diff --git a/examples/demo_manual.ipynb b/examples/demo_manual.ipynb index 3f657c2..5469254 100644 --- a/examples/demo_manual.ipynb +++ b/examples/demo_manual.ipynb @@ -42,7 +42,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "Apply `nest_asyncio` and bring your own LlamaCloud API key:" + "Follow [instruction](https://docs.cloud.llamaindex.ai/llamacloud/getting_started/api_key) to get an API key from https://cloud.llamaindex.ai/" ] }, { @@ -51,14 +51,11 @@ "metadata": {}, "outputs": [], "source": [ - "# llama-extract is async-first, running the sync code in a notebook requires the use of nest_asyncio\n", - "import nest_asyncio\n", - "\n", - "nest_asyncio.apply()\n", - "\n", "import os\n", "\n", - "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"llx-...\"" + "os.environ[\n", + " \"LLAMA_CLOUD_API_KEY\"\n", + "] = \"llx-7PV0mlZKNetJn5hG5UwEucDdhiHXLu4fXo4tgOusoPWVwzMJ\"" ] }, { @@ -88,7 +85,7 @@ " },\n", "}\n", "\n", - "extraction_schema = extractor.create_schema(\"Test Schema\", data_schema)" + "extraction_schema = await extractor.acreate_schema(\"Test Schema\", data_schema)" ] }, { @@ -104,15 +101,21 @@ "metadata": {}, "outputs": [ { - "name": "stdout", - "output_type": "stream", - "text": [ - "id='88ea0633-937b-42f1-a35d-7da19c2db74e' created_at=datetime.datetime(2024, 7, 24, 19, 48, 49, 968786, tzinfo=datetime.timezone.utc) updated_at=datetime.datetime(2024, 7, 24, 19, 48, 49, 968786, tzinfo=datetime.timezone.utc) name='Test Schema' project_id='b1be5ffd-3f90-4fd1-9742-ca7c0a30f6f7' data_schema={'type': 'object', 'properties': {'date': {'type': 'string'}, 'amount': {'type': 'number'}, 'number': {'type': 'string'}}}\n" - ] + "data": { + "text/plain": [ + "{'type': 'object',\n", + " 'properties': {'date': {'type': 'string'},\n", + " 'amount': {'type': 'number'},\n", + " 'number': {'type': 'string'}}}" + ] + }, + "execution_count": null, + "metadata": {}, + "output_type": "execute_result" } ], "source": [ - "print(extraction_schema)" + "extraction_schema.data_schema" ] }, { @@ -132,12 +135,12 @@ "name": "stderr", "output_type": "stream", "text": [ - "Extracting files: 100%|██████████| 2/2 [00:06<00:00, 3.31s/it]\n" + "Extracting files: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:04<00:00, 2.06s/it]\n" ] } ], "source": [ - "extractions = extractor.extract(\n", + "extractions = await extractor.aextract(\n", " extraction_schema.id,\n", " [\"./data/noisebridge_receipt.pdf\", \"./data/parallels_invoice.pdf\"],\n", ")" @@ -156,21 +159,24 @@ "metadata": {}, "outputs": [ { - "name": "stdout", - "output_type": "stream", - "text": [ - "{'date': 'Jul 23, 2024', 'amount': '119.99', 'number': 'BKD-73649835575'}\n" - ] + "data": { + "text/plain": [ + "{'date': 'July 19, 2024', 'amount': '10.0', 'number': '2721 5058'}" + ] + }, + "execution_count": null, + "metadata": {}, + "output_type": "execute_result" } ], "source": [ - "print(extractions[0].data)" + "extractions[0].data" ] } ], "metadata": { "kernelspec": { - "display_name": "llama-extract-tm5usU00-py3.11", + "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, @@ -187,5 +193,5 @@ } }, "nbformat": 4, - "nbformat_minor": 2 + "nbformat_minor": 4 }