Create three-yaks-beg.md

Refactored InvalidExtractionData to read the `error` field from
ExtractRun and prominently display it in the exception message.
The job-level error is now stored in the `extraction_error` attribute
and included in the invalid_item's metadata as `job_error`.

.changeset/three-yaks-beg.md

@@ -0,0 +1,5 @@
+---
+"llama-cloud-services-py": patch
+---
+
+Use error description in ExtractedData invalid extraction error

.github/workflows/test_e2e_py.yml

@@ -12,6 +12,7 @@ env:
 jobs:
   test_e2e:
     runs-on: ubuntu-latest
+    timeout-minutes: 30
     strategy:
       # You can use PyPy versions in python-version.
       # For example, pypy-2.7 and pypy-3.8

examples/batch/parse/.gitignore

@@ -0,0 +1 @@
+sample_files/

examples/batch/parse/batch_parse_directory.ipynb

@@ -0,0 +1,807 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "cell-0",
+   "metadata": {},
+   "source": [
+    "# Batch Parse with LlamaCloud Directories\n",
+    "\n",
+    "This notebook demonstrates how to use LlamaCloud's batch processing API to parse multiple files in a directory. The workflow includes:\n",
+    "\n",
+    "1. **Creating a Directory** - Set up a directory to organize your files\n",
+    "2. **Uploading Files** - Upload multiple files to the directory\n",
+    "3. **Starting a Batch Parse Job** - Kick off batch processing on all files\n",
+    "4. **Monitoring Progress** - Check the status and view results\n",
+    "\n",
+    "This is useful when you need to parse many documents at once, as the batch API handles the orchestration and provides progress tracking."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cell-1",
+   "metadata": {},
+   "source": [
+    "## Setup and Installation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cell-2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-cloud python-dotenv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cell-3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from dotenv import load_dotenv\n",
+    "import httpx\n",
+    "\n",
+    "# Load environment variables\n",
+    "load_dotenv()\n",
+    "\n",
+    "# Set your API key\n",
+    "LLAMA_CLOUD_API_KEY = os.environ.get(\"LLAMA_CLOUD_API_KEY\", \"llx-...\")\n",
+    "\n",
+    "# Optional: Set base URL (defaults to https://api.cloud.llamaindex.ai if not set)\n",
+    "LLAMA_CLOUD_BASE_URL = os.environ.get(\n",
+    "    \"LLAMA_CLOUD_BASE_URL\", \"https://api.cloud.llamaindex.ai\"\n",
+    ")\n",
+    "\n",
+    "# Optional: Set project_id if you have one, otherwise it will use your default project\n",
+    "PROJECT_ID = os.environ.get(\"LLAMA_CLOUD_PROJECT_ID\", None)\n",
+    "\n",
+    "print(\"✅ API key configured\")\n",
+    "print(f\"   Base URL: {LLAMA_CLOUD_BASE_URL}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cell-4",
+   "metadata": {},
+   "source": [
+    "## Setup HTTP Client\n",
+    "\n",
+    "Since the current version of the llama-cloud SDK has some issues with the beta endpoints, we'll use direct HTTP requests with httpx for reliability."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cell-5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create HTTP client with authentication\n",
+    "headers = {\n",
+    "    \"Authorization\": f\"Bearer {LLAMA_CLOUD_API_KEY}\",\n",
+    "}\n",
+    "\n",
+    "print(\"✅ HTTP client configured\")\n",
+    "print(f\"   Using base URL: {LLAMA_CLOUD_BASE_URL}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cell-6",
+   "metadata": {},
+   "source": [
+    "## Step 1: Create a Directory\n",
+    "\n",
+    "First, we'll create a directory to organize our files. Directories help you group related files together for batch processing."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cell-7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from datetime import datetime\n",
+    "\n",
+    "# Create a directory with a timestamp in the name\n",
+    "timestamp = datetime.now().strftime(\"%Y%m%d-%H%M%S\")\n",
+    "directory_name = f\"batch-parse-demo-{timestamp}\"\n",
+    "\n",
+    "# Create directory using HTTP request\n",
+    "response = httpx.post(\n",
+    "    f\"{LLAMA_CLOUD_BASE_URL}/api/v1/beta/directories\",\n",
+    "    headers=headers,\n",
+    "    params={\"project_id\": PROJECT_ID},\n",
+    "    json={\n",
+    "        \"name\": directory_name,\n",
+    "        \"description\": \"Demo directory for batch parse example\",\n",
+    "    },\n",
+    "    timeout=60.0,\n",
+    ")\n",
+    "\n",
+    "if response.status_code in [200, 201]:\n",
+    "    directory = response.json()\n",
+    "    directory_id = directory[\"id\"]\n",
+    "    project_id = directory[\"project_id\"]\n",
+    "\n",
+    "    print(f\"✅ Created directory: {directory['name']}\")\n",
+    "    print(f\"   Directory ID: {directory_id}\")\n",
+    "    print(f\"   Project ID: {project_id}\")\n",
+    "else:\n",
+    "    raise Exception(\n",
+    "        f\"Failed to create directory: {response.status_code} - {response.text}\"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cell-8",
+   "metadata": {},
+   "source": [
+    "## Step 2: Upload Files to the Directory\n",
+    "\n",
+    "Now we'll upload some files to our directory. For this demo, we'll download some sample PDFs and upload them.\n",
+    "\n",
+    "You can replace these with your own files."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cell-9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a directory for sample files\n",
+    "import requests\n",
+    "\n",
+    "os.makedirs(\"sample_files\", exist_ok=True)\n",
+    "\n",
+    "# Sample documents to download\n",
+    "sample_docs = {\n",
+    "    \"attention.pdf\": \"https://arxiv.org/pdf/1706.03762.pdf\",\n",
+    "    \"bert.pdf\": \"https://arxiv.org/pdf/1810.04805.pdf\",\n",
+    "}\n",
+    "\n",
+    "# Download sample documents\n",
+    "for filename, url in sample_docs.items():\n",
+    "    filepath = f\"sample_files/{filename}\"\n",
+    "    if not os.path.exists(filepath):\n",
+    "        print(f\"📥 Downloading {filename}...\")\n",
+    "        response = requests.get(url)\n",
+    "        if response.status_code == 200:\n",
+    "            with open(filepath, \"wb\") as f:\n",
+    "                f.write(response.content)\n",
+    "            print(f\"   ✅ Downloaded {filename}\")\n",
+    "        else:\n",
+    "            print(f\"   ❌ Failed to download {filename}\")\n",
+    "    else:\n",
+    "        print(f\"📁 {filename} already exists\")\n",
+    "\n",
+    "print(\"\\n✅ Sample files ready!\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cell-10",
+   "metadata": {},
+   "source": [
+    "### Upload Files to Directory\n",
+    "\n",
+    "Now let's upload the files to our directory using the `upload_file_to_directory` endpoint."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cell-11",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "uploaded_files = []\n",
+    "\n",
+    "# Workaround: Use direct HTTP requests instead of SDK due to SDK bug\n",
+    "import httpx\n",
+    "\n",
+    "for filename in os.listdir(\"sample_files\"):\n",
+    "    if filename.endswith(\".pdf\"):\n",
+    "        filepath = f\"sample_files/{filename}\"\n",
+    "\n",
+    "        print(f\"📤 Uploading {filename}...\")\n",
+    "\n",
+    "        # Upload file using direct HTTP request (SDK has a bug with file uploads)\n",
+    "        with open(filepath, \"rb\") as f:\n",
+    "            # Prepare the multipart form data correctly\n",
+    "            files = {\"upload_file\": (filename, f, \"application/pdf\")}\n",
+    "\n",
+    "            # Make the request directly\n",
+    "            response = httpx.post(\n",
+    "                f\"{LLAMA_CLOUD_BASE_URL}/api/v1/beta/directories/{directory_id}/files/upload\",\n",
+    "                params={\"project_id\": project_id},\n",
+    "                files=files,\n",
+    "                headers={\"Authorization\": f\"Bearer {LLAMA_CLOUD_API_KEY}\"},\n",
+    "                timeout=60.0,\n",
+    "            )\n",
+    "\n",
+    "            if response.status_code in [200, 201]:\n",
+    "                directory_file = response.json()\n",
+    "                uploaded_files.append(directory_file)\n",
+    "                print(f\"   ✅ Uploaded: {directory_file.get('display_name')}\")\n",
+    "                print(f\"      File ID: {directory_file.get('id')}\")\n",
+    "            else:\n",
+    "                print(f\"   ❌ Upload failed: {response.status_code}\")\n",
+    "                print(f\"      Error: {response.text[:200]}\")\n",
+    "\n",
+    "print(f\"\\n✅ Uploaded {len(uploaded_files)} files to directory\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cell-12",
+   "metadata": {},
+   "source": [
+    "## Step 3: Create a Batch Parse Job\n",
+    "\n",
+    "Now that we have files in our directory, let's create a batch parse job to process them all at once.\n",
+    "\n",
+    "The batch processing API uses the same configuration as LlamaParse."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cell-13",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Configure the parse job\n",
+    "# This configuration will apply to all files in the directory\n",
+    "job_config = {\n",
+    "    \"job_name\": \"parse_raw_file_job\",  # Must match the JobNames enum value\n",
