# Openai > Start tasks, view diffs, and push PRs—while you're away from your desk. ## Pages - [Codex in the ChatGPT iOS app](2025-05-19.md): - Date: 2025-05-19 - [Reworked environment page](2025-05-22.md): - Date: 2025-05-22 - [June update](2025-06-03.md): - Date: 2025-06-03 - [Best of N](2025-06-13.md): - Date: 2025-06-13 - [Mid August update](2025-08-21.md): - Date: 2025-08-21 - [Late August update](2025-08-27.md): - Date: 2025-08-27 - [Introducing GPT-5-Codex](2025-09-15.md): - Date: 2025-09-15 - [GPT-5-Codex in the API](2025-09-23.md): - Date: 2025-09-23 - [Codex is now GA](2025-10-06.md): - Date: 2025-10-06 - [Tag @Codex on GitHub Issues and PRs](2025-10-22.md): - Date: 2025-10-22 - [Credits on ChatGPT Pro and Plus](2025-10-30.md): - Date: 2025-10-30 - [GPT-5-Codex model update](2025-11-06.md): - Date: 2025-11-06 - [Introducing GPT-5-Codex-Mini](2025-11-07.md): - Date: 2025-11-07 - [Introducing GPT-5.1-Codex and GPT-5.1-Codex-Mini](2025-11-13.md): - Date: 2025-11-13 - [Introducing GPT-5.1-Codex-Max](2025-11-18.md): - Date: 2025-11-18 - [Usage and credits fixes](2025-11-24.md): - Date: 2025-11-24 - [Resources updates](2025-11-4.md): - Date: 2025-11-04 - [Introducing Codex for Linear](2025-12-04.md): - Date: 2025-12-04 - [Introducing GPT-5.2-Codex](2025-12-18.md): - Date: 2025-12-18 - [Agent skills in Codex](2025-12-19.md): - Date: 2025-12-19 - [GPT-5.2-Codex API availability](2026-01-14.md): - Date: 2026-01-14 - [Session metadata for tool calls & requestModal template switching](2026-01-15.md): - Date: 2026-01-15 - [Company knowledge compatibility guidance](2026-01-21.md): - Date: 2026-01-21 - [Custom prompts deprecated](2026-01-22.md): - Date: 2026-01-22 - [Team Config for shared configuration](2026-01-23.md): - Date: 2026-01-23 - [Web search is now enabled by default](2026-01-28.md): - Date: 2026-01-28 - [Introducing the Codex app](2026-02-02.md): - Date: 2026-02-02 - [4o image generation intro](4o-image-generation-intro.md): Video introduction to 4o model image generation capabilities. - [Admin Setup](admin-setup.md): This guide is for ChatGPT Enterprise admins who want to set up Codex for their workspace. - [Agentic Commerce Protocol](agentic-commerce-guide.md): Design flows for embedded commerce in ChatGPT. - [Build, deploy, and optimize agentic workflows with AgentKit](agentkit-walkthrough.md): At DevDay 2025 we launched [AgentKit](https://openai.com/index/introducing-agentkit/), a complete set of tools for de... - [Custom instructions with AGENTS.md](agents-md.md): Codex reads`AGENTS.md`files before doing any work. By layering global guidance with project-specific overrides, you... - [Agents SDK quickstart](agents-quickstart-guide.md): Step-by-step guide to quickly build agents with the OpenAI Agents SDK. - [Agents SDK — Python](agents-sdk-python.md): Python SDK for developing agents with OpenAI. - [Agents SDK quickstart](agents-sdk-quickstart.md): Quickstart project for building agents with the Agents SDK. - [Agents SDK — TypeScript](agents-sdk-typescript.md): TypeScript SDK for developing agents with OpenAI. - [Use Codex with the Agents SDK](agents-sdk.md): You can run Codex as an MCP server and connect it from other MCP clients (for example, an agent built with the [OpenA... - [Using an OpenAI API key](api-key.md): You can extend your local Codex usage (CLI and IDE extension) with an API key. API key usage is billed through your O... - [Codex App Server](app-server.md): Codex app-server is the interface Codex uses to power rich clients (for example, the Codex VS Code extension). Use it... - [App submission guidelines](app-submission-guidelines.md): The ChatGPT app ecosystem is built on trust. People come to ChatGPT expecting an experience that is safe, useful, and... - [Codex app](app.md): The Codex app is a focused desktop experience for working on Codex threads in parallel, with built-in worktree suppor... - [Introduction](app-assistant-voice-agents.md): Let's say you're an AI lead at a consumer tech company. You have the vision of deploying a single entry point digital... - [Apps SDK examples](apps-sdk-examples.md): Example demo apps and corresponding MCP servers for the Apps SDK. - [Assistants API Overview (Python SDK)](assistants-api-overview-python.md): The new [Assistants API](https://platform.openai.com/docs/assistants/overview) is a stateful evolution of our [Chat C... - [Audio & speech guide](audio-speech-guide.md): Overview of approaches for audio processing and speech in applications. - [Authentication](auth.md): Many Apps SDK apps can operate in a read-only, anonymous mode, but anything that exposes customer-specific data or wr... - [Autofix CI failures with Codex](autofix-ci.md): Codex can keep your continuous integration (CI) signal green by running automatically whenever a workflow fails. This... - [Autofix CI failures on GitHub with Codex CLI](autofix-github-actions.md): This cookbook shows you how to embed the OpenAI Codex CLI into your CI/CD pipeline so that when your builds or tests ... - [Automations](automations.md): Automate recurring tasks in the background. Codex adds findings to the inbox, or automatically archives the task if t... - [Self-Evolving Agents: A Cookbook for Autonomous Agent Retraining](autonomous-agent-retraining.md): Agentic systems often reach a plateau after proof-of-concept because they depend on humans to diagnose edge cases and... - [Azure AI Search as a vector database + Azure Functions for GPT integration in ChatGPT](azure-ai-search-with-azure-functions-and-gpt-actions-in-chatgpt.md): This notebook provides step by step instuctions on using Azure AI Search (f.k.a Azure Cognitive Search) as a vector d... - [Background mode guide](background-mode-guide.md): Guide to running tasks in the background with Responses. - [Balance accuracy, latency, and cost](balancing-accuracy-latency-cost-video.md): Talk on optimizing AI systems for accuracy, speed, and cost. - [Batch API guide](batch-api-guide.md): Guide on how to use the Batch API to reduce costs - [Batch processing with the Batch API](batch-processing.md): The new Batch API allows to **create async batch jobs for a lower price and with higher rate limits**. - [Building an AI-Native Engineering Team](build-ai-native-engineering-team.md): AI models are rapidly expanding the range of tasks they can perform, with significant implications for engineering. F... - [Build beautiful frontends with OpenAI Codex](build-frontends-codex-video.md): Learn how OpenAI Codex's multimodal abilities accelerate frontend development. - [Build hour — agentic tool calling](build-hour-tool-calling-video.md): Build hour giving an overview of agentic tool calling. - [**Build your own content fact-checker with OpenAI gpt-oss-120B, Cerebras, and Parallel**](build-your-own-fact-checker-cerebras.md): Ever read an article only to discover later that some of the “facts” were fabricated? As information becomes more abu... - [Building a Coding Agent with GPT-5.1 and the OpenAI Agents SDK](build-a-coding-agent-with-gpt-51.md): GPT-5.1 is exceptionally strong at coding, and with the new code-editing and command-execution tools available in the... - [Build Code Review with the Codex SDK](build-code-review-with-codex-sdk.md): With [Code Review](https://chatgpt.com/codex/settings/code-review) in Codex Cloud, you can connect your team's cloud ... - [Building agents guide](building-agents-guide.md): Official guide to building agents using the OpenAI platform. - [Building with Open Models](building-with-open-models-video.md): Talk covering how developers customize and deploy OpenAI’s open models. - [Building Consistent Workflows with Codex CLI & Agents SDK](building-consistent-workflows-codex-cli-agents-sdk.md): Developers strive for consistency in everything they do. With Codex CLI and the Agents SDK, that consistency can now ... - [Building_Resilient_Prompts_Using_An_Evaluation_Flywheel](building-resilient-prompts-using-an-evaluation-flywheel.md): This cookbook provides a practical guide on how to use the OpenAI Platform to easily build resilience into your prompts. - [Build with Realtime Mini](building-w-rt-mini.md): Growing up, I was fascinated by the idea of Jarvis—an intelligent assistant that could autonomously handle complex wo... - [Built-in tools guide](built-in-tools-guide.md): Guide to using OpenAI's built-in tools with the Responses API. - [Build hour — built-in tools](built-in-tools-video.md): Build hour giving an overview of built-in tools available in the Responses API. - [Evaluations Example: Push Notifications Bulk Experimentation](bulk-experimentation.md): Evals are **task oriented** and iterative, they're the best way to check how your LLM integration is doing and improv... - [Azure chat completions example](chat.md): This example will cover chat completions using the Azure OpenAI service. It also includes information on content filt... - [Data preparation and analysis for chat model fine-tuning](chat-finetuning-data-prep.md): This notebook serves as a tool to preprocess and analyze the chat dataset used for fine-tuning a chat model. - [Azure chat completion models with your own data (preview)](chat-with-your-own-data.md): This example shows how to use Azure OpenAI service models with your own data. The feature is currently in preview. - [Build your ChatGPT UI](chatgpt-ui.md): UI components turn structured tool results from your MCP server into a human-friendly UI. Your components run inside ... - [ChatKit advanced samples](chatkit-advanced-samples.md): Advanced samples showcasing the capabilities of