Update main.py

main.py

@@ -1,11 +1,46 @@
-from fastapi import FastAPI
+import asyncio
+import aiohttp
+from fastapi import FastAPI, BackgroundTasks
 from pydantic import BaseModel
-from huggingface_hub import InferenceClient
-from fastapi.responses import StreamingResponse
+from datetime import datetime
+import logging
+
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
 
 app = FastAPI()
 
-client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
+# The URL of the API we want to call
+API_URL = "https://b917-160-179-178-105.ngrok-free.app/test-ai-call"
+
+async def call_api():
+    async with aiohttp.ClientSession() as session:
+        while True:
+            try:
+                async with session.get(API_URL) as response:
+                    if response.status == 200:
+                        data = await response.json()
+                        logger.info(f"API Response: {data}")
+                    else:
+                        logger.error(f"API call failed with status code: {response.status}")
+            except Exception as e:
+                logger.error(f"Error calling API: {e}")
+            
+            # Wait for 10 seconds before the next call
+            await asyncio.sleep(10)
+
+@app.on_event("startup")
+async def startup_event():
+    # Start the background task when the app starts
+    asyncio.create_task(call_api())
+
+@app.get("/")
+async def root():
+    return {"message": "API caller is running"}
+
+# You can keep your existing endpoints if needed
+# For example:
 
 class Item(BaseModel):
     prompt: str
@@ -16,43 +51,9 @@ class Item(BaseModel):
     top_p: float = 0.15
     repetition_penalty: float = 1.0
 
-def format_prompt(message, history):
-    prompt = "<s>"
-    for user_prompt, bot_response in history:
-        prompt += f"[INST] {user_prompt} [/INST]"
-        prompt += f" {bot_response}</s> "
-    prompt += f"[INST] {message} [/INST]"
-    return prompt
-
-async def generate_stream(item: Item):
-    try:
-        temperature = max(float(item.temperature), 1e-2)
-        top_p = float(item.top_p)
-
-        generate_kwargs = dict(
-            temperature=temperature,
-            max_new_tokens=item.max_new_tokens,
-            top_p=top_p,
-            repetition_penalty=item.repetition_penalty,
-            do_sample=True,
-            seed=42,
-        )
-
-        formatted_prompt = format_prompt(f"{item.system_prompt}, {item.prompt}", item.history)
-        stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-
-        for response in stream:
-            yield response.token.text
-    except Exception as e:
-        print(f"Error in generate_stream: {e}")
-    finally:
-        if 'stream' in locals():
-            stream.close()
-
 @app.post("/generate/")
 async def generate_text(item: Item):
-    try:
-        return StreamingResponse(generate_stream(item), media_type="text/plain")
-    except Exception as e:
-        print(f"Error in generate_text: {e}")
-        return {"error": str(e)}
+    # Your existing generate_text logic here
+    return {"message": "Text generation endpoint"}
+
+# Add any other endpoints or functionality you need