diff --git a/src/clients/ollama_client.py b/src/clients/ollama_client.py
index b5169aa..aaa4457 100644
--- a/src/clients/ollama_client.py
+++ b/src/clients/ollama_client.py
@@ -249,7 +249,8 @@ class OllamaClient:
         self,
         prompt: str,
         model: Optional[str] = None,
-        stream: bool = False
+        stream: bool = False,
+        temperature: Optional[float] = None
     ) -> Optional[str]:
         """
         Generate text completion (for non-embedding use cases).
@@ -258,12 +259,15 @@ class OllamaClient:
             prompt: Input prompt
             model: Model name (defaults to self.model)
             stream: Enable streaming response
+            temperature: Sampling temperature (0.0 = deterministic, higher = more creative)
+                        None uses model default (~0.7 for mistral-nemo)
 
         Returns:
             Generated text or None on failure
 
-        Note: This is primarily for debugging/testing. Use specialized
-        LLM services for production text generation.
+        Note: Use temperature=0.0 for deterministic outputs like JSON parsing,
+        ranking, and factual extraction. Use higher values (0.3-0.7) for
+        creative content generation.
         """
         try:
             payload = {
@@ -272,6 +276,10 @@ class OllamaClient:
                 "stream": stream
             }
 
+            # Add temperature to options if specified
+            if temperature is not None:
+                payload["options"] = {"temperature": temperature}
+
             response = await self.client.post(
                 self.generate_url,
                 json=payload