Support OpenAI gpt-4o and gpt-4o-mini for img2text (#4300)

### What problem does this PR solve?

OpenAI has deprecated the gpt-4-vision-preview model. This PR adds
support for the newer gpt-4o and gpt-4o-mini models in the img2text
feature.


![image](https://github.com/user-attachments/assets/6dddf2dc-1b9e-4e94-bf07-6bf77d39122b)

This PR add addtional 4o/4o-mini entry for img2text besides original
ones. Utilized [alias](https://platform.openai.com/docs/models#gpt-4o)
model names (e.g., gpt-4o-2024-08-06) because the database schema uses
the model name as the primary key.



- [x] Other (please describe): model update

conf/llm_factories.json

@@ -73,9 +73,15 @@
                     "model_type": "chat"
                 },
                 {
-                    "llm_name": "gpt-4-vision-preview",
+                    "llm_name": "gpt-4o-2024-08-06",
                     "tags": "LLM,CHAT,IMAGE2TEXT",
-                    "max_tokens": 765,
+                    "max_tokens": 128000,
+                    "model_type": "image2text"
+                },
+                 {
+                    "llm_name": "gpt-4o-mini-2024-07-18",
+                    "tags": "LLM,CHAT,IMAGE2TEXT",
+                    "max_tokens": 128000,
                     "model_type": "image2text"
                 },
                 {