mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-12 20:15:26 +00:00
Alex
7da46c2bea
- Ship tiktoken's cl100k_base inside the package and build the encoding from it, so token counting never downloads anything. - Default EMBEDDINGS_CACHE_DIR to <data home>/models instead of FastEmbed's temp dir, and read tokenizer.json and repo metadata from that cache, so a model downloads once and survives reboots. - TTS_PROVIDER=none and STT_PROVIDER=none switch the speech features off: the endpoints return 404, audio files fail to ingest with a clear message, /api/config reports tts_available/stt_available, and the UI hides the Speak and microphone buttons. - Drop the Google Fonts Roboto import from the web UI. - prefetch-models fills the cache the app reads; verify-offline checks the packaged encoding. - Docs: new Air-Gapped Deployment guide, settings and cache notes.
28 lines
882 B
Python
28 lines
882 B
Python
from typing import Optional
|
|
|
|
from docsgpt.stt.base import BaseSTT
|
|
from docsgpt.stt.faster_whisper_stt import FasterWhisperSTT
|
|
from docsgpt.stt.openai_stt import OpenAISTT
|
|
|
|
#: STT_PROVIDER value that switches speech-to-text off.
|
|
DISABLED = "none"
|
|
|
|
|
|
class STTCreator:
|
|
stt_providers = {
|
|
"openai": OpenAISTT,
|
|
"faster_whisper": FasterWhisperSTT,
|
|
}
|
|
|
|
@staticmethod
|
|
def is_enabled(stt_type: Optional[str]) -> bool:
|
|
"""False when the provider is ``none`` or empty: speech-to-text is switched off."""
|
|
return (stt_type or "").strip().lower() not in ("", DISABLED)
|
|
|
|
@classmethod
|
|
def create_stt(cls, stt_type, *args, **kwargs) -> BaseSTT:
|
|
stt_class = cls.stt_providers.get(stt_type.lower())
|
|
if not stt_class:
|
|
raise ValueError(f"No stt class found for type {stt_type}")
|
|
return stt_class(*args, **kwargs)
|