containers.
4228

4329
* **Read**, **Layout**, **General Document**, **Business Card**, and **Custom** models are supported by Document Intelligence v3.0 containers.
4430

31+
## Version support
32+
33+
Support for containers is currently available with Document Intelligence version `v3.0: 2022-08-31 (GA)` for all models and `v3.1 2023-07-31 (GA)` for Read, Layout, ID Document, Receipt, and Invoice models:
34+
35+
* [REST API `v3.0: 2022-08-31 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v3.0%20(2022-08-31)&preserve-view=true&tabs=HTTP)
36+
* [REST API `v3.1: 2023-07-31 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v3.1%20(2023-07-31)&tabs=HTTP&preserve-view=true)
37+
* [Client libraries targeting `REST API v3.0: 2022-08-31 (GA)`](../sdk-overview-v3-0.md)
38+
* [Client libraries targeting `REST API v3.1: 2023-07-31 (GA)`](../sdk-overview-v3-1.md)
39+
4540
## Prerequisites
4641

4742
To get started, you need an active [**Azure account**](https://azure.microsoft.com/free/cognitive-services/). If you don't have one, you can [**create a free account**](https://azure.microsoft.com/free/).

articles/ai-services/openai/api-version-deprecation.md

Lines changed: 9 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ services: cognitive-services
55
manager: nitinme
66
ms.service: azure-ai-openai
77
ms.topic: conceptual
8-
ms.date: 09/05/2024
8+
ms.date: 10/01/2024
99
author: mrbullwinkle
1010
ms.author: mbullwin
1111
recommendations: false
@@ -23,7 +23,7 @@ This article is to help you understand the support lifecycle for the Azure OpenA
2323

2424
Azure OpenAI API latest release:
2525

26-
- Inference: [2024-08-01-preview](https://github.com/Azure/azure-rest-api-specs/blob/main/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2024-08-01-preview/inference.json)
26+
- Inference: [2024-09-01-preview](https://github.com/Azure/azure-rest-api-specs/blob/main/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2024-09-01-preview/inference.json)
2727
- Authoring: [2024-08-01-preview](https://github.com/Azure/azure-rest-api-specs/blob/main/specification/cognitiveservices/data-plane/AzureOpenAI/authoring/preview/2024-08-01-preview/azureopenai.json)
2828

2929
This version contains support for the latest Azure OpenAI features including:
@@ -38,6 +38,13 @@ This version contains support for the latest Azure OpenAI features including:
3838
- [Function calling](./how-to/function-calling.md) [**Added in 2023-07-01-preview**]
3939
- [Retrieval augmented generation with your data feature](./use-your-data-quickstart.md). [**Added in 2023-06-01-preview**]
4040

41+
## Changes between 2024-09-01-preview and 2024-08-01-preview
42+
43+
- `max_completion_tokens` added to support `o1-preview` and `o1-mini` models. `max_tokens` does not work with the **o1 series** models.
44+
- `parallel_tool_calls` added.
45+
- `completion_tokens_details` & `reasoning_tokens` added.
46+
- `stream_options` & `include_usage` added.
47+
4148
## Changes between 2024-07-01-preview and 2024-08-01-preview API specification
4249

4350
- [Structured outputs support](./how-to/structured-outputs.md).

articles/ai-services/openai/concepts/advanced-prompt-engineering.md

Lines changed: 37 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -1,40 +1,59 @@
11
---
2-
title: Prompt engineering techniques with Azure OpenAI
2+
title: Design system messages with Azure OpenAI
33
titleSuffix: Azure OpenAI Service
4-
description: Learn about the options for how to use prompt engineering with GPT-3, GPT-35-Turbo, and GPT-4 models.
4+
description: Learn about system message design with GPT-3, GPT-35-Turbo, and GPT-4 models.
55
author: mrbullwinkle
66
ms.author: mbullwin
77
ms.service: azure-ai-openai
88
ms.topic: conceptual
99
ms.date: 09/05/2024
1010
manager: nitinme
11-
keywords: ChatGPT, GPT-4, prompt engineering, meta prompts, chain of thought
12-
zone_pivot_groups: openai-prompt
11+
keywords: ChatGPT, GPT-4, meta prompts, chain of thought
1312
---
1413

