### Implement Few-Shot Prompting Source: https://help.openai.com/en/articles/6654000-best-practices-for-prompt-engineering-with-the-openai-api Provide examples to guide the model's response pattern when zero-shot prompting is insufficient. ```text Extract keywords from the below text. Text: {text} Keywords: ``` ```text Extract keywords from the corresponding texts below. Text 1: Stripe provides APIs that web developers can use to integrate payment processing into their websites and mobile applications. Keywords 1: Stripe, payment processing, APIs, web developers, websites, mobile applications ## Text 2: OpenAI has trained cutting-edge language models that are very good at understanding and generating text. Our API provides access to these models and can be used to solve virtually any task that involves processing language. Keywords 2: OpenAI, language models, text processing, API. ## Text 3: {text} Keywords 3: ``` -------------------------------- ### Configure Template MCP Server URLs Source: https://help.openai.com/en/articles/20001040 Example of mapping a template URL with placeholders to a concrete example URL for MCP server configuration. ```text Example MCP Server URL: https://acme.example.com/mcp Template MCP Server URL: https://{workspace}.example.com/mcp ``` -------------------------------- ### Install ChatGPT via winget Source: https://help.openai.com/en/articles/10003026-windows-app-release-notes Use this command to install the ChatGPT Windows application via the winget package manager. ```bash winget.exe install --id=9NT1R1C2HH7J --source=msstore --accept-package-agreements --accept-source-agreements –silent ``` -------------------------------- ### GET /v1/me Source: https://help.openai.com/en/articles/9132009-how-can-i-view-the-users-or-organizations-associated-with-an-api-key Retrieves information about the user and organizations associated with the provided API key. ```APIDOC ## GET /v1/me ### Description Retrieves the user and organization details associated with the API key used in the request. ### Method GET ### Endpoint https://api.openai.com/v1/me ### Request Example curl https://api.openai.com/v1/me \ -H "Authorization: Bearer $OPENAI_API_KEY" ### Response #### Success Response (200) - **object** (string) - The type of object returned (e.g., "user"). - **id** (string) - The unique identifier for the user. - **email** (string) - The email address of the user. - **name** (string) - The name of the user. - **orgs** (object) - A list of organizations associated with the user. #### Response Example { "object": "user", "id": "user-1234", "email": "user@yourcompany.com", "name": "Users Name", "orgs": { "object": "list", "data": [ { "object": "organization", "id": "org-abcd", "title": "Org 1 Name" }, { "object": "organization", "id": "org-1234", "title": "Org 2 Name" } ] } } ``` -------------------------------- ### Compliance API Error Response Source: https://help.openai.com/en/articles/8983778-chat-and-file-retention-policies-in-chatgpt?q=chatgpt+files+retained Example of the error returned by the Compliance API when attempting to access or delete a file that is no longer active or found in the workspace. ```json { "error": { "message": "File not found in workspace.", "type": "invalid_request_error" } } ```