Merge pull request #5 from run-llama/feat/examples

Add more example notebooks
run-llama · Jul 25, 2024 · 5f81c52 · 5f81c52
2 parents e769622 + e878ab8
commit 5f81c52
Show file tree

Hide file tree

Showing 5 changed files with 265 additions and 5 deletions.
diff --git a/examples/data/noisebridge_receipt.pdf b/examples/data/noisebridge_receipt.pdf
diff --git a/examples/data/parallels_invoice.pdf b/examples/data/parallels_invoice.pdf
diff --git a/examples/demo_basic.ipynb b/examples/demo_basic.ipynb
@@ -42,7 +42,9 @@
     "\n",
     "extractor = LlamaExtract()\n",
     "\n",
-    "extraction_schema = extractor.infer_schema(\"Test Schema\", [...])"
+    "extraction_schema = extractor.infer_schema(\n",
+    "    \"Test Schema\", [\"./data/noisebridge_receipt.pdf\", \"./data/parallels_invoice.pdf\"]\n",
+    ")"
    ]
   },
   {
@@ -54,7 +56,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'type': 'object', 'properties': {'Contact': {'type': 'object', 'properties': {'name': {'type': 'string'}, 'email': {'type': 'string'}, 'telephone': {'type': 'string'}}}, 'PaymentNotice': {'type': 'object', 'properties': {'investor': {'type': 'object', 'properties': {'name': {'type': 'string'}}}, 'dealCusip': {'type': 'string'}, 'loanShare': {'type': 'string'}, 'reference': {'type': 'string'}, 'bankDetails': {'type': 'object', 'properties': {'aba': {'type': 'string'}, 'bankName': {'type': 'string'}, 'attention': {'type': 'string'}, 'accountNumber': {'type': 'string'}, 'bankToBankInfo': {'type': 'string'}}}, 'paymentType': {'type': 'string'}, 'effectiveDate': {'type': 'string'}, 'facilityCusip': {'type': 'string'}, 'remittedAmount': {'type': 'string'}, 'interestPayment': {'type': 'string'}, 'paymentDescription': {'type': 'string'}}}, 'LoanRepricingNotice': {'type': 'object', 'properties': {'dealIsin': {'type': 'string'}, 'allInRate': {'type': 'string'}, 'dealCusip': {'type': 'string'}, 'rateBasis': {'type': 'string'}, 'yourShare': {'type': 'string'}, 'loanAmount': {'type': 'string'}, 'description': {'type': 'string'}, 'facilityIsin': {'type': 'string'}, 'lookBackDays': {'type': 'integer'}, 'baseRateFloor': {'type': 'string'}, 'effectiveDate': {'type': 'string'}, 'facilityCusip': {'type': 'string'}, 'referenceRate': {'type': 'string'}, 'repricingDate': {'type': 'string'}, 'spreadAdjustment': {'type': 'string'}, 'nextRepricingDate': {'type': 'string'}, 'legacyBaseRateFloor': {'type': 'string'}, 'projectedInterestDue': {'type': 'string'}}}}}\n"
+      "{'type': 'object', 'properties': {'Invoice': {'type': 'object', 'properties': {'total': {'type': 'string'}, 'products': {'type': 'string'}, 'salesTax': {'type': 'string'}, 'subtotal': {'type': 'string'}, 'invoiceDate': {'type': 'string'}, 'invoiceNumber': {'type': 'string'}, 'billingAddress': {'type': 'object', 'properties': {'city': {'type': 'string'}, 'name': {'type': 'string'}, 'country': {'type': 'string'}, 'postalCode': {'type': 'string'}}}, 'paymentDetails': {'type': 'object', 'properties': {'taxId': {'type': 'string'}, 'merchant': {'type': 'string'}, 'merchantAddress': {'type': 'object', 'properties': {'city': {'type': 'string'}, 'suite': {'type': 'string'}, 'street': {'type': 'string'}, 'country': {'type': 'string'}, 'postalCode': {'type': 'string'}}}, 'creditCardLastFour': {'type': 'string'}}}, 'referenceNumber': {'type': 'string'}}}}}\n"
      ]
     }
    ],
@@ -71,12 +73,15 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Extracting files: 100%|██████████| 2/2 [01:02<00:00, 31.19s/it]\n"
+      "Extracting files: 100%|██████████| 2/2 [00:14<00:00,  7.11s/it]\n"
      ]
     }
    ],
    "source": [
-    "extractions = extractor.extract(extraction_schema.id, [...])"
+    "extractions = extractor.extract(\n",
+    "    extraction_schema.id,\n",
+    "    [\"./data/noisebridge_receipt.pdf\", \"./data/parallels_invoice.pdf\"],\n",
+    ")"
    ]
   },
   {
@@ -88,7 +93,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'Contact': {'name': 'HASHNEET KAUR', 'email': '[email protected]', 'telephone': '+1-302-634-1253'}, 'PaymentNotice': {'investor': {'name': 'FARALLON CAPITAL (AM) INVESTORS, L.P.'}, 'dealCusip': 'CORELOGIC INC. $4BN 6/4/21 MUCY*', 'loanShare': 'USD 17,773.30', 'reference': 'CORELOGIC INC. $4BN 6/4/21 MUCY*, CME Term SOFR Reference Rates - Effective Repricing', 'bankDetails': {'aba': '021000089', 'bankName': 'CITIBANK NA', 'attention': 'Goldman Sachs & Co New York', 'accountNumber': '30649484', 'bankToBankInfo': 'FFC 002458339 Farallon Capital AM Investors LP'}, 'paymentType': 'Interest Payment', 'effectiveDate': '31-Oct-2023', 'facilityCusip': None, 'remittedAmount': 'USD 132.39', 'interestPayment': 'USD 132.39', 'paymentDescription': 'Your share of the CME Term SOFR Reference Rates - Effective interest payment'}, 'LoanRepricingNotice': {'dealIsin': None, 'allInRate': '8.938600%', 'dealCusip': None, 'rateBasis': None, 'yourShare': 'USD 17,773.30', 'loanAmount': None, 'description': None, 'facilityIsin': None, 'lookBackDays': None, 'baseRateFloor': None, 'effectiveDate': '31-Oct-2023', 'facilityCusip': None, 'referenceRate': None, 'repricingDate': '29-Nov-2023', 'spreadAdjustment': None, 'nextRepricingDate': None, 'legacyBaseRateFloor': None, 'projectedInterestDue': None}}\n"
+      "{'Invoice': {'total': '$119.99', 'products': 'Parallels Desktop for Mac Pro Edition (1 Year)', 'salesTax': '$0.00', 'subtotal': '$119.99', 'invoiceDate': 'Jul 23, 2024', 'invoiceNumber': 'BKD-73649835575', 'billingAddress': {'city': 'California', 'name': 'Laurie Voss', 'country': 'United States', 'postalCode': '94110'}, 'paymentDetails': {'taxId': '20-4503251', 'merchant': 'Cleverbridge, Inc.', 'merchantAddress': {'city': 'Chicago', 'suite': 'Suite 700', 'street': '350 N Clark', 'country': 'United States', 'postalCode': '60654'}, 'creditCardLastFour': '4469'}, 'referenceNumber': '474534804'}}\n"
      ]
     }
    ],

