Upload app.py

app.py

@@ -6,6 +6,47 @@ import h5py
 from io import BytesIO
 
 
+faq_content="""
+# Frequently Asked Questions (FAQs)
+
+Technically I am writing this before anyone but me has used the tool, so no one has asked questions yet.  But if they did, here are the questions I think they might ask:
+
+## Does input order matter?
+
+No
+
+## Should I use underscores in the input tags?
+
+It doesn't matter.  The application handles tags either way.
+
+## Why are some valid tags marked as "unseen", and why don't some artists ever get returned?
+
+Some data is excluded from consideration if it did not occur frequently enough in the sample from which the application makes its calculations.
+If an artist or tag is too infrequent, we might not think we have enough data to make predictions about it.
+
+## Are there any special tags?
+
+Yes.  We normalized the favorite counts of each image to a range of 0-9, with 0 being the lowest favcount, and 9 being the highest.
+You can include any of these special tags: "score:0", "score:1", "score:2", "score:3", "score:4", "score:5", "score:6", "score:7", "score:8", "score:9"
+in your list to bias the output toward artists with higher or lower scoring images.
+
+## Are there any other special tricks?
+
+Yes.  If you want to more strongly bias the artist output toward a specific tag, you can just list it multiple times.  
+So for example, the query "red fox, red fox, red fox, score:7" will yield a list of artists who are more strongly associated with the tag "red fox"
+than the query "red fox, score:7".
+
+## What calculation is this thing actually performing?
+
+Each artist is represented by a "pseudo-document" composed of all the tags from their uploaded images, treating these tags similarly to words in a text document. 
+Similarly, when you input a set of tags, the system creates a pseudo-document for your query out of all the tags. 
+It then uses a technique called cosine similarity to compare your tags against each artist's collection, essentially finding which artist's tags are most "similar" to yours.
+This method helps identify artists whose work is closely aligned with the themes or elements you're interested in.
+For those curious about the underlying mechanics of comparing text-like data, we employ the TF-IDF (Term Frequency-Inverse Document Frequency) method, a standard approach in information retrieval. 
+You can read more about TF-IDF on its [Wikipedia page](https://en.wikipedia.org/wiki/Tf%E2%80%93idf).
+"""
+
+
 # Load the model and data once at startup
 with h5py.File('complete_artist_data.hdf5', 'r') as f:
     # Deserialize the vectorizer
@@ -48,7 +89,8 @@ iface = gr.Interface(
         gr.Textbox(label="Dynamic Prompts Format", info="For if you're using the Automatic1111 webui (https://github.com/AUTOMATIC1111/stable-diffusion-webui) with the Dynamic Prompts extension activated (https://github.com/adieyal/sd-dynamic-prompts) and want to try them all individually.") 
     ],
     title="Tagset Completer",
-    description="Enter a list of comma-separated e6 tags"
+    description="Enter a list of comma-separated e6 tags",
+    article=faq_content 
 )
 
 iface.launch()