Fix

app.py

@@ -254,9 +254,9 @@ try:
                 st.markdown('$\\rightarrow$')
                 if i == len(steps) - 1:
                     # The final step
-                    st.markdown("Execute {} Interpreter".format(selected_language))
+                    st.markdown("{} Interpreter".format(selected_language.replace("Binder ", "")))
                 else:
-                    st.markdown("Prompt GPT3 Codex")
+                    st.markdown("GPT3 Codex")
             with st.spinner('...'):
                 time.sleep(1)
             with open("tmp_for_vis/{}_result_step_{}.txt".format(stamp, i), "r") as f:

resources/demo_description.md

@@ -1,8 +1,9 @@
 This is an interactive demo of Binder based on GPT3 Codex.
 You can input a question about the table (maybe requiring external knowledge/functionality), and a Binder program will be generated and executed to derive the output answer.
-For more details, check out our [website](https://lm-code-binder.github.io/).
+For more details, check out the project [website](https://lm-code-binder.github.io/).
 
 
-*Note:* 1) Codex has query limits for openai keys, thus it may be slow in generation/execution when (high) concurrent requests occur.
-2) This page is just for demonstration, so we generate fewer program for speeding up, please check the [paper](https://arxiv.org/abs/2210.02875) and [code](https://github.com/HKUNLP/Binder) on majority vote and weight bias better result.
-3) We are trying to make the demo faster and more robust, please let us know if you have any feedback!
+*Note:* 
+- Codex has query limits for openai keys, thus it may be slow in generation/execution when (high) concurrent requests occur. 
+- This page is just for demonstration, so we generate fewer program for speeding up, please check the [paper](https://arxiv.org/abs/2210.02875) and [code](https://github.com/HKUNLP/Binder) on majority vote and weight bias better result. 
+- We are trying to make the demo faster and more robust, please let us know if you have any feedback!