update gradio launch

Author: chiral-carbon

.github/workflows/update_space.yml

@@ -1,82 +1,28 @@
-name: Deploy to Hugging Face Spaces
+name: Run Python script
 
 on:
   push:
     branches:
       - main
 
 jobs:
-  deploy:
+  build:
     runs-on: ubuntu-latest
 
     steps:
     - name: Checkout
-      uses: actions/checkout@v3
+      uses: actions/checkout@v2
 
-    - name: Set up Conda
-      uses: conda-incubator/setup-miniconda@v2
+    - name: Set up Python
+      uses: actions/setup-python@v2
       with:
-        activate-environment: kg4s
-        environment-file: environment.yml
-        auto-activate-base: false
-        use-mamba: true
+        python-version: '3.9'
 
-    - name: Verify Conda installation
-      shell: bash -l {0}
-      run: |
-        conda info
-        conda list
+    - name: Install Gradio
+      run: python -m pip install gradio
 
-    - name: Install huggingface_hub
-      shell: bash -l {0}
-      run: |
-        pip install huggingface_hub
-        pip list
+    - name: Log in to Hugging Face
+      run: python -c 'import huggingface_hub; huggingface_hub.login(token="${{ secrets.hf_token }}")'
 
-    - name: Deploy to Hugging Face Spaces
-      env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
-      shell: bash -l {0}
-      run: |
-        python - <<EOF
-        import os
-        import sys
-        from huggingface_hub import HfApi
-        
-        print("Python script started")
-        print(f"Python version: {sys.version}")
-        print(f"Current working directory: {os.getcwd()}")
-        print(f"Contents of current directory: {os.listdir('.')}")
-        
-        sys.path.append('scripts')
-        print(f"Updated sys.path: {sys.path}")
-        print(f"Contents of scripts directory: {os.listdir('scripts')}")
-        
-        print("Importing demo from run_db_interface")
-        from run_db_interface import demo
-        print("Demo imported successfully")
-        
-        api = HfApi()
-        print("HfApi initialized")
-        
-        print("Creating/verifying repository")
-        api.create_repo(
-            repo_id="abby101/xurveyor-0",
-            repo_type="space",
-            space_sdk="gradio",
-            token="$HF_TOKEN"
-        )
-        print("Repository created or verified")
-        
-        print("Starting deployment")
-        demo.deploy(
-            repo_id="abby101/xurveyor-0",
-            hf_token="$HF_TOKEN",
-        )
-        print("Deployment completed")
-        EOF
-
-    - name: Check Hugging Face Space
-      run: |
-        echo "Deployment process completed. Please check your Hugging Face Space at https://huggingface.co/spaces/abby101/xurveyor-0"
-        echo "If the space is not updated, please check the logs above for any errors."
+    - name: Deploy to Spaces
+      run: gradio deploy

README.md

@@ -1,3 +1,9 @@
+---
+title: surveyor-0
+app_file: scripts/run_db_interface.py
+sdk: gradio
+sdk_version: 4.40.0
+---
 # Mapping the Data Landscape For Generalizable Scientific Models
 
 We introduce a method to build a knowledge base to store structured information extracted from scientific publications, datasets and articles by leveraging large language models!

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()

run_tool.sh

@@ -0,0 +1,19 @@
+#!/bin/bash
+#SBATCH --partition=gen
+#SBATCH --nodes=1
+#SBATCH --ntasks-per-node=1
+#SBATCH --cpus-per-task=10
+#SBATCH --mem=50G
+#SBATCH --time=7-00:00:00
+#SBATCH --output=slurm_logs/%x-%j.out
+#SBATCH --error=slurm_logs/%x-%j.err
+#SBATCH --job-name=gradio-tool
+
+module --force purge
+module load modules/2.2-20230808 modules/2.3-20240529
+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 -u app.py

scripts/run_db_interface.py

@@ -7,13 +7,14 @@
 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 @@ def load_database_with_graphs(db_name):
 }
 """
 
-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()