[Frontend] Multimodal support in offline chat (#8098)

This commit is contained in:
Cyrus Leung
2024-09-04 05:22:17 +00:00
committed by GitHub
parent 2be8ec6e71
commit 855c262a6b
8 changed files with 356 additions and 112 deletions
+10
View File
@@ -120,6 +120,16 @@ async def async_fetch_audio(
return librosa.load(BytesIO(audio_bytes), sr=None)
def get_and_parse_audio(audio_url: str) -> MultiModalDataDict:
audio, sr = fetch_audio(audio_url)
return {"audio": (audio, sr)}
def get_and_parse_image(image_url: str) -> MultiModalDataDict:
image = fetch_image(image_url)
return {"image": image}
async def async_get_and_parse_audio(audio_url: str) -> MultiModalDataDict:
audio, sr = await async_fetch_audio(audio_url)
return {"audio": (audio, sr)}