Openai
We track 26 posts about Openai from 12 engineering blogs. Most active: Pamela Fox, Twilio, Vercel. Latest post: Oct 9, 2026.
Companies writing about Openai
Recent posts
Generate Images in Python With OpenAI's GPT Image API (opens on the source site)
You’ve probably asked ChatGPT for a picture and watched one appear a few seconds later. The same models also sit behind OpenAI’s GPT Image API, so you can generate images from your own Python code instead of a chat window. You send a prompt, and image data comes back for your script to work with. By the end of this tutorial, you’ll understand that: You generate images from a text prompt by calling client.images.generate() with a GPT Image model like gpt-image-2.5-flare. Image data always arrives Base64-encoded in .b64_json, so you save it as a file with b64decode(). You choose your image’s…
Quiz: Generate Images in Python With OpenAI's GPT Image API (opens on the source site)
In this quiz, you’ll test your understanding of Generate Images in Python With OpenAI’s GPT Image API. By working through this quiz, you’ll revisit how to install the OpenAI Python library, store your API key, generate images from text prompts with the GPT Image models, tune their size and quality, decode Base64 responses into PNG files, and edit an image with a follow-up prompt. [ Improve Your Python With 🐍 Python Tricks 💌 – Get a short & sweet Python Trick delivered to your inbox every couple of days. >> Click here to learn more and see examples ]
OpenAI Decisions API now available on AI Gateway (opens on the source site)
Vercel ·
OpenAI's Decisions API is now available on AI Gateway through an OpenAI-compatible /v1/decisions endpoint. Use it with GPT-6 Luna Decisions or any other decision model on AI Gateway. Decision models answer typed questions about a shared input and return probabilities, choices, and scores instead of generated text, which suits routing, triage, guardrails, and rubric scoring. You can ask predicate (yes/no), choice, and score questions against the same input in one request. openai/gpt-6-luna-decisions is a separate model ID from openai/gpt-6-luna, which stays a language model for text…
Elastic Security and OpenAI GPT Cyber models: What frontier cyber defense means for the public sector (opens on the source site)
Elastic ·
Elastic responded to OpenAI’s call for stronger, faster cyber defense against AI-enabled threats by joining the OpenAI Daybreak Defense Network and announcing plans to integrate OpenAI GPT Cyber models directly into Elastic Security.
OpenAI Ultrafast mode now available on AI Gateway (opens on the source site)
Vercel ·
AI Gateway now supports OpenAI's Ultrafast service tier for GPT-6 Astra, providing faster output for interactive applications and rapid coding iterations. To use Ultrafast, request it for openai/gpt-6-astra through AI SDK, the Chat Completions API, or Responses API: For workflows with frequent tool calls, OpenAI recommends the Responses API over a persistent WebSocket connection to reduce overhead between turns. See the Ultrafast service-tier examples for persistent connections, including AI SDK over WebSocket. Ultrafast supports US and global processing. Requests pinned to unsupported…
How NVIDIA GPUs Help Accelerate OpenAI’s GPT-6 Astra Ultrafast (opens on the source site)
Nvidia ·
GPT-6 Astra Ultrafast, running on NVIDIA Blackwell GPUs, is available now in the OpenAI API and to eligible ChatGPT Work and Codex users. Accelerated by inference optimizations through OpenAI’s models that tap into the capabilities of the NVIDIA Blackwell architecture, Ultrafast offers up to 8x faster token generation than the Astra Standard mode. For developers, […]
Build an AI Voice Assistant with Twilio Voice and Media Streams, OpenAI's GPT-Live API, and Node.js (opens on the source site)
Twilio ·
Build an AI voice assistant that answers a phone call with Twilio Programmable Voice and Media Streams, powered by OpenAI's GPT-Live-1.
How to Build a Voice AI Agent with OpenAI's GPT-Live, Twilio Agent Connect, and Python (opens on the source site)
Twilio ·
Build inbound and outbound voice AI assistants that can handle tool calls using Python, Twilio Agent Connect, and OpenAI's GPT-Live.
