Upload folder using huggingface_hub

.gitattributes

@@ -10,32 +10,3 @@ data/raw/astro_physpace/astro-ph_6000_last_updated_date_desc_20240715_134752.jso
 data/raw/evo_bio/q-bio.PE_10000_last_updated_date_desc_20240723_163228.jsonl filter=lfs diff=lfs merge=lfs -text
 data/raw/fluid_dyn/physics.flu-dyn_10000_last_updated_date_desc_20240723_155932.jsonl filter=lfs diff=lfs merge=lfs -text
 data/raw/phy_strat/stratified_arxiv_data_combined_astro_physpace.jsonl filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_json_QdeCg2hM_20240801_034716/logs/log.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_json_QdeCg2hM_20240801_034716/predicted_responses.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_json_QdeCg2hM_20240801_034716/predictions.json filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_json_QdeCg2hM_20240801_034716/prompts.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_json_bsnlEItA_20240725_031746/logs/log.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_json_bsnlEItA_20240725_031746/prompts.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_json_combined_preds_across_runs_astrophyspace/new_random_json_NPhqPpXy_20240716_040707/logs/log.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_json_combined_preds_across_runs_astrophyspace/new_random_json_lWUgWudS_20240717_164223/logs/log.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_json_combined_preds_across_runs_astrophyspace/new_random_json_lWUgWudS_20240717_164223/prompts.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_json_combined_preds_across_runs_astrophyspace/predictions.json filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_json_g1PPhwYp_20240725_031815/logs/log.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_json_g1PPhwYp_20240725_031815/prompts.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_Y7zNEy1v_20240725_031826/duped_predictions.json filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_Y7zNEy1v_20240725_031826/logs/log.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_Y7zNEy1v_20240725_031826/predicted_responses.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_Y7zNEy1v_20240725_031826/prompts.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_b1AKFDbd_20240725_031800/duped_predictions.json filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_b1AKFDbd_20240725_031800/logs/log.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_b1AKFDbd_20240725_031800/predicted_responses.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_b1AKFDbd_20240725_031800/prompts.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_combined_preds_across_runs_astrophyspace/new_random_readable_RLKNTmuL_20240716_141932/prompts.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_combined_preds_across_runs_astrophyspace/new_random_readable_dpjyPtQ1_20240717_161329/duped_predictions.json filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_combined_preds_across_runs_astrophyspace/new_random_readable_dpjyPtQ1_20240717_161329/logs/log.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_combined_preds_across_runs_astrophyspace/new_random_readable_dpjyPtQ1_20240717_161329/predicted_responses.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_combined_preds_across_runs_astrophyspace/new_random_readable_dpjyPtQ1_20240717_161329/prompts.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_combined_preds_across_runs_astrophyspace/predictions.json filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_ffDyTFzv_20240801_034725/logs/log.txt filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_ffDyTFzv_20240801_034725/predictions.json filter=lfs diff=lfs merge=lfs -text
-data/results/new_random_readable_ffDyTFzv_20240801_034725/prompts.txt filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,10 @@
+import sys
+import os
+
+sys.stdout.reconfigure(line_buffering=True)
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+
+from scripts.run_db_interface import launch
+
+if __name__ == "__main__":
+    launch()

assets/graph-prev.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:263c60b4a26b6d32e96ccdacd92a4edf9787581f5dee9b9eb182d8b1502044c0
-size 7540171
+oid sha256:ba3ff1c5a2ec16b31177a9662f6ac1cbb8a13a52d2eec1e1cdb162145d627028
+size 132

assets/graph.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28392771ef7d72e204adf2273cadc2728a6f89f9e54ab71c162bf387d596faa4
-size 21734557
+oid sha256:04b1b37adf5de681bf53060f35c0be2c6112b4b2b10deb08b991c166596eb3e6
+size 133

assets/kg4s-demo.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3faa731c6f5cb5bc694a56c80690acc0486356fd51bbe5163b4feff50d316f7
-size 90726535
+oid sha256:6dfd2fbff562ce37b5b3ab9ed65387a801c079733425ca4ffec102299904f83a
+size 133

assets/kg4s-graph.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8d4980ac07ef08ea940fbc6ddb5c0fed460e385074be6eae1f069a9c7c4844
-size 27332577
+oid sha256:e542acbdac64b580143bfa2e726f7d7f22c86c33e86af4004a88a29fd954a042
+size 133

assets/kg4s-preview.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48078c4726cbea8dae008016bcafff51c40c16cd4d7914f8e01a16bac4102901
-size 8467193
+oid sha256:323e09894a658a0b450db58454e451e2736b8ee1f090986ae1a51904b8a448d4
+size 132

run_tool.sh

@@ -16,4 +16,4 @@ module load gcc/10.3.0 cuda/12.1.1 python/3.11.7
 cd /mnt/home/adas1/projects/knowledge-graph/kg-for-science
 conda init
 conda activate kg4s
-python scripts/run_db_interface.py
+python -u app.py

scripts/run_db_interface.py

@@ -7,13 +7,14 @@ import plotly.graph_objects as go
 import re
 import sys
 import sqlite3
+import time
 
 from plotly.subplots import make_subplots
 from tabulate import tabulate
 
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-from create_db import ArxivDatabase
 from config import DEFAULT_TABLES_DIR, DEFAULT_INTERFACE_MODEL_ID, canned_queries
+from scripts.create_db import ArxivDatabase
 from src.utils.utils import set_env_vars
 
 db = None
@@ -216,71 +217,85 @@ css = """
 }
 """
 