diff --git a/examples/demo_existent_schema.ipynb b/examples/demo_existent_schema.ipynb
@@ -0,0 +1,123 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Extracting data from files using an existing schema"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-extract"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "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-...\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_extract import LlamaExtract\n",
+    "\n",
+    "extractor = LlamaExtract()\n",
+    "\n",
+    "extraction_schema = extractor.get_schema(\"schema_id...\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "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"
+     ]
+    }
+   ],
+   "source": [
+    "print(extraction_schema)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Extracting files: 100%|██████████| 2/2 [00:03<00:00,  1.71s/it]\n"
+     ]
+    }
+   ],
+   "source": [
+    "extractions = extractor.extract(\n",
+    "    extraction_schema.id,\n",
+    "    [\"./data/noisebridge_receipt.pdf\", \"./data/parallels_invoice.pdf\"],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'date': 'Jul 23, 2024', 'amount': '119.99', 'number': 'BKD-73649835575'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(extractions[1].data)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama-extract-tm5usU00-py3.11",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/examples/demo_manual.ipynb b/examples/demo_manual.ipynb
@@ -0,0 +1,132 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Create a schema with your own schema to extract data from files"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-extract"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "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-...\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_extract import LlamaExtract\n",
+    "\n",
+    "extractor = LlamaExtract()\n",
+    "\n",
+    "data_schema = {\n",
+    "    \"type\": \"object\",\n",
+    "    \"properties\": {\n",
+    "        \"number\": {\"type\": \"string\"},\n",
+    "        \"date\": {\"type\": \"string\"},\n",
+    "        \"amount\": {\"type\": \"number\"},\n",
+    "    },\n",
+    "}\n",
+    "\n",
+    "extraction_schema = extractor.create_schema(\"Test Schema\", data_schema)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "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"
+     ]
+    }
+   ],
+   "source": [
+    "print(extraction_schema)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Extracting files: 100%|██████████| 2/2 [00:06<00:00,  3.31s/it]\n"
+     ]
+    }
+   ],
+   "source": [
+    "extractions = extractor.extract(\n",
+    "    extraction_schema.id,\n",
+    "    [\"./data/noisebridge_receipt.pdf\", \"./data/parallels_invoice.pdf\"],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'date': 'Jul 23, 2024', 'amount': '119.99', 'number': 'BKD-73649835575'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(extractions[0].data)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama-extract-tm5usU00-py3.11",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}