Build Voice AI Experiences with Twilio and GPT-Live-1 in the OpenAI API (opens on the source site)
Twilio ·
Build real-time voice AI Agents with Twilio and GPT-Live-1 in the OpenAI API with these tutorials, sample apps, and more.
Build with OpenAI Agents API on Vercel (opens on the source site)
Vercel ·
OpenAI Agents API provides an OpenAI-hosted agent harness for long-running, tool-using workflows. You can host the agent experience on Vercel and connect each session to Vercel Sandbox for code execution and file access. OpenAI runs the agent loop and maintains session state. Signed OpenAI webhooks are processed through Vercel Queues, while Vercel Sandbox provides an isolated, persistent execution environment for each agent session. With this integration, you get: An OpenAI-managed agent loop and session state Durable processing of sandbox lifecycle events An isolated execution environment…
Make Outbound Calls with Twilio Voice and Media Streams, GPT-Live-1 in the OpenAI API, and Node.js (opens on the source site)
Twilio ·
Build an AI agent that places outbound calls with Twilio Programmable Voice and Media Streams, powered by OpenAI’s GPT-Live-1.
Try the Ansible playbook generation lab with Gemini and OpenAI (opens on the source site)
Red Hat ·
Red Hat Ansible Automation Platform's official Visual Studio Code (VS Code) extension has undergone many iterations and improvements since its initial release in 2021. Along with its automatic linting and easy documentation access, one of the most helpful features of the extension is its ability for users to generate Ansible playbooks and roles using their AI large language model of choice. The post Try the Ansible playbook generation lab with Gemini and OpenAI appeared first on Red Hat Developer.
Codex CLI: OpenAI's Open Agent Harness — Installation, Commands, and CI Integration (opens on the source site)
OpenAI released Codex CLI as Apache 2.0 open-source agent harness with interactive CLI, programmatic SDK, and Codex app-server for product embedding. v0.147.0 shipped August 7, 2026. Most articles cover it as chat interface — developers need practical coverage of codex exec for CI pipelines and one-shot tasks. Continue reading Codex CLI: OpenAI's Open Agent Harness — Installation, Commands, and CI Integration on SitePoint.
The Generator Can't Be the Validator: What OpenAI's Hugging Face Incident Proves About AI Security (opens on the source site)
Snyk ·
OpenAI’s Hugging Face incident is a wake-up call: AI systems can escape their own test harnesses, and vendors can’t be the only ones validating safety.
GPT-Red: OpenAI Is Training Models to Break Other Models (opens on the source site)
Prompt injection is still one of the least comfortable problems in AI development. You can improve your system prompt, restrict tools, validate outputs, and add approval steps before sensitive actions. Still, the model eventually has to read data you do not control. It might browse a webpage, process an email, inspect a repository, or use […] The post GPT-Red: OpenAI Is Training Models to Break Other Models appeared first on RisingStack Engineering.
OpenAI employees… are you okay? (opens on the source site)
You might have seen an article making the rounds this week, about a young man who ended his life after ChatGPT encouraged him to do so. The chat logs are really upsetting.Someone two degrees removed from me took their life a few weeks ago. A close friend related the story to me, about how this person had approached their neighbor one evening to catch up, make small talk, and casually discussed their suicidal ideation at some length. At the end of the conversation, they asked to borrow a rope, and their neighbor agreed without giving the request any critical thought. The neighbor found them…
Watch the recordings from my Python + AI series (opens on the source site)
My colleague and I just wrapped up a live series on Python + AI, a nine-part journey diving deep into how to use generative AI models from Python. I gave the english streams while my colleague Gwen gave the spanish streams (and I hung out in her live chat, working on my technical spanish!). The series introduced multiple types of models, including LLMs, embedding models, and vision models. We dug into popular techniques like RAG, tool calling, and structured outputs. We assessed AI quality and safety using automated evaluations and red-teaming. Finally, we developed AI agents using popular…
Filter the tools from MCP servers (opens on the source site)
What I like about MCP servers: they give me lots of great tools that can make my agents more powerful, with very little work on my side. 🎉 What I don't like about MCP servers: they give me TOO many tools! I usually only need a handful of tools for a task, but a server can expose dozens. 😿 The problems with too many tools: LLM confusion. The LLM will be presented with the tool definition for every single tool in the server, and it needs to decide which tool (if any) is the best for the job. That's a hard decision for an LLM - it's always better to make it easier for the LLM by narrowing the…
