Update HF space

app.py

@@ -5,10 +5,8 @@ from pipelines.keyphrase_generation_pipeline import KeyphraseGenerationPipeline
 import orjson
 
 from annotated_text.util import get_annotated_html
-from st_aggrid import AgGrid, GridOptionsBuilder, GridUpdateMode
 import re
 import string
-import numpy as np
 
 
 @st.cache(allow_output_mutation=True, show_spinner=False)
@@ -21,28 +19,13 @@ def load_pipeline(chosen_model):
 
 def extract_keyphrases():
     st.session_state.keyphrases = pipe(st.session_state.input_text)
-    st.session_state.data_frame = pd.concat(
-        [
-            st.session_state.data_frame,
-            pd.DataFrame(
-                data=[
-                    np.concatenate(
-                        (
-                            [
-                                st.session_state.chosen_model,
-                                st.session_state.input_text,
-                            ],
-                            st.session_state.keyphrases,
-                        )
-                    )
-                ],
-                columns=["model", "text"]
-                + [str(i) for i in range(len(st.session_state.keyphrases))],
-            ),
-        ],
-        ignore_index=True,
-        axis=0,
-    ).fillna("")
+    st.session_state.history[f"run_{st.session_state.current_run_id}"] = {
+        "run_id": st.session_state.current_run_id,
+        "model": st.session_state.chosen_model,
+        "text": st.session_state.input_text,
+        "keyphrases": st.session_state.keyphrases,
+    }
+    st.session_state.current_run_id += 1
 
 
 def get_annotated_text(text, keyphrases):
@@ -90,51 +73,36 @@ def get_annotated_text(text, keyphrases):
     return result
 
 
-def rerender_output(layout):
-    layout.write("⚙️ Output")
-    if (
-        len(st.session_state.keyphrases) > 0
-        and len(st.session_state.selected_rows) == 0
-    ):
-        text, keyphrases = st.session_state.input_text, st.session_state.keyphrases
-    else:
-        text, keyphrases = (
-            st.session_state.selected_rows["text"].values[0],
-            [
-                keyphrase
-                for keyphrase in st.session_state.selected_rows.loc[
-                    :,
-                    st.session_state.selected_rows.columns.difference(
-                        ["model", "text"]
-                    ),
-                ]
-                .astype(str)
-                .values.tolist()[0]
-                if keyphrase != ""
-            ],
-        )
+def render_output(layout, runs, reverse=False, multi_select=False):
+    runs = list(runs.values())[::-1] if reverse else list(runs.values())
+    for run in runs:
+        layout.markdown(f"**⚙️ Output run {run.get('run_id')}**")
 
-    result = get_annotated_text(text, list(keyphrases))
+        layout.markdown(f"**Model**: {run.get('model')}")
+        result = get_annotated_text(run.get("text"), list(run.get("keyphrases")))
 
-    layout.markdown(
-        get_annotated_html(*result),
-        unsafe_allow_html=True,
-    )
-    if "generation" in st.session_state.chosen_model:
-        abstractive_keyphrases = [
-            keyphrase
-            for keyphrase in keyphrases
-            if keyphrase.lower() not in text.lower()
-        ]
-        layout.write(", ".join(abstractive_keyphrases))
+        layout.markdown(
+            get_annotated_html(*result),
+            unsafe_allow_html=True,
+        )
+        if "generation" in st.session_state.chosen_model:
+            abstractive_keyphrases = [
+                keyphrase
+                for keyphrase in run.get("keyphrases")
+                if keyphrase.lower() not in run.get("text").lower()
+            ]
+            layout.write(", ".join(abstractive_keyphrases))
+        layout.markdown("---")
 
 
 if "config" not in st.session_state:
     with open("config.json", "r") as f:
         content = f.read()
     st.session_state.config = orjson.loads(content)
-    st.session_state.data_frame = pd.DataFrame(columns=["model"])
+    st.session_state.history = {}
     st.session_state.keyphrases = []
+    st.session_state.current_run_id = 1
+    st.session_state.chosen_model = st.session_state.config.get("models")[0]
 
 if "select_rows" not in st.session_state:
     st.session_state.selected_rows = []
@@ -177,42 +145,43 @@ Do you want to see some magic 🧙‍♂️? Try it out yourself! 👇
 
 st.write(description)
 
