Update README.md to clarify some of the most important points

README.md

@@ -7,4 +7,12 @@ sdk: docker
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+The following code allows you to search images by text and image prompts. The dataset used is COCO, but a smaller version, given that the original set of images was too big,
+and I did not want to do so in this repository. You can adapt this code to your own image dataset. The Dockerfile allows you to build and run your own image/container. 
+
+# NOTE:
+
+Given that the dataset is quite small, some prompts can produce inaccurate results. For example, if you search for "Apple", you will find images of apples, but it is possible
+that after a few images, the system will start to struggle. Also, I have chosen a selector to set the number of provided results, with a maximum of 50 images. Despite that, I
+agree that a value bigger than 20 can be too much. Nevertheless, this is just a demo and you can get the idea of how it works. The real interest of this space is to be able
+to replicate an image search engine like this.