diff --git a/docs/docs/how_to/document_loader_custom.ipynb b/docs/docs/how_to/document_loader_custom.ipynb index 2eecb72bfdb..9fb0aec5595 100644 --- a/docs/docs/how_to/document_loader_custom.ipynb +++ b/docs/docs/how_to/document_loader_custom.ipynb @@ -152,7 +152,6 @@ " ) -> AsyncIterator[Document]: # <-- Does not take any arguments\n", " \"\"\"An async lazy loader that reads a file line by line.\"\"\"\n", " # Requires aiofiles\n", - " # Install with `pip install aiofiles`\n", " # https://github.com/Tinche/aiofiles\n", " import aiofiles\n", "\n", @@ -723,109 +722,11 @@ ] }, { - "cell_type": "code", - "execution_count": 23, - "id": "6139b546b8c4d524", - "metadata": { - "ExecuteTime": { - "end_time": "2025-04-21T08:50:15.514959Z", - "start_time": "2025-04-21T08:50:01.219848Z" - } - }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - " 17%|█▋ | 1/6 [00:04<00:20, 4.20s/it]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "metadata={} mimetype='application/pdf' path='s3://bucket-01/Annual-Report-2016.pdf'\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - " 33%|███▎ | 2/6 [00:05<00:09, 2.28s/it]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "metadata={} mimetype='application/pdf' path='s3://bucket-01/ComingHomeToNature_ActivityBooklet.pdf'\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - " 50%|█████ | 3/6 [00:06<00:06, 2.01s/it]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "metadata={} mimetype='application/pdf' path='s3://bucket-01/ComingHomeToNature_ActivityBookletFoyles.pdf'\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - " 67%|██████▋ | 4/6 [00:07<00:02, 1.44s/it]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "metadata={} mimetype='application/pdf' path='s3://bucket-01/EVENTS E-POSTER_DAYS OF AWE.pdf'\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - " 83%|████████▎ | 5/6 [00:07<00:01, 1.11s/it]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "metadata={} mimetype='application/pdf' path='s3://bucket-01/MH.pdf'\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "100%|██████████| 6/6 [00:08<00:00, 1.02s/it]" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "metadata={} mimetype='application/pdf' path='s3://bucket-01/SRT Annual Report 2018.pdf'\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "100%|██████████| 6/6 [00:11<00:00, 1.87s/it]\n" - ] - } - ], + "cell_type": "markdown", + "id": "d3f84501-b0aa-4a60-aad2-5109cbd37d4f", + "metadata": {}, "source": [ + "```python\n", "from cloudpathlib import S3Client, S3Path\n", "from langchain_community.document_loaders.blob_loaders import CloudBlobLoader\n", "\n", @@ -839,7 +740,8 @@ "cloud_loader = CloudBlobLoader(path, glob=\"**/*.pdf\", show_progress=True)\n", "\n", "for blob in cloud_loader.yield_blobs():\n", - " print(blob)" + " print(blob)\n", + "```" ] }, { @@ -1016,7 +918,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.1" + "version": "3.10.4" } }, "nbformat": 4,