Refa: ollama keep alive issue. (#8216)

### What problem does this PR solve?

#8122

### Type of change

- [x] Refactoring

rag/llm/chat_model.py

         ctx_size = self._calculate_dynamic_ctx(history)
 
         gen_conf["num_ctx"] = ctx_size
-        response = self.client.chat(model=self.model_name, messages=history, options=gen_conf)
+        response = self.client.chat(model=self.model_name, messages=history, options=gen_conf, keep_alive=-1)
         ans = response["message"]["content"].strip()
         token_count = response.get("eval_count", 0) + response.get("prompt_eval_count", 0)
         return ans, token_count
 
             ans = ""
             try:
-                response = self.client.chat(model=self.model_name, messages=history, stream=True, options=options)
+                response = self.client.chat(model=self.model_name, messages=history, stream=True, options=options, keep_alive=-1)
                 for resp in response:
                     if resp["done"]:
                         token_count = resp.get("prompt_eval_count", 0) + resp.get("eval_count", 0)

rag/llm/cv_model.py

             response = self.client.chat(
                 model=self.model_name,
                 messages=history,
-                options=options
+                options=options,
+                keep_alive=-1
             )
 
             ans = response["message"]["content"].strip()
                 model=self.model_name,
                 messages=history,
                 stream=True,
-                options=options
+                options=options,
+                keep_alive=-1
             )
             for resp in response:
                 if resp["done"]: