show last update

.github/workflows/actions.yml

@@ -1,35 +1,37 @@
-name: Run main.py on schedule
+name: Update Job Database
 
 on:
   schedule:
-    # Run the workflow every three hours
-    - cron: "0 */3 * * *"
-  workflow_dispatch: # Allows manual triggering of the workflow
+    - cron: "0 */6 * * *" # Runs every 6 hours
+  workflow_dispatch: # Allows manual triggering
 
 jobs:
-  run-python-script:
+  update-database:
     runs-on: ubuntu-latest
-
-    env: # Define environment variables for the entire job
-      PINECONE_API_KEY: ${{ secrets.PINECONE_API_KEY }}
-
     steps:
-      # Step 1: Check out the code
-      - name: Check out repository
+      - name: Checkout repository
         uses: actions/checkout@v3
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
 
-      # Step 2: Set up Python
       - name: Set up Python
         uses: actions/setup-python@v4
         with:
-          python-version: "3.12" # Match your Python version
+          python-version: "3.10"
 
-      # Step 3: Install dependencies
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+          pip install -r requirements.txt
 
-      # Step 4: Run the script
-      - name: Run main.py
+      - name: Run update script
+        env:
+          PINECONE_API_KEY: ${{ secrets.PINECONE_API_KEY }}
         run: python main.py
+
+      - name: Commit and push if timestamp changed
+        run: |
+          git config --local user.email "github-actions[bot]@users.noreply.github.com"
+          git config --local user.name "github-actions[bot]"
+          git add timestamp2.txt
+          git diff --quiet && git diff --staged --quiet || (git commit -m "Update timestamp" && git push)

app.py

@@ -6,6 +6,7 @@ from typing import Optional
 import re
 from pinecone_handler import PineconeHandler
 from time_handling import read_timestamp
+from datetime import datetime
 
 def extract_text_from_pdf(pdf_file) -> str:
     """Extract text content from PDF file"""
@@ -103,6 +104,15 @@ def format_job_description(description: str, truncated: bool = False) -> str:
 
 def main():
     st.title("Resume-Based Job Search")
+
+    # Add last update time display
+    try:
+        last_update = read_timestamp()
+        last_update_dt = datetime.strptime(last_update, "%Y-%m-%d %H:%M:%S")
+        st.markdown(f"*Last database update: {last_update_dt.strftime('%B %d, %Y at %I:%M %p')}*")
+    except Exception as e:
+        st.warning("Unable to retrieve last update time")
+
     st.write("Upload your resume to find matching job opportunities")
     
     # Initialize PineconeHandler

main.py

@@ -14,7 +14,6 @@ logging.basicConfig(stream=sys.stdout, level=LOG_LEVEL, format=LOG_FORMAT, datef
 def keep_updated():
     handler = PineconeHandler()
     last_timestamp = read_timestamp()
-    counter = 0
     
     while True:
         new_timestamp = timestamp_now()
@@ -27,14 +26,6 @@ def keep_updated():
 
         write_timestamp(new_timestamp)
         break
-        #counter += 1
-        #log.info(f"Completed update {counter} of {MAX_UPDATES}")
-        
-        #if counter == MAX_UPDATES:
-        #    break
-            
-        #log.info(f"Waiting {SLEEP_TIME_MINUTES} minutes before collecting ads again")
-        #sleep(SLEEP_TIME_MINUTES * 60)
 
     log.info('Finished')
 

timestamp2.txt

@@ -1 +1 @@
-2024-12-22T13:55:53
+2024-12-22T16:19:41