Adds missing tags and import catch statement

contrib/hamilton/contrib/dagworks/sphinx_doc_chunking/__init__.py

@@ -9,11 +9,17 @@
  5. what this doesn't do is create embeddings -- but that would be easy to extend.
 """
 
+import logging
 import re
 
-import requests
-from langchain import text_splitter
-from langchain_core import documents
+logger = logging.getLogger(__name__)
+
+from hamilton import contrib
+
+with contrib.catch_import_errors(__name__, __file__, logger):
+    import requests
+    from langchain import text_splitter
+    from langchain_core import documents
 
 from hamilton.htypes import Collect, Parallelizable
 
@@ -160,3 +166,12 @@ def collect_chunked_url_text(url_result: Collect[dict]) -> list:
         .build()
     )
     dr.display_all_functions("dag.png")
+    result = dr.execute(
+        ["collect_chunked_url_text"],
+        inputs={"chunk_size": 256, "chunk_overlap": 32},
+    )
+    # do something with the result...
+    import pprint
+
+    for chunk in result["collect_chunked_url_text"]:
+        pprint.pprint(chunk)

contrib/hamilton/contrib/dagworks/sphinx_doc_chunking/tags.json

@@ -3,5 +3,8 @@
   "use_case_tags": ["data processing", "document chunking", "chunking", "langchain"],
   "secondary_tags": {
     "language": "English"
+  },
+  "driver_tags": {
+    "executor": "multithreading"
   }
 }

contrib/hamilton/contrib/user/elijahbenizzy/parallel_load_dataframes_s3/tags.json

@@ -4,5 +4,8 @@
   "secondary_tags": {
     "dataframe-library" : "pandas",
     "cloud-provider": "aws"
+  },
+  "driver_tags": {
+    "executor": "multithreading"
   }
 }