How I learn about generative AI (opens on the source site)
I do not consider myself an expert in generative AI, but I now know enough to build full-stack web applications on top of generative AI models, evaluate the quality of those applications, and decide whether new models or frameworks will be useful. These are the resources that I personally used for getting up to speed with generative AI. AI foundation Let's start first with the long-form content: books and videos that gave me a more solid foundation. AI Engineering By Chip Huyen This book is a fantastic high-level overview of the AI Engineering industry from an experienced ML researcher. I…
GPT-5: Will it RAG? (opens on the source site)
OpenAI released the GPT-5 model family today, with an emphasis on accurate tool calling and reduced hallucinations. For those of us working on RAG (Retrieval-Augmented Generation), it's particularly exciting to see a model specifically trained to reduce hallucination. There are five variants in the family: gpt-5 gpt-5-mini gpt-5-nano gpt-5-chat: Not a reasoning model, optimized for chat applications gpt-5-pro: Only available in ChatGPT, not via the API As soon as GPT-5 models were available in Azure AI Foundry, I deployed them and evaluated them inside our popular open source RAG template. I…
Red-teaming a RAG app: gpt-4o-mini v. llama3.1 v. hermes3 (opens on the source site)
When we develop user-facing applications that are powered by LLMs, we're taking on a big risk that the LLM may produce output that is unsafe in some way - like responses that encourage violence, hate speech, or self-harm. How can we be confident that a troll won't get our app to say something horrid? We could throw a few questions at it while manually testing, like "how do I make a bomb?", but that's only scratching the surface. Malicious users have gone to far greater lengths to manipulate LLMs into responding in ways that we definitely don't want happening in domain-specific user…
A visual introduction to vector embeddings (opens on the source site)
For Pycon 2025, I created a poster exploring vector embedding models, which you can download at full-size. In this post, I'll translate that poster into words. Vector embeddings A vector embedding is a mapping from an input (like a word, list of words, or image) into a list of floating point numbers. That list of numbers represents that input in the multidimensional embedding space of the model. We refer to the length of the list as its dimensions, so a list with 1024 numbers would have 1024 dimensions. Embedding models Each embedding model has its own dimension length, allowed input types,…
Building a streaming DeepSeek-R1 app on Azure (opens on the source site)
Update: The approach has slightly changed (in a good way!). Read this Microsoft Learn article for an updated guide. This year, we're seeing the rise in "reasoning models", models that include an additional thinking process in order to generate their answer. Reasoning models can produce more accurate answers and can answer more complex questions. Some of those models, like o1 and o3, do the reasoning behind the scenes and only report how many tokens it took them (quite a few!). The DeepSeek-R1 model is interesting because it reveals its reasoning process along the way. When we can see the…
Evaluating gpt-4o-mini vs. gpt-3.5-turbo for RAG applications (opens on the source site)
The azure-search-openai-demo repository was first created in March 2023 and is now the most popular RAG sample solution for Azure. Since the world of generative AI changes so rapidly, we've made many upgrades to its underlying packages and technologies over the past two years. But we've never changed the default GPT model used for the RAG flow: gpt-35-turbo. Why, when there are new models that are cheaper and reportedly better, such as gpt-4o-mini? Well, changing the model is one of the most significant changes you can make to impact RAG answer quality, and I did not want to make the change…
CLI Chatbot with LangChain and OpenAI in Node.js (opens on the source site)
How to: OpenAI in JavaScript with LangChain. A step by step example on how to use the OpenAI API in JavaScript with LangChain ...
LangChain: OpenAI in JavaScript with React.js & Next.js (opens on the source site)
How to: OpenAI in JavaScript with LangChain. A step by step example on how to use the OpenAI API in JavaScript with LangChain ...
Related topics
This page is generated automatically from the engineering blogs we follow. Every post links to its source, where it was published. See all sources.