+    "    \"partitions\": {},\n",
+    "    \"parameters\": {\n",
+    "        \"type\": \"parse\",\n",
+    "        \"lang\": \"en\",\n",
+    "        \"fast_mode\": True,\n",
+    "    },\n",
+    "}\n",
+    "\n",
+    "print(\"✅ Job configuration created\")\n",
+    "print(f\"   Language: {job_config['parameters']['lang']}\")\n",
+    "print(f\"   Fast mode: {job_config['parameters']['fast_mode']}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cell-14",
+   "metadata": {},
+   "source": [
+    "### Submit the Batch Job\n",
+    "\n",
+    "Now let's submit the batch job to process all files in the directory."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cell-15",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(f\"🚀 Submitting batch parse job for directory: {directory_id}\")\n",
+    "print(f\"   Processing {len(uploaded_files)} files...\\n\")\n",
+    "\n",
+    "# Submit batch job using HTTP request\n",
+    "response = httpx.post(\n",
+    "    f\"{LLAMA_CLOUD_BASE_URL}/api/v1/beta/batch-processing\",\n",
+    "    headers=headers,\n",
+    "    params={\"project_id\": project_id},\n",
+    "    json={\n",
+    "        \"directory_id\": directory_id,\n",
+    "        \"job_config\": job_config,\n",
+    "        \"page_size\": 100,  # Number of files to fetch per batch\n",
+    "        \"continue_as_new_threshold\": 10,  # Workflow continuation threshold\n",
+    "    },\n",
+    "    timeout=60.0,\n",
+    ")\n",
+    "\n",
+    "if response.status_code in [200, 201]:\n",
+    "    batch_job = response.json()\n",
+    "    batch_job_id = batch_job[\"id\"]\n",
+    "\n",
+    "    print(\"✅ Batch job submitted successfully!\")\n",
+    "    print(f\"   Batch Job ID: {batch_job_id}\")\n",
+    "    print(f\"   Workflow ID: {batch_job.get('workflow_id')}\")\n",
+    "    print(f\"   Status: {batch_job.get('status')}\")\n",
+    "    print(f\"   Total Items: {batch_job.get('total_items')}\")\n",
+    "else:\n",
+    "    raise Exception(\n",
+    "        f\"Failed to create batch job: {response.status_code} - {response.text}\"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cell-16",
+   "metadata": {},
+   "source": [
+    "## Step 4: Monitor Job Progress\n",
+    "\n",
+    "Now let's monitor the batch job progress. We'll poll the status endpoint to see how the job is progressing."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cell-17",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import time\n",
+    "\n",
+    "\n",
+    "def print_job_status(status_data):\n",
+    "    \"\"\"Helper function to print job status in a readable format.\"\"\"\n",
+    "    job = status_data[\"job\"]\n",
+    "    progress_pct = status_data[\"progress_percentage\"]\n",
+    "\n",
+    "    print(f\"\\n{'='*60}\")\n",
+    "    print(f\"Job Status: {job['status']}\")\n",
+    "    print(f\"{'='*60}\")\n",
+    "    print(f\"Total Items: {job['total_items']}\")\n",
+    "    print(f\"Completed: {job['processed_items']}\")\n",
+    "    print(f\"Failed: {job['failed_items']}\")\n",
+    "    print(f\"Skipped: {job['skipped_items']}\")\n",
+    "    print(f\"Progress: {progress_pct:.1f}%\")\n",
+    "\n",
+    "    if job.get(\"completed_at\"):\n",
+    "        print(f\"Completed At: {job['completed_at']}\")\n",
+    "    elif job.get(\"started_at\"):\n",
+    "        print(f\"Started At: {job['started_at']}\")\n",
+    "\n",
+    "    print(f\"{'='*60}\")\n",
+    "\n",
+    "\n",
+    "# Poll for status updates\n",
+    "print(\"🔄 Monitoring batch job progress...\")\n",
+    "print(\n",
+    "    \"Note: It may take a few seconds for the workflow to initialize and count files.\\n\"\n",
+    ")\n",
+    "\n",
+    "max_polls = 60  # Maximum number of status checks (increased for longer jobs)\n",
+    "poll_interval = 10  # Seconds between checks\n",
+    "\n",
+    "for i in range(max_polls):\n",
+    "    response = httpx.get(\n",
+    "        f\"{LLAMA_CLOUD_BASE_URL}/api/v1/beta/batch-processing/{batch_job_id}\",\n",
+    "        headers=headers,\n",
+    "        params={\"project_id\": project_id},\n",
+    "        timeout=60.0,\n",
+    "    )\n",
+    "\n",
+    "    if response.status_code == 200:\n",
+    "        status_data = response.json()\n",
+    "        print_job_status(status_data)\n",
+    "\n",
+    "        # Check if job is complete\n",
+    "        job_status = status_data[\"job\"][\"status\"]\n",
+    "        if job_status in [\"completed\", \"failed\", \"cancelled\"]:\n",
+    "            print(f\"\\n✅ Job finished with status: {job_status}\")\n",
+    "            break\n",
+    "\n",
+    "        if i < max_polls - 1:\n",
+    "            print(f\"\\n⏳ Waiting {poll_interval} seconds before next check...\")\n",
+    "            time.sleep(poll_interval)\n",
+    "    else:\n",
+    "        print(f\"Error getting status: {response.status_code} - {response.text}\")\n",
+    "        break\n",
+    "else:\n",
+    "    print(f\"\\n⚠️  Reached maximum polling attempts. Job may still be running.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cell-18",
+   "metadata": {},
+   "source": [
+    "## Step 5: View Job Items\n",
+    "\n",
+    "Let's look at the individual items in the batch job to see which files were processed successfully."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cell-19",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Get all items in the batch job\n",
+    "response = httpx.get(\n",
+    "    f\"{LLAMA_CLOUD_BASE_URL}/api/v1/beta/batch-processing/{batch_job_id}/items\",\n",
+    "    headers=headers,\n",
+    "    params={\"project_id\": project_id, \"limit\": 100},\n",
+    "    timeout=60.0,\n",
+    ")\n",
+    "\n",
+    "if response.status_code == 200:\n",
+    "    items_response = response.json()\n",
+    "\n",
+    "    print(f\"\\n📋 Batch Job Items ({items_response['total_size']} total)\")\n",
+    "    print(f\"{'='*80}\\n\")\n",
+    "\n",
+    "    for item in items_response[\"items\"]:\n",
+    "        status_emoji = (\n",
+    "            \"✅\"\n",
+    "            if item[\"status\"] == \"completed\"\n",
+    "            else \"❌\"\n",
+    "            if item[\"status\"] == \"failed\"\n",
+    "            else \"⏳\"\n",
+    "        )\n",
+    "        print(f\"{status_emoji} {item['item_name']}\")\n",
+    "        print(f\"   Status: {item['status']}\")\n",
+    "        print(f\"   Item ID: {item['item_id']}\")\n",
+    "\n",
+    "        if item.get(\"error_message\"):\n",
+    "            print(f\"   Error: {item['error_message']}\")\n",
+    "\n",
+    "        print()\n",
+    "else:\n",
+    "    print(f\"Error listing items: {response.status_code} - {response.text}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cell-20",
+   "metadata": {},
+   "source": [
+    "## Step 6: Retrieve Processing Results\n",
+    "\n",
+    "For each completed file, we can retrieve the processing results to see where the parsed output is stored."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cell-21",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Get processing results for a specific item\n",
+    "if items_response[\"items\"]:\n",
+    "    first_item = items_response[\"items\"][0]\n",
+    "\n",
+    "    print(f\"\\n🔍 Processing results for: {first_item['item_name']}\")\n",
+    "    print(f\"{'='*80}\\n\")\n",
+    "\n",
+    "    response = httpx.get(\n",
+    "        f\"{LLAMA_CLOUD_BASE_URL}/api/v1/beta/batch-processing/items/{first_item['item_id']}/processing-results\",\n",
+    "        headers=headers,\n",
+    "        params={\"project_id\": project_id},\n",
+    "        timeout=60.0,\n",
+    "    )\n",
+    "\n",
+    "    if response.status_code == 200:\n",
+    "        results = response.json()\n",
+    "\n",
+    "        print(f\"Item: {results['item_name']}\")\n",
+    "        print(f\"Total processing runs: {len(results['processing_results'])}\\n\")\n",
+    "\n",
+    "        for i, result in enumerate(results[\"processing_results\"], 1):\n",
+    "            print(f\"Run {i}:\")\n",
+    "            print(f\"  Job Type: {result['job_type']}\")\n",
+    "            print(f\"  Processed At: {result['processed_at']}\")\n",
+    "            print(f\"  Parameters Hash: {result['parameters_hash']}\")\n",
+    "\n",
+    "            if result.get(\"output_s3_path\"):\n",
+    "                print(f\"  Output S3 Path: {result['output_s3_path']}\")\n",
+    "\n",
+    "            if result.get(\"output_metadata\"):\n",
+    "                print(f\"  Output Metadata: {result['output_metadata']}\")\n",
+    "\n",
+    "            print()\n",
+    "    else:\n",
+    "        print(f\"Error getting results: {response.status_code} - {response.text}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cell-22",
+   "metadata": {},
+   "source": [
+    "## Optional: List All Batch Jobs\n",
+    "\n",
+    "You can also list all batch jobs in your project to see the history of batch processing operations."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cell-23",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# List all parse jobs in the project\n",
+    "response = httpx.get(\n",
+    "    f\"{LLAMA_CLOUD_BASE_URL}/api/v1/beta/batch-processing\",\n",
+    "    headers=headers,\n",
