Delete app_old.py

app_old.py

@@ -1,107 +0,0 @@
-import os
-import logging
-import json
-import httpx
-from fastapi import FastAPI, Request, HTTPException
-from fastapi.responses import StreamingResponse
-from fastapi.middleware.cors import CORSMiddleware
-
-# Configure logging
-logging.basicConfig(level=logging.INFO)
-logger = logging.getLogger(__name__)
-
-app = FastAPI()
-
-# Optional: Configure CORS if needed
-origins = [
-    # Add allowed origins if you implement a frontend later
-]
-
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=origins,  # Adjust as needed
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-# Load your API key from the environment (defaults to "change_me")
-API_KEY = os.environ.get("API_KEY", "change_me")
-logger.info(f"API key loaded: {API_KEY}")
-
-# Since Ollama is working with /api/generate, set this accordingly
-OLLAMA_SERVER_URL = "http://localhost:11434/api/generate"
-
-@app.post("/api/generate")
-async def generate(request: Request):
-    """Endpoint that generates text based on the prompt."""
-    try:
-        # 1. Parse the incoming request
-        body = await request.json()
-        logger.info(f"Received request body: {body}")
-
-        model = body.get("model", "hf.co/abanm/Dubs-Q8_0-GGUF:latest")  # Default model
-        prompt_text = body.get("prompt", "")
-        if not prompt_text:
-            logger.error("No prompt provided in the request body")
-            raise HTTPException(status_code=400, detail="No prompt provided")
-
-        # 2. Validate API key
-        auth_header = request.headers.get("Authorization")
-        logger.info(f"Received Authorization header: {auth_header}")
-
-        if not auth_header or not auth_header.startswith("Bearer "):
-            logger.error("Invalid or missing Authorization header")
-            raise HTTPException(status_code=401, detail="Missing or invalid Authorization header")
-
-        token = auth_header.split(" ")[1]
-        if token != API_KEY:
-            logger.error(f"Invalid API key: {token}")
-            raise HTTPException(status_code=401, detail="Invalid API key")
-
-        # 3. Prepare request payload
-        payload = {"model": model, "prompt": prompt_text}
-        logger.info(f"Sending payload to Ollama: {payload}")
-
-        # 4. Stream response from Ollama
-        async def stream_response():
-            try:
-                async with httpx.AsyncClient() as client:
-                    async with client.stream(
-                        "POST",
-                        OLLAMA_SERVER_URL,
-                        json=payload,
-                        headers={"Content-Type": "application/json"}
-                    ) as response:
-                        # If we get 4xx or 5xx, raise_for_status() triggers HTTPStatusError
-                        response.raise_for_status()
-
-                        # Stream out the content as it arrives
-                        async for chunk in response.aiter_text():
-                            yield chunk
-
-            except httpx.RequestError:
-                logger.exception("Request error while communicating with Ollama")
-                yield json.dumps({"error": "Unable to communicate with Ollama"})
-
-            except httpx.HTTPStatusError as exc:
-                # Avoid reading the body since it's a streaming response and is closed on error
-                logger.error(f"HTTP error from Ollama: {exc.response.status_code}")
-                yield json.dumps({"error": f"HTTP error: {exc.response.status_code}"})
-
-        return StreamingResponse(stream_response(), media_type="application/json")
-
-    except Exception:
-        logger.exception("Unhandled exception in /api/generate")
-        raise HTTPException(status_code=500, detail="Internal server error")
-
-@app.get("/health")
-async def health():
-    """Health check endpoint."""
-    logger.info("Health check endpoint called")
-    return {"status": "OK"}
-
-if __name__ == "__main__":
-    import uvicorn
-    logger.info("Starting server on http://0.0.0.0:7860")
-    uvicorn.run(app, host="0.0.0.0", port=7860)