restoring the make venv

Signed-off-by: SHAHROKH DAIJAVAD <shahrokh@us.ibm.com>
IBM · Nov 20, 2024 · 11ed291 · 11ed291
1 parent 0ddcca1
commit 11ed291
Showing 1 changed file with 19 additions and 19 deletions.
diff --git a/transforms/language/pdf2parquet/pdf2parquet.ipynb b/transforms/language/pdf2parquet/pdf2parquet.ipynb
@@ -9,8 +9,8 @@
     "\n",
     "##### **** example: \n",
     "```\n",
-    "python -m venv && source venv/bin/activate\n",
-    "pip install -r requirements.txt\n",
+    "make venv \n",
+    "source venv/bin/activate \n",
     "pip install jupyterlab\n",
     "```"
    ]
@@ -122,22 +122,22 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "13:23:55 INFO - pdf2parquet parameters are : {'batch_size': -1, 'artifacts_path': None, 'contents_type': <pdf2parquet_contents_types.MARKDOWN: 'text/markdown'>, 'do_table_structure': True, 'do_ocr': True, 'ocr_engine': <pdf2parquet_ocr_engine.EASYOCR: 'easyocr'>, 'bitmap_area_threshold': 0.05, 'pdf_backend': <pdf2parquet_pdf_backend.DLPARSE_V2: 'dlparse_v2'>, 'double_precision': 0}\n",
-      "13:23:55 INFO - pipeline id pipeline_id\n",
-      "13:23:55 INFO - code location None\n",
-      "13:23:55 INFO - data factory data_ is using local data access: input_folder - python/test-data/input output_folder - python/output\n",
-      "13:23:55 INFO - data factory data_ max_files -1, n_sample -1\n",
-      "13:23:55 INFO - data factory data_ Not using data sets, checkpointing False, max files -1, random samples -1, files to use ['.pdf', '.docx', '.pptx', '.zip'], files to checkpoint ['.parquet']\n",
-      "13:23:55 INFO - orchestrator pdf2parquet started at 2024-11-20 13:23:55\n",
-      "13:23:55 INFO - Number of files is 2, source profile {'max_file_size': 0.3013172149658203, 'min_file_size': 0.2757863998413086, 'total_file_size': 0.5771036148071289}\n",
-      "13:23:55 INFO - Initializing models\n",
-      "13:23:58 INFO - Processing archive_doc_filename='2305.03393v1-pg9.pdf' \n",
-      "13:23:59 INFO - Processing archive_doc_filename='2408.09869v1-pg1.pdf' \n",
-      "13:24:00 INFO - Completed 1 files (50.0%) in 0.029 min\n",
-      "13:24:03 INFO - Completed 2 files (100.0%) in 0.08 min\n",
-      "13:24:03 INFO - Done processing 2 files, waiting for flush() completion.\n",
-      "13:24:03 INFO - done flushing in 0.0 sec\n",
-      "13:24:03 INFO - Completed execution in 0.132 min, execution result 0\n"
+      "15:13:18 INFO - pdf2parquet parameters are : {'batch_size': -1, 'artifacts_path': None, 'contents_type': <pdf2parquet_contents_types.MARKDOWN: 'text/markdown'>, 'do_table_structure': True, 'do_ocr': True, 'ocr_engine': <pdf2parquet_ocr_engine.EASYOCR: 'easyocr'>, 'bitmap_area_threshold': 0.05, 'pdf_backend': <pdf2parquet_pdf_backend.DLPARSE_V2: 'dlparse_v2'>, 'double_precision': 0}\n",
+      "15:13:18 INFO - pipeline id pipeline_id\n",
+      "15:13:18 INFO - code location None\n",
+      "15:13:18 INFO - data factory data_ is using local data access: input_folder - python/test-data/input output_folder - python/output\n",
+      "15:13:18 INFO - data factory data_ max_files -1, n_sample -1\n",
+      "15:13:18 INFO - data factory data_ Not using data sets, checkpointing False, max files -1, random samples -1, files to use ['.pdf', '.docx', '.pptx', '.zip'], files to checkpoint ['.parquet']\n",
+      "15:13:18 INFO - orchestrator pdf2parquet started at 2024-11-20 15:13:18\n",
+      "15:13:18 INFO - Number of files is 2, source profile {'max_file_size': 0.3013172149658203, 'min_file_size': 0.2757863998413086, 'total_file_size': 0.5771036148071289}\n",
+      "15:13:18 INFO - Initializing models\n",
+      "15:14:08 INFO - Processing archive_doc_filename='2305.03393v1-pg9.pdf' \n",
+      "15:14:09 INFO - Processing archive_doc_filename='2408.09869v1-pg1.pdf' \n",
+      "15:14:10 INFO - Completed 1 files (50.0%) in 0.04 min\n",
+      "15:14:18 INFO - Completed 2 files (100.0%) in 0.179 min\n",
+      "15:14:18 INFO - Done processing 2 files, waiting for flush() completion.\n",
+      "15:14:18 INFO - done flushing in 0.0 sec\n",
+      "15:14:18 INFO - Completed execution in 1.007 min, execution result 0\n"
      ]
     }
    ],
@@ -205,7 +205,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.10"
+   "version": "3.10.8"
   }
  },
  "nbformat": 4,