update

app/app.py

@@ -8,6 +8,7 @@ from app.db import User, create_db_and_tables
 from app.schemas import UserCreate, UserRead, UserUpdate
 from app.users import auth_backend, current_active_user, fastapi_users
 from dotenv import load_dotenv
+from tenacity import retry, stop_after_attempt, wait_exponential
 
 import examples as chatbot_examples
 
@@ -244,6 +245,7 @@ async def authenticated_route(user: User = Depends(current_active_user)):
     return {"message": f"Hello {user.email}!"}
 
 
+@retry(stop=stop_after_attempt(5), wait=wait_exponential(multiplier=1, min=2, max=30))
 @app.post("/v1/embeddings")
 async def openai_api_embeddings_passthrough(
     request: Request,
@@ -273,6 +275,7 @@ async def openai_api_embeddings_passthrough(
     return response.json()
 
 
+@retry(stop=stop_after_attempt(5), wait=wait_exponential(multiplier=1, min=2, max=30))
 @app.post("/v1/engines/text-embedding-ada-002/embeddings")
 async def openai_api_embeddings_passthrough(
     request: Request,
@@ -302,6 +305,7 @@ async def openai_api_embeddings_passthrough(
     return response.json()
 
 
+@retry(stop=stop_after_attempt(5), wait=wait_exponential(multiplier=1, min=2, max=30))
 @app.post("/v1/completions")
 async def openai_api_completions_passthrough(
     request: Request,
@@ -331,6 +335,7 @@ async def openai_api_completions_passthrough(
     return response.json()
 
 
+@retry(stop=stop_after_attempt(5), wait=wait_exponential(multiplier=1, min=2, max=30))
 @app.post("/v1/chat/completions")
 async def openai_api_chat_completions_passthrough(
     request: Request,
@@ -344,8 +349,8 @@ async def openai_api_chat_completions_passthrough(
     request_headers = request.headers
     openai_api_key = os.getenv("OPENAI_API_KEY")
 
-    if "gpt-4" in request_data["model"]:
-        request_data["model"] = "gpt-3.5-turbo"
+    # if "gpt-4" in request_data["model"]:
+    #     request_data["model"] = "gpt-3.5-turbo"
 
     # Forward the request to the OpenAI API
     async with AsyncClient() as client:
@@ -363,6 +368,66 @@ async def openai_api_chat_completions_passthrough(
     return response.json()
 
 
+@retry(stop=stop_after_attempt(5), wait=wait_exponential(multiplier=1, min=2, max=30))
+@app.post("/v1/images/generations")
+async def openai_api_chat_completions_passthrough(
+    request: Request,
+    user: User = Depends(fastapi_users.current_user()),
+):
+    if not user:
+        raise HTTPException(status_code=401, detail="Unauthorized")
+
+    # Get the request data and headers
+    request_data = await request.json()
+    request_headers = request.headers
+    openai_api_key = os.getenv("OPENAI_API_KEY")
+
+    # Forward the request to the OpenAI API
+    async with AsyncClient() as client:
+        response = await client.post(
+            "https://api.openai.com/v1/images/generations",
+            json=request_data,
+            headers={
+                "Content-Type": request_headers.get("Content-Type"),
+                "Authorization": f"Bearer {openai_api_key}",
+            },
+            timeout=120.0,
+        )
+
+    # Return the OpenAI API response
+    return response.json()
+
+
+@retry(stop=stop_after_attempt(5), wait=wait_exponential(multiplier=1, min=2, max=30))
+@app.post("/v1/audio/speech")
+async def openai_api_audio_speech_passthrough(
+    request: Request,
+    user: User = Depends(fastapi_users.current_user()),
+):
+    if not user:
+        raise HTTPException(status_code=401, detail="Unauthorized")
+
+    # Get the request data and headers
+    request_data = await request.json()
+    request_headers = request.headers
+    openai_api_key = os.getenv("OPENAI_API_KEY")
+
+    # Forward the request to the OpenAI API
+    async with AsyncClient() as client:
+        response = await client.post(
+            "https://api.openai.com/v1/audio/speech",
+            json=request_data,
+            headers={
+                "Content-Type": request_headers.get("Content-Type"),
+                "Authorization": f"Bearer {openai_api_key}",
+            },
+            timeout=120.0,
+        )
+
+    # Return the OpenAI API response
+    return response.json()
+
+
 @app.on_event("startup")
 async def on_startup():
     # Not needed if you setup a migration system like Alembic

requirements.txt

@@ -8,3 +8,4 @@ Requests
 sqlalchemy[asyncio]
 uvicorn
 asyncpg
+tenacity