Files
ragflow/web/src/pages/user-setting/constants.tsx
zhifu gao 06e36d24f4 feat(stt): add FunASR / SenseVoice provider (#16473)
### Summary

Adds FunASR as a self-hosted speech-to-text provider through its
OpenAI-compatible `/v1/audio/transcriptions` endpoint.

This is a focused replacement for #15526 by @Rene0422 and relates to
#15448. The unrelated Markdown parser changes from the previous branch
are intentionally removed so this PR contains only the FunASR provider
integration.

- register FunASR as a `SPEECH2TEXT` factory;
- add `FunASRSeq2txt` with `sensevoice` and `http://localhost:8000/v1`
defaults, an optional API key, URL normalization, and inherited
transcription handling;
- wire FunASR into the current local-provider schema with a prefilled
local URL and official documentation link;
- discover the server's `/v1/models` dynamically and expose every
returned model as speech-to-text in the model picker;
- use RAGFlow's existing default provider icon fallback instead of
referencing a missing `funasr` asset;
- list FunASR in the supported-provider documentation;
- add focused backend and frontend regression tests.

### Validation

- focused backend pytest suite -> `7 passed`
- real CPU `funasr-server` + RAGFlow provider smoke test -> discovered
`fun-asr-nano`, `sensevoice`, and `paraformer`; transcribed a real WAV
as `我现在在录一段测试音频` (`10` tokens, `0.504s`)
- `ruff check` and `ruff format --check` on the changed Python files
- `python3 -m py_compile` on the provider and its test
- JSON parse and a semantic assertion for exactly one enabled FunASR
`SPEECH2TEXT` factory
- focused frontend Jest test -> `2 passed`
- ESLint and Prettier on all changed TypeScript files
- `npm run build` -> production build succeeded (`14,181` modules
transformed)
- `git diff --check`

### Deployment

Run FunASR separately and point the RAGFlow provider at it:

```bash
pip install funasr
funasr-server --device cuda --model sensevoice
```

The API key remains optional because the stock local server does not
require authentication. A key can still be supplied when the endpoint is
protected by a gateway.

---------

Signed-off-by: LauraGPT <LauraGPT@users.noreply.github.com>
Co-authored-by: LauraGPT <LauraGPT@users.noreply.github.com>
2026-07-15 19:02:05 +08:00

51 lines
1.3 KiB
TypeScript

import {
ApiIcon,
LogOutIcon,
ModelProviderIcon,
PasswordIcon,
ProfileIcon,
TeamIcon,
} from '@/assets/icon/next-icon';
import { IconFont } from '@/components/icon-font';
import { LLMFactory } from '@/constants/llm';
import { UserSettingRouteKey } from '@/constants/setting';
import { MonitorOutlined } from '@ant-design/icons';
export const UserSettingIconMap = {
[UserSettingRouteKey.Profile]: <ProfileIcon />,
[UserSettingRouteKey.Password]: <PasswordIcon />,
[UserSettingRouteKey.Model]: <ModelProviderIcon />,
[UserSettingRouteKey.System]: <MonitorOutlined style={{ fontSize: 24 }} />,
[UserSettingRouteKey.Team]: <TeamIcon />,
[UserSettingRouteKey.Logout]: <LogOutIcon />,
[UserSettingRouteKey.Api]: <ApiIcon />,
[UserSettingRouteKey.MCP]: (
<IconFont name="mcp" className="size-6"></IconFont>
),
};
export * from '@/constants/setting';
export const LocalLlmFactories = [
LLMFactory.Ollama,
LLMFactory.Xinference,
LLMFactory.LocalAI,
LLMFactory.LMStudio,
LLMFactory.OpenAiAPICompatible,
LLMFactory.TogetherAI,
LLMFactory.Replicate,
LLMFactory.OpenRouter,
LLMFactory.HuggingFace,
LLMFactory.GPUStack,
LLMFactory.ModelScope,
LLMFactory.VLLM,
LLMFactory.RAGcon,
LLMFactory.FunASR,
];
export enum TenantRole {
Owner = 'owner',
Invite = 'invite',
Normal = 'normal',
}