Implement LLM chat completions with multi-turn conversations using the z-ai-web-dev-sdk.
npx skills add https://github.com/mukaddam-ali/Anadolu-Kitchen --skill llm-mukaddam-ali
Please help me install this Agent Skill. Skill: LLM Source: https://github.com/mukaddam-ali/Anadolu-Kitchen/tree/main/skills/LLM Command: npx skills add https://github.com/mukaddam-ali/Anadolu-Kitchen --skill llm-mukaddam-ali
High-intent search queries and answers about installing and using this skill.
Call ZAI.create() to initialize the SDK, then use zai.chat.completions.create with a messages array containing an assistant system prompt and a user message. The response text is available at completion.choices[0].message.content.
Store messages in an array starting with the system prompt, append each user message and assistant response, and pass the full array to each completion call. Trim older messages when the history exceeds your limit to avoid token constraints.
No, the SDK must be used in backend code only. Import and call it from server-side routes or API handlers, never from client-side JavaScript, to protect credentials and ensure proper operation.
Use the CLI for quick one-off questions, simple automation scripts, and prompt testing with commands like z-ai chat --prompt. Use the SDK for multi-turn conversations, web application integration, and production chat workflows.
Empty responses occur when completion.choices[0].message.content is missing or blank. Validate the response before using it, and implement retry logic with exponential backoff to handle transient API failures.
designershubh1208-pixelAnalyze images and generate conversational responses using z-ai-web-dev-sdk in Node.js.
zot24Scaffold Next.js AI chatbots with generative UI and provider integrations.
arcjetAdds Arcjet rate limiting, bot detection, and email validation to server-side routes.
curiositechStream LLM responses with Server-Sent Events for real-time token display.