-with gr.Blocks(css=css) as demo:
-    gr.Markdown("# ArXiv Database Query Interface")
 
-    with gr.Row():
-        db_dropdown = gr.Dropdown(
-            choices=get_available_databases(), label="Select Database"
+def launch():
+    with gr.Blocks(css=css) as demo:
+        gr.Markdown("# ArXiv Database Query Interface")
+
+        with gr.Row():
+            db_dropdown = gr.Dropdown(
+                choices=get_available_databases(), label="Select Database"
+            )
+            load_db_btn = gr.Button("Load Database", size="sm")
+            status = gr.Textbox(label="Status")
+
+        with gr.Row():
+            graph_output = gr.Plot(label="Concept Co-occurrence Graph")
+
+        with gr.Row():
+            wrap_checkbox = gr.Checkbox(label="Wrap long text", value=False)
+            canned_query_dropdown = gr.Dropdown(
+                choices=[q[0] for q in canned_queries], label="Select Query", scale=3
+            )
+            limit_input = gr.Number(
+                label="Limit", value=10000, step=1, minimum=1, scale=1
+            )
+            selected_query = gr.Textbox(
+                label="Selected Query",
+                interactive=False,
+                scale=2,
+                show_label=True,
+                show_copy_button=True,
+                elem_id="selected-query",
+            )
+            canned_query_submit = gr.Button("Submit Query", size="sm", scale=1)
+
+        with gr.Row():
+            sql_input = gr.Textbox(label="Custom SQL Query", lines=3, scale=4)
+            sql_submit = gr.Button("Submit Custom SQL", size="sm", scale=1)
+
+        output = gr.DataFrame(label="Results", wrap=True)
+
+        def update_selected_query(query_description):
+            for desc, sql in canned_queries:
+                if desc == query_description:
+                    return sql
+            return ""
+
+        def submit_canned_query(query_description, limit, wrap):
+            for desc, sql in canned_queries:
+                if desc == query_description:
+                    return query_db(sql, True, limit, wrap)
+            return pd.DataFrame({"Error": ["Selected query not found."]})
+
+        load_db_btn.click(
+            load_database_with_graphs,
+            inputs=[db_dropdown],
+            outputs=[status, graph_output],
         )
-        load_db_btn = gr.Button("Load Database", size="sm")
-        status = gr.Textbox(label="Status")
-
-    with gr.Row():
-        graph_output = gr.Plot(label="Concept Co-occurrence Graph")
-
-    with gr.Row():
-        wrap_checkbox = gr.Checkbox(label="Wrap long text", value=False)
-        canned_query_dropdown = gr.Dropdown(
-            choices=[q[0] for q in canned_queries], label="Select Query", scale=3
+        canned_query_dropdown.change(
+            update_selected_query,
+            inputs=[canned_query_dropdown],
+            outputs=[selected_query],
         )
-        limit_input = gr.Number(label="Limit", value=10000, step=1, minimum=1, scale=1)
-        selected_query = gr.Textbox(
-            label="Selected Query",
-            interactive=False,
-            scale=2,
-            show_label=True,
-            show_copy_button=True,
-            elem_id="selected-query",
+        canned_query_submit.click(
+            submit_canned_query,
+            inputs=[canned_query_dropdown, limit_input, wrap_checkbox],
+            outputs=output,
+        )
+        sql_submit.click(
+            query_db,
+            inputs=[sql_input, gr.Checkbox(value=True), limit_input, wrap_checkbox],
+            outputs=output,
         )
-        canned_query_submit = gr.Button("Submit Query", size="sm", scale=1)
-
-    with gr.Row():
-        sql_input = gr.Textbox(label="Custom SQL Query", lines=3, scale=4)
-        sql_submit = gr.Button("Submit Custom SQL", size="sm", scale=1)
-
-    output = gr.DataFrame(label="Results", wrap=True)
-
-    def update_selected_query(query_description):
-        for desc, sql in canned_queries:
-            if desc == query_description:
-                return sql
-        return ""
-
-    def submit_canned_query(query_description, limit, wrap):
-        for desc, sql in canned_queries:
-            if desc == query_description:
-                return query_db(sql, True, limit, wrap)
-        return pd.DataFrame({"Error": ["Selected query not found."]})
 
-    load_db_btn.click(
-        load_database_with_graphs, inputs=[db_dropdown], outputs=[status, graph_output]
-    )
-    canned_query_dropdown.change(
-        update_selected_query, inputs=[canned_query_dropdown], outputs=[selected_query]
-    )
-    canned_query_submit.click(
-        submit_canned_query,
-        inputs=[canned_query_dropdown, limit_input, wrap_checkbox],
-        outputs=output,
-    )
-    sql_submit.click(
-        query_db,
-        inputs=[sql_input, gr.Checkbox(value=True), limit_input, wrap_checkbox],
-        outputs=output,
+    print("Launching Gradio app...", flush=True)
+    demo.launch(share=True)
+    print(
+        "Gradio app launched. If you don't see a URL above, there might be network restrictions.",
+        flush=True,
     )
 
-if __name__ == "__main__":
-    demo.launch(share=True)
 
-demo.launch()
+if __name__ == "__main__":
+    launch()