Update app.py

app.py

@@ -1,16 +1,33 @@
-from fastapi import FastAPI
-from langchain_community.llms import Ollama
+from fastapi import FastAPI, HTTPException
+import requests
 
 app = FastAPI()
 
-# Initialize the Ollama model
-llm = Ollama(model="tinyllama")
+# Ollama internal URL (running locally in the container)
+OLLAMA_BASE_URL = "http://localhost:11434"
+
+# Proxy endpoint to Ollama's API
+@app.get("/api/{path:path}")
+async def ollama_proxy(path: str, query: str = None):
+    url = f"{OLLAMA_BASE_URL}/api/{path}"
+    params = {"query": query} if query else {}
+    try:
+        response = requests.get(url, params=params)
+        response.raise_for_status()
+        return response.json()
+    except requests.exceptions.RequestException as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.post("/api/{path:path}")
+async def ollama_proxy_post(path: str, body: dict):
+    url = f"{OLLAMA_BASE_URL}/api/{path}"
+    try:
+        response = requests.post(url, json=body)
+        response.raise_for_status()
+        return response.json()
+    except requests.exceptions.RequestException as e:
+        raise HTTPException(status_code=500, detail=str(e))
 
 @app.get("/")
 async def root():
-    return {"message": "Ollama is running on Hugging Face Spaces!"}
-
-@app.get("/chat")
-async def chat(query: str):
-    response = llm.invoke(query)
-    return {"response": response}
+    return {"message": "Ollama running on Hugging Face Spaces! use the space url"}