diff --git a/docs/source/users/index.md b/docs/source/users/index.md
index b519f6ea4..fbaeeee73 100644
--- a/docs/source/users/index.md
+++ b/docs/source/users/index.md
@@ -492,6 +492,19 @@ use the `-c` or `--chunk-size` option and the `-o` or `--chunk-overlap` option.
 /learn --chunk-size 1000 --chunk-overlap 200 <directory>
 ```
 
+By default, `/learn` will not read directories named `node_modules`, `lib`, or `build`,
+and will not read hidden files or hidden directories, where the file or directory name
+starts with a `.`. To force `/learn` to read all supported file types in all directories,
+use the `-a` or `--all` option.
+
+```
+# do not learn from hidden files, hidden directories, or node_modules, lib, or build directories
+/learn <directory>
+
+# learn from all supported files
+/learn -a <directory>
+```
+
 ### Additional chat commands
 
 To clear the chat panel, use the `/clear` command. This does not reset the AI model; the model may still remember previous messages that you sent it, and it may use them to inform its responses.
diff --git a/packages/jupyter-ai/jupyter_ai/chat_handlers/learn.py b/packages/jupyter-ai/jupyter_ai/chat_handlers/learn.py
index 2d011e522..8fdffba66 100644
--- a/packages/jupyter-ai/jupyter_ai/chat_handlers/learn.py
+++ b/packages/jupyter-ai/jupyter_ai/chat_handlers/learn.py
@@ -38,6 +38,7 @@ def __init__(
         self.root_dir = root_dir
         self.dask_client_future = dask_client_future
         self.parser.prog = "/learn"
+        self.parser.add_argument("-a", "--all", action="store_true")
         self.parser.add_argument("-v", "--verbose", action="store_true")
         self.parser.add_argument("-d", "--delete", action="store_true")
         self.parser.add_argument("-l", "--list", action="store_true")
@@ -115,7 +116,7 @@ async def _process_message(self, message: HumanChatMessage):
         if args.verbose:
             self.reply(f"Loading and splitting files for {load_path}", message)
 
-        await self.learn_dir(load_path, args.chunk_size, args.chunk_overlap)
+        await self.learn_dir(load_path, args.chunk_size, args.chunk_overlap, args.all)
         self.save()
 
         response = f"""🎉 I have learned documents at **{load_path}** and I am ready to answer questions about them.
@@ -132,7 +133,7 @@ def _build_list_response(self):
         {dir_list}"""
         return message
 
-    async def learn_dir(self, path: str, chunk_size: int, chunk_overlap: int):
+    async def learn_dir(self, path: str, chunk_size: int, chunk_overlap: int, all: bool):
         dask_client = await self.dask_client_future
         splitter_kwargs = {"chunk_size": chunk_size, "chunk_overlap": chunk_overlap}
         splitters = {
@@ -146,7 +147,7 @@ async def learn_dir(self, path: str, chunk_size: int, chunk_overlap: int):
             default_splitter=RecursiveCharacterTextSplitter(**splitter_kwargs),
         )
 
-        delayed = split(path, splitter=splitter)
+        delayed = split(path, all, splitter=splitter)
         doc_chunks = await dask_client.compute(delayed)
 
         em_provider_cls, em_provider_args = self.get_embedding_provider()
diff --git a/packages/jupyter-ai/jupyter_ai/document_loaders/directory.py b/packages/jupyter-ai/jupyter_ai/document_loaders/directory.py
index 0ce4bb739..ea4db8b42 100644
--- a/packages/jupyter-ai/jupyter_ai/document_loaders/directory.py
+++ b/packages/jupyter-ai/jupyter_ai/document_loaders/directory.py
@@ -17,14 +17,11 @@ def path_to_doc(path):
         metadata = {"path": str(path), "sha256": m.digest(), "extension": path.suffix}
         return Document(page_content=text, metadata=metadata)
 
-
+# Unless /learn has the "all files" option passed in, files and directories beginning with '.' are excluded
 EXCLUDE_DIRS = {
-    ".ipynb_checkpoints",
     "node_modules",
     "lib",
     "build",
-    ".git",
-    ".DS_Store",
 }
 SUPPORTED_EXTS = {
     ".py",
@@ -50,11 +47,15 @@ def flatten(*chunk_lists):
     return list(itertools.chain(*chunk_lists))
 
 
-def split(path, splitter):
+def split(path, all: bool, splitter):
     chunks = []
 
     for dir, _, filenames in os.walk(path):
-        if dir in EXCLUDE_DIRS:
+        if all is False and dir in EXCLUDE_DIRS:
+            continue
+
+        # Exclude hidden directories
+        if all is False and dir[0] == '.':
             continue
 
         for filename in filenames:
@@ -62,6 +63,10 @@ def split(path, splitter):
             if filepath.suffix not in SUPPORTED_EXTS:
                 continue
 
+            # Unless we're learning "all" files, exclude hidden files
+            if all is False and filepath.name[0] == '.':
+                continue
+
             document = dask.delayed(path_to_doc)(filepath)
             chunk = dask.delayed(split_document)(document, splitter)
             chunks.append(chunk)