fixed urls, added demo curl example at the bottom

app.py

@@ -71,6 +71,14 @@ def ollama_completion():
     }
 
 """
+curl -X POST http://localhost:8000/api/groq/generate -H "Content-Type: application/json" -d '{
+    "query": "How do I create a sphere in FURY?",
+    "llm": "llama3-70b-8192",
+    "knn": "3",
+    "stream": false
+  }'
+
+  
 curl -X POST http://localhost:8000/api/ollama/generate -H "Content-Type: application/json" -d '{
     "query": "How do I create a sphere in FURY?",
     "llm": "phi3",

utils.py

@@ -71,8 +71,8 @@ def db_output(embedding: list, knn: int) -> dict:
 
 
 def ollama_llm_output(question: str, db_knn: dict, llm: str, stream: bool) -> tuple[str, str]:
-    # URL_LLM = 'https://robinroy03-ollama-server-backend.hf.space'
-    URL_LLM = "http://localhost:11434"
+    URL_LLM = 'https://robinroy03-ollama-server-backend.hf.space'
+    # URL_LLM = "http://localhost:11434"
     prompt, context, references = prompt_generator(question, db_knn)
     obj = {
         "model": llm,