ChatKit (part of AgentKit). - [ChatKit starter app](chatkit-starter-app.md): Integrate ChatKit with an Agent Builder workflow in your application. - [Agentic Checkout Spec](checkout.md): Enable merchants to run end-to-end checkout flows inside ChatGPT while keeping orders, payments, and compliance on th... - [Codex CLI](cli.md): Codex CLI is OpenAI's coding agent that you can run locally from your terminal. It can read, change, and run code on ... - [Codex web](cloud.md): Codex is OpenAI's coding agent that can read, edit, and run code. It helps you build faster, fix bugs, and understand... - [Code interpreter guide](code-interpreter-guide.md): Guide to using the built-in code interpreter tool. - [Modernizing your Codebase with Codex](code-modernization.md): Cookbook to modernize legacy codebases using the OpenAI Codex CLI. - [Modernizing your Codebase with Codex](code-modernization-2.md): Codex is trained to read and reason about large, complex codebases, plan work alongside engineers, and produce high-q... - [Reasoning over Code Quality and Security in GitHub Pull Requests](code-quality-and-security-scan-with-github-actions.md): This guide explains how to integrate OpenAI reasoning models into your GitHub Pull Request (PR) workflow to automatic... - [How Codex ran OpenAI DevDay 2025](codex-at-devday.md): This week we wrapped up our third and largest OpenAI DevDay in San Francisco. The event was the result of the hard wo... - [Using OpenAI Codex CLI with GPT-5-Codex](codex-cli-gpt5-video.md): Overview of running the Codex CLI locally with GPT-5-Codex. - [Codex code review](codex-code-review-video.md): Walkthrough of how Codex drives end-to-end pull request reviews with the new onboarding flow. - [Using Codex for education at Dagster Labs](codex-for-documentation-dagster.md): At [Dagster Labs](https://dagster.io), we produce a lot of technical educational content for data engineers, machine ... - [OpenAI Codex in your code editor](codex-ide-extension-video.md): Walkthrough of the Codex IDE extension for VS Code, Cursor, and other forks. - [Codex intro](codex-intro.md): Introductory video introducing Codex and its capabilities. - [Codex in JetBrains IDEs](codex-jetbrains-ides-video.md): How to use Codex inside JetBrains IDEs like Rider, IntelliJ, PyCharm, and WebStorm. - [Codex Prompting Guide](codex-prompting-guide.md): Codex models advance the frontier of intelligence and efficiency and our recommended agentic coding model. Follow thi... - [Using PLANS.md for multi-hour problem solving](codex-exec-plans.md): Codex and the`gpt-5.2-codex`model (recommended) can be used to implement complex tasks that take significant time t... - [**Codex** Prompting Guide](codex-prompting-guide-2.md): Codex models advance the frontier of intelligence and efficiency and our recommended agentic coding model. Follow thi... - [Codex app commands](commands.md): Use these commands and keyboard shortcuts to navigate the Codex app. - [Evaluations Example: Push Notifications Summarizer Monitoring](completion-monitoring.md): Evals are **task-oriented** and iterative, they're the best way to check how your LLM integration is doing and improv... - [How to use the Usage API and Cost API to monitor your OpenAI usage](completions-usage-api.md): Cookbook to fetch and visualize Completions Usage and cost data via API. - [OpenAI Completions Usage API Extended Example](completions-usage-api-2.md): For most of our users, the [default usage and cost dashboards](https://platform.openai.com/usage) are sufficient. How... - [Design components](components.md): UI components are the human-visible half of your connector. They let users view or edit data inline, switch to fullsc... - [Tasks & Prompts](concepts.md): Codex can perform two types of tasks for you: local tasks and cloud tasks. - [Advanced Configuration](config-advanced.md): Use these options when you need more control over providers, policies, and integrations. For a quick start, see [Conf... - [Config basics](config-basic.md): Codex reads configuration details from more than one location. Your personal defaults live in`~/.codex/config.toml`,... - [Configuration Reference](config-reference.md): Use this page as a searchable reference for Codex configuration files. For conceptual guidance and examples, start wi... - [Sample Configuration](config-sample.md): Use this example configuration as a starting point. It includes most keys Codex reads from`config.toml`, along with ... - [Connect from ChatGPT](connect-chatgpt.md): You can test your app in ChatGPT with your account using [developer mode](https://platform.openai.com/docs/guides/dev... - [Context Engineering & Coding Agents with Cursor](context-engineering-cursor-video.md): Session on structuring context for agent workflows inside the Cursor editor. - [Context Engineering for Personalization - State Management with Long-Term Memory Notes using OpenAI Agents SDK](context-personalization.md): Modern AI agents are no longer just reactive assistants—they’re becoming adaptive collaborators. The leap from “respo... - [Context Summarization with Realtime API](context-summarization-with-realtime-api.md): Build an end‑to‑end **voice bot** that listens to your mic, speaks back in real time and **summarises long conversati... - [Conversation state guide](conversation-state-guide.md): Guide for managing conversation state with the Responses API. - [Keep costs low & accuracy high](cost-accuracy-guide.md): Guide on balancing cost efficiency with model accuracy. - [Create skills](create-skill.md): [Skills](https://developers.openai.com/codex/skills) let teams capture institutional knowledge and turn it into reusa... - [Creating slides with the Assistants API (GPT-4), and DALL·E-3](creating-slides-with-assistants-api-and-dall-e3.md): This notebook illustrates the use of the new [Assistants API](https://platform.openai.com/docs/assistants/overview) (... - [CS agents demo](cs-agents-demo.md): Demo showcasing customer service agents orchestration. - [Computer Use API guide](cua-guide.md): Guide to using the Computer Use API (CUA). - [Computer Use API — starter app](cua-starter-app.md): Sample app showcasing Computer Use API integration. - [Building an LLM-as-a-judge evaluation to detect hallucinations with Braintrust](custom-llm-as-a-judge.md): Let's say you're working on a customer service bot and trying to evaluate the quality of its responses. Consider a qu... - [Custom Prompts](custom-prompts.md): Custom prompts are deprecated. Use [skills](https://developers.openai.com/codex/skills) for reusable - [Multimodal RAG with CLIP Embeddings and GPT-4 Vision](custom-image-embedding-search.md): Multimodal RAG integrates additional modalities into traditional text-based RAG, enhancing LLMs' question-answering b... - [Practical guide to data-intensive apps with the Realtime API](data-intensive-realtime-apps.md): This cookbook serves as a practical guide to help AI Engineers maximize the effectiveness of OpenAI's Realtime API, s... - [Data Extraction and Transformation in ELT Workflows using GPT-4o as an OCR Alternative](data-extraction-transformation.md): A lot of enterprise data is unstructured and locked up in difficult-to-use formats, e.g. PDFs, PPT, PNG, that are not... - [Building a Supply-Chain Copilot with OpenAI Agent SDK and Databricks MCP Servers](databricks-mcp-cookbook.md): In supply-chain operations, an agent can resolve questions that directly affect service levels and revenue: Do we hav... - [Question Answering with LangChain, Deep Lake, & OpenAI](deeplake-langchain-qa.md): This notebook shows how to implement a question answering system with LangChain, [Deep Lake](https://activeloop.ai/) ... - [Deploy your app](deploy.md): During development you can expose your local server to ChatGPT using a tunnel such as ngrok: - [DevDay — distillation breakout](devday-distillation-breakout.md): DevDay session on model distillation techniques. - [DevDay — optimization breakout](devday-optimization-breakout.md): DevDay session discussing optimization of models and prompts. - [DevDay — realtime breakout](devday-realtime-breakout.md): DevDay session focused on realtime agent capabilities. - [DevDay — structured outputs breakout](devday-structured-outputs-breakout.md): Session covering structured outputs from DevDay. - [Developing Hallucination Guardrails](developing-hallucination-guardrails.md): Cookbook to build hallucination guardrails with evals for support agents. - [Function to set up display options for pandas](developing-hallucination-guardrails-2.md): A guardrail is a set of rules and checks designed to ensure that the outputs of an LLM are accurate, appropriate, and... - [Introduction](dispute-agent.md): We recently announced our new open-source **Agents SDK**, designed to help you build agentic AI applications using a ... - [Docs MCP](docs-mcp.md): OpenAI hosts a public Model Context Protocol (MCP) server for developer documentation on developers.openai.com and pl... - [Retrieval augmented generation using Elasticsearch and OpenAI](elasticsearch-retrieval-augmented-generation.md): This notebook demonstrates how to: - [Semantic search using Elasticsearch and OpenAI](elasticsearch-semantic-search.md): This notebook demonstrates how to: - [Embedding Wikipedia articles for search](embedding-wikipedia-articles-for-search.md): This notebook shows how we prepared a dataset of Wikipedia articles for search, used in [Question_answering_using_emb... - [Meta Prompting: A Guide to Automated Prompt Optimization](enhance-your-prompts-with-meta-prompting.md): Welcome