+    "    params={\"project_id\": project_id, \"job_type\": \"parse\", \"limit\": 10},\n",
+    "    timeout=60.0,\n",
+    ")\n",
+    "\n",
+    "if response.status_code == 200:\n",
+    "    jobs_response = response.json()\n",
+    "\n",
+    "    print(f\"\\n📊 Recent Batch Parse Jobs ({jobs_response['total_size']} total)\")\n",
+    "    print(f\"{'='*80}\\n\")\n",
+    "\n",
+    "    for job in jobs_response[\"items\"]:\n",
+    "        status_emoji = (\n",
+    "            \"✅\"\n",
+    "            if job[\"status\"] == \"completed\"\n",
+    "            else \"❌\"\n",
+    "            if job[\"status\"] == \"failed\"\n",
+    "            else \"⏳\"\n",
+    "        )\n",
+    "        print(f\"{status_emoji} Job ID: {job['id']}\")\n",
+    "        print(f\"   Status: {job['status']}\")\n",
+    "        print(f\"   Directory: {job['directory_id']}\")\n",
+    "        print(f\"   Total Items: {job['total_items']}\")\n",
+    "        print(f\"   Completed: {job['processed_items']}\")\n",
+    "        print(f\"   Created: {job['created_at']}\")\n",
+    "        print()\n",
+    "else:\n",
+    "    print(f\"Error listing jobs: {response.status_code} - {response.text}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "uug7591rkq",
+   "metadata": {},
+   "source": [
+    "## Step 7: Retrieve Parsed Text Results\n",
+    "\n",
+    "Once the batch job is complete, each BatchJobItem will have a `job_id` field that maps to a parse job ID. We can use this ID with the standard parse client methods to fetch the actual parsed text results."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "vpp0vxtc0y",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Get all completed items and their job IDs\n",
+    "completed_items = [\n",
+    "    item for item in items_response[\"items\"] if item[\"status\"] == \"completed\"\n",
+    "]\n",
+    "\n",
+    "print(f\"📄 Found {len(completed_items)} completed items\\n\")\n",
+    "print(f\"{'='*80}\\n\")\n",
+    "\n",
+    "# Display the job_id for each completed item\n",
+    "for item in completed_items:\n",
+    "    print(f\"📝 {item['item_name']}\")\n",
+    "    print(f\"   Item ID: {item['item_id']}\")\n",
+    "    print(f\"   Parse Job ID: {item['job_id']}\")\n",
+    "    print()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4gck6hwpnl6",
+   "metadata": {},
+   "source": [
+    "### Fetch Parsed Text for a Specific Document\n",
+    "\n",
+    "Now let's use the `job_id` to retrieve the actual parsed text content using the parse client methods."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "g191kvgxxvk",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Get the parsed text for the first completed item\n",
+    "if completed_items:\n",
+    "    first_completed = completed_items[0]\n",
+    "\n",
+    "    print(f\"📖 Retrieving parsed text for: {first_completed['item_name']}\")\n",
+    "    print(f\"   Using Parse Job ID: {first_completed['job_id']}\\n\")\n",
+    "    print(f\"{'='*80}\\n\")\n",
+    "\n",
+    "    # Use the job_id to fetch the parse result\n",
+    "    response = httpx.get(\n",
+    "        f\"{LLAMA_CLOUD_BASE_URL}/api/v1/parsing/job/{first_completed['job_id']}/result/text\",\n",
+    "        headers=headers,\n",
+    "        params={\"project_id\": project_id},\n",
+    "        timeout=60.0,\n",
+    "    )\n",
+    "\n",
+    "    if response.status_code == 200:\n",
+    "        parse_result = response.text\n",
+    "\n",
+    "        print(f\"✅ Retrieved parsed text ({len(parse_result)} characters)\\n\")\n",
+    "\n",
+    "        # Display first 1000 characters as a preview\n",
+    "        print(\"Preview (first 1000 characters):\")\n",
+    "        print(\"-\" * 80)\n",
+    "        print(parse_result[:1000])\n",
+    "        print(\"-\" * 80)\n",
+    "\n",
+    "        if len(parse_result) > 1000:\n",
+    "            print(f\"\\n... and {len(parse_result) - 1000} more characters\")\n",
+    "    else:\n",
+    "        print(\n",
+    "            f\"Error retrieving parse result: {response.status_code} - {response.text}\"\n",
+    "        )\n",
+    "else:\n",
+    "    print(\"⚠️  No completed items found to retrieve results from\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2olccb4l8fj",
+   "metadata": {},
+   "source": [
+    "### Retrieve Parsed Results in Other Formats\n",
+    "\n",
+    "You can also retrieve the parsed results in JSON or Markdown format using different client methods."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "lcqsfxiw0sr",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if completed_items:\n",
+    "    first_completed = completed_items[0]\n",
+    "\n",
+    "    print(\n",
+    "        f\"📋 Retrieving parse results in different formats for: {first_completed['item_name']}\\n\"\n",
+    "    )\n",
+    "\n",
+    "    # Get as JSON (includes structured data with pages, images, etc.)\n",
+    "    print(\"1️⃣ Retrieving as JSON...\")\n",
+    "    response = httpx.get(\n",
+    "        f\"{LLAMA_CLOUD_BASE_URL}/api/v1/parsing/job/{first_completed['job_id']}/result/json\",\n",
+    "        headers=headers,\n",
+    "        params={\"project_id\": project_id},\n",
+    "        timeout=60.0,\n",
+    "    )\n",
+    "\n",
+    "    if response.status_code == 200:\n",
+    "        json_result = response.json()\n",
+    "        print(f\"   ✅ JSON result with {len(json_result['pages'])} pages\")\n",
+    "        print(f\"      Keys: {list(json_result.keys())}\\n\")\n",
+    "    else:\n",
+    "        print(f\"   Error: {response.status_code}\\n\")\n",
+    "\n",
+    "    # Get as Markdown\n",
+    "    print(\"2️⃣ Retrieving as Markdown...\")\n",
+    "    response = httpx.get(\n",
+    "        f\"{LLAMA_CLOUD_BASE_URL}/api/v1/parsing/job/{first_completed['job_id']}/result/markdown\",\n",
+    "        headers=headers,\n",
+    "        params={\"project_id\": project_id},\n",
+    "        timeout=60.0,\n",
+    "    )\n",
+    "\n",
+    "    if response.status_code == 200:\n",
+    "        markdown_result = response.text\n",
+    "        print(f\"   ✅ Markdown result ({len(markdown_result)} characters)\\n\")\n",
+    "\n",
+    "        # Display markdown preview\n",
+    "        print(\"Markdown Preview (first 500 characters):\")\n",
+    "        print(\"-\" * 80)\n",
+    "        print(markdown_result[:500])\n",
+    "        print(\"-\" * 80)\n",
+    "\n",
+    "        if len(markdown_result) > 500:\n",
+    "            print(f\"\\n... and {len(markdown_result) - 500} more characters\")\n",
+    "    else:\n",
+    "        print(f\"   Error: {response.status_code}\")\n",
+    "else:\n",
+    "    print(\"⚠️  No completed items found to retrieve results from\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "lr61wqkfq3",
+   "metadata": {},
+   "source": [
+    "### Batch Process All Parsed Results\n",
+    "\n",
+    "You can also loop through all completed items to retrieve and process all the parsed results."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "kltydf9xzkl",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Process all completed items\n",
+    "print(f\"🔄 Processing all {len(completed_items)} completed items...\\n\")\n",
+    "print(f\"{'='*80}\\n\")\n",
+    "\n",
+    "all_results = {}\n",
+    "\n",
+    "for item in completed_items:\n",
+    "    print(f\"📄 Processing: {item['item_name']}\")\n",
+    "    print(f\"   Parse Job ID: {item['job_id']}\")\n",
+    "\n",
+    "    try:\n",
+    "        # Retrieve the parsed text for this item\n",
+    "        response = httpx.get(\n",
+    "            f\"{LLAMA_CLOUD_BASE_URL}/api/v1/parsing/job/{item['job_id']}/result/text\",\n",
+    "            headers=headers,\n",
+    "            params={\"project_id\": project_id},\n",
+    "            timeout=60.0,\n",
+    "        )\n",
+    "\n",
+    "        if response.status_code == 200:\n",
+    "            parsed_text = response.text\n",
+    "\n",
+    "            all_results[item[\"item_name\"]] = {\n",
+    "                \"job_id\": item[\"job_id\"],\n",
+    "                \"text\": parsed_text,\n",
+    "                \"length\": len(parsed_text),\n",
+    "            }\n",
+    "\n",
+    "            print(f\"   ✅ Retrieved {len(parsed_text)} characters\")\n",
+    "        else:\n",
+    "            all_results[item[\"item_name\"]] = {\n",
+    "                \"job_id\": item[\"job_id\"],\n",
+    "                \"error\": f\"HTTP {response.status_code}\",\n",
+    "            }\n",
+    "            print(f\"   ❌ Error: HTTP {response.status_code}\")\n",
+    "\n",
+    "    except Exception as e:\n",
+    "        print(f\"   ❌ Error: {str(e)}\")\n",
+    "        all_results[item[\"item_name\"]] = {\"job_id\": item[\"job_id\"], \"error\": str(e)}\n",
+    "\n",
+    "    print()\n",
+    "\n",
+    "print(f\"{'='*80}\")\n",
+    "print(f\"\\n✅ Processed {len(all_results)} items\")\n",
+    "print(f\"\\nSummary:\")\n",
+    "for name, result in all_results.items():\n",
+    "    if \"error\" in result:\n",
+    "        print(f\"  ❌ {name}: Error - {result['error']}\")\n",
+    "    else:\n",
+    "        print(f\"  ✅ {name}: {result['length']:,} characters\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": 5
+}

