Update app.py

app.py

@@ -1,3 +1,5 @@
+
+
 from fastapi import FastAPI
 from pydantic import BaseModel
 from huggingface_hub import InferenceClient
@@ -11,9 +13,12 @@ app = FastAPI()
 #model_name = "serkanarslan/mistral-7b-mini-ft"
 # Choose a smaller model for free-tier
 #model_name = "microsoft/phi-2"
-model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"  # You can switch to Phi-2, OpenChat, etc.
+#model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"  # You can switch to Phi-2, OpenChat, etc.
+
 
-client = InferenceClient(model_name)
+# ✅ Use the full Hugging Face Inference API URL
+HF_API_URL = "https://api-inference.huggingface.co/models/TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+client = InferenceClient(HF_API_URL)
 
 # Define request format
 class ChatRequest(BaseModel):
@@ -21,11 +26,13 @@ class ChatRequest(BaseModel):
 
 @app.post("/chat")
 async def chat(request: ChatRequest):
-    # Send message to Hugging Face Inference API
-    response = client.text_generation(request.message, max_new_tokens=100)
-    return {"response": response}
-
-
+    # ✅ Corrected function call with `model` argument
+    response = client.text_generation(
+        request.message, 
+        model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", 
+        max_new_tokens=100
+    )
+    return {"response": response}  # ✅ Removed extra quote