to our cookbook on meta prompting! In this guide, we'll explore how to take a basic prompt and refine it to e... - [Enterprise admin guide](enterprise.md): This guide is for **ChatGPT Enterprise Admins** looking to set up Codex for their workspace. If you’re a developer, c... - [Long Document Content Extraction](entity-extraction-for-long-documents.md): GPT-3 can help us extract key figures, dates or other bits of important content from documents that are too big to fi... - [Cloud environments](environments.md): Use environments to control what Codex installs and runs during cloud tasks. For example, you can add dependencies, i... - [Testing Agent Skills Systematically with Evals](eval-skills.md): When you’re iterating on a skill for an agent like Codex, it’s hard to tell whether you’re actually improving it or j... - [Evals Best Practices](evals-best-practices-guide.md): Best practices for designing and running evals. - [Getting Started with Evals](evals-getting-started-guide.md): Step-by-step guide to setting up your first eval. - [Evals API: Audio Inputs](evalsapi-audio-inputs.md): This cookbook demonstrates how to use OpenAI's Evals framework for audio-based tasks. Leveraging the Evals API, we wi... - [Evals API: Image Inputs](evalsapi-image-inputs.md): This cookbook demonstrates how to use OpenAI's Evals framework for image-based tasks. Leveraging the Evals API, we wi... - [Evaluating Agents with Langfuse](evaluate-agents.md): In this cookbook, we will learn how to **monitor the internal steps (traces) of the [OpenAI agent SDK](https://github... - [Evaluate RAG with LlamaIndex](evaluate-rag-with-llamaindex.md): In this notebook we will look into building an RAG pipeline and evaluating it with LlamaIndex. It has following 3 sec... - [Working with the Evals API](evaluating-model-performance-guide.md): Guide to building evaluations with the Evals API. - [Examples](examples.md): The Pizzaz demo app bundles a handful of UI components so you can see the full tool surface area end-to-end. The foll... - [Execution policy rules](exec-policy.md): Use execution policy rules to control which commands Codex can run outside the sandbox. - [Explore](explore.md): client:load - [Feature Maturity](feature-maturity.md): Some Codex features ship behind a maturity label so you can understand how reliable each one is, what might change, a... - [Codex app features](features.md): The Codex app is a focused desktop experience for working on Codex threads in parallel, - [Product Feed Spec](feed.md): The Product Feed Specification defines how merchants share structured product data with OpenAI so ChatGPT can accurat... - [File search guide](file-search-guide.md): Guide to retrieving context from files using the Responses API. - [Doing RAG on PDFs using File Search in the Responses API](file-search-responses.md): Cookbook to search PDFs with the Responses API file search tool. - [Using file search tool in the Responses API](file-search-responses-2.md): Although RAG can be overwhelming, searching amongst PDF file shouldn't be complicated. One of the most adopted option... - [Filtered Search with Milvus and OpenAI](filtered-search-with-milvus-and-openai.md): In this notebook we will be going over generating embeddings of movie descriptions with OpenAI and using those embedd... - [Filtered Search with Zilliz and OpenAI](filtered-search-with-zilliz-and-openai.md): In this notebook we will be going over generating embeddings of movie descriptions with OpenAI and using those embedd... - [Financial Document Analysis with LlamaIndex](financial-document-analysis-with-llamaindex.md): In this example notebook, we showcase how to perform financial analysis over [**10-K**](https://en.wikipedia.org/wiki... - [=== Model & Training Params ===](fine-tune-korean.md): 이 노트북은 OpenAI의 **gpt-oss (open‑weight)** 모델을 **한국 뉴스 문체 + 최신 대화체**로 세밀 튜닝하는 방법을 - [Fine-tuning with gpt-oss and Hugging Face Transformers](fine-tune-transfomers.md): Authored by: Edward Beeching, Quentin Gallouédec, and Lewis Tunstall Large reasoning models like OpenAI o3 generate a... - [Fine-tuning best practices](fine-tuning-best-practices-guide.md): Recommendations for effective and efficient model fine-tuning. - [Fine-tuning guide](fine-tuning-guide.md): Comprehensive guide to fine-tuning OpenAI models. - [Fine-Tuning Techniques: Choosing Between SFT, DPO, and RFT (Including a Guide to DPO)](fine-tuning-direct-preference-optimization-guide.md): *This guide is for developers and ML practitioners who have some experience with OpenAIʼs APIs and wish to use their ... - [Fine tuning with function-calling](fine-tuning-for-function-calling.md): This notebook covers how to fine-tune to increase function calling accuracy and reliability. You can find more inform... - [Flex processing guide](flex-processing-guide.md): Guide on how to reduce costs with flex processing - [Frontend testing demo](frontend-testing-demo.md): Demo application for frontend testing using CUA. - [Fine-Tuning OpenAI Models for Retrieval Augmented Generation (RAG) with Qdrant and Few-Shot Learning](ft-retrieval-augmented-generation-qdrant.md): The aim of this notebook is to walk through a comprehensive example of how to fine-tune OpenAI models for Retrieval A... - [Function calling guide](function-calling-guide.md): Introduction to function calling with OpenAI models. - [Function calling for nearby places: Leveraging the Google Places API and customer profiles](function-calling-finding-nearby-places.md): This notebook is centered around the integration of the Google Places API and custom user profiles to enhance locatio... - [Function-calling with an OpenAPI specification](function-calling-with-an-openapi-spec.md): Much of the internet is powered by RESTful APIs. Giving GPT the ability to call them opens up a world of possibilitie... - [Azure functions example](functions.md): This notebook shows how to use the function calling capability with the Azure OpenAI service. Functions allow a calle... - [Retrieval Augmented Generative Question Answering with Pinecone](gen-qa.md): In this notebook we will learn how to query relevant contexts to our queries from Pinecone, and pass these to a gener... - [Generate images with GPT Image](generate-images-with-gpt-image.md): Cookbook to generate and edit images with GPT Image capabilities. - [Generate images with high input fidelity](generate-images-with-high-input-fidelity.md): Cookbook to preserve image details using high input fidelity in Image API. - [Generate and edit images with GPT Image](generate-images-with-gpt-image-2.md): In this cookbook, you'll learn how to use GPT Image, our new large language model with image generation capabilities. - [Generate images with high input fidelity](generate-images-with-high-input-fidelity-2.md): This cookbook shows how you can leverage the`input_fidelity`parameter, available in the Image API and the Responses... - [Using Weaviate with Generative OpenAI module for Generative Search](generative-search-with-weaviate-and-openai.md): This notebook is prepared for a scenario where: - [Agentic Commerce Protocol](get-started.md): OpenAI and Stripe built the Agentic Commerce Protocol to be: - [Using Redis as a Vector Database with OpenAI](getting-started-with-redis-and-openai.md): This notebook provides an introduction to using Redis as a vector database with OpenAI embeddings. Redis is a scalabl... - [Using Weaviate with OpenAI vectorize module for Embeddings Search](getting-started-with-weaviate-and-openai.md): This notebook is prepared for a scenario where: - [Using AnalyticDB as a vector database for OpenAI embeddings](getting-started-with-analyticdb-and-openai.md): This notebook guides you step by step on using AnalyticDB as a vector database for OpenAI embeddings. - [Azure AI Search as a vector database for OpenAI embeddings](getting-started-with-azure-ai-search-and-openai.md): This notebook provides step by step instuctions on using Azure AI Search (f.k.a Azure Cognitive Search) as a vector d... - [GCP Bigquery with GCP Functions and GPT actions in ChatGPT](getting-started-with-bigquery-vector-search-and-openai.md): This notebook provides step-by-step instructions on using Google Cloud BigQuery as a database with vector search capa... - [Using Hologres as a vector database for OpenAI embeddings](getting-started-with-hologres-and-openai.md): This notebook guides you step by step on using Hologres as a vector database for OpenAI embeddings. - [Kusto as a Vector database for AI embeddings](getting-started-with-kusto-and-openai-embeddings.md): This Notebook provides step by step instuctions on using Azure Data Explorer (Kusto) as a vector database with OpenAI... - [Getting Started with Milvus and OpenAI](getting-started-with-milvus-and-openai.md): In this notebook we will be going over generating embeddings of book descriptions with OpenAI and using those embeddi... - [Using MyScale as a vector database for OpenAI embeddings](getting-started-with-myscale-and-openai.md): This notebook provides a step-by-step guide on using MyScale as a vector database for OpenAI embeddings. The process ... - [Getting Started with OpenAI Evals](getting-started-with-openai-evals.md): **Note: OpenAI now has a hosted evals product with an API! We recommend you use this instead. - [Using PolarDB-PG as a vector database for OpenAI embeddings](getting-started-with-polardb-and-openai.md): This notebook guides you step by step on using PolarDB-PG as a vector database for OpenAI embeddings. - [Using Qdrant as a vector database for OpenAI