examples/parse/batch_parse_folder.py

@@ -0,0 +1,183 @@
+"""
+Example: Batch Processing a Folder of PDFs with LlamaParse
+
+This script demonstrates how to process multiple PDFs from a folder
+using LlamaParse with controlled concurrency using asyncio and semaphores.
+
+Usage:
+    python batch_parse_folder.py --input-dir ./pdfs --max-concurrent 5
+"""
+
+import asyncio
+import argparse
+from pathlib import Path
+from typing import List, Dict, Any
+from datetime import datetime
+from dotenv import load_dotenv
+import os
+
+from llama_cloud_services import LlamaParse
+
+# Load environment variables from .env file
+load_dotenv()
+
+
+async def parse_single_file(
+    parser: LlamaParse,
+    file_path: Path,
+    semaphore: asyncio.Semaphore,
+) -> Dict[str, Any]:
+    """
+    Parse a single PDF file with concurrency control.
+
+    Args:
+        parser: LlamaParse instance
+        file_path: Path to the PDF file
+        semaphore: Semaphore to control concurrent requests
+
+    Returns:
+        Dictionary with file info and parse result
+    """
+    async with semaphore:
+        try:
+            print(f"Starting parse: {file_path.name}")
+
+            result = await parser.aparse(str(file_path))
+
+            print(f"✓ Completed: {file_path.name} ({len(result.pages)} pages)")
+
+            return {
+                "file": file_path.name,
+                "status": "success",
+                "result": result,
+                "pages": len(result.pages) if result.pages else 0,
+            }
+        except Exception as e:
+            print(f"✗ Error parsing {file_path.name}: {str(e)}")
+            return {
+                "file": file_path.name,
+                "status": "error",
+                "error": str(e),
+            }
+
+
+async def parse_folder(
+    input_dir: Path,
+    max_concurrent: int = 5,
+    api_key: str = None,
+) -> List[Dict[str, any]]:
+    """
+    Parse all PDFs in a folder with controlled concurrency.
+
+    Args:
+        input_dir: Directory containing PDF files
+        max_concurrent: Maximum number of concurrent parse operations
+        api_key: LlamaCloud API key (loaded from .env file)
+
+    Returns:
+        List of parse results for each file
+    """
+    # Find all PDF files
+    pdf_files = list(input_dir.glob("*.pdf"))
+
+    if not pdf_files:
+        print(f"No PDF files found in {input_dir}")
+        return []
+
+    print(f"Found {len(pdf_files)} PDF files to parse")
+
+    # Initialize parser
+    parser = LlamaParse(
+        api_key=api_key,
+        num_workers=1,  # We control concurrency with semaphore
+        show_progress=False,  # We'll show our own progress
+    )
+
+    # Create semaphore to limit concurrent requests
+    semaphore = asyncio.Semaphore(max_concurrent)
+
+    # Create tasks for all files
+    tasks = [parse_single_file(parser, pdf_file, semaphore) for pdf_file in pdf_files]
+
+    # Run all tasks concurrently (but limited by semaphore)
+    print(
+        f"Processing {len(tasks)} files with max {max_concurrent} concurrent operations..."
+    )
+    start_time = datetime.now()
+
+    results = await asyncio.gather(*tasks)
+
+    end_time = datetime.now()
+    duration = (end_time - start_time).total_seconds()
+
+    # Process results
+    successful = [
+        r for r in results if isinstance(r, dict) and r.get("status") == "success"
+    ]
+    failed = [r for r in results if isinstance(r, dict) and r.get("status") == "error"]
+
+    # Print summary
+    print("PARSE SUMMARY \n")
+    print(f"Total files: {len(pdf_files)}")
+    print(f"Successful: {len(successful)}")
+    print(f"Failed: {len(failed)}")
+    print(f"Total time: {duration:.2f} seconds")
+    print(f"Average time per file: {duration / len(pdf_files):.2f} seconds")
+
+    if failed:
+        print("\nFailed files:")
+        for result in failed:
+            print(f"  - {result['file']}: {result.get('error', 'Unknown error')}")
+
+    return results
+
+
+def main():
+    """Main entry point for the script."""
+    parser = argparse.ArgumentParser(
+        description="Batch process PDFs in a folder with LlamaParse"
+    )
+    parser.add_argument(
+        "--input-dir",
+        type=str,
+        required=True,
+        help="Directory containing PDF files to parse",
+    )
+    parser.add_argument(
+        "--max-concurrent",
+        type=int,
+        default=5,
+        help="Maximum number of concurrent parse operations (default: 5)",
+    )
+
+    args = parser.parse_args()
+
+    input_dir = Path(args.input_dir)
+
+    # Validate input directory
+    if not input_dir.exists():
+        print(f"Error: Input directory does not exist: {input_dir}")
+        return
+
+    if not input_dir.is_dir():
+        print(f"Error: Input path is not a directory: {input_dir}")
+        return
+
+    # Get API key from environment (loaded from .env file)
+    api_key = os.getenv("LLAMA_CLOUD_API_KEY")
+    if not api_key:
+        print("Error: LLAMA_CLOUD_API_KEY not found. Please set it in your .env file")
+        return
+
+    # Run async function
+    asyncio.run(
+        parse_folder(
+            input_dir=input_dir,
+            max_concurrent=args.max_concurrent,
+            api_key=api_key,
+        )
+    )
+
+
+if __name__ == "__main__":
+    main()

