원문에서 더 깊이 읽기

GEO·AI 검색·마케팅 관련 자료를 주제별로 찾아보세요.

원문 1095건 · 9 / 46페이지

Batch API

> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Run large sets of Agent API requests asynchronously from a JSONL file, then download the results. The Batch API runs many Agent API requests asynchronously. You upload a JSONL file of requests, create a batch from it, poll the batch, and download an output file when it finishes. Use batch for work that does not need an immediate answer, such as evaluations, classification, enrichment, or offline research over a large dataset. Each request

Background Mode

> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Run long agentic tasks asynchronously — submit with background, poll by response id, stream, reconnect, and cancel. Long agentic runs, such as deep research or heavy sandbox work, can take several minutes. Background mode runs these tasks asynchronously so your application can avoid timeouts and dropped connections: submit the run, store its response id, then poll for the result. The run continues server-side even if your client disconnect

Image Attachments

> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Learn how to upload and analyze images using base64 encoding or HTTPS URLs The Agent API supports image analysis through direct image uploads. Images can be provided either as base64 encoded strings within a data URI or as standard HTTPS URLs. > [!WARNING] > > * When using base64 encoding, the API currently only supports images up to 50 MB per image. > * Supported formats for base64 encoded images: PNG (image/png), JPEG (image/jpeg), WEBP

Conversation state

> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Continue an Agent API conversation across turns, either by replaying input yourself or by pointing at a completed prior response. A follow-up request understands earlier turns only if you provide them: either by replaying them yourself, or by pointing at a completed prior response with `previous_response_id`. `previous_response_id` is a shortcut for the common case: it points a new request at a completed prior response so you don't have to

Output Control

> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Streaming and structured outputs for the Agent API Streaming allows you to receive partial responses from the Perplexity API as they are generated, rather than waiting for the complete response. This is particularly useful for real-time user experiences, long responses, and interactive applications. > [!NOTE] > > Streaming is supported across all models available through the Agent API. To enable streaming, set `stream=True` (Python) or `st

Custom Functions

> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Define a custom function, execute model-requested calls in your code, and return each result to the Agent API. Custom functions let an agent use code you control, such as a database query, an internal API, or business logic. You describe the function in the request, but the Agent API never executes it for you. Your application handles the call and returns the result. This example defines an order-status function and completes the entire to

Connectors

> Fetch the complete documentation index at: https://docs.perplexity.ai/llms.txt > Use this file to discover all available pages before exploring further. > Connect services or bring your own MCP server to your Project, then use them by connector ID in Agent API requests. Connectors are integrations that you configure once on your [Project connectors page](https://console.perplexity.ai/project/connectors). Choose a managed connector from the catalog, or add a custom connector for your own remote Model Context Protocol (MCP) server. Perplexity stores the connection settings and credentials for

How do I change my name for my OpenAI account?

How do I change my name for my OpenAI account? Changing your display name used for your OpenAI account. Updated: 11 days ago Note : The time for the name change you make on platform.openai.com to be reflected in ChatGPT may take up to 15 minutes. You can change your name in your user settings in platform .openai.com under User Profile Image -> Your Profile -> User -> Name. https://platform.openai.com/account/user-settings ChatGPT ChatGPT pulls your name from API Platform Organization. Please follow the steps above to change your name on platform.openai.com and refresh ChatGPT to see the update

How can I report fraud or suspicious activity?

How can I report fraud or suspicious activity? Secure your account, rotate exposed API keys, and report suspected fraud or unauthorized activity to OpenAI. Updated: 11 days ago At OpenAI, your account security is a top priority. If you notice suspicious or fraudulent activity on your account, please follow the steps below to protect your information and report the issue to us immediately. Steps to Secure Your Account: Update Your Password: Navigate to your OpenAI account settings . Choose a strong, unique password that you haven't used elsewhere. Log Out of All Devices: In your account setting

How can I contact support?

How can I contact support? Need assistance? Here's how to reach us and get the help you need. Updated: 11 days ago Contacting Support You can contact OpenAI Support by opening the chat bubble icon displayed at the bottom-right of help.openai.com . When you start a new chat, you’ll first interact with our virtual assistant. If the bot can’t resolve your issue and a human agent joins, please be prepared to share the details listed in the Best Practices checklist below so we can route and resolve your request as quickly as possible. OpenAI Support is available in most languages. Contact us in you

Creating a new ChatGPT account after deletion

Creating a new ChatGPT account after deletion Learn whether you can reactivate your ChatGPT account after deletion or deactivation and when you can create a new account with the same email address. Updated: 12 days ago Overview A deleted ChatGPT account cannot be restored. If you deleted the account yourself, you may be able to create a new account using the same email address after 30 days. A deactivated account has a different recovery process. Check whether your account was deleted or deactivated If you see “You do not have an account because it has been deleted or deactivated,” your next s

Changing your account sign-in method

Changing your account sign-in method Learn when you can change your sign-in method and how it affects MFA and account access. Updated: 5 days ago Logging in with a different method If you originally signed up using an email and password, you can later log in using a social login method (Google, Microsoft, or Apple) as long as the email address matches. Your account will automatically combine both login methods, allowing you to log in using either your original email/password or your new social login. Social login methods If you initially signed up using SSO or a social login method (such as Go

Changing your OpenAI account email address

Changing your OpenAI account email address Learn how to change your OpenAI account email for ChatGPT and the API Platform, and when to ask your organization’s administrator for help. Updated: 5 days ago Overview ChatGPT and the API Platform share one OpenAI account. Changing its email in ChatGPT also updates your API sign-in. Changing the email on your existing account keeps your chat history, projects, workspace memberships, settings, and preferences. Before you begin You can’t change your email yourself if you belong to a Business, Enterprise, or Edu workspace or your account uses your organ