embeddings](getting-started-with-qdrant-and-openai.md): This notebook guides you step by step on using **`Qdrant`** as a vector database for OpenAI embeddings. [Qdrant](http... - [Using Tair as a vector database for OpenAI embeddings](getting-started-with-tair-and-openai.md): This notebook guides you step by step on using Tair as a vector database for OpenAI embeddings. - [Getting Started with Zilliz and OpenAI](getting-started-with-zilliz-and-openai.md): In this notebook we will be going over generating embeddings of book descriptions with OpenAI and using those embeddi... - [Codex GitHub Action](github-action.md): Use the Codex GitHub Action (`openai/codex-action@v1`) to run Codex in CI/CD jobs, apply patches, or post reviews fro... - [Use Codex in GitHub](github.md): Use Codex to review pull requests without leaving GitHub. Add a pull request comment with`@codex review`, and Codex ... - [Governance](governance.md): Codex gives enterprise teams visibility into adoption and impact, plus the auditability needed for security and compl... - [GPT-5.1 prompting guide](gpt-5-1-prompting-guide.md): GPT-5.1, our newest flagship model, is designed to balance intelligence and speed for a variety of agentic and coding... - [GPT-5.2 Prompting Guide](gpt-5-2-prompting-guide.md): Cookbook to prompt GPT-5.2 for accurate, concise enterprise workflows. - [GPT-5.2 Prompting Guide](gpt-5-2-prompting-guide-2.md): GPT-5.2 is our newest flagship model for enterprise and agentic workloads, designed to deliver higher accuracy, stron... - [Frontend with GPT-5](gpt-5-frontend.md): GPT-5 is a large leap forward in frontend development. We have seen the model be excellent at developing full stack a... - [GPT-5 New Params and Tools](gpt-5-new-params-and-tools.md): We’re introducing new developer controls in the GPT-5 series that give you greater control over model responses—from ... - [GPT-5 prompting guide](gpt-5-prompting-guide.md): GPT-5, our newest flagship model, represents a substantial leap forward in agentic task performance, coding, raw inte... - [GPT-5 Troubleshooting Guide](gpt-5-troubleshooting-guide.md): Now that GPT-5 has been out in the world, we’ve been amazed by all of the incredible things developers are building w... - [Gpt Action Pinecone Retool Rag](gpt-action-pinecone-retool-rag.md): This notebook provides a step-by-step guide for using Pinecone as a vector database to store OpenAI embeddings. As an... - [User guide for gpt-oss-safeguard](gpt-oss-safeguard-guide.md): ROOST and OpenAI have prepared a guide that explains how to write policy prompts that maximize [gpt-oss-safeguard's](... - [GPT-4.1 Prompting Guide](gpt4-1-prompting-guide.md): The GPT-4.1 family of models represents a significant step forward from GPT-4o in capabilities across coding, instruc... - [Retrieval Augmentation for GPT-4 using Pinecone](gpt4-retrieval-augmentation.md): In this notebook we will learn how to query relevant contexts to our queries from Pinecone, and pass these to a GPT-4... - [GPT Action Library: BigQuery](gpt-action-bigquery.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [GPT Action Library: Box](gpt-action-box.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [Canvas LMS Cookbook](gpt-action-canvas.md): 1. **General App Information** - Overview of Canvas LMS, its functionality, and the role ... - [GPT Action Library: Confluence](gpt-action-confluence.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [GPT Action Library: GitHub](gpt-action-github.md): This page provides instructions for developers connecting a GPT Action to GitHub. Before proceeding, familiarize your... - [GPT Action Library: Gmail](gpt-action-gmail.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [GPT Action Library: Google Calendar](gpt-action-google-calendar.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [**GPT Action Library: Google Drive**](gpt-action-google-drive.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [GPT Action Library - Google Ads via Adzviser](gpt-action-googleads-adzviser.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [GPT Action Library: Jira](gpt-action-jira.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [GPT Action Library: Notion](gpt-action-notion.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [GPT Action Library: Outlook](gpt-action-outlook.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [GPT Action Library: AWS RedShift](gpt-action-redshift.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [GPT Action Library: Retool Workflow](gpt-action-retool-workflow.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [Gpt_Action_Salesforce](gpt-action-salesforce.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [GPT Action Library: Salesforce + Gong](gpt-action-salesforce-gong.md): This page provides an instruction & guide for developers building middleware to connect a GPT Action to a specific ap... - [GPT Action Library: Sharepoint (Return file for Data Analysis / Document Summarization)](gpt-action-sharepoint-doc.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [GPT Action Library: Sharepoint (Return as Document)](gpt-action-sharepoint-text.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [GPT Actions - Snowflake direct](gpt-action-snowflake-direct.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [GPT Actions - Snowflake middleware](gpt-action-snowflake-middleware.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [GPT Action Library: SQL Database](gpt-action-sql-database.md): This is a guide for developers seeking to give ChatGPT the ability to query a SQL database using a GPT Action. Before... - [GPT Action Library: Tray.ai API Management Operations](gpt-action-trayai-apim.md): This page provides an instruction & guide for developers building a set of GPT Actions across a set of applications. ... - [**Workday GPT Action Cookbook**](gpt-action-workday.md): 1. General App Information - [GPT Action Library: Zapier](gpt-action-zapier.md): This page provides an instruction & guide for developers building a GPT Action for a specific application. Before you... - [Fine-tune ChatGPT-3.5 and GPT-4 with Weights & Biases](gpt-finetuning-with-wandb.md): **Note:** you will need an [OpenAI API key](https://platform.openai.com/account/api-keys) to run this colab. - [GPT Action Library (Middleware): AWS Lambda](gpt-middleware-aws-function.md): This particular GPT Action provides an overview of how to build an **AWS Lambda** function. This documentation helps ... - [GPT Action Library (Middleware): Azure Function](gpt-middleware-azure-function.md): This page provides an instruction & guide for developers building middleware to connect a GPT Action to a specific ap... - [GPT Action Library (Middleware): Google Cloud Function](gpt-middleware-google-cloud-function.md): This page provides an instruction & guide for developers building middleware to connect a GPT Action to a specific ap... - [Processing and narrating a video with GPT-4.1-mini's visual capabilities and GPT-4o TTS API](gpt-with-vision-for-video-understanding.md): This notebook demonstrates how to use GPT's visual capabilities with a video. Although GPT-4.1-mini doesn't take vide... - [Graders](graders-guide.md): Guide to using graders for evaluations. - [Building guardrails for agents](guardrails-guide.md): Guide to implementing safeguards and guardrails in agent applications. - [How to handle the raw chain of thought in gpt-oss](handle-raw-cot.md): The [gpt-oss models](https://openai.com/open-models) provide access to a raw chain of thought (CoT) meant for analysi... - [How to automate tasks with functions (S3 bucket example)](how-to-automate-s3-storage-with-functions.md): This code demonstrates how to interact with ChatGPT functions to perform tasks related to Amazon S3 buckets. The note... - [How to build a tool-using agent with LangChain](how-to-build-a-tool-using-agent-with-langchain.md): This notebook takes you through how to use LangChain to augment an OpenAI model with access to external tools. In par... - [How to build an agent with the Node.js SDK](how-to-build-an-agent-with-the-node-sdk.md): OpenAI functions enable your app to take action based on user inputs. This means that it can, e.g., search the web, s... - [How to use functions with a knowledge base](how-to-call-functions-for-knowledge-retrieval.md): This notebook builds on the concepts in the [argument generation](https://developers.openai.com/cookbook/examples/How... - [How to call functions with chat models](how-to-call-functions-with-chat-models.md): This notebook covers how to use the Chat Completions API in combination with external functions to extend the capabil... - [How to Combine GPT-4o Mini with RAG - Create a Clothing Matchmaker App](how-to-combine-gpt4o-with-rag-outfit-assistant.md): Welcome to the Clothing Matchmaker App Jupyter Notebook! This project demonstrates the power of the GPT-4o mini model... - [How to create dynamic masks with DALL·E and Segment Anything](how-to-create-dynamic-masks-with-dall-e-and-segment-anything.md): Segment Anything is a model from Meta that can be used to select portions of images. Combined with DALL·E's ability t... - [How to evaluate a summarization task](how-to-eval-abstractive-summarization.md): In this notebook we delve into the evaluation techniques for abstractive summarization tasks using a simple example. ... - [How to test and evaluate LLMs for SQL generation](how-to-evaluate-llms-for-sql-generation.md): LLMs are fundamentally non-deterministic in their responses, this attribute makes them