examples/split/document_splitting/document_splitting.ipynb

@@ -0,0 +1,540 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Document Splitting with LlamaCloud\n",
+    "\n",
+    "This notebook demonstrates how to use the LlamaCloud **Split** API to automatically segment a concatenated PDF into logical document sections based on content categories.\n",
+    "\n",
+    "## Use Case\n",
+    "\n",
+    "When dealing with large PDFs that contain multiple distinct documents or sections (e.g., a bundle of research papers, a collection of reports), you often need to split them into individual segments. The Split API uses AI to:\n",
+    "\n",
+    "1. Analyze each page's content\n",
+    "2. Classify pages into user-defined categories\n",
+    "3. Group consecutive pages of the same category into segments\n",
+    "\n",
+    "## Example Document\n",
+    "\n",
+    "We'll use a PDF containing three concatenated documents:\n",
+    "- **Alan Turing's essay** \"Intelligent Machinery, A Heretical Theory\" (an essay)\n",
+    "- **ImageNet paper** (a research paper)\n",
+    "- **\"Attention is All You Need\"** paper (a research paper)\n",
+    "\n",
+    "We'll split this into segments categorized as either `essay` or `research_paper`.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: llama-cloud in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (0.1.44)\n",
+      "Requirement already satisfied: python-dotenv in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (1.2.1)\n",
+      "Requirement already satisfied: requests in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (2.32.5)\n",
+      "Requirement already satisfied: certifi>=2024.7.4 in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (from llama-cloud) (2025.11.12)\n",
+      "Requirement already satisfied: httpx>=0.20.0 in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (from llama-cloud) (0.28.1)\n",
+      "Requirement already satisfied: pydantic>=1.10 in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (from llama-cloud) (2.12.5)\n",
+      "Requirement already satisfied: charset_normalizer<4,>=2 in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (from requests) (3.4.4)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (from requests) (3.11)\n",
+      "Requirement already satisfied: urllib3<3,>=1.21.1 in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (from requests) (2.5.0)\n",
+      "Requirement already satisfied: anyio in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (from httpx>=0.20.0->llama-cloud) (4.11.0)\n",
+      "Requirement already satisfied: httpcore==1.* in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (from httpx>=0.20.0->llama-cloud) (1.0.9)\n",
+      "Requirement already satisfied: h11>=0.16 in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (from httpcore==1.*->httpx>=0.20.0->llama-cloud) (0.16.0)\n",
+      "Requirement already satisfied: annotated-types>=0.6.0 in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (from pydantic>=1.10->llama-cloud) (0.7.0)\n",
+      "Requirement already satisfied: pydantic-core==2.41.5 in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (from pydantic>=1.10->llama-cloud) (2.41.5)\n",
+      "Requirement already satisfied: typing-extensions>=4.14.1 in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (from pydantic>=1.10->llama-cloud) (4.15.0)\n",
+      "Requirement already satisfied: typing-inspection>=0.4.2 in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (from pydantic>=1.10->llama-cloud) (0.4.2)\n",
+      "Requirement already satisfied: sniffio>=1.1 in /Users/javier/llama_cloud_services/.venv/lib/python3.11/site-packages (from anyio->httpx>=0.20.0->llama-cloud) (1.3.1)\n",
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m25.0.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m25.3\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Install required packages\n",
+    "%pip install llama-cloud python-dotenv requests"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "✅ API configured with base URL: https://api.cloud.llamaindex.ai\n",
+      "✅ Project ID: using default project\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import time\n",
+    "import requests\n",
+    "from dotenv import load_dotenv\n",
+    "\n",
+    "# Load environment variables\n",
+    "load_dotenv()\n",
+    "\n",
+    "# Configuration\n",
+    "LLAMA_CLOUD_API_KEY = os.environ.get(\"LLAMA_CLOUD_API_KEY\", \"llx-...\")\n",
+    "BASE_URL = os.environ.get(\"LLAMA_CLOUD_BASE_URL\", \"https://api.cloud.llamaindex.ai\")\n",
+    "PROJECT_ID = os.environ.get(\"LLAMA_CLOUD_PROJECT_ID\", None)\n",
+    "\n",
+    "# Headers for API requests\n",
+    "headers = {\n",
+    "    \"Authorization\": f\"Bearer {LLAMA_CLOUD_API_KEY}\",\n",
+    "    \"Content-Type\": \"application/json\",\n",
+    "}\n",
+    "\n",
+    "print(f\"✅ API configured with base URL: {BASE_URL}\")\n",
+    "print(f\"✅ Project ID: {PROJECT_ID or 'using default project'}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Step 1: Upload the PDF File\n",
+    "\n",
+    "First, we'll upload our concatenated PDF to LlamaCloud using the Files API. This can be done using the `llama-cloud` SDK.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "📤 Uploading ./data/turing+imagenet+attention.pdf...\n",
+      "✅ File uploaded successfully!\n",
+      "   File name: turing+imagenet+attention.pdf\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_cloud.client import LlamaCloud\n",
+    "\n",
+    "# Initialize the client\n",
+    "client = LlamaCloud(token=LLAMA_CLOUD_API_KEY, base_url=BASE_URL)\n",
+    "\n",
+    "# Path to the PDF file\n",
+    "pdf_path = \"./data/turing+imagenet+attention.pdf\"\n",
+    "\n",
+    "# Upload the file\n",
+    "print(f\"📤 Uploading {pdf_path}...\")\n",
+    "\n",
+    "with open(pdf_path, \"rb\") as f:\n",
+    "    uploaded_file = client.files.upload_file(upload_file=f, project_id=PROJECT_ID)\n",
+    "\n",
+    "file_id = uploaded_file.id\n",
+    "print(f\"✅ File uploaded successfully!\")\n",
+    "print(f\"   File name: {uploaded_file.name}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Step 2: Create a Split Job\n",
+    "\n",
+    "Now we'll create a split job using the Split API. Since the Split API is in beta and not yet available in the SDK, we'll use raw HTTP requests.\n",
+    "\n",
+    "We define two categories:\n",
+    "- **essay**: For philosophical or reflective writing\n",
+    "- **research_paper**: For formal academic documents with methodology and citations\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "🔄 Creating split job...\n",
+      "✅ Split job created!\n",
+      "   Job ID: spl-zsssb632a742aikliu96pqkb56t5\n",
+      "   Status: pending\n",
+      "   Categories: ['essay', 'research_paper']\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Define the split job request\n",
+    "split_request = {\n",
+    "    \"document_input\": {\n",
+    "        \"type\": \"file_id\",  # only file_id is supported for now\n",
+    "        \"value\": file_id,\n",
+    "    },\n",
+    "    \"categories\": [\n",
+    "        {\n",
+    "            \"name\": \"essay\",\n",
+    "            \"description\": \"A philosophical or reflective piece of writing that presents personal viewpoints, arguments, or thoughts on a topic without strict formal structure\",\n",
+    "        },\n",
+    "        {\n",
+    "            \"name\": \"research_paper\",\n",
+    "            \"description\": \"A formal academic document presenting original research, methodology, experiments, results, and conclusions with citations and references\",\n",
+    "        },\n",
+    "    ],\n",
+    "}\n",
+    "\n",
+    "# Create the split job\n",
+    "print(\"🔄 Creating split job...\")\n",
+    "response = requests.post(\n",
+    "    f\"{BASE_URL}/api/v1/beta/split/jobs\",\n",
+    "    params={\"project_id\": PROJECT_ID},\n",
+    "    headers=headers,\n",
+    "    json=split_request,\n",
+    ")\n",
+    "response.raise_for_status()\n",
+    "\n",
+    "split_job = response.json()\n",
+    "job_id = split_job[\"id\"]\n",
+    "\n",
+    "print(f\"✅ Split job created!\")\n",
+    "print(f\"   Job ID: {job_id}\")\n",
+    "print(f\"   Status: {split_job['status']}\")\n",
+    "print(f\"   Categories: {[c['name'] for c in split_job['categories']]}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Step 3: Poll for Job Completion\n",
+    "\n",
+    "The split job runs asynchronously. We'll poll the job status until it completes.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "⏳ Waiting for split job to complete...\n",
+      "   Status: processing (elapsed: 0s)\n",
+      "   Status: processing (elapsed: 5s)\n",
+      "   Status: processing (elapsed: 11s)\n",
+      "   Status: completed (elapsed: 16s)\n",
+      "\n",
+      "✅ Split job completed successfully!\n"
+     ]
+    }
+   ],
+   "source": [
+    "def poll_split_job(job_id: str, max_wait_seconds: int = 180, poll_interval: int = 5):\n",
+    "    \"\"\"\n",
+    "    Poll a split job until it reaches a terminal state.\n",
+    "\n",
+    "    Args:\n",
+    "        job_id: The split job ID\n",
+    "        max_wait_seconds: Maximum time to wait for completion\n",
+    "        poll_interval: Seconds between poll attempts\n",
+    "\n",
+    "    Returns:\n",
+    "        The completed job response\n",
+    "    \"\"\"\n",
+    "    start_time = time.time()\n",
+    "\n",
+    "    while (time.time() - start_time) < max_wait_seconds:\n",
+    "        response = requests.get(\n",
+    "            f\"{BASE_URL}/api/v1/beta/split/jobs/{job_id}\",\n",
+    "            params={\"project_id\": PROJECT_ID},\n",
+    "            headers=headers,\n",
+    "        )\n",
+    "        response.raise_for_status()\n",
+    "        job = response.json()\n",
+    "\n",
+    "        status = job[\"status\"]\n",
+    "        elapsed = int(time.time() - start_time)\n",
+    "        print(f\"   Status: {status} (elapsed: {elapsed}s)\")\n",
+    "\n",
+    "        if status in [\"completed\", \"failed\"]:\n",
+    "            return job\n",
+    "\n",
+    "        time.sleep(poll_interval)\n",
+    "\n",
+    "    raise TimeoutError(f\"Job did not complete within {max_wait_seconds} seconds\")\n",
+    "\n",
+    "\n",
+    "print(\"⏳ Waiting for split job to complete...\")\n",
+    "completed_job = poll_split_job(job_id)\n",
+    "\n",
+    "if completed_job[\"status\"] == \"completed\":\n",
+    "    print(\"\\n✅ Split job completed successfully!\")\n",
+    "else:\n",
+    "    print(\n",
+    "        f\"\\n❌ Split job failed: {completed_job.get('error_message', 'Unknown error')}\"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Step 4: Analyze the Results\n",
+    "\n",
+    "Let's examine the split results to see how the document was segmented.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "📊 Split Results Summary\n",
+      "==================================================\n",
+      "Total segments found: 3\n",
+      "\n",
+      "Segments by category:\n",
+      "   • essay: 1 segment(s)\n",
+      "   • research_paper: 2 segment(s)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Get the segments from the result\n",
+    "segments = completed_job.get(\"result\", {}).get(\"segments\", [])\n",
+    "\n",
+    "print(f\"📊 Split Results Summary\")\n",
+    "print(f\"=\" * 50)\n",
+    "print(f\"Total segments found: {len(segments)}\")\n",
+    "print()\n",
+    "\n",
+    "# Count by category\n",
+    "category_counts = {}\n",
+    "for segment in segments:\n",
+    "    cat = segment[\"category\"]\n",
+    "    category_counts[cat] = category_counts.get(cat, 0) + 1\n",
+    "\n",
+    "print(\"Segments by category:\")\n",
+    "for cat, count in category_counts.items():\n",
+    "    print(f\"   • {cat}: {count} segment(s)\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "📄 Segment Details\n",
+      "==================================================\n",
+      "\n",
+      "Segment 1:\n",
+      "   Category: essay\n",
+      "   Pages 1-4 (4 pages)\n",
+      "   Confidence: high\n",
+      "\n",
+      "Segment 2:\n",
+      "   Category: research_paper\n",
+      "   Pages 5-13 (9 pages)\n",
+      "   Confidence: high\n",
+      "\n",
+      "Segment 3:\n",
+      "   Category: research_paper\n",
+      "   Pages 14-24 (11 pages)\n",
+      "   Confidence: high\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Display detailed segment information\n",
+    "print(f\"\\n📄 Segment Details\")\n",
+    "print(f\"=\" * 50)\n",
+    "\n",
+    "for i, segment in enumerate(segments, 1):\n",
+    "    category = segment[\"category\"]\n",
+    "    pages = segment[\"pages\"]\n",
+    "    confidence = segment[\"confidence_category\"]\n",
+    "\n",
+    "    # Format page range\n",
+    "    if len(pages) == 1:\n",
+    "        page_range = f\"Page {pages[0]}\"\n",
+    "    else:\n",
+    "        page_range = f\"Pages {min(pages)}-{max(pages)}\"\n",
+    "\n",
+    "    print(f\"\\nSegment {i}:\")\n",
+    "    print(f\"   Category: {category}\")\n",
+    "    print(f\"   {page_range} ({len(pages)} page{'s' if len(pages) > 1 else ''})\")\n",
+    "    print(f\"   Confidence: {confidence}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Expected Results\n",
+    "\n",
+    "Based on our test document, we expect:\n",
+    "- **1 essay segment**: Alan Turing's \"Intelligent Machinery, A Heretical Theory\"\n",
+    "- **2 research paper segments**: ImageNet paper and \"Attention is All You Need\" paper\n",
+    "\n",
+    "The pages should be grouped consecutively, with no overlap between segments.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "✅ Validation\n",
+      "==================================================\n",
+      "Total pages assigned: 24\n",
+      "Unique pages: 24\n",
+      "✅ No page overlap detected - each page belongs to exactly one segment\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Verify no page overlap\n",
+    "all_pages = []\n",
+    "for segment in segments:\n",
+    "    all_pages.extend(segment[\"pages\"])\n",
+    "\n",
+    "unique_pages = set(all_pages)\n",
+    "\n",
+    "print(f\"\\n✅ Validation\")\n",
+    "print(f\"=\" * 50)\n",
+    "print(f\"Total pages assigned: {len(all_pages)}\")\n",
+    "print(f\"Unique pages: {len(unique_pages)}\")\n",
+    "\n",
+    "if len(all_pages) == len(unique_pages):\n",
+    "    print(f\"✅ No page overlap detected - each page belongs to exactly one segment\")\n",
+    "else:\n",
+    "    print(\n",
+    "        f\"⚠️  Page overlap detected - {len(all_pages) - len(unique_pages)} duplicate assignments\"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Using `allow_uncategorized` Strategy\n",
+    "\n",
+    "You can also use the `allow_uncategorized` splitting strategy. This is useful when you want to capture pages that don't match any defined category.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "📝 With allow_uncategorized=True and only 'essay' category defined,\n",
+      "   pages that don't match 'essay' will be grouped as 'uncategorized'.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Example with allow_uncategorized strategy\n",
+    "split_request_uncategorized = {\n",
+    "    \"document_input\": {\"type\": \"file_id\", \"value\": file_id},\n",
+    "    \"categories\": [\n",
+    "        {\n",
+    "            \"name\": \"essay\",\n",
+    "            \"description\": \"A philosophical or reflective piece of writing that presents personal viewpoints, arguments, or thoughts on a topic\",\n",
+    "        }\n",
+    "        # Note: We only define 'essay' category\n",
+    "        # Research papers will be classified as 'uncategorized'\n",
+    "    ],\n",
+    "    \"splitting_strategy\": {\"allow_uncategorized\": True},\n",
+    "}\n",
+    "\n",
+    "print(\"📝 With allow_uncategorized=True and only 'essay' category defined,\")\n",
+    "print(\"   pages that don't match 'essay' will be grouped as 'uncategorized'.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Conclusion\n",
+    "\n",
+    "The LlamaCloud Split API provides a powerful way to automatically segment concatenated documents based on content categories. This is useful for:\n",
+    "\n",
+    "- **Document processing pipelines**: Automatically separate bundled documents before further processing\n",
+    "- **Content organization**: Categorize and organize mixed document collections\n",
+    "- **Information extraction**: Identify different document types within a single file\n",
+    "\n",
+    "### Key Features\n",
+    "\n",
+    "- **AI-powered classification**: Uses LLMs to understand page content and assign categories\n",
+    "- **Flexible categories**: Define any categories relevant to your use case\n",
+    "- **Confidence scoring**: Each segment includes a confidence level\n",
+    "- **Page-level granularity**: Results include exact page numbers for each segment\n",
+    "\n",
+    "### API Reference\n",
+    "\n",
+    "- **Create Split Job**: `POST /api/v1/beta/split/jobs`\n",
+    "- **Get Split Job**: `GET /api/v1/beta/split/jobs/{job_id}`\n",
+    "- **List Split Jobs**: `GET /api/v1/beta/split/jobs`\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "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
+}

