update docling and test results

Signed-off-by: Michele Dolfi <[email protected]>

transforms/language/doc_chunk/requirements.txt

@@ -1,3 +1,3 @@
-docling-core==2.3.0
-pydantic>=2.0.0,<2.10.0 
+docling-core==2.18.0
+pydantic>=2.0.0
 llama-index-core>=0.11.22,<0.12.0

transforms/language/doc_chunk/test-data/expected/metadata.json

@@ -5,8 +5,8 @@
     "job name": "doc_chunk",
     "job type": "pure python",
     "job id": "job_id",
-    "start_time": "2024-10-30 18:38:40",
-    "end_time": "2024-10-30 18:38:40",
+    "start_time": "2025-02-10 15:20:06",
+    "end_time": "2025-02-10 15:20:07",
     "status": "success"
   },
   "code": {
@@ -25,6 +25,7 @@
     "output_bbox_column_name": "bbox",
     "chunk_size_tokens": 128,
     "chunk_overlap_tokens": 30,
+    "dl_min_chunk_len": null,
     "checkpointing": false,
     "max_files": -1,
     "random_samples": -1,
@@ -34,29 +35,29 @@
     "num_processors": 0
   },
   "execution_stats": {
-    "cpus": 19.5,
+    "cpus": 25.8,
     "gpus": 0,
-    "memory": 27.48,
+    "memory": 24.41,
     "object_store": 0,
     "execution time, min": 0.001
   },
   "job_output_stats": {
     "source_files": 1,
     "source_size": 12073,
     "result_files": 1,
-    "result_size": 14363,
-    "processing_time": 0.043,
+    "result_size": 16705,
+    "processing_time": 0.044,
     "nfiles": 1,
-    "nrows": 39,
+    "nrows": 29,
     "source_doc_count": 1,
-    "result_doc_count": 39
+    "result_doc_count": 29
   },
   "source": {
-    "name": "/Users/dol/codes/data-prep-kit/transforms/language/doc_chunk/python/test-data/input",
+    "name": "/Users/dol/codes/data-prep-kit/transforms/language/doc_chunk/test-data/input",
     "type": "path"
   },
   "target": {
-    "name": "/Users/dol/codes/data-prep-kit/transforms/language/doc_chunk/python/output",
+    "name": "/Users/dol/codes/data-prep-kit/transforms/language/doc_chunk/output",
     "type": "path"
   }
 }