mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-30 11:22:34 +00:00
feat(ai): add MiniMax recipe (#148 reworked)
11th recipe. embo-01 model, 1536 dims, $0.07/1M tokens.
OpenAI-compatible at api.minimax.chat. MiniMax requires a `type:
'db' | 'query'` field for asymmetric retrieval (documents indexed with
type='db', queries embedded with type='query'). gbrain has no
query/document signal at the embed-call site today, so v1 defaults to
type='db' for both indexing and retrieval — same vector space, symmetric
similarity. Asymmetric query support is a follow-up TODO that needs the
embed seam to thread query/document context.
Plumbed via src/core/ai/dims.ts: dimsProviderOptions returns
{openaiCompatible: {type: 'db'}} for modelId === 'embo-01'.
Conservative max_batch_tokens=4096 declared (MiniMax docs don't publish
the limit). Recursive halving in the gateway catches token-limit errors
at runtime.
Tests: bun test test/ai/ — 101/101 (6 new + 95 prior).
Plan: ~/.claude/plans/ok-lets-turn-this-enumerated-sonnet.md (commit 5
of 11). Reworked from #148.
Co-Authored-By: cacity <20351699+cacity@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
cacity
Claude Opus 4.7
parent
74c849f970
commit
1abbe8d5a0
@@ -58,6 +58,14 @@ export function dimsProviderOptions(
|
||||
if (VOYAGE_OUTPUT_DIMENSION_MODELS.has(modelId)) {
|
||||
return { openaiCompatible: { output_dimension: dims } };
|
||||
}
|
||||
// MiniMax embo-01 takes a `type: 'db' | 'query'` field for asymmetric
|
||||
// retrieval. Default to 'db' (the indexing path) so embed() works for
|
||||
// import. Queries also embed with type:'db', making retrieval
|
||||
// symmetric. Asymmetric query support is a follow-up TODO that needs
|
||||
// a query/document signal threaded through the embed seam.
|
||||
if (modelId === 'embo-01') {
|
||||
return { openaiCompatible: { type: 'db' } };
|
||||
}
|
||||
return undefined;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -16,6 +16,7 @@ import { deepseek } from './deepseek.ts';
|
||||
import { groq } from './groq.ts';
|
||||
import { together } from './together.ts';
|
||||
import { llamaServer } from './llama-server.ts';
|
||||
import { minimax } from './minimax.ts';
|
||||
|
||||
const ALL: Recipe[] = [
|
||||
openai,
|
||||
@@ -28,6 +29,7 @@ const ALL: Recipe[] = [
|
||||
groq,
|
||||
together,
|
||||
llamaServer,
|
||||
minimax,
|
||||
];
|
||||
|
||||
/** Map from `provider:id` key to recipe. */
|
||||
|
||||
@@ -0,0 +1,44 @@
|
||||
import type { Recipe } from '../types.ts';
|
||||
|
||||
/**
|
||||
* MiniMax (海螺AI). OpenAI-compatible /embeddings endpoint at
|
||||
* api.minimax.chat. The flagship embedding model is `embo-01` (1536 dims).
|
||||
*
|
||||
* MiniMax's API takes an extra `type: 'db' | 'query'` field for asymmetric
|
||||
* retrieval. gbrain currently has no notion of "this is a document vs a
|
||||
* query" at the embed-call site (embed() takes only texts), so we default
|
||||
* to `type: 'db'` for the indexing path. Queries also embed with `type:
|
||||
* 'db'`, making retrieval symmetric. This sacrifices some retrieval
|
||||
* quality vs. a true asymmetric setup but works correctly. A follow-up
|
||||
* TODO will thread query/document context through the embed seam for
|
||||
* full asymmetric support.
|
||||
*
|
||||
* Reference: https://www.minimaxi.com/document/guides/embeddings
|
||||
*/
|
||||
export const minimax: Recipe = {
|
||||
id: 'minimax',
|
||||
name: 'MiniMax (海螺AI)',
|
||||
tier: 'openai-compat',
|
||||
implementation: 'openai-compatible',
|
||||
base_url_default: 'https://api.minimax.chat/v1',
|
||||
auth_env: {
|
||||
required: ['MINIMAX_API_KEY'],
|
||||
optional: ['MINIMAX_GROUP_ID'],
|
||||
setup_url: 'https://www.minimaxi.com/document/guides/embeddings',
|
||||
},
|
||||
touchpoints: {
|
||||
embedding: {
|
||||
models: ['embo-01'],
|
||||
default_dims: 1536,
|
||||
cost_per_1m_tokens_usd: 0.07,
|
||||
price_last_verified: '2026-05-09',
|
||||
// MiniMax docs don't publish a hard batch-token cap; declare a
|
||||
// conservative 4096-token budget so the gateway pre-splits before
|
||||
// hitting whatever undocumented server-side limit exists. Recursive
|
||||
// halving in the gateway catches token-limit errors at runtime.