extract.md

@@ -398,6 +398,6 @@ Another option (orthogonal to the above) is to break the document into smaller s
 ## Additional Resources
 
 - [Extract Documentation](https://docs.cloud.llamaindex.ai/llamaextract/getting_started) - Details on Extract features, API and examples.
-- [Example Notebook](docs/examples-py/extract/resume_screening.ipynb) - Detailed walkthrough of resume parsing
+- [Example Notebook](examples/extract/resume_screening.ipynb) - Detailed walkthrough of resume parsing
 - [Example Application with TypeScript](./examples-ts/extract/) - End-to-end examples using LlamaExtract TypeScript client.
 - [Discord Community](https://discord.com/invite/eN6D2HQ4aX) - Get help and share feedback

parse.md

@@ -97,7 +97,7 @@ for page in result.pages:
     print(page.structuredData)
 ```
 
-See more details about the result object in the [example notebook](./docs/examples-py/parse/demo_json_tour.ipynb).
+See more details about the result object in the [example notebook](./examples/parse/demo_json_tour.ipynb).
 
 ### Using with file object / bytes
 
@@ -153,10 +153,10 @@ Full documentation for `SimpleDirectoryReader` can be found on the [LlamaIndex D
 
 Several end-to-end indexing examples can be found in the examples folder
 
-- [Getting Started](docs/examples-py/parse/demo_basic.ipynb)
-- [Advanced RAG Example](docs/examples-py/parse/demo_advanced.ipynb)
-- [Raw API Usage](docs/examples-py/parse/demo_api.ipynb)
-- [Result Object Tour](docs/examples-py/parse/demo_json_tour.ipynb)
+- [Getting Started](examples/parse/demo_basic.ipynb)
+- [Advanced RAG Example](examples/parse/demo_advanced.ipynb)
+- [Raw API Usage](examples/parse/demo_api.ipynb)
+- [Result Object Tour](examples/parse/demo_json_tour.ipynb)
 
 ## Documentation
 

py/CHANGELOG.md

@@ -1,5 +1,53 @@
 # llama-cloud-services-py
 
+## 0.6.90
+
+### Patch Changes
+
+- 19cbb25: Remove extension filter
+
+## 0.6.89
+
+### Patch Changes
+
+- b9b83c9: Parse bounding boxes from extract jobs results in agent data
+
+## 0.6.88
+
+### Patch Changes
+
+- 71db318: Add tier and version
+
+## 0.6.87
+
+### Patch Changes
+
+- 06c3c55: Update spreadsheet parsing config
+
+## 0.6.86
+
+### Patch Changes
+
+- 1b7198d: Update extract to have confidence scores available in all modes
+
+## 0.6.85
+
+### Patch Changes
+
+- ae30990: Add line-level bbox support
+
+## 0.6.84
+
+### Patch Changes
+
+- 0a110de: Release to re-align versions
+
+## 0.6.83
+
+### Patch Changes
+
+- ca78113: Do not use presigned URLs by default in files client
+
 ## 0.6.82
 
 ### Patch Changes

py/Makefile

@@ -15,4 +15,4 @@ test:	## Run unit tests via pytest
 
 .PHONY: e2e
 e2e:	## Run all tests. Run with high parallelism using xdist since tests are bottlenecked bound by the slow backend parsing
-	uv run pytest -v -n 32 tests/
+	uv run pytest -v -n 32 --timeout=300 --session-timeout=1740 tests/

py/llama_cloud_services/beta/agent_data/__init__.py

@@ -11,6 +11,9 @@ from .schema import (
     InvalidExtractionData,
     ExtractedFieldMetadata,
     ExtractedFieldMetaDataDict,
+    FieldCitation,
+    BoundingBox,
+    PageDimensions,
 )
 from .client import AsyncAgentDataClient
 
@@ -28,4 +31,7 @@ __all__ = [
     "InvalidExtractionData",
     "ExtractedFieldMetadata",
     "ExtractedFieldMetaDataDict",
+    "FieldCitation",
+    "BoundingBox",
+    "PageDimensions",
 ]

py/llama_cloud_services/beta/agent_data/schema.py

@@ -174,6 +174,22 @@ class TypedAgentDataItems(BaseModel, Generic[AgentDataT]):
     )
 
 
+class BoundingBox(BaseModel):
+    """Bounding box coordinates for a citation location on a page."""
+
+    x: float = Field(description="X coordinate of the bounding box origin")
+    y: float = Field(description="Y coordinate of the bounding box origin")
+    w: float = Field(description="Width of the bounding box")
+    h: float = Field(description="Height of the bounding box")
+
+
+class PageDimensions(BaseModel):
+    """Dimensions of a page in the source document."""
+
+    width: float = Field(description="Width of the page")
+    height: float = Field(description="Height of the page")
+
+
 class FieldCitation(BaseModel):
     page: Optional[int] = Field(
         None, description="The page number that the field occurred on"
@@ -182,6 +198,14 @@ class FieldCitation(BaseModel):
         None,
         description="The original text this field's value was derived from",
     )
+    bounding_boxes: Optional[List[BoundingBox]] = Field(
+        None,
+        description="Bounding boxes indicating where the citation appears on the page",
+    )
+    page_dimensions: Optional[PageDimensions] = Field(
+        None,
+        description="Dimensions of the page containing the citation",
+    )
 
 
 class ExtractedFieldMetadata(BaseModel):
@@ -201,6 +225,10 @@ class ExtractedFieldMetadata(BaseModel):
         None,
         description="The confidence score for the field based on the extracted text only",
     )
+    parsing_confidence: Optional[float] = Field(
+        None,
+        description="The confidence score for the field based on the parsing/OCR quality",
+    )
     citation: Optional[List[FieldCitation]] = Field(
         None,
         description="The citation for the field, including page number and matching text",
@@ -447,26 +475,49 @@ class ExtractedData(BaseModel, Generic[ExtractedT]):
                 },
             )
         except ValidationError as e:
+            # Capture the job-level error from the extraction run if available
+            job_error = result.error
+
             invalid_item = ExtractedData[Dict[str, Any]].create(
                 data=result.data or {},
                 status="error",
                 field_metadata=field_metadata,
-                metadata={"extraction_error": str(e), **(metadata or {})},
+                metadata={
+                    "extraction_error": str(e),
+                    **({"job_error": job_error} if job_error else {}),
+                    **(metadata or {}),
+                },
                 file_id=file_id,
                 file_name=file_name,
                 file_hash=file_hash,
             )
-            raise InvalidExtractionData(invalid_item) from e
+            raise InvalidExtractionData(invalid_item, extraction_error=job_error) from e
 
 
 class InvalidExtractionData(Exception):
     """
     Exception raised when the extracted data does not conform to the schema.
+
+    Attributes:
+        invalid_item: The ExtractedData instance containing the invalid data and metadata
+        extraction_error: The error message from the extraction job, if available
     """
 
-    def __init__(self, invalid_item: ExtractedData[Dict[str, Any]]):
+    def __init__(
+        self,
+        invalid_item: ExtractedData[Dict[str, Any]],
+        extraction_error: Optional[str] = None,
+    ):
         self.invalid_item = invalid_item
-        super().__init__("Not able to parse the extracted data, parsed invalid format")
+        self.extraction_error = extraction_error
+
+        # Build an informative error message
+        if extraction_error:
+            message = f"Extraction error: {extraction_error}"
+        else:
+            message = "Not able to parse the extracted data, parsed invalid format"
+
+        super().__init__(message)
 
 
 def calculate_overall_confidence(

py/llama_cloud_services/beta/sheets/client.py

@@ -2,7 +2,7 @@ import asyncio
 import io
 import os
 import time
-from typing import TYPE_CHECKING
+from typing import Any, Dict, TYPE_CHECKING
 
 import httpx
 from llama_cloud.client import AsyncLlamaCloud
@@ -68,6 +68,8 @@ class LlamaSheets:
         max_timeout: int = 300,
         poll_interval: int = 5,
         max_retries: int = 3,
+        project_id: str | None = None,
+        organization_id: str | None = None,
         async_httpx_client: httpx.AsyncClient | None = None,
     ) -> None:
         """Initialize the LlamaSheets client.
@@ -78,6 +80,8 @@ class LlamaSheets:
             max_timeout: Maximum time to wait for job completion in seconds
             poll_interval: Interval between status checks in seconds
             max_retries: Maximum number of retries for failed requests
+            project_id: Project ID for file operations. If not provided, will use LLAMA_CLOUD_PROJECT_ID env var
+            organization_id: Organization ID for file operations. If not provided, will use LLAMA_CLOUD_ORGANIZATION_ID env var
             async_httpx_client: Optional custom async httpx client
         """
         self.api_key = api_key or os.environ.get("LLAMA_CLOUD_API_KEY")
@@ -93,15 +97,32 @@ class LlamaSheets:
         self.poll_interval = poll_interval
         self.max_retries = max_retries
 
+        self.project_id = project_id or os.environ.get("LLAMA_CLOUD_PROJECT_ID")
+        self.organization_id = organization_id or os.environ.get(
+            "LLAMA_CLOUD_ORGANIZATION_ID"
+        )
+
         self._async_client: httpx.AsyncClient | None = async_httpx_client
         self._files_client = FileClient(
             AsyncLlamaCloud(
                 token=self.api_key,
                 base_url=self.base_url,
                 httpx_client=async_httpx_client,
-            )
+            ),
+            project_id=self.project_id,
+            organization_id=self.organization_id,
         )
 
+    def _get_default_params(self) -> dict[str, str]:
+        """Get default query parameters for API requests"""
+        params = {}
+        if self.project_id is not None:
+            params["project_id"] = self.project_id
+        if self.organization_id is not None:
+            params["organization_id"] = self.organization_id
+
+        return params
+
     def _get_async_client(self) -> httpx.AsyncClient:
         """Get or create the async httpx client"""
         if self._async_client is None:
@@ -306,6 +327,8 @@ class LlamaSheets:
             "config": config.model_dump(mode="json", exclude_none=True),
         }
 
+        params = self._get_default_params()
+
         try:
             async for attempt in AsyncRetrying(
                 stop=stop_after_attempt(self.max_retries),
@@ -318,6 +341,7 @@ class LlamaSheets:
                     response = await client.post(
                         f"{self.base_url}/api/v1/beta/sheets/jobs",
                         headers=self._get_headers(),
+                        params=params,
                         json=payload,
                     )
                     response.raise_for_status()
@@ -347,12 +371,17 @@ class LlamaSheets:
             ):
                 with attempt:
                     client = self._get_async_client()
+                    params: Dict[str, Any] = {
+                        "include_results": include_results_metadata,
+                        **self._get_default_params(),
+                    }
                     response = await client.get(
                         f"{self.base_url}/api/v1/beta/sheets/jobs/{job_id}",
                         headers=self._get_headers(),
-                        params={"include_results": include_results_metadata},
+                        params=params,
                     )
                     response.raise_for_status()
+
                     return SpreadsheetJobResult.model_validate(response.json())
         except Exception as e:
             raise SpreadsheetAPIError(f"Failed to get job status: {e}") from e
@@ -415,6 +444,8 @@ class LlamaSheets:
         # Get presigned URL
         presigned_response = None
         result_type_str = str(result_type)
+        params = self._get_default_params()
+
         try:
             async for attempt in AsyncRetrying(
                 stop=stop_after_attempt(self.max_retries),
@@ -427,6 +458,7 @@ class LlamaSheets:
                     response = await client.get(
                         f"{self.base_url}/api/v1/beta/sheets/jobs/{job_id}/regions/{region_id}/result/{result_type_str}",
                         headers=self._get_headers(),
+                        params=params,
                     )
                     response.raise_for_status()
                     presigned_response = PresignedUrlResponse.model_validate(

py/llama_cloud_services/beta/sheets/types.py

@@ -1,5 +1,6 @@
 from datetime import datetime
 from enum import Enum
+from typing import Literal
 
 from pydantic import BaseModel, ConfigDict, Field, field_validator
 
@@ -63,7 +64,7 @@ class SpreadsheetParseResult(BaseModel):
 class SpreadsheetParsingConfig(BaseModel):
     """Configuration for spreadsheet parsing and region extraction"""
 
-    model_config = ConfigDict(extra="forbid")
+    model_config = ConfigDict(extra="ignore")
 
     sheet_names: list[str] | None = Field(
         default=None,
@@ -86,6 +87,16 @@ class SpreadsheetParsingConfig(BaseModel):