Canceling your ChatGPT subscription

Canceling your ChatGPT subscription Learn how to cancel a ChatGPT subscription purchased on the web, through the Apple App Store, or through Google Play. Updated: 6 hours ago Overview This article covers personal ChatGPT subscriptions and self-service ChatGPT Business subscriptions. It does not cover ChatGPT Enterprise or Edu plans. Cancel your subscription through the platform where you purchased it: If you subscribed on chatgpt.com, cancel through your ChatGPT account. If you subscribed through the Apple App Store, cancel through your Apple subscriptions. If you subscribed through Google Pla

Canceling API pay-as-you-go service

Canceling API pay-as-you-go service Learn how to cancel API pay-as-you-go service and understand access, outstanding charges, and prepaid credits after cancellation. Updated: 12 days ago Overview You can cancel your API pay-as-you-go service at any time. Cancellation does not automatically refund charges already accrued during the current billing month. Refund eligibility is reviewed separately. Cancel your plan Before you begin, make sure you have permission to manage billing for the API organization you want to cancel. Go to that organization’s Billing overview . Select Cancel plan or Cancel

AI phone support

AI phone support Learn how OpenAI’s AI phone support works, including supported regions, service limitations, and call data handling. Updated: 11 days ago By communicating with OpenAI's AI phone support, you agree to our Terms of Use and acknowledge that you have read our Privacy Policy . Calls may be used to improve OpenAI’s services. Remember, models can make mistakes, so please check important info. This service is for users 13+. What is AI phone support? AI phone support is an AI phone agent and is designed to answer general questions about ChatGPT and other OpenAI products. You don't need

Account management

Account management AI phone support Learn how OpenAI’s AI phone support works, including supported regions, service limitations, and call data handling. Canceling API pay-as-you-go service Learn how to cancel API pay-as-you-go service and understand access, outstanding charges, and prepaid credits after cancellation. Canceling your ChatGPT subscription Learn how to cancel a ChatGPT subscription purchased on the web, through the Apple App Store, or through Google Play. Changing your OpenAI account email address Learn how to change your OpenAI account email for ChatGPT and the API Platform, and

CLI customization

> For the complete documentation index, see [llms.txt](https://learn.chatgpt.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to the page URL. The Codex CLI provides terminal-specific options for how interactive sessions look and how you enter commands and prompts. The terminal UI (TUI) syntax-highlights fenced Markdown code blocks and file diffs. Run `/theme` to open the theme picker, preview themes, and save your selection to `tui.theme` in `$CODEX_HOME/config.toml`. To add a custom theme, place a `.tmTheme` file in `$CODEX_HOME/themes`, then select it

Configuration Reference

> For the complete documentation index, see [llms.txt](https://learn.chatgpt.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to the page URL. Use this page as a searchable reference for Codex configuration files. For conceptual guidance and examples, start with [Config basics](https://learn.chatgpt.com/docs/config-file/config-basic) and [Advanced Config](https://learn.chatgpt.com/docs/config-file/config-advanced). With Local computer access with Work Cloud enabled, OpenAI's cloud coordinates the task while supported tools run in the cloud or on a connec

Agentic Checkout Spec

> For the complete documentation index, see [llms.txt](/llms.txt). Markdown versions of documentation pages are available by appending `.md` to the page URL. Enable merchants to run end-to-end checkout flows inside ChatGPT while keeping orders, payments, and compliance on their existing commerce stack. **How it works** 1. Create session (REST). ChatGPT calls your `POST /checkout_sessions` to start a session with cart contents and buyer context; your response must include a rich, authoritative cart state. 2. Update session (REST). As the user changes items, shipping, or discounts, ChatGPT calls

Quickstart

> For the complete documentation index, see [llms.txt](/llms.txt). Markdown versions of documentation pages are available by appending `.md` to the page URL. The Ads API can programmatically create ad campaigns and monitor your results. This guide covers the minimal implementation to get an ad live, and check your results. Ads live inside an Ad Group, and Ad Groups live inside a Campaign. Campaigns and Ad Groups define your budget and targeting, while Ads host your Ad's title, description and images. Issue an API key in the Settings tab of your [Ads Manager](https://ads.openai.com) account. Se

Trigger workspace agent runs

> For the complete documentation index, see [llms.txt](/llms.txt). Markdown versions of documentation pages are available by appending `.md` to the page URL. Use the Workspace Agents API to programmatically trigger a published ChatGPT workspace agent through API. This endpoint is designed to integrate with workflows where an external system needs to trigger an agent outside of the ChatGPT UI and third party triggers offered. ```text POST https://api.chatgpt.com/v1/workspace_agents/{id}/trigger GET https://api.chatgpt.com/v1/workspace_agents/{id}/runs/{run_id} ``` `id` is the stable public API

Image Evals for Image Generation and Editing Use Cases

> For the complete documentation index, see [llms.txt](/llms.txt). Markdown versions of documentation pages are available by appending `.md` to the page URL. Image models are increasingly used in real product workflows—design mockups, marketing assets, virtual try-on, and high-precision edits to existing brand materials. To trust these systems in production, you need more than “does it look good?” You need **repeatable, workflow-specific evaluation** that measures whether outputs satisfy requirements, fail safely, and improve predictably over time. Vision evaluations(or vision evals) are harde

Function calling

> For the complete documentation index, see [llms.txt](/llms.txt). Markdown versions of documentation pages are available by appending `.md` to the page URL. **Function calling** (also known as **tool calling**) provides a powerful and flexible way for OpenAI models to interface with external systems and access data outside their training data. This guide shows how you can connect a model to data and actions provided by your application. We'll show how to use function tools (defined by a JSON schema) and custom tools which work with free form text inputs and outputs. For Agents API sessions, u