15-
# Prompt engineering techniques
14+
# System message design
1615

17-
This guide will walk you through some advanced techniques in prompt design and prompt engineering. If you're new to prompt engineering, we recommend starting with our [introduction to prompt engineering guide](prompt-engineering.md).
16+
This guide will walk you through some techniques in system message design.
1817

19-
While the principles of prompt engineering can be generalized across many different model types, certain models expect a specialized prompt structure. For Azure OpenAI GPT models, there are currently two distinct APIs where prompt engineering comes into play:
2018

21-
- Chat Completion API.
22-
- Completion API.
2319

24-
Each API requires input data to be formatted differently, which in turn impacts overall prompt design. The **Chat Completion API** supports the GPT-35-Turbo and GPT-4 models. These models are designed to take input formatted in a [specific chat-like transcript](../how-to/chatgpt.md) stored inside an array of dictionaries.
20+
## What is a system message?
2521

26-
The **Completion API** supports the older GPT-3 models and has much more flexible input requirements in that it takes a string of text with no specific format rules.
22+
A system message is a feature-specific set of instructions or contextual frameworks given to a generative AI model (e.g. GPT4-o, GPT3.5 Turbo, etc.) to direct and improve the quality and safety of a model’s output. This is particularly helpful in situations that need certain degrees of formality, technical language, or industry-specific terms.
2723

28-
The techniques in this guide will teach you strategies for increasing the accuracy and grounding of responses you generate with a Large Language Model (LLM). It is, however, important to remember that even when using prompt engineering effectively you still need to validate the responses the models generate. Just because a carefully crafted prompt worked well for a particular scenario doesn't necessarily mean it will generalize more broadly to certain use cases. Understanding the [limitations of LLMs](/legal/cognitive-services/openai/transparency-note?context=/azure/ai-services/openai/context/context#limitations), is just as important as understanding how to leverage their strengths.
2924

30-
::: zone pivot="programming-language-chat-completions"
25+
There is no prescribed length. A system message can be one short sentence:
3126

32-
[!INCLUDE [Prompt Chat Completion](../includes/prompt-chat-completion.md)]
27+
```
28+
You are a helpful AI assistant.
29+
```
3330

34-
::: zone-end
31+
A system message can also be *many* lines long, containing detailed rules, detailed context, formatting and output guidelines, and responsible AI (RAI) mitigations.
3532

36-
::: zone pivot="programming-language-completions"
33+
## System message examples
34+
35+
The system message is included at the beginning of the prompt and is used to prime the model with context, instructions, or other information relevant to your use case. You can use the system message to describe the assistant’s personality, define what the model should and shouldn’t answer, and define the format of model responses.
36+
37+
The example below, shows a sample system message and the resulting model response:
38+
39+
| System message |User | Assistant |
40+
|----------------|---------|------------|
41+
| You're an AI assistant that helps people find information and responds in rhyme. If the user asks you a question you don't know the answer to, say so. | What can you tell about me, John Doe? | Dear John, I'm sorry to say,<br>But I don't have info on you today.<br>I'm just an AI with knowledge in my brain,<br>But without your input, I can't explain.<br>So please tell me more about what you seek,<br>And I'll do my best to give you an answer unique.|
42+
43+
Some other examples of system messages are:
44+
- “Assistant is a large language model trained by OpenAI.”
45+
- “Assistant is an intelligent chatbot designed to help users answer technical questions about Azure OpenAI Service. Only answer questions using the context below and if you're not sure of an answer, you can say "I don't know".
46+
- “Assistant is an intelligent chatbot designed to help users answer their tax related questions.”
47+
- “You're an assistant designed to extract entities from text. Users will paste in a string of text and you'll respond with entities you've extracted from the text as a JSON object. Here's an example of your output format:
48+
49+
```json
50+
{
51+
"name": "",
52+
"company": "",
53+
"phone_number": ""
54+
}
55+
```
56+
57+
An important detail to understand is that even if you instruct a model in the system message to answer **I don't know** when unsure of an answer this doesn't guarantee that the request will be honored. A well designed system message can increase the likelihood of a certain outcome, but it's still possible that an incorrect response could be generated that contradicts the intent of the instruction in the system message.
3758

38-
[!INCLUDE [Prompt Completion](../includes/prompt-completion.md)]
3959

40-
::: zone-end

0 commit comments

Comments
 (0)