friendliai/capabilities

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

FriendliAI model capabilities table

FriendliAI model capabilities are as follows: Model: deepseek-r1 - Image Input: No - Object Generation: Yes - Tool Usage: No - Tool Streaming: No Model: meta-llama-3.3-70b-instruct - Image Input: No - Object Generation: Yes - Tool Usage: Yes - Tool Streaming: Yes Model: meta-llama-3.1-8b-instruct - Image Input: No - Object Generation: Yes - Tool Usage: Yes - Tool Streaming: Yes

FriendliAI generateText function support

FriendliAI language models can be used with the generateText function from the ai package to generate text based on a prompt.

FriendliAI streamText function support

FriendliAI language models can be used with the streamText function from the ai package for streaming text generation.

FriendliAI structured data generation support

FriendliAI supports structured data generation with the Output object from the ai package for both generateText and streamText functions.

FriendliAI deepseek-r1 reasoning extraction

FriendliAI exposes the thinking of deepseek-r1 in the generated text using the <think> tag. The extractReasoningMiddleware can be used with wrapLanguageModel to extract this reasoning and expose it as a 'reasoning' property on the result.

FriendliAI JSON schema structured output

FriendliAI supports JSON schema structured outputs through guided generation. The schema conforms to Zod format and is passed via the Output.object configuration in generateText, ensuring outputs always conform to the specified schema.

FriendliAI reasoning extraction example

import { friendli } from '@friendliai/ai-provider'; import { wrapLanguageModel, extractReasoningMiddleware } from 'ai'; const enhancedModel = wrapLanguageModel({ model: friendli('deepseek-r1'), middleware: extractReasoningMiddleware({ tagName: 'think' }), }); const { text, reasoning } = await generateText({ model: enhancedModel, prompt: 'Explain quantum entanglement.', });

FriendliAI JSON structured output example

import { friendli } from '@friendliai/ai-provider'; import { generateText, Output } from 'ai'; import { z } from 'zod'; const { output } = await generateText({ model: friendli('meta-llama-3.3-70b-instruct'), output: Output.object({ schemaName: 'CalendarEvent', schema: z.object({ name: z.string(), date: z.string(), participants: z.array(z.string()), }), }), system: 'Extract the event information.', prompt: 'Alice and Bob are going to a science fair on Friday.', }); console.log(output);

Give your agent this brain