Microsoft AzureのAzure OpenAI On Your Dataを検証することとなった。
Azure OpenAI Serviceの利用には、事前申請が必要ということで、2024/2/6時点での申請方法をメモ。
事前準備
2024/2/6時点の申請フォームはこちら。
利用申請はサブスクリプション単位。申請フォームに有効化するサブスクリプションのSubscriptions IDを入力する必要があるため、すべてのサービス > サブスクリプションから、IDを確認しておく。
また、メールアドレスの入力が必要だが、 gmail.com, hotmail.com などは使用できず、会社のものを使用する必要がある模様。
Your Company Email Address - Applications submitted with a personal email address (e.g. gmail.com, hotmail.com, outlook.com, etc.) will be DENIED.
申請内容
引っ掛かった項目をメモしていく。なお、名前や会社名、会社の住所などは、日本語で入力して申請が通った。
14, 15: If you have a contact at Microsoft, ...
14「If you have a contact at Microsoft, please provide their full name.」および15「If you have a contact at Microsoft, please provide their email address.」。よくわからないため、空白にしておく。
17: Which Azure OpenAI service feature(s) are you requesting access for
17「Which Azure OpenAI service feature(s) are you requesting access for?」に対して以下の選択肢、複数選択可能。検証に使用するのはGPT-3.5系だけでいいため、一番上のみチェック。
- GPT-3.5, GPT-3.5 Turbo, GPT-4, GPT-4 Turbo, and/or Embeddings Models (Conversational AI, Search, Summarization, Writing Assistance or content generation, Code-based scenarios, Reason over Structured and Unstructured data)
- DALL-E 2 and/or DALL-E 3 models (text to image)
- OpenAI Whisper model (Speech-to-Text)
- GPT-4 Turbo with Vision
18: ユースケース
17でWhisper以外を選択すると、18としてユースケースを聞かれる。
GPT-3.5...を選択した場合以下。1, 2, 6, 8を選択。
- Chat and conversation interaction: Users can interact with a conversational agent that responds with responses drawn from trusted documents such as internal company documentation or tech support documentation; conversations must be limited to answering scoped questions. Available to internal, authenticated external users, and unauthenticated external users.
- Chat and conversation creation: Users can create a conversational agent that responds with responses drawn from trusted documents such as internal company documentation or tech support documentation; conversations must be limited to answering scoped questions. Limited to internal users only.
- Code generation or transformation scenarios: For example, converting one programming language to another, generating docstrings for functions, converting natural language to SQL. Limited to internal and authenticated external users.
- Journalistic content: For use to create new journalistic content or to rewrite journalistic content submitted by the user as a writing aid for pre-defined topics. Users cannot use the application as a general content creation tool for all topics. May not be used to generate content for political campaigns. Limited to internal users.
- Most Valuable Professional (MVP) or Regional Director (RD) Demo Use: Any applicant who is not in the Microsoft Most Valuable Professional (MVP) Award Program and in the MVP database, or in theRegional Director (RD) Program, will be denied if this use case is selected. For use by a current participant in the MVP or RD Program (the name entered in Questions 1-2 must be the name of the MVP or RD participant) solely to develop, test, and demonstrate one or more sample applications showcasing the Azure OpenAI Service GPT-3.5, GPT-3.5 Turbo, GPT-4, GPT-4 Turbo, and/or Embeddings Models capability (in accordance with a use case listed in this Question [X]). No production use, sale, or other disposition of an application is permitted under this use case; if an MVP, RD, or their employer wants to use an Azure OpenAI Service application in production, a separate form must be submitted, the appropriate use case must be selected, and a separate eligibility determination will be made.
- Question-answering: Users can ask questions and receive answers from trusted source documents such as internal company documentation. The application does not generate answers ungrounded in trusted source documentation. Available to internal, authenticated external users, and unauthenticated external users.
- Reason over structured and unstructured data: Users can analyze inputs using classification, sentiment analysis of text, or entity extraction. Examples include analyzing product feedback sentiment, analyzing support calls and transcripts, and refining text-based search with embeddings. Limited to internal and authenticated external users.
- Search: Users can search trusted source documents such as internal company documentation. The application does not generate results ungrounded in trusted source documentation. Available to internal, authenticated external users, and unauthenticated external users.
- Summarization: Users can submit content to be summarized for pre-defined topics built into the application and cannot use the application as an open-ended summarizer. Examples include summarization of internal company documentation, call center transcripts, technical reports, and product reviews. Limited to internal, authenticated external users, and unauthenticated external users.
- Writing assistance on specific topics: Users can create new content or rewrite content submitted by the user as a writing aid for business content or pre-defined topics. Users can only rewrite or create content for specific business purposes or pre-defined topics and cannot use the application as a general content creation tool for all topics. Examples of business content include proposals and reports. May not be selected to generate journalistic content (for journalistic use, select the above Journalistic content use case). Limited to internal users and authenticated external users.
- Data generation for fine-tuning: Users can use a model in Azure OpenAI to generate data which is used solely to fine-tune (i) another Azure OpenAI model, using the fine-tuning capabilities of Azure OpenAI, and/or (ii) another Azure AI custom model, using the fine-tuning capabilities of the Azure AI service. Generating data and fine-tuning models is limited to internal users only; the fine-tuned model may only be used for inferencing in the applicable Azure AI service and, for Azure OpenAI service, only for customer’s permitted use case(s) under this form.
ユースケース以降の項目
ユースケースの次(今回の場合は19)は利用規約の確認チェック。
20はコンテンツフィルターによってフラグが立てられた場合、デバッグや不正使用の調査のため、Microsoftの従業員がコンテンツを確認する場合があることへの同意チェック。
21はアンケートなので記入不要。
申請結果
左下の「送信」ボタンをクリックすると以下のメッセージ。だいたい1日で終わるとのこと。
Most applications are processed within 24 hours. Some applications may require additional processing time and take up to 10 business days
メッセージ通り、翌日には「Welcome to the Azure OpenAI Service, <名前>! [ApplicationID <7桁の数字>]」という件名で、申請が通ったとのメールが来た。
振り返り
設問がすべて英語なので、ユースケースの内容を理解するのが大変だった。
他は一般的な利用申請という感じだが、会社メールアドレスでないと2024/2時点では申請できそうにないので、個人で試すのは難しそう。
