refac: audio

backend/apps/audio/main.py

@@ -10,9 +10,18 @@ from fastapi import (
     File,
     Form,
 )
+
+from fastapi.responses import StreamingResponse, JSONResponse, FileResponse
+
 from fastapi.middleware.cors import CORSMiddleware
 from faster_whisper import WhisperModel
 
+import requests
+import hashlib
+from pathlib import Path
+import json
+
+
 from constants import ERROR_MESSAGES
 from utils.utils import (
     decode_token,
@@ -30,6 +39,8 @@ from config import (
     WHISPER_MODEL_DIR,
     WHISPER_MODEL_AUTO_UPDATE,
     DEVICE_TYPE,
+    OPENAI_API_BASE_URL,
+    OPENAI_API_KEY,
 )
 
 log = logging.getLogger(__name__)
@@ -44,12 +55,78 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
+
+app.state.OPENAI_API_BASE_URL = OPENAI_API_BASE_URL
+app.state.OPENAI_API_KEY = OPENAI_API_KEY
+
 # setting device type for whisper model
 whisper_device_type = DEVICE_TYPE if DEVICE_TYPE and DEVICE_TYPE == "cuda" else "cpu"
 log.info(f"whisper_device_type: {whisper_device_type}")
 
+SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/")
+SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
 
-@app.post("/transcribe")
+
+@app.post("/speech")
+async def speech(request: Request, user=Depends(get_verified_user)):
+    idx = None
+    try:
+        body = await request.body()
+        name = hashlib.sha256(body).hexdigest()
+
+        file_path = SPEECH_CACHE_DIR.joinpath(f"{name}.mp3")
+        file_body_path = SPEECH_CACHE_DIR.joinpath(f"{name}.json")
+
+        # Check if the file already exists in the cache
+        if file_path.is_file():
+            return FileResponse(file_path)
+
+        headers = {}
+        headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEY}"
+        headers["Content-Type"] = "application/json"
+
+        r = None
+        try:
+            r = requests.post(
+                url=f"{app.state.OPENAI_API_BASE_URL}/audio/speech",
+                data=body,
+                headers=headers,
+                stream=True,
+            )
+
+            r.raise_for_status()
+
+            # Save the streaming content to a file
+            with open(file_path, "wb") as f:
+                for chunk in r.iter_content(chunk_size=8192):
+                    f.write(chunk)
+
+            with open(file_body_path, "w") as f:
+                json.dump(json.loads(body.decode("utf-8")), f)
+
+            # Return the saved file
+            return FileResponse(file_path)
+
+        except Exception as e:
+            log.exception(e)
+            error_detail = "Open WebUI: Server Connection Error"
+            if r is not None:
+                try:
+                    res = r.json()
+                    if "error" in res:
+                        error_detail = f"External: {res['error']}"
+                except:
+                    error_detail = f"External: {e}"
+
+            raise HTTPException(
+                status_code=r.status_code if r else 500, detail=error_detail
+            )
+
+    except ValueError:
+        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.OPENAI_NOT_FOUND)
+
+
+@app.post("/transcriptions")
 def transcribe(
     file: UploadFile = File(...),
     user=Depends(get_current_user),