-with st.form("test"):
-    chosen_model = st.selectbox(
-        "Choose your model:",
-        st.session_state.config.get("models"),
+with st.form("keyphrase-extraction-form"):
+    selectbox_container, _ = st.columns(2)
+
+    st.session_state.chosen_model = selectbox_container.selectbox(
+        "Choose your model:", st.session_state.config.get("models")
     )
-    st.session_state.chosen_model = chosen_model
+
     st.markdown(
-        f"For more information about the chosen model, please be sure to check it out the [🤗 Model Card](https://huggingface.co/DeDeckerThomas/{chosen_model})."
+        f"For more information about the chosen model, please be sure to check out the [🤗 Model Card](https://huggingface.co/DeDeckerThomas/{st.session_state.chosen_model})."
     )
 
-    with st.spinner("Loading pipeline..."):
-        pipe = load_pipeline(
-            f"{st.session_state.config.get('model_author')}/{st.session_state.chosen_model}"
-        )
-
     st.session_state.input_text = st.text_area(
-        "✍ Input", st.session_state.config.get("example_text"), height=300
+        "✍ Input", st.session_state.config.get("example_text"), height=250
     ).replace("\n", " ")
 
     with st.spinner("Extracting keyphrases..."):
-        pressed = st.form_submit_button("Extract", on_click=extract_keyphrases)
+        pressed = st.form_submit_button("Extract")
+
+if pressed:
+    with st.spinner("Loading pipeline..."):
+        pipe = load_pipeline(
+            f"{st.session_state.config.get('model_author')}/{st.session_state.chosen_model}"
+        )
+    with st.spinner("Extracting keyphrases"):
+        extract_keyphrases()
 
-if len(st.session_state.selected_rows) > 0 or len(st.session_state.keyphrases) > 0:
-    rerender_output(st)
+options = st.multiselect(
+    "Specify runs you want to see",
+    st.session_state.history.keys(),
+    format_func=lambda run_id: f"Run {run_id.split('_')[1]}",
+)
 
-if len(st.session_state.data_frame.columns) > 0:
-    st.subheader("📜 History")
-    builder = GridOptionsBuilder.from_dataframe(
-        st.session_state.data_frame, sortable=False
-    )
-    builder.configure_selection(selection_mode="single", use_checkbox=True)
-    builder.configure_column("text", hide=True)
-    go = builder.build()
-    data = AgGrid(
-        st.session_state.data_frame,
-        gridOptions=go,
-        update_mode=GridUpdateMode.SELECTION_CHANGED,
-    )
-    st.session_state.selected_rows = pd.DataFrame(data["selected_rows"])
+if len(st.session_state.history.keys()) > 0:
+    if options:
+        render_output(
+            st,
+            {key: st.session_state.history[key] for key in options},
+        )
+    else:
+        render_output(st, st.session_state.history, reverse=True)

css/style.css

@@ -1,5 +1,24 @@
+/*
+
+  Fonts
+  
+*/
 @import url('https://fonts.googleapis.com/css2?family=Roboto:ital,wght@0,100;0,300;0,400;0,500;0,700;0,900;1,100;1,300;1,400;1,500;1,700;1,900&display=swap');
 
+/*
+
+  HTML body
+  
+*/
 body {
   font-family: 'Roboto', 'Source Sans Pro', sans-serif;
 }
+
+/*
+
+  Component: Extract Button
+
+*/
+.css-1cpxqw2{
+  float: right;
+}

requirements.txt

@@ -3,4 +3,3 @@ transformers[torch]==4.17.0
 pandas==1.4.1
 numpy==1.22.3
 st-annotated-text==3.0.0
-streamlit-aggrid==0.2.3.post2