wonderfully creative and dynam... - [How to fine-tune chat models](how-to-finetune-chat-models.md): Fine-tuning improves the model by training on many more examples than can fit in a prompt, letting you achieve better... - [How to format inputs to ChatGPT models](how-to-format-inputs-to-chatgpt-models.md): ChatGPT is powered by`gpt-3.5-turbo`and`gpt-4`, OpenAI's most advanced models. - [How to handle rate limits](how-to-handle-rate-limits.md): When you call the OpenAI API repeatedly, you may encounter error messages that say`429: 'Too Many Requests'`or`Rat... - [How to use guardrails](how-to-use-guardrails.md): In this notebook we share examples of how to implement guardrails for your LLM applications. A guardrail is a generic... - [How to use the moderation API](how-to-use-moderation.md): **Note:** This guide is designed to complement our Guardrails Cookbook by providing a more focused look at moderation... - [Using Weaviate with OpenAI vectorize module for Hybrid Search](hybrid-search-with-weaviate-and-openai.md): This notebook is prepared for a scenario where: - [Robust Question Answering with Chroma and OpenAI](hyde-with-chroma-and-openai.md): This notebook guides you step-by-step through answering questions about a collection of data, using [Chroma](https://... - [Codex IDE extension](ide.md): Codex is OpenAI's coding agent that can read, edit, and run code. It helps you build faster, squash bugs, and underst... - [Gpt-image-1.5 Prompting Guide](image-gen-1-5-prompting-guide.md): Cookbook to prompt gpt-image-1.5 for reliable image generation results. - [Gpt-image-1.5 Prompting Guide](image-gen-15-prompting-guide.md): `gpt-image-1.5`is our latest image generation model, designed for production-quality visuals and highly controllable... - [Image generation guide](image-generation-guide.md): Guide to generating images using OpenAI models. - [Image Understanding with RAG using OpenAI's Vision & Responses APIs](image-understanding-with-rag.md): Welcome! This notebook demonstrates how to build a Retrieval-Augmented Generation (RAG) system using OpenAI’s Vision ... - [Agent internet access](internet-access.md): By default, Codex blocks internet access during the agent phase. Setup scripts still run with internet access so you ... - [Hello, world!](intro.md): We're launching a new home for technical deep dives, notes on releases, and best practices for developers building wi... - [Introduction to the Deep Research API](introduction-to-deep-research-api.md): The Deep Research API enables you to automate complex research workflows that require reasoning, planning, and synthe... - [Deep Research Agents Cookbook](introduction-to-deep-research-api-agents.md): This cookbook demonstrates how to build Agentic research workflows using the OpenAI Deep Research API and the OpenAI ... - [Introduction to GPT-4o and GPT-4o mini](introduction-to-gpt4o.md): GPT-4o ("o" for "omni") and GPT-4o mini are natively multimodal models designed to handle a combination of text, audi... - [Automate Jira ↔ GitHub with `codex-cli`](jira-github.md): This cookbook provides a practical, step-by-step approach to automating the workflow between Jira and GitHub. By labe... - [Key concepts](key-concepts.md): Supporting Instant Checkout in ChatGPT requires a merchant to implement three flows. - [Latency optimization guide](latency-optimization-guide.md): Best practices for reducing model response latency. - [Launch apps with evaluations](launching-products-evaluations-video.md): Video on incorporating evals when deploying AI products. - [Leveraging model distillation to fine-tune a model](leveraging-model-distillation-to-fine-tune-a-model.md): Cookbook to distill a larger model into a smaller fine-tuned model. - [Leveraging model distillation to fine-tune a model](leveraging-model-distillation-to-fine-tune-a-model-2.md): OpenAI recently released **Distillation** which allows to leverage the outputs of a (large) model to fine-tune anothe... - [Use Codex in Linear](linear.md): Use Codex in Linear to delegate work from issues. Assign an issue to Codex or mention`@Codex`in a comment, and Code... - [Configuring Codex](local-config.md): Codex should work out of the box for most users. But sometimes you want to configure Codex to your own liking to bett... - [Local environments](local-environments.md): Local environments let you configure setup steps for worktrees as well as common actions for a project. - [OpenAI Compliance Logs Platform quickstart](logs-platform.md): Use this notebook to get started using the OpenAI Compliance Logs Platform. The examples focus on downloading log fil... - [LLM correctness and consistency](maximizing-llm-correctness-guide.md): Best practices for achieving accurate and consistent model outputs. - [MCP guide](mcp-guide.md): Guide to using the Model Context Protocol for portable tools. - [MCP intro](mcp-intro.md): Introduction video to Model Customization Platform (MCP). - [Build your MCP server](mcp-server.md): By the end of this guide, you’ll know how to connect your backend MCP server to ChatGPT, define tools, register UI te... - [Guide to Using the Responses API's MCP Tool](mcp-tool-guide.md): Cookbook to connect external services using the Responses API MCP tool. - [Model Context Protocol](mcp.md): Model Context Protocol (MCP) connects models to tools and context. Use it to give Codex access to third-party documen... - [Evaluating MCP-Based Answers with a Custom Dataset](mcp-eval-notebook.md): This notebook evaluates a model's ability to answer questions about the [tiktoken](https://github.com/openai/tiktoken... - [MCP‑Powered Agentic Voice Framework](mcp-powered-agents-cookbook.md): Agents are becoming the de-facto framework in which we orchestrate various, often specialized, LLMs applications to w... - [Guide to Using the Responses API's MCP Tool](mcp-tool-guide-2.md): Building agentic application often requires connecting to external services. Traditionally, this is done through func... - [Model distillation overview](model-distillation-overview.md): Overview of distillation techniques for creating efficient models. - [Model optimization guide](model-optimization-guide.md): Guide on optimizing OpenAI models for performance and cost. - [Practical Guide for Model Selection for Real‑World Use Cases](model-selection-guide.md): This cookbook serves as your practical guide to selecting, prompting, and deploying the right OpenAI model (between G... - [OpenAI models page](models-page.md): Overview of the models available on the OpenAI platform. - [Codex Models](models.md): client:load - [Monetization](monetization.md): When building a ChatGPT app, developers are responsible for choosing how to monetize their experience. Today, the **r... - [Multi-Agent Portfolio Collaboration with OpenAI Agents SDK](multi-agent-portfolio-collaboration.md): Cookbook for multi-agent portfolio analysis workflows using the OpenAI Agents SDK. - [Multi-Agent Orchestration with OpenAI Agents SDK: Financial Portfolio Analysis Example](multi-agent-portfolio-collaboration-2.md): *This guide is for readers already familiar with OpenAI models and LLM agents, and want to see how to orchestrate a t... - [estimate inference cost assuming gpt-3.5-turbo (4K context)](named-entity-recognition-to-enrich-text.md): `Named Entity Recognition`(NER) is a`Natural Language Processing`task that identifies and classifies named entitie... - [Vector similarity search using Neon Postgres](neon-postgres-vector-search-pgvector.md): This notebook guides you through using [Neon Serverless Postgres](https://neon.tech/) as a vector database for OpenAI... - [New audio models intro](new-audio-models-intro.md): Overview video of new audio models for speech and transcription. - [Non-interactive mode](noninteractive.md): Non-interactive mode lets you run Codex from scripts (for example, continuous integration (CI) jobs) without opening ... - [o3/o4-mini Function Calling Guide](o3o4-mini-prompting-guide.md): Cookbook to improve o3/o4-mini function calling with prompt best practices. - [o3/o4-mini Function Calling Guide](o3o4-mini-prompting-guide-2.md): The o3/o4-mini models are the latest in our o-series of models trained to think for longer before responding. They ar... - [Multi-Language One-Way Translation with the Realtime API](one-way-translation-using-realtime-api.md): Cookbook to build one-way speech translation with the Realtime API. - [Multi-Language Conversational Translation with the Realtime API](one-way-translation-using-realtime-api-2.md): One of the most exciting things about the Realtime API is that the emotion, tone and pace of speech are all passed to... - [Open Source](open-source.md): OpenAI develops key parts of Codex in the open. That work lives on GitHub so you can follow progress, report issues, ... - [openai.fm](openai-fm.md): Code samples for speech processing from the openai.fm repo. - [OpenAI for Developers in 2025](openai-for-developers-2025.md): 2025 wasn't about a single model launch–it was the year AI got easier to run in production. As models improved at pla... - [OpenAI harmony response format](openai-harmony.md): The [`gpt-oss`models](https://openai.com/open-models) were trained on the harmony response format for defining conve... - [OpenAI API Monitoring with W&B Weave](openai-monitoring-with-wandb-weave.md): **Note:** you will need an [OpenAI API key](https://platform.openai.com/account/api-keys) to run this colab. - [Intro](openai-wikipedia-semantic-search.md): This notebook is an example on how you can use SingleStoreDB vector