fix(ocr): prevent native binary crash and handle AVX2 CPUs (RR-1325)

Author: kiet08hogit

nodes/src/nodes/ocr/requirements.txt

@@ -4,9 +4,5 @@
 # by ai.common.models which uses ai.common.torch for torch installation.
 # This node only needs img2table for table structure detection.
 #
-# numpy and pillow are base engine dependencies - don't reinstall them here
+# numpy, pillow, and img2table are base engine dependencies - don't reinstall them here
 # as that can corrupt already-loaded modules in the server process.
-#
-img2table
-pillow
-numpy

nodes/src/nodes/requirements.txt

@@ -23,3 +23,6 @@ safetensors
 # Needed for dependencies compilations
 Cython
 versioneer
+
+# OCR base dependencies
+img2table

packages/server/engine-lib/rocketlib-python/lib/depends.py

@@ -654,14 +654,52 @@ def _save_hash(hash_file: str, hash_value: str):
         f.write(hash_value)
 
 
+def _is_x86_64_missing_avx2() -> bool:
+    """Check if CPU is x86_64 but lacks AVX2 (e.g. Rosetta 2 or old Intel)."""
+    machine = platform.machine().lower()
+    if machine not in ('x86_64', 'amd64'):
+        return False
+        
+    system = platform.system()
+    if system == 'Darwin':
+        # Check Rosetta or old Mac without AVX2
+        try:
+            output = subprocess.check_output(['sysctl', '-n', 'hw.optional.avx2_0'], text=True)
+            return output.strip() != '1'
+        except Exception:
+            return True
+    elif system == 'Linux':
+        try:
+            with open('/proc/cpuinfo', 'r', encoding='utf-8') as f:
+                return 'avx2' not in f.read()
+        except Exception:
+            return True
+    elif system == 'Windows':
+        try:
+            import ctypes
+            # PF_AVX2_INSTRUCTIONS_AVAILABLE is 40
+            return not ctypes.windll.kernel32.IsProcessorFeaturePresent(40)
+        except Exception:
+            return False
+            
+    return False
+
+
 def _combine_requirements(file_paths: list[str], output_path: str):
     """Concatenate all requirement files into one."""
+    needs_polars_override = False
     with open(output_path, 'w', encoding='utf-8') as out:
         for path in file_paths:
             out.write(f'# Source: {path}\n')
             with open(path, 'r', encoding='utf-8') as inp:
-                out.write(inp.read())
+                content = inp.read()
+                if 'img2table' in content or 'polars' in content:
+                    needs_polars_override = _is_x86_64_missing_avx2()
+                out.write(content)
             out.write('\n')
+            
+        if needs_polars_override:
+            out.write('\n# Injected to support older/emulated CPUs without AVX2\npolars-lts-cpu\n')
 
 
 def _compile_constraints(constraints_path: str):
@@ -764,6 +802,11 @@ def _write_excludes_file() -> str:
     excludes = 'uv\n'
     if platform.system() != 'Darwin':
         excludes += 'onnxruntime\n'
+        
+    if _is_x86_64_missing_avx2():
+        # Exclude standard polars so uv doesn't install it alongside polars-lts-cpu
+        excludes += 'polars\n'
+
     with open(excludes_path, 'w', encoding='utf-8') as f:
         f.write(excludes)
     return excludes_path