|
||||
max_batch_tokens: 4096,
|
||||
},
|
||||
},
|
||||
setup_hint:
|
||||
'Get an API key at https://www.minimaxi.com, then `export MINIMAX_API_KEY=...`',
|
||||
};
|
||||
@@ -0,0 +1,59 @@
|
||||
/**
|
||||
* MiniMax recipe smoke (Commit 5 of the v0.32 wave).
|
||||
*
|
||||
* Coverage:
|
||||
* - Recipe registered with expected shape
|
||||
* - default auth: MINIMAX_API_KEY → "Bearer <key>"; missing → AIConfigError
|
||||
* - dimsProviderOptions threads `type: 'db'` for embo-01 (the asymmetric
|
||||
* retrieval field default) — pins the v1 indexing-only behavior
|
||||
*/
|
||||
|
||||
import { describe, expect, test } from 'bun:test';
|
||||
import { getRecipe } from '../../src/core/ai/recipes/index.ts';
|
||||
import { defaultResolveAuth } from '../../src/core/ai/gateway.ts';
|
||||
import { dimsProviderOptions } from '../../src/core/ai/dims.ts';
|
||||
import { AIConfigError } from '../../src/core/ai/errors.ts';
|
||||
|
||||
describe('recipe: minimax', () => {
|
||||
test('registered with expected shape', () => {
|
||||
const r = getRecipe('minimax');
|
||||
expect(r).toBeDefined();
|
||||
expect(r!.id).toBe('minimax');
|
||||
expect(r!.tier).toBe('openai-compat');
|
||||
expect(r!.implementation).toBe('openai-compatible');
|
||||
expect(r!.base_url_default).toBe('https://api.minimax.chat/v1');
|
||||
expect(r!.auth_env?.required).toEqual(['MINIMAX_API_KEY']);
|
||||
expect(r!.auth_env?.optional).toContain('MINIMAX_GROUP_ID');
|
||||
});
|
||||
|
||||
test('embedding touchpoint declares embo-01 + 1536 dims', () => {
|
||||
const r = getRecipe('minimax')!;
|
||||
expect(r.touchpoints.embedding).toBeDefined();
|
||||
expect(r.touchpoints.embedding!.models).toEqual(['embo-01']);
|
||||
expect(r.touchpoints.embedding!.default_dims).toBe(1536);
|
||||
expect(r.touchpoints.embedding!.user_provided_models ?? false).toBe(false);
|
||||
expect(r.touchpoints.embedding!.max_batch_tokens).toBe(4096);
|
||||
});
|
||||
|
||||
test('default auth: MINIMAX_API_KEY set → "Bearer <key>"', () => {
|
||||
const r = getRecipe('minimax')!;
|
||||
const auth = defaultResolveAuth(r, { MINIMAX_API_KEY: 'fake-mm-key' }, 'embedding');
|
||||
expect(auth.headerName).toBe('Authorization');
|
||||
expect(auth.token).toBe('Bearer fake-mm-key');
|
||||
});
|
||||
|
||||
test('default auth: missing MINIMAX_API_KEY → AIConfigError', () => {
|
||||
const r = getRecipe('minimax')!;
|
||||
expect(() => defaultResolveAuth(r, {}, 'embedding')).toThrow(AIConfigError);
|
||||
});
|
||||
|
||||
test('dimsProviderOptions threads type:db for embo-01', () => {
|
||||
const opts = dimsProviderOptions('openai-compatible', 'embo-01', 1536);
|
||||
expect(opts).toEqual({ openaiCompatible: { type: 'db' } });
|
||||
});
|
||||
|
||||
test('dimsProviderOptions returns undefined for non-MiniMax openai-compat models', () => {
|
||||
expect(dimsProviderOptions('openai-compatible', 'voyage-3-lite', 512)).toBeUndefined();
|
||||
expect(dimsProviderOptions('openai-compatible', 'nomic-embed-text', 768)).toBeUndefined();
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user