storage and functions to build an interactive Q&A... - [Optimize Metadata](optimize-metadata.md): ChatGPT decides when to call your connector based on the metadata you provide. Well-crafted names, descriptions, and ... - [Optimize Prompts](optimize-prompts.md): Crafting effective prompts is a critical skill when working with AI models. Even experienced users can inadvertently ... - [Orchestrating Agents: Routines and Handoffs](orchestrating-agents.md): Cookbook for orchestrating agent workflows with routines and handoffs. - [Orchestrating multiple agents](orchestrating-multiple-agents-guide.md): Guide to coordinating multiple agents with shared context. - [Orchestrating Agents: Routines and Handoffs](orchestrating-agents-2.md): When working with language models, quite often all you need for solid performance is a good prompt and the right tool... - [Codex](overview.md): alt="Codex app showing a project sidebar, thread list, and review pane" - [Running Specialized Agents in Parallel with the OpenAI Agents SDK](parallel-agents.md): Why would you want to do this? - [Parsing PDF documents for RAG applications](parse-pdf-docs-for-rag.md): This notebook shows how to leverage GPT-4o to turn rich PDF documents such as slide decks or exports from web pages i... - [Delegated Payment Spec](payment.md): The delegated payment spec allows OpenAI to securely share payment details with the merchant or its designated paymen... - [Philosophy with Vector Embeddings, OpenAI and Cassandra / Astra DB through CQL](philosophical-quotes-cassio.md): In this quickstart you will learn how to build a "philosophy quote finder & generator" using OpenAI's vector embeddin... - [Philosophy with Vector Embeddings, OpenAI and Cassandra / Astra DB](philosophical-quotes-cql.md): In this quickstart you will learn how to build a "philosophy quote finder & generator" using OpenAI's vector embeddin... - [Predicted outputs guide](predicted-outputs-guide.md): Guide to understanding and using predicted outputs. - [Codex Pricing](pricing.md): For a limited time, **try Codex for free in ChatGPT Free and Go**, or enjoy - [Production best practices](production-best-practices-guide.md): Guide on best practices for running AI applications in production - [Agentic commerce in production](production.md): Before going live, complete and document the following tests in a sandbox environment. - [Prompt Caching 101](prompt-caching101.md): Cookbook to reduce latency and cost using OpenAI prompt caching. - [Prompt engineering guide](prompt-engineering-guide.md): Detailed guide on prompt engineering strategies. - [GPT-5 Prompt Migration and Improvement using the new prompt optimizer](prompt-optimization-cookbook.md): The GPT-5 Family of models are the smartest models we’ve released to date, representing a step change in the models’ ... - [Prompt Optimizer](prompt-optimizer-guide.md): Guide to refining prompts with the Prompt Optimizer. - [Prompt Caching 101](prompt-caching101-2.md): OpenAI offers discounted prompt caching for prompts exceeding 1024 tokens, resulting in up to an 80% reduction in lat... - [Prompt Migration Guide](prompt-migration-guide.md): Newer models, such as GPT-4.1, are best in class in performance and instruction following. As model gets smarter, the... - [Shaping your agent’s personality](prompt-personalities.md): Similar to ChatGPT’s built-in personality [presets](https://help.openai.com/en/articles/11899719-customizing-your-cha... - [Prompting](prompting.md): You interact with Codex by sending prompts (user messages) that describe what you want it to do. - [Question Answering with Langchain, AnalyticDB and OpenAI](qa-with-langchain-analyticdb-and-openai.md): This notebook presents how to implement a Question Answering system with Langchain, AnalyticDB as a knowledge based a... - [Question Answering with Langchain, Qdrant and OpenAI](qa-with-langchain-qdrant-and-openai.md): This notebook presents how to implement a Question Answering system with Langchain, Qdrant as a knowledge based and O... - [Question Answering with Langchain, Tair and OpenAI](qa-with-langchain-tair-and-openai.md): This notebook presents how to implement a Question Answering system with Langchain, Tair as a knowledge based and Ope... - [Question Answering in Weaviate with OpenAI Q&A module](question-answering-with-weaviate-and-openai.md): This notebook is prepared for a scenario where: - [Question answering using a search API and re-ranking](question-answering-using-a-search-api.md): Searching for relevant information can sometimes feel like looking for a needle in a haystack, but don’t despair, GPT... - [RAG technique overview](rag-technique-overview.md): Overview of retrieval-augmented generation techniques. - [Retrieval Augmented Generation with a Graph Database](rag-with-graph-db.md): This notebook shows how to use LLMs in combination with [Neo4j](https://neo4j.com/), a graph database, to perform Ret... - [Rate limits guide](rate-limits-guide.md): Guide to understanding and managing rate limits - [MCP for Deep Research](readme.md): This is a minimal example of a Deep Research style MCP server for searching and fetching files from the OpenAI file s... - [Realtime agents starter app](realtime-agents-starter-app.md): Starter app demonstrating realtime agent capabilities. - [Developer notes on the Realtime API](realtime-api.md): We recently [announced](https://openai.com/index/introducing-gpt-realtime/) our latest speech-to-speech - [Realtime console](realtime-console.md): Console application demonstrating realtime API usage. - [Realtime tool delegation guide](realtime-delegation-tools-guide.md): Guide on delegating tasks through tools in realtime agents. - [Realtime guide](realtime-guide.md): Comprehensive guide to building realtime interactions. - [Realtime intro](realtime-intro.md): Introduction to building realtime voice applications. - [Transcribing User Audio with a Separate Realtime Request](realtime-out-of-band-transcription.md): Cookbook to transcribe user audio using out-of-band Realtime sessions. - [Realtime solar system](realtime-solar-system.md): Demo of realtime agent interactions in a solar system example. - [Realtime transcription guide](realtime-transcription-guide.md): Guide for implementing realtime speech transcription. - [Realtime translation guide](realtime-translation-guide.md): Guide to performing realtime speech translation. - [Realtime & Twilio starter app](realtime-twilio-starter-app.md): Starter app integrating realtime agents with Twilio. - [Realtime Eval Guide](realtime-eval-guide.md): width="650" src=" - [Transcribing User Audio with a Separate Realtime Request](realtime-out-of-band-transcription-2.md): **Purpose**: This notebook demonstrates how to use the Realtime model itself to accurately transcribe user audio`out... - [Realtime Prompting Guide](realtime-prompting-guide.md): style="width:450px; height:450px;" - [Reasoning best practices](reasoning-best-practices-guide.md): Prompting and optimization tips for reasoning models - [Reasoning guide](reasoning-guide.md): Overview of what reasoning is and how to prompt reasoning models - [Managing Function Calls With Reasoning Models](reasoning-function-calls.md): OpenAI now offers function calling using [reasoning models](https://platform.openai.com/docs/guides/reasoning?api-mod... - [calling the function](reasoning-items.md): By leveraging the Responses API with OpenAI’s latest reasoning models, you can unlock higher intelligence, lower cost... - [Eval Driven System Design - From Prototype to Production](receipt-inspection.md): Cookbook for eval-driven design of a receipt parsing automation workflow. - [Eval-Driven System Design: From Prototype to Production](receipt-inspection-2.md): This cookbook provides a **practical**, end-to-end guide on how to effectively use - [Running Hybrid VSS Queries with Redis and OpenAI](redis-hybrid-query-examples.md): This notebook provides an introduction to using Redis as a vector database with OpenAI embeddings and running hybrid ... - [Redis Vectors as JSON with OpenAI](redisjson.md): This notebook expands on the other Redis OpenAI-cookbook examples with examples of how to use JSON with vectors. - [Redis as a Context Store with OpenAI Chat](redisqna.md): This notebook demonstrates how to use Redis as high-speed context memory with ChatGPT. - [Reference](reference.md): See [build a ChatGPT UI](https://developers.openai.com/apps-sdk/build/chatgpt-ui) for implementation walkthroughs. - [Evaluations Example: Push Notifications Summarizer Prompt Regression,](regression.md): Evals are **task oriented** and iterative, they're the best way to check how your LLM integration is doing and improv... - [Reinforcement fine-tuning overview](reinforcement-fine-tuning-guide.md): Guide on reinforcement learning-based fine-tuning techniques. - [Exploring Model Graders for Reinforcement Fine-Tuning](reinforcement-fine-tuning.md): Cookbook to use model graders for reinforcement fine-tuning in expert tasks. - [Reinforcement Fine-Tuning for Conversational Reasoning with the OpenAI API](reinforcement-finetuning-healthbench.md): Cookbook for reinforcement fine-tuning conversational reasoning using HealthBench evaluations. - [**Exploring Model Graders for Reinforcement Fine-Tuning**](reinforcement-fine-tuning-2.md): *This guide is for developers and ML practitioners who already know their way around OpenAIʼs APIs, have a basic unde... - [Reinforcement Fine-Tuning with the OpenAI API for Conversational Reasoning](reinforcement-finetuning-healthbench-2.md): *This