Add a better reference to the model and the date of the dataset to the description

app.py

@@ -293,15 +293,19 @@ def main():
         significand = round(significand, 1 if (n_digits % 3 == 1) else None)
         quantity = str(significand) + postfix
 
+        # split the (huggingface) model name and get the link
+        model_publisher, model_human_name = model_name.split("/")
+        model_link = f"https://huggingface.co/{model_publisher}/{model_human_name}"
+
         gr.Markdown("# abstracts-index")
         gr.Markdown(
             f"Explore {quantity} academic publications selected from the "
-            "[OpenAlex](https://openalex.org) dataset. This project is an index of the "
-            "embeddings generated from their titles and abstracts. The embeddings were "
-            f"generated using the {model_name} model provided by the "
-            "[sentence-transformers](https://www.sbert.net/) module, and the index was "
-            "built using the [faiss](https://github.com/facebookresearch/faiss) "
-            "module. The build scripts and more information available at the main repo "
+            "[OpenAlex](https://openalex.org) dataset (as of January 1st, 2025). This "
+            "project is an index of the embeddings generated from their titles and "
+            "abstracts. The embeddings were generated using the "
+            f"[{model_human_name}]({model_link}) model, and the index was built using "
+            "the [faiss](https://github.com/facebookresearch/faiss) module. The build "
+            "scripts and more information available at the main repo "
             "[abstracts-search](https://github.com/colonelwatch/abstracts-search) on "
             "Github."
         )