Move imports inside function and update decorator

autogen/agentchat/contrib/captainagent/tools/information_retrieval/arxiv_download.py

@@ -4,13 +4,9 @@
 
 
 from ......coding.func_with_reqs import with_requirements
-from ......import_utils import optional_import_block
-
-with optional_import_block():
-    import arxiv
 
 
-@with_requirements(["arxiv"], ["arxiv"])
+@with_requirements(["arxiv"])
 def arxiv_download(id_list: list, download_dir="./"):
     """Downloads PDF files from ArXiv based on a list of arxiv paper IDs.
 
@@ -21,6 +17,8 @@ def arxiv_download(id_list: list, download_dir="./"):
     Returns:
         list: A list of paths to the downloaded PDF files.
     """
+    import arxiv
+
     paths = []
     for paper in arxiv.Client().results(arxiv.Search(id_list=id_list)):
         path = paper.download_pdf(download_dir, filename=paper.get_short_id() + ".pdf")

autogen/agentchat/contrib/captainagent/tools/information_retrieval/arxiv_search.py

@@ -4,13 +4,9 @@
 
 
 from ......coding.func_with_reqs import with_requirements
-from ......import_utils import optional_import_block
-
-with optional_import_block():
-    import arxiv
 
 
-@with_requirements(["arxiv"], ["arxiv"])
+@with_requirements(["arxiv"])
 def arxiv_search(query, max_results=10, sortby="relevance"):
     """Search for articles on arXiv based on the given query.
 
@@ -28,6 +24,7 @@ def arxiv_search(query, max_results=10, sortby="relevance"):
             - 'doi': The DOI of the article (If applicable).
             - 'published': The publication date of the article in the format 'Y-M'.
     """
+    import arxiv
 
     def get_author(r):
         return ", ".join(a.name for a in r.authors)

autogen/agentchat/contrib/captainagent/tools/information_retrieval/image_qa.py

@@ -4,13 +4,9 @@
 import os
 
 from ......coding.func_with_reqs import with_requirements
-from ......import_utils import optional_import_block
-
-with optional_import_block():
-    from PIL import Image
 
 
-@with_requirements(["transformers", "torch"], ["transformers", "torch", "PIL", "os"])
+@with_requirements(["transformers", "torch", "PIL"], ["transformers", "torch", "os"])
 def image_qa(image, question, ckpt="Salesforce/blip-vqa-base"):
     """Perform question answering on an image using a pre-trained VQA model.
 
@@ -22,6 +18,7 @@ def image_qa(image, question, ckpt="Salesforce/blip-vqa-base"):
         dict: The generated answer text.
     """
     import torch
+    from PIL import Image
     from transformers import BlipForQuestionAnswering, BlipProcessor
 
     def image_processing(img):