guide is for developers and ML practitioners who have some experience with OpenAIʼs APIs and wish to use their ... - [How to make your completions outputs reproducible with the new seed parameter](reproducible-outputs-with-the-seed-parameter.md): **TLDR**: Developers can now specify`seed`parameter in the Chat Completion request to receive (mostly) consistent o... - [Multi-Tool Orchestration with RAG approach using OpenAI's Responses API](responses-api-tool-orchestration.md): Cookbook to route queries across tools with RAG using the Responses API. - [Responses API — tools and features](responses-api-tools-video.md): Overview video of available tools and capabilities in the Responses API. - [Why we built the Responses API](responses-api.md): With GPT-5 out in the world, we wanted to give some more context on the best way to integrate it, the [Responses API]... - [Evals API Use-case - Responses Evaluation](responses-evaluation.md): Cookbook to evaluate new models against stored Responses API logs. - [Responses guide](responses-guide.md): Introduction to the Responses API and its endpoints. - [Responses starter app](responses-starter-app.md): Starter application demonstrating OpenAI Responses API with tools. - [Responses vs. chat completions guide](responses-vs-chat-completions-guide.md): Comparison of the Responses API and Chat Completions. - [Import OpenAI client and initialize with your API key.](responses-api-tool-orchestration-2.md): This cookbook guides you through building dynamic, multi-tool workflows using OpenAI's Responses API. It demonstrates... - [Display the image from the provided URL](responses-example.md): The Responses API is a new way to interact with OpenAI models, designed to be simpler and more flexible than previous... - [Review](review.md): The review pane helps you understand what Codex changed, give targeted feedback, and decide what to keep. - [Rules](rules.md): Use rules to control which commands Codex can run outside the sandbox. - [Run OpenAI gpt-oss 20B in a FREE Google Colab](run-colab.md): OpenAI released`gpt-oss`[120B](https://hf.co/openai/gpt-oss-120b) and [20B](https://hf.co/openai/gpt-oss-20b). Both... - [How to run gpt-oss locally with LM Studio](run-locally-lmstudio.md): LM Studio is a performant and friendly desktop application for running large language models (LLMs) on local hardware... - [How to run gpt-oss locally with Ollama](run-locally-ollama.md): Want to get OpenAI gpt-oss running on your own hardware? This guide will walk you through how to use Ollama to set up... - [Optimizing OpenAI GPT-OSS Models with NVIDIA TensorRT-LLM](run-nvidia.md): This notebook provides a step-by-step guide on how to optimizing`gpt-oss`models using NVIDIA's TensorRT-LLM for hig... - [How to run gpt-oss with Hugging Face Transformers](run-transformers.md): The Transformers library by Hugging Face provides a flexible way to load and run large language models locally or on ... - [How to run gpt-oss with vLLM](run-vllm.md): [vLLM](https://docs.vllm.ai/en/latest/) is an open-source, high-throughput inference engine designed to efficiently s... - [In .env.local, set your environment variables](running-realtime-api-speech-on-esp32-arduino-edge-runtime-elatoai.md): This guide shows how to build a AI voice agent device with Realtime AI Speech powered by OpenAI Realtime API, ESP32, ... - [Sandboxing](sandbox.md): Codex runs local tasks by default in a sandbox environment meaning the model is limited in which files it can access,... - [Synthetic Data generation (Part 1)](sdg1.md): Synthetic data generation using large language models (LLMs) offers a powerful solution to a commonly faced problem: ... - [Codex SDK](sdk.md): If you use Codex through the Codex CLI, the IDE extension, or Codex Web, you can also control it programmatically. - [Search reranking with cross-encoders](search-reranking-with-cross-encoders.md): This notebook takes you through examples of using a cross-encoder to re-rank search results. - [Run the container in restricted mode. The container will run in the background.](secure-code-interpreter-tool-for-llm-agents.md): At the core of providing a LLM Agent capability to interact with the outside world or other Agents is “tool (or funct... - [Automating Code Quality and Security Fixes with Codex CLI in GitLab](secure-quality-gitlab.md): When deploying production code, most teams rely on CI/CD pipelines to validate changes before merging. Reviewers typi... - [Security & Privacy](security-privacy.md): Apps SDK gives your code access to user data, third-party APIs, and write actions. Treat every connector as productio... - [Security](security.md): Codex helps protect your code and data and reduces the risk of misuse. - [Selecting a Model Based on Stripe Conversion: A Practical Eval for Startups](selecting-a-model-based-on-stripe-conversion.md): The best model for you depends on your business goal. Many startups choose large language models (LLMs) based on offl... - [Semantic search using Supabase Vector](semantic-search.md): The purpose of this guide is to demonstrate how to store OpenAI embeddings in [Supabase Vector](https://supabase.com/... - [Semantic Search with Pinecone and OpenAI](semantic-search-2.md): In this guide you will learn how to use the OpenAI Embedding API to generate language embeddings, and then index thos... - [Step 1: Setup the environment](semantic-search-using-mongodb-atlas-vector-search.md): This notebook demonstrates how to build a semantic search application using OpenAI and [MongoDB Atlas vector search... - [Context Engineering - Short-Term Memory Management with Sessions from OpenAI Agents SDK](session-memory.md): AI agents often operate in **long-running, multi-turn interactions**, where keeping the right balance of **context** ... - [Codex app settings](settings.md): Use the settings panel to tune how the Codex app behaves, how it opens files, - [Shipping with Codex](shipping-with-codex-video.md): DevDay talk on building, testing, and delivering products with Codex. - [Agent Skills](skills.md): Use agent skills to extend Codex with task-specific capabilities. A skill packages instructions, resources, and optio... - [Supercharging Codex with JetBrains MCP at Skyscanner](skyscanner-codex-jetbrains-mcp.md): _Learn how Skyscanner turbocharged OpenAI’s Codex CLI by integrating it with JetBrains IDEs, giving their AI assistan... - [Use Codex in Slack](slack.md): Use Codex in Slack to kick off coding tasks from channels and threads. Mention`@Codex`with a prompt, and Codex crea... - [Slash commands in Codex CLI](slash-commands.md): Slash commands give you fast, keyboard-first control over Codex. Type`/`in the composer to open the slash popup, ch... - [Sora, ImageGen, and Codex: The Next Wave of Creative Production](sora-imagegen-codex-video.md): Panel discussion on combining Sora, ImageGen, and Codex for media creation. - [Sora starter app](sora-starter-app.md): Sample app showcasing integrations with Sora in the API. - [Sora 2 Prompting Guide](sora2-prompting-guide.md): Cookbook to craft effective video prompts for Sora 2 generation. - [Sora 2: Prompting Guide](sora2-prompting-guide-2.md): Think of prompting like briefing a cinematographer who has never seen your storyboard. If you leave out details, they... - [Comparing Speech-to-Text Methods with the OpenAI API](speech-transcription-methods.md): Cookbook to compare speech-to-text methods and choose the right approach. - [🗣️ Comparing Speech-to-Text Methods with the OpenAI API](speech-transcription-methods-2.md): This notebook provides a clear, hands-on guide for beginners to quickly get started with Speech-to-Text (STT) using t... - [Managing State](state-management.md): This guide explains how to manage state for custom UI components rendered inside ChatGPT when building an app using t... - [Steering_Tts](steering-tts.md): Our traditional [TTS APIs](https://platform.openai.com/docs/guides/text-to-speech) don't have the ability to steer th... - [Structured Output Evaluation Cookbook](structured-outputs-evaluation.md): This notebook walks you through a set of focused, runnable examples how to use the OpenAI **Evals** framework to **te... - [Structured outputs guide](structured-outputs-guide.md): Guide for producing structured outputs with the Responses API. - [Structured outputs samples](structured-outputs-samples.md): Sample code demonstrating structured outputs with OpenAI APIs. - [Introduction to Structured Outputs](structured-outputs-intro.md): Structured Outputs is a new capability in the Chat Completions API and Assistants API that guarantees the model will ... - [Structured Outputs for Multi-Agent Systems](structured-outputs-multi-agent.md): In this cookbook, we will explore how to use Structured Outputs to build multi-agent systems. - [Speech-to-text guide](stt-guide.md): Guide for building speech recognition pipelines. - [Speech-to-text intro](stt-intro.md): Introduction to speech recognition with OpenAI. - [Submit your app](submission.md): Once you have built and [tested your app](https://developers.openai.com/apps-sdk/deploy/testing) in Developer Mode, y... - [Summarizing Long Documents](summarizing-long-documents.md): The objective of this notebook is to demonstrate how to summarize large documents with a controllable level of detail. - [Supervised fine-tuning overview](supervised-fine-tuning-guide.md): Guide to supervised fine-tuning for customizing model behavior. - [Support agent demo](support-agent-demo.md): Demo showing a customer support agent with a human in the loop. - [Using