         description="Enables experimental processing. Accuracy may be impacted.",
     )
 
+    flatten_hierarchical_tables: bool = Field(
+        default=False,
+        description="Return a flattened dataframe when a detected table is recognized as hierarchical.",
+    )
+
+    table_merge_sensitivity: Literal["strong", "weak"] = Field(
+        default="strong",
+        description="Influences how likely similar-looking regions are merged into a single table. Useful for spreadsheets that either have sparse tables (strong merging) or many distinct tables close together (weak merging).",
+    )
+
 
 class SpreadsheetJob(BaseModel):
     """A spreadsheet parsing job"""

py/llama_cloud_services/extract/extract.py

@@ -240,11 +240,6 @@ def _extraction_config_warning(config: ExtractConfig) -> None:
             raise ValueError(
                 "`cite_sources` is only supported with MULTIMODAL or PREMIUM extraction modes."
             )
-    if config.confidence_scores:
-        if config.extraction_mode in (ExtractMode.FAST, ExtractMode.BALANCED):
-            raise ValueError(
-                "`confidence_scores` is only supported with MULTIMODAL or PREMIUM extraction modes."
-            )
 
 
 class ExtractionAgent:

py/llama_cloud_services/files/client.py

@@ -11,7 +11,7 @@ from llama_cloud_services.utils import SourceText, FileInput
 class FileClient:
     """
     Higher-level client for interacting with the LlamaCloud Files API.
-    Uses presigned URLs for uploads by default.
+    Optionally uses presigned URLs for uploads.
 
     Args:
         client: The LlamaCloud client to use.
@@ -25,7 +25,7 @@ class FileClient:
         client: AsyncLlamaCloud,
         project_id: Optional[str] = None,
         organization_id: Optional[str] = None,
-        use_presigned_url: bool = True,
+        use_presigned_url: bool = False,
     ):
         self.client = client
         self.project_id = project_id
@@ -91,6 +91,10 @@ class FileClient:
                 organization_id=self.organization_id,
             )
         else:
+            # Set buffer.name if not already set, so the upload uses external_file_id
+            # for file type detection
+            if not getattr(buffer, "name", None):
+                setattr(buffer, "name", external_file_id)
             return await self.client.files.upload_file(
                 upload_file=buffer,
                 external_file_id=external_file_id,

py/llama_cloud_services/index/base.py

@@ -654,6 +654,9 @@ class LlamaCloudIndex(BaseManagedIndex):
             ],
         )
 
+        # Trigger a sync
+        client.pipelines.sync_pipeline(pipeline_id=index.pipeline.id)
+
         doc_ids = [doc.id for doc in upserted_documents]
         index.wait_for_completion(
             doc_ids=doc_ids, verbose=verbose, raise_on_error=raise_on_error
@@ -738,6 +741,10 @@ class LlamaCloudIndex(BaseManagedIndex):
                     )
                 ],
             )
+
+            # Trigger a sync
+            self._client.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
+
             upserted_document = upserted_documents[0]
             self.wait_for_completion(
                 doc_ids=[upserted_document.id], verbose=verbose, raise_on_error=True
@@ -760,6 +767,9 @@ class LlamaCloudIndex(BaseManagedIndex):
                     )
                 ],
             )
+            # Trigger a sync
+            await self._aclient.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
+
             upserted_document = upserted_documents[0]
             await self.await_for_completion(
                 doc_ids=[upserted_document.id], verbose=verbose, raise_on_error=True
@@ -782,6 +792,9 @@ class LlamaCloudIndex(BaseManagedIndex):
                     )
                 ],
             )
+            # Trigger a sync
+            self._client.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
+
             upserted_document = upserted_documents[0]
             self.wait_for_completion(
                 doc_ids=[upserted_document.id], verbose=verbose, raise_on_error=True
@@ -804,6 +817,9 @@ class LlamaCloudIndex(BaseManagedIndex):
                     )
                 ],
             )
+            # Trigger a sync
+            await self._aclient.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
+
             upserted_document = upserted_documents[0]
             await self.await_for_completion(
                 doc_ids=[upserted_document.id], verbose=verbose, raise_on_error=True
@@ -827,6 +843,9 @@ class LlamaCloudIndex(BaseManagedIndex):
                     for doc in documents
                 ],
             )
+            # Trigger a sync
+            self._client.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
+
             doc_ids = [doc.id for doc in upserted_documents]
             self.wait_for_completion(doc_ids=doc_ids, verbose=True, raise_on_error=True)
             return [True] * len(doc_ids)
@@ -849,6 +868,9 @@ class LlamaCloudIndex(BaseManagedIndex):
                     for doc in documents
                 ],
             )
+            # Trigger a sync
+            await self._aclient.pipelines.sync_pipeline(pipeline_id=self.pipeline.id)
+
             doc_ids = [doc.id for doc in upserted_documents]
             await self.await_for_completion(
                 doc_ids=doc_ids, verbose=True, raise_on_error=True

py/llama_cloud_services/parse/base.py

@@ -285,7 +285,7 @@ class LlamaParse(BasePydanticReader):
         description="Note: Non compatible with gpt-4o. If set to true, the parser will use a faster mode to extract text from documents. This mode will skip OCR of images, and table/heading reconstruction.",
     )
 
-    guess_xlsx_sheet_names: Optional[bool] = Field(
+    guess_xlsx_sheet_name: Optional[bool] = Field(
         default=False,
         description="Whether to guess the sheet names of the xlsx file.",
     )
@@ -313,6 +313,10 @@ class LlamaParse(BasePydanticReader):
         default=False,
         description="If set to true, the parser will ignore document elements for layout detection and only rely on a vision model.",
     )
+    inline_images_in_markdown: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will inline images in the markdown output.",
+    )
     input_s3_region: Optional[str] = Field(
         default=None,
         description="The region of the input S3 bucket if input_s3_path is specified.",
@@ -329,6 +333,10 @@ class LlamaParse(BasePydanticReader):
         default=None,
         description="The maximum timeout in seconds to wait for the parsing to finish. Override default timeout of 30 minutes. Minimum is 120 seconds.",
     )
+    keep_page_separator_when_merging_tables: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will keep the page separator when merging tables across pages.",
+    )
     language: Optional[str] = Field(
         default="en", description="The language of the text to parse."
     )
@@ -400,6 +408,10 @@ class LlamaParse(BasePydanticReader):
         default=False,
         description="If set, the parser will try to preserve very small text lines. This can be useful for documents containing vector graphics with very small text lines that may not be recognized by OCR or a vision model (such as in CAD drawings).",
     )
+    presentation_out_of_bounds_content: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will include out-of-bounds content in presentation files.",
+    )
     precise_bounding_box: Optional[bool] = Field(
         default=False,
         description="If set to true, the parser will use a more precise bounding box to extract text from documents. This will increase the accuracy of the parsing job, but reduce the speed.",
@@ -416,6 +428,14 @@ class LlamaParse(BasePydanticReader):
         default=None,
         description="A suffix to add after error message in failed pages. If not set, no suffix will be used.",
     )
+    remove_hidden_text: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will remove hidden text from the document.",
+    )
+    save_images: Optional[bool] = Field(
+        default=True,
+        description="If set to true, the parser will save images extracted from the document.",
+    )
     skip_diagonal_text: Optional[bool] = Field(
         default=False,
         description="If set to true, the parser will ignore diagonal text (when the text rotation in degrees modulo 90 is not 0).",
@@ -440,6 +460,10 @@ class LlamaParse(BasePydanticReader):
         default=False,
         description="If set to true, the parser will use a specialized one-shot chart parsing model to extract data from charts. This model is able to understand the chart type and extract the data accordingly. It is more accurate than the efficient model, but also more expensive.",
     )
+    specialized_image_parsing: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will use a specialized image parsing model to extract data from images.",
+    )
     strict_mode_buggy_font: Optional[bool] = Field(
         default=False,
         description="If set to true, the parser will fail if it can't extract text from a document because of a buggy font.",
@@ -540,6 +564,17 @@ class LlamaParse(BasePydanticReader):
         default=None,
         description="Whether to extract the printed page numbers from pages in the document.",
     )
+    line_level_bounding_box: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will include line-level bounding boxes in the result.",
+    )
+    tier: Optional[str] = Field(
+        default=None, description="The tier to use for the parsing job."
+    )
+    version: Optional[str] = Field(
+        default=None,
+        description="The version of the parser to use at the specified tier.",
+    )
 
     # Deprecated
     bounding_box: Optional[str] = Field(
@@ -584,6 +619,23 @@ class LlamaParse(BasePydanticReader):
         description="Automatically check for Python SDK updates.",
     )
 
+    @model_validator(mode="before")
+    @classmethod
+    def handle_deprecated_params(cls, data: Dict[str, Any]) -> Dict[str, Any]:
+        # Handle deprecated guess_xlsx_sheet_names -> guess_xlsx_sheet_name
+        if "guess_xlsx_sheet_names" in data:
+            warnings.warn(
+                "The parameter 'guess_xlsx_sheet_names' is deprecated and will be removed in a future release. "
+                "Use 'guess_xlsx_sheet_name' instead.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+            # Only set the new parameter if it's not already explicitly set
+            if "guess_xlsx_sheet_name" not in data:
+                data["guess_xlsx_sheet_name"] = data["guess_xlsx_sheet_names"]
+            del data["guess_xlsx_sheet_names"]
+        return data
+
     @model_validator(mode="before")
     @classmethod
     def warn_extra_params(cls, data: Dict[str, Any]) -> Dict[str, Any]:
@@ -699,11 +751,9 @@ class LlamaParse(BasePydanticReader):
             file_path = str(file_input)
             file_ext = os.path.splitext(file_path)[1].lower()
             if file_ext not in SUPPORTED_FILE_TYPES:
-                raise Exception(
-                    f"Currently, only the following file types are supported: {SUPPORTED_FILE_TYPES}\n"
-                    f"Current file type: {file_ext}"
-                )
-            mime_type = mimetypes.guess_type(file_path)[0]
+                mime_type = "application/octet-stream"
+            else:
+                mime_type = mimetypes.guess_type(file_path)[0]
             # Open the file here for the duration of the async context
             # load data, set the mime type
             fs = fs or get_default_fs()
@@ -824,8 +874,8 @@ class LlamaParse(BasePydanticReader):
             )
             data["formatting_instruction"] = self.formatting_instruction
 
-        if self.guess_xlsx_sheet_names:
-            data["guess_xlsx_sheet_names"] = self.guess_xlsx_sheet_names
+        if self.guess_xlsx_sheet_name:
+            data["guess_xlsx_sheet_name"] = self.guess_xlsx_sheet_name
 
         if self.html_make_all_elements_visible:
             data["html_make_all_elements_visible"] = self.html_make_all_elements_visible
@@ -849,6 +899,9 @@ class LlamaParse(BasePydanticReader):
                 "ignore_document_elements_for_layout_detection"
             ] = self.ignore_document_elements_for_layout_detection
 
+        if self.inline_images_in_markdown:
+            data["inline_images_in_markdown"] = self.inline_images_in_markdown
+
         if input_url is not None:
             files = None
             data["input_url"] = str(input_url)
@@ -877,6 +930,11 @@ class LlamaParse(BasePydanticReader):
         if self.job_timeout_in_seconds is not None:
             data["job_timeout_in_seconds"] = self.job_timeout_in_seconds
 
+        if self.keep_page_separator_when_merging_tables:
+            data[
+                "keep_page_separator_when_merging_tables"
+            ] = self.keep_page_separator_when_merging_tables
+
         if self.language:
             data["language"] = self.language
 
@@ -955,6 +1013,11 @@ class LlamaParse(BasePydanticReader):
         if self.preserve_very_small_text:
             data["preserve_very_small_text"] = self.preserve_very_small_text
 
+        if self.presentation_out_of_bounds_content:
+            data[
+                "presentation_out_of_bounds_content"
+            ] = self.presentation_out_of_bounds_content
+
         if self.preset is not None:
             data["preset"] = self.preset
 
@@ -974,6 +1037,11 @@ class LlamaParse(BasePydanticReader):
                 "replace_failed_page_with_error_message_suffix"
             ] = self.replace_failed_page_with_error_message_suffix
 
+        if self.remove_hidden_text:
+            data["remove_hidden_text"] = self.remove_hidden_text
+
+        data["save_images"] = self.save_images
+
         if self.skip_diagonal_text:
             data["skip_diagonal_text"] = self.skip_diagonal_text
 
@@ -998,6 +1066,9 @@ class LlamaParse(BasePydanticReader):
         if self.specialized_chart_parsing_plus:
             data["specialized_chart_parsing_plus"] = self.specialized_chart_parsing_plus
 
+        if self.specialized_image_parsing:
+            data["specialized_image_parsing"] = self.specialized_image_parsing
+
         if self.strict_mode_buggy_font:
             data["strict_mode_buggy_font"] = self.strict_mode_buggy_font
 
@@ -1056,6 +1127,15 @@ class LlamaParse(BasePydanticReader):
         if self.extract_printed_page_number is not None:
             data["extract_printed_page_number"] = self.extract_printed_page_number
 
+        if self.line_level_bounding_box is not None:
+            data["line_level_bounding_box"] = self.line_level_bounding_box
+
+        if self.tier is not None:
+            data["tier"] = self.tier
+
+        if self.version is not None:
+            data["version"] = self.version
+
         # Deprecated
         if self.bounding_box is not None:
             data["bounding_box"] = self.bounding_box

py/llama_cloud_services/parse/types.py

@@ -115,6 +115,26 @@ class BBox(SafeBaseModel):
     )
 
 
+class LineLevelBboxItem(SafeBaseModel):
+    """A line-level bounding box item."""
+
+    md: Optional[str] = Field(
+        default=None, description="The markdown-formatted content of the line."
+    )
+    text: Optional[str] = Field(
+        default=None, description="The text content of the line."
+    )
+    bBox: Optional[BBox] = Field(
+        default=None, description="The bounding box of the line."
+    )
+    startIndex: Optional[int] = Field(
+        default=None, description="The start index of the line in the page text."
+    )
+    endIndex: Optional[int] = Field(
+        default=None, description="The end index of the line in the page text."
+    )
+
+
 class PageItem(SafeBaseModel):
     """An item in a page."""
 
@@ -138,6 +158,9 @@ class PageItem(SafeBaseModel):
         default=None,
         description="The HTML-formatted content of the item. Only applicable for table items when output_tables_as_HTML=True.",
     )
+    lines: Optional[List[LineLevelBboxItem]] = Field(
+        default=None, description="The line-level bounding box items of the item."
+    )
 
 
 class ImageItem(SafeBaseModel):

py/llama_parse/CHANGELOG.md

@@ -1,5 +1,63 @@
 # llama_parse
 
+## 0.6.90
+
+### Patch Changes
+
+- 19cbb25: Remove extension filter
+- Updated dependencies [19cbb25]
+  - llama-cloud-services-py@0.6.90
+
+## 0.6.89
+
+### Patch Changes
+
+- Updated dependencies [b9b83c9]
+  - llama-cloud-services-py@0.6.89
+
+## 0.6.88
+
+### Patch Changes
+
+- Updated dependencies [71db318]
+  - llama-cloud-services-py@0.6.88
+
+## 0.6.87
+
+### Patch Changes
+
+- Updated dependencies [06c3c55]
+  - llama-cloud-services-py@0.6.87
+
+## 0.6.86
+
+### Patch Changes
+
+- 1b7198d: Update extract to have confidence scores available in all modes
+- Updated dependencies [1b7198d]
+  - llama-cloud-services-py@0.6.86
+
+## 0.6.85
+
+### Patch Changes
+
+- Updated dependencies [ae30990]
+  - llama-cloud-services-py@0.6.85
+
+## 0.6.84
+
+### Patch Changes
+
+- Updated dependencies [0a110de]
+  - llama-cloud-services-py@0.6.84
+
+## 0.6.83
+
+### Patch Changes
+
+- Updated dependencies [ca78113]
+  - llama-cloud-services-py@0.6.83
+
 ## 0.6.82
 
 ### Patch Changes

py/llama_parse/README.md

@@ -146,9 +146,9 @@ Full documentation for `SimpleDirectoryReader` can be found on the [LlamaIndex D
 
 Several end-to-end indexing examples can be found in the examples folder
 
-- [Getting Started](/docs/examples-py/parse/demo_basic.ipynb)
-- [Advanced RAG Example](/docs/examples-py/parse/demo_advanced.ipynb)
-- [Raw API Usage](/docs/examples-py/parse/demo_api.ipynb)
+- [Getting Started](../../examples/parse/demo_basic.ipynb)
+- [Advanced RAG Example](../../examples/parse/demo_advanced.ipynb)
+- [Raw API Usage](../../examples/parse/demo_api.ipynb)
 
 ## Documentation
 

py/llama_parse/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llama_parse",
-  "version": "0.6.82",
+  "version": "0.6.90",
   "description": "",
   "main": "index.js",
   "private": false,

py/llama_parse/pyproject.toml

@@ -11,13 +11,13 @@ dev = [
 
 [project]
 name = "llama-parse"
-version = "0.6.82"
+version = "0.6.90"
 description = "Parse files into RAG-Optimized formats."
 authors = [{name = "Logan Markewich", email = "logan@llamaindex.ai"}]
 requires-python = ">=3.9,<4.0"
 readme = "README.md"
 license = "MIT"
-dependencies = ["llama-cloud-services>=0.6.82"]
+dependencies = ["llama-cloud-services>=0.6.90"]
 
 [project.scripts]
 llama-parse = "llama_parse.cli.main:parse"

py/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llama-cloud-services-py",
-  "version": "0.6.82",
+  "version": "0.6.90",
   "private": false,
   "license": "MIT",
   "scripts": {},

py/pyproject.toml

@@ -7,6 +7,7 @@ dev = [
   "pytest>=8.0.0,<9",
   "pytest-xdist>=3.6.1,<4",
   "pytest-asyncio",
+  "pytest-timeout>=2.3.1",
   "ipykernel>=6.29.0,<7",
   "pre-commit==3.2.0",
   "autoevals>=0.0.114,<0.0.115",
@@ -22,7 +23,7 @@ dev = [
 
 [project]
 name = "llama-cloud-services"
-version = "0.6.82"
+version = "0.6.90"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = [{name = "Logan Markewich", email = "logan@runllama.ai"}]
 requires-python = ">=3.9,<4.0"
@@ -30,7 +31,7 @@ readme = "README.md"
 license = "MIT"
 dependencies = [
   "llama-index-core>=0.12.0",
-  "llama-cloud==0.1.44",
+  "llama-cloud==0.1.45",
   "pydantic>=2.8,!=2.10",
   "click>=8.1.7,<9",
   "python-dotenv>=1.0.1,<2",

py/tests/beta/sheets/test_sheets.py

@@ -2,24 +2,58 @@ import os
 import tempfile
 import pytest
 import pandas as pd
+from pydantic import ValidationError
 
 from llama_cloud_services.beta.sheets import LlamaSheets
 from llama_cloud_services.beta.sheets.types import SpreadsheetParsingConfig
 
 
+class TestSpreadsheetParsingConfig:
+    """Unit tests for SpreadsheetParsingConfig."""
+
+    def test_default_values(self):
+        """Test that default values are set correctly."""
+        config = SpreadsheetParsingConfig()
+        assert config.flatten_hierarchical_tables is False
+        assert config.table_merge_sensitivity == "strong"
+
+    def test_custom_values(self):
+        """Test setting custom values for new fields."""
+        config = SpreadsheetParsingConfig(
+            flatten_hierarchical_tables=True,
+            table_merge_sensitivity="weak",
+        )
+        assert config.flatten_hierarchical_tables is True
+        assert config.table_merge_sensitivity == "weak"
+
+    def test_table_merge_sensitivity_validation(self):
+        """Test that invalid table_merge_sensitivity values are rejected."""
+        with pytest.raises(ValidationError):
+            SpreadsheetParsingConfig(table_merge_sensitivity="invalid")
+
+    def test_unknown_fields_ignored(self):
+        """Test that unknown fields are silently ignored."""
+        config = SpreadsheetParsingConfig(
+            unknown_field="test",
+            another_unknown=123,
+        )
+        assert not hasattr(config, "unknown_field")
+        assert not hasattr(config, "another_unknown")
+
+
 @pytest.fixture
 def sheets_client():
     """Create a LlamaSheets client for testing."""
-    api_key = os.getenv(
-        "LLAMA_CLOUD_API_KEY", "llx-3AEorIw5v0lnJPzEOI9xSl0N8yFx3fguw0Zn8QJHzGWmwg5r"
-    )
-    base_url = os.getenv("LLAMA_CLOUD_BASE_URL", "https://api.staging.llamaindex.ai")
+    api_key = os.getenv("LLAMA_CLOUD_API_KEY")
+    base_url = os.getenv("LLAMA_CLOUD_BASE_URL", "https://api.cloud.llamaindex.ai")
+    project_id = os.getenv("LLAMA_CLOUD_PROJECT_ID")
 
     client = LlamaSheets(
         api_key=api_key,
         base_url=base_url,
         max_timeout=300,
         poll_interval=2,
+        project_id=project_id,
     )
     return client
 
@@ -51,10 +85,7 @@ def sample_excel_file():
 
 
 @pytest.mark.skipif(
-    os.environ.get(
-        "LLAMA_CLOUD_API_KEY", "llx-3AEorIw5v0lnJPzEOI9xSl0N8yFx3fguw0Zn8QJHzGWmwg5r"
-    )
-    == "",
+    os.environ.get("LLAMA_CLOUD_API_KEY", "") == "",
     reason="LLAMA_CLOUD_API_KEY not set",
 )
 @pytest.mark.asyncio
@@ -134,10 +165,7 @@ async def test_spreadsheet_extraction_e2e(
 
 
 @pytest.mark.skipif(
-    os.environ.get(
-        "LLAMA_CLOUD_API_KEY", "llx-3AEorIw5v0lnJPzEOI9xSl0N8yFx3fguw0Zn8QJHzGWmwg5r"
-    )
-    == "",
+    os.environ.get("LLAMA_CLOUD_API_KEY", "") == "",
     reason="LLAMA_CLOUD_API_KEY not set",
 )
 @pytest.mark.asyncio

py/tests/test_files_client.py

@@ -78,7 +78,7 @@ async def test_upload_bytes(
     uploaded_file = await file_client.upload_bytes(file_bytes, external_file_id)
 
     assert isinstance(uploaded_file, File)
-    expected_name = external_file_id if use_presigned_url else "upload"
+    expected_name = external_file_id
     assert uploaded_file.name == expected_name
     assert uploaded_file.external_file_id == external_file_id
 
@@ -100,7 +100,7 @@ async def test_upload_buffer(
     uploaded_file = await file_client.upload_buffer(buffer, external_file_id, file_size)
 
     assert isinstance(uploaded_file, File)
-    expected_name = external_file_id if use_presigned_url else "upload"
+    expected_name = external_file_id
     assert uploaded_file.name == expected_name
     assert uploaded_file.external_file_id == external_file_id
 

py/unit_tests/beta/agent/test_agent_data_schema.py

@@ -11,10 +11,12 @@ from llama_cloud.types.aggregate_group import AggregateGroup
 from pydantic import BaseModel, Field, ValidationError
 
 from llama_cloud_services.beta.agent_data.schema import (
+    BoundingBox,
     ExtractedData,
     ExtractedFieldMetadata,
     FieldCitation,
     InvalidExtractionData,
+    PageDimensions,
     TypedAgentData,
     TypedAggregateGroup,
     calculate_overall_confidence,
@@ -421,6 +423,7 @@ def create_extract_run(
     },
     data_schema: Dict[str, Any] = {},
     file: File = create_file(),
+    error: Optional[str] = None,
 ) -> ExtractRun:
     return ExtractRun.parse_obj(
         {
@@ -437,6 +440,7 @@ def create_extract_run(
             "status": "SUCCESS",
             "project_id": str(uuid.uuid4()),
             "from_ui": False,
+            "error": error,
         }
     )
 
@@ -542,6 +546,46 @@ def test_extracted_data_from_extraction_result_invalid_data():
     assert invalid_data.field_metadata["name"].confidence == 0.9
     assert invalid_data.overall_confidence == 0.9
 
+    # Verify default error message when no job error present
+    assert exc_info.value.extraction_error is None
+    assert "Not able to parse the extracted data" in str(exc_info.value)
+
+
+def test_extracted_data_from_extraction_result_with_job_error():
+    """Test ExtractedData.from_extraction_result with job-level error prominently displayed."""
+    job_error_message = "Failed to process document: unsupported file format"
+
+    # Create ExtractRun with both invalid data AND a job-level error
+    extract_run = create_extract_run(
+        data={
+            "missing_name": "Valid Name",
+            "age": "not_a_number",
+        },  # Invalid age, missing name
+        extraction_metadata={
+            "name": {"confidence": 0.9},
+        },
+        data_schema={},
+        file=create_file(id="error-file", name="bad_data.pdf"),
+        error=job_error_message,
+    )
+
+    # Should raise InvalidExtractionData with the job error prominently displayed
+    with pytest.raises(InvalidExtractionData) as exc_info:
+        ExtractedData.from_extraction_result(
+            