new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

llamagate/capabilities

7 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

LlamaGate vision example

import { createLlamaGate } from '@llamagate/ai-sdk-provider'; import { generateText } from 'ai'; const llamagate = createLlamaGate({ apiKey: 'YOU••••••EY', }); const { text } = await generateText({ model: llamagate('qwen3-vl-8b'), messages: [ { role: 'user', content: [ { type: 'text', text: 'What is in this image?' }, { type: 'file', mediaType: 'image', data: new URL('https://example.com/image.jpg'), }, ], }, ], }); console.log(text);

LlamaGate language models access

Access LlamaGate chat models via the llamagate() function or llamagate.chatModel() method. Both approaches work identically for specifying model IDs.

LlamaGate embedding models access

Access LlamaGate text embedding models using the llamagate.textEmbeddingModel() method with the model ID.

LlamaGate generateText example

import { createLlamaGate } from '@llamagate/ai-sdk-provider'; import { generateText } from 'ai'; const llamagate = createLlamaGate({ apiKey: 'YOU••••••EY', }); const { text } = await generateText({ model: llamagate('llama-3.1-8b'), prompt: 'Explain quantum computing in simple terms.', }); console.log(text);

LlamaGate streamText example

import { createLlamaGate } from '@llamagate/ai-sdk-provider'; import { streamText } from 'ai'; const llamagate = createLlamaGate({ apiKey: 'YOU••••••EY', }); const result = streamText({ model: llamagate('qwen3-8b'), prompt: 'Write a short story about a robot.', }); for await (const chunk of result) { console.log(chunk); }

LlamaGate embed example

import { createLlamaGate } from '@llamagate/ai-sdk-provider'; import { embed } from 'ai'; const llamagate = createLlamaGate({ apiKey: 'YOU••••••EY', }); const { embedding } = await embed({ model: llamagate.textEmbeddingModel('nomic-embed-text'), value: 'The quick brown fox jumps over the lazy dog.', }); console.log(embedding);

LlamaGate vision model capabilities

LlamaGate supports vision models including qwen3-vl-8b and llava-7b, enabling multimodal tasks with image analysis.

Give your agent this brain