GPT-4o mini to tag & caption images](tag-caption-images-with-gpt4v.md): This notebook explores how to leverage the vision capabilities of the GPT-4* models (for example`gpt-4o`,`gpt-4o-mi... - [1. Executive Summary](temporal-agents.md): This cookbook is designed for flexible engagement: - [Test your integration](testing.md): Testing validates that your connector behaves predictably before you expose it to users. Focus on three areas: tool c... - [Tool Evaluation with OpenAI Evals](tools-evaluation.md): This cookbook shows how to **measure and improve a model’s ability to extract structured information from source code... - [Tools overview guide](tools-overview-guide.md): Guide covering realtime delegation through tools. - [Live Demo Showcase: Tools That 10x Your Codebase](tools-that-10x-your-codebase-video.md): Live walkthrough of Codex-powered tooling that accelerates software delivery. - [Define tools](tools.md): In Apps SDK, tools are the contract between your MCP server and the model. They describe what the connector can do, h... - [Tracing module](tracing-guide.md): Guide to monitoring and debugging agents with tracing. - [Transcription guide](transcription-guide.md): Detailed guide for building transcription pipelines. - [Transcription intro](transcription-intro.md): Introduction to converting speech to text with OpenAI APIs. - [Translation use case](translation-use-case.md): Overview of building multilingual voice applications. - [Troubleshooting](troubleshooting.md): When something goes wrong—components failing to render, discovery missing prompts, auth loops—start by isolating whic... - [Realtime agent demo](typescript-agents-sdk-intro.md): Video introduction to the TypeScript Agents SDK. - [UI guidelines](ui-guidelines.md): Apps are developer-built experiences that are available in ChatGPT. They extend what users can do without breaking th... - [Unit test writing using a multi-step prompt (with the older API)](unit-test-writing-using-a-multi-step-prompt-with-older-completions-api.md): Complex tasks, such as writing unit tests, can benefit from multi-step prompts. In contrast to a single prompt, a mul... - [Unlock agentic power — Agents SDK](unlock-agentic-power-video.md): Video demonstrating advanced capabilities of the Agents SDK. - [Updates for developers building with voice](updates-audio-models.md): AI audio capabilities unlock an exciting new frontier of user experiences. Earlier this year we released several new ... - [Research use cases](use-case.md): Every successful Apps SDK app starts with a crisp understanding of what the user is trying to accomplish. Discovery i... - [User Interaction](user-interaction.md): Discovery refers to the different ways a user or the model can find out about your app and the tools it provides: nat... - [Using chained calls for reasoning structured outputs](using-chained-calls-for-o1-structured-outputs.md): The initially released versions (September 2024) of [o1](https://openai.com/index/introducing-openai-o1-preview/) rea... - [Using Chroma for Embeddings Search](using-chroma-for-embeddings-search.md): This notebook takes you through a simple flow to download some data, embed it, and then index and search it using a s... - [How to use GPT-4o Vision with Function Calling](using-gpt4-vision-with-function-calling.md): The GPT-4o, available as gpt-4o-2024-11-20 as of Novemeber 2024, now enables function calling with vision capabilitie... - [Using logprobs for classification and Q&A evaluation](using-logprobs.md): This notebook demonstrates the use of the`logprobs`parameter in the Chat Completions API. When`logprobs`is enable... - [Using MyScale for Embeddings Search](using-myscale-for-embeddings-search.md): This notebook takes you through a simple flow to download some data, embed it, and then index and search it using a s... - [Using Pinecone for Embeddings Search](using-pinecone-for-embeddings-search.md): This notebook takes you through a simple flow to download some data, embed it, and then index and search it using a s... - [Using Qdrant for Embeddings Search](using-qdrant-for-embeddings-search.md): This notebook takes you through a simple flow to download some data, embed it, and then index and search it using a s... - [Using reasoning for data validation](using-reasoning-for-data-validation.md): In this guide, we’ll explore how to use the o1 model, specifically o1-preview, to perform data validation through rea... - [Using reasoning for routine generation](using-reasoning-for-routine-generation.md): When developing customer service solutions, one of the initial steps involves transforming knowledge base articles in... - [Using Redis for Embeddings Search](using-redis-for-embeddings-search.md): This notebook takes you through a simple flow to download some data, embed it, and then index and search it using a s... - [Using Tool Required for Customer Service](using-tool-required-for-customer-service.md): The`ChatCompletion`endpoint now includes the ability to specify whether a tool **must** be called every time, by ad... - [Using Typesense for Embeddings Search](using-typesense-for-embeddings-search.md): This notebook takes you through a simple flow to download some data, embed it, and then index and search it using a s... - [Import the Pinecone library](using-vision-modality-for-rag-with-pinecone.md): Implementing Retrieval-Augmented Generation (RAG) presents unique challenges when working with documents rich in imag... - [Using Weaviate for Embeddings Search](using-weaviate-for-embeddings-search.md): This notebook takes you through a simple flow to download some data, embed it, and then index and search it using a s... - [UX principles](ux-principles.md): Creating a great ChatGPT app is about delivering a focused, conversational experience that feels native to ChatGPT. - [Verifying gpt-oss implementations](verifying-implementations.md): The OpenAI gpt-oss models are introducing a lot of new concepts to the open-model ecosystem and getting them to perfo... - [Videos](videos.md): title="How designers prototype using the Codex app" - [Vision fine-tuning overview](vision-fine-tuning-guide.md): Guide to fine-tuning models on vision tasks. - [Vision Fine-tuning on GPT-4o for Visual Question Answering](vision-fine-tuning-on-gpt4o-for-visual-question-answering.md): We're excited to announce the launch of [Vision Fine-Tuning on GPT-4o](https://openai.com/index/introducing-vision-to... - [Column Non-Null Count DataGrid Type](visualizing-embeddings-in-kangas.md): In this Jupyter Notebook, we construct a Kangas DataGrid containing the data and projections of the embeddings into 2... - [Load the embeddings](visualizing-embeddings-in-wandb.md): We will upload the data to [Weights & Biases](http://wandb.ai) and use an [Embedding Projector](https://docs.wandb.ai... - [Load the embeddings](visualizing-embeddings-with-atlas.md): In this example, we will upload food review embeddings to [Atlas](https://atlas.nomic.ai) to visualize the embeddings. - [Voice agents guide](voice-agents-guide.md): Guide to building voice agents using speech-to-speech API. - [Voice applications intro](voice-applications-intro.md): Introduction to building voice-enabled applications with OpenAI. - [Make sure requests package is installed](voice-translation-into-different-languages-using-gpt-4o.md): Have you ever wanted to translate a podcast into your native language? Translating and dubbing audio content can make... - [Evaluating Web Search Quality with a Custom Dataset](web-search-evaluation.md): This notebook demonstrates how to evaluate a model's ability to retrieve correct answers from the web using the OpenA... - [Web search guide](web-search-guide.md): Guide to using web search with the Responses API. - [Web_Search_With_Google_Api_Bring_Your_Own_Browser_Tool](web-search-with-google-api-bring-your-own-browser-tool.md): **Disclaimer: This cookbook is for educational purposes only. Ensure that you comply with all applicable laws and ser... - [What makes a great ChatGPT app](what-makes-a-great-chatgpt-app.md): At DevDay we introduced [ChatGPT Apps](https://openai.com/index/introducing-apps-in-chatgpt/) — a new way to bring yo... - [What’s new with DALL·E-3?](what-is-new-with-dalle-3.md): DALL·E-3 is the latest version of our DALL-E text-to-image generation models. As the current state of the art in text... - [What makes documentation good](what-makes-documentation-good.md): Documentation puts useful information inside other people’s heads. Follow these tips to write better documentation. - [Addressing transcription misspellings: prompt vs post-processing](whisper-correct-misspelling.md): We are addressing the problem of enhancing the precision of transcriptions, particularly when it comes to company nam... - [Enhancing Whisper transcriptions: pre- & post-processing techniques](whisper-processing-guide.md): This notebook offers a guide to improve the Whisper's transcriptions. We'll streamline your audio data via trimming a... - [Whisper prompting guide](whisper-prompting-guide.md): OpenAI's audio transcription API has an optional parameter called`prompt`. - [Windows](windows.md): The easiest way to use Codex on Windows is to [set up the IDE extension](https://developers.openai.com/codex/ide) or ... - [Workflows](workflows.md): Codex works best when you treat it like a teammate with explicit context and a clear definition of "done." - [Worktrees](worktrees.md): In the Codex app, worktrees let Codex run multiple independent tasks in the same project without interfering with eac...