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

sambanova/options

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

SambaNova provider baseURL option

The `baseURL` option allows you to use a different URL prefix for API calls, such as for proxy servers. The default is `https://api.sambanova.ai/v1`.

SambaNova provider apiKey option

The `apiKey` option specifies the API key sent using the Authorization header. It defaults to the `SAMBANOVA_API_KEY` environment variable.

SambaNova provider headers option

The `headers` option accepts a `Record<string,string>` to include custom headers in requests.

SambaNova provider fetch option

The `fetch` option accepts a custom fetch implementation with signature `(input: RequestInfo, init?: RequestInit) => Promise<Response>`. It defaults to the global fetch function and can be used as middleware to intercept requests or provide custom implementations.

SambaNova fetch intercepting example

Example of intercepting fetch requests with SambaNova provider: ```ts import { createSambaNova } from 'sambanova-ai-provider'; import { generateText } from 'ai'; const sambanovaProvider = createSambaNova({ apiKey: 'YOUR_API_KEY', fetch: async (url, options) => { console.log('URL', url); console.log('Headers', JSON.stringify(options.headers, null, 2)); console.log(`Body ${JSON.stringify(JSON.parse(options.body), null, 2)}`); return await fetch(url, options); }, }); const model = sambanovaProvider('Meta-Llama-3.1-70B-Instruct'); const { text } = await generateText({ model, prompt: 'Hello, nice to meet you.', }); ```

Give your agent this brain