Fix scanner task creator

aiworker/run.pl

@@ -6,16 +6,27 @@ use JSON;
 use Data::Dumper;
 
 my $seconds = $ENV{'SECONDS_PER_FRAME'} || 30;
-my $ollama = $ENV{'OLLAMA_URL'} || die "OLLAMA_URL environment variable not set\n";
-my $api = $ENV{'API_BASE_URL'} || die "API_BASE_URL environment variable not set\n";
+my $ollama = $ENV{'OLLAMA_URL'} || 'http://10.0.1.7:11434';
+my $api = $ENV{'API_BASE_URL'} || 'http://10.0.1.7:3000';
 my $task_count = $ENV{'TASK_COUNT'} || 1;
+my $image_count = $ENV{'IMAGE_COUNT'} || 10; # Number of images to extract from the video
+my $min_time = $ENV{'MIN_TIME'} || 5; # Minimum time between images
 my $sensitivity = 20;
 my $resolution = "672:672";
+#my $model = "hf.co/Jommarn/UNSEEN_Gemma_4_26B_NSFW-GGUF:Q8_0";
+my $model = "hf.co/Jommarn/UNSEEN_Gemma_4_26B_NSFW-GGUF:Q5_K_M";
 
 chdir("/tmp") || die "Unable to change directory to /tmp: $!\n";
+
 my $ua = LWP::UserAgent->new;
 $ua->timeout(60);
 
+if(@ARGV) {
+    CheckPath($ARGV[0], {'duration' => 0});
+
+    exit;
+}
+
 for(my $i=0; $i<$task_count; $i++) {
     my $ref = GetNext();
     my $task = $ref->{'task'};
@@ -24,7 +35,7 @@ for(my $i=0; $i<$task_count; $i++) {
     my $task_id = $task->{'id'};
     my $video_id = $video->{'id'};
     my $path = $video->{'file_path'};
-    my $result = CheckPath($path);
+    my $result = CheckPath($path, $video);
 
     next unless $result;
     
@@ -35,12 +46,21 @@ print "Done\n";
 exit(0);
 
 sub CheckPath {
-    my ($path) = @_;
+    my ($path, $video) = @_;
     die "File path not set\n" unless $path;
     die "File does not exist: $path\n" unless -e $path;
 
     unlink(<*.png>);
-    system("ffmpeg -i \"$path\" -vf fps=1/$seconds,scale=$resolution output_%04d.png");
+
+    # Pick a frame interval that spreads $image_count frames across the video,
+    # but never more frequently than 1 frame per $min_time seconds.
+    my $interval = $seconds; # fallback if duration is unknown
+    if (my $duration = $video->{'duration'}) {
+        my $desired = $duration / $image_count;
+        $interval = ($desired > $min_time) ? $desired : $min_time;
+    }
+
+    system("ffmpeg -i \"$path\" -vf fps=1/$interval,scale=$resolution output_%04d.png 2>&1");
 
 
     my $total=0;
@@ -56,17 +76,21 @@ sub CheckPath {
         $data=undef;
 
         my $ref = {
-            'model'     => 'srizon/pixie:latest',
-            'prompt'    => "Are there any african american people in this photo, whether they are shown completely or not?  Please answer 'yes' or 'no' only.",
+            'model'     => $model,
+            'prompt'    => "Are there any african american men in this photo, whether they are shown completely or not?  Judge based on skin tone, accounting for shadows.  Answer yes for very dark skin.Please answer 'yes' or 'no' only.",
             'images'    => [$base64],
         };
 
         my $url = "$ollama/api/generate";
         my $res = GetRest($url, $ref);
-        print "\t$res\n";
+        print "$file\t$res\n";
+        #Remove thought information from the response
+        $res =~ s/<\|channel>.*?<channel\|>//s;
+        $res =~ s/^\s+|\s+$//g;
         $total++;
         if($res=~/yes/i) {
             $yes++;
+            print "\tYES\n";
         }
         unlink($file);
     }
@@ -91,6 +115,8 @@ sub CheckPath {
         'yes'       => $yes,
         'percentage'=> $percentage,
         'verdict'   => $verdict,
+        'model'     => $model,
+        'path'      => $path,
 
     };
 }

scanner/scanner.pl

@@ -196,30 +196,18 @@ sub CreateReviewTasks {
     # This avoids MariaDB's inconsistent JSON functions in SQL WHERE clauses,
     # which behave differently between CLI client and DBI connections.
     my $sth = $dbh->prepare("
-SELECT id, video_id, results 
+SELECT id, video_id 
 FROM tasks
-WHERE task_type='AISCAN' AND status='COMPLETED'
+WHERE task_type='AISCAN'
+AND status='COMPLETED'
+AND JSON_EXTRACT(results, '\$.verdict') = 1
+AND (SELECT 1 FROM tasks t2 WHERE t2.video_id = tasks.video_id AND t2.task_type = 'REVIEW' LIMIT 1) IS NULL
 ");
 
     $sth->execute();
     while (my $row = $sth->fetchrow_hashref()) {
-        my $results = decode_json($row->{results});
-        next unless $results && ref($results) eq 'HASH';
-        next unless $results->{verdict} == 1;
-        next if exists $results->{reviewed};
-
         print "Creating REVIEW task for video_id: $row->{video_id}\n";
         create_task($row->{video_id}, 'REVIEW');
-
-        # Re-encode the whole JSON blob in Perl and update it.
-        # This avoids MariaDB JSON_SET path parsing issues through DBI connections.
-        $results->{reviewed} = 1;
-        my $updated = encode_json($results);
-        my $sth_update = $dbh->prepare(
-            "UPDATE tasks SET results = ? WHERE id = ?"
-        );
-        $sth_update->execute($updated, $row->{id});
-        $sth_update->finish();
     }
     $sth->finish();
 }

ui/app.py

@@ -214,6 +214,10 @@ def index():
 @app.route("/review/<int:task_id>")
 def review_task(task_id):
     """Detail view: show task info + embedded video player."""
+    return_page = request.args.get("page", 1, type=int) or 1
+    return_page = max(return_page, 1)
+    return_queue_url = "/" if return_page == 1 else f"/?page={return_page}"
+
     try:
         data = api_get(f"task/{task_id}")
         if not data or not data.get("id"):
@@ -240,7 +244,11 @@ def review_task(task_id):
     except (json.JSONDecodeError, TypeError):
         video_obj["prev_results"] = {}
 
-    return render_template_string(_REVIEW_TEMPLATE, video=video_obj)
+    return render_template_string(
+        _REVIEW_TEMPLATE,
+        video=video_obj,
+        return_queue_url=return_queue_url,
+    )
 
 
 # ---------------------------------------------------------------------------
@@ -411,7 +419,7 @@ _INDEX_TEMPLATE = """
                 <td><span class="badge">{{ t.task_type }}</span></td>
                 <td>{{ t.status }}</td>
                 <td>{{ t.created_at|string|truncate(19, True, '') if t.created_at else '&mdash;' }}</td>
-                <td><a href="/review/{{ t.id }}" class="btn">Review</a></td>
+                <td><a href="{{ url_for('review_task', task_id=t.id, page=page) }}" class="btn">Review</a></td>
             </tr>
             {% endfor %}
             </tbody>
@@ -464,7 +472,7 @@ _REVIEW_TEMPLATE = """
 <div id="flash"></div>
 <div class="header">
     <h1>VideoDetect</h1>
-    <a href="/">&laquo; Back to queue</a>
+    <a href="{{ return_queue_url }}">&laquo; Back to queue</a>
 </div>
 <div class="container">
     {% if video.prev_results and video.prev_results.review_verdict %}
@@ -505,6 +513,8 @@ _REVIEW_TEMPLATE = """
 </div>
 
 <script>
+const returnQueueUrl = {{ return_queue_url|tojson }};
+
 async function submitVerdict(verdict) {
     setActionButtonsDisabled(true);
     showFlash('Submitting verdict...', '#007bff');
@@ -518,7 +528,7 @@ async function submitVerdict(verdict) {
         const body = await resp.json().catch(() => ({}));
         if (resp.ok) {
             showFlash('Verdict submitted', '#28a745');
-            setTimeout(() => location.href = '/', 1000);
+            setTimeout(() => location.href = returnQueueUrl, 1000);
         } else {
             alert(body.error || 'Submission failed');
             setActionButtonsDisabled(false);
@@ -538,7 +548,7 @@ async function skipTask() {
         const resp = await fetch(`/api/review/skip/{{ video.id }}`, {method: 'POST'});
         if (resp.ok) {
             showFlash('Task skipped, returned to queue', '#6c757d');
-            setTimeout(() => location.href = '/', 1000);
+            setTimeout(() => location.href = returnQueueUrl, 1000);
         } else {
             alert('Skip failed');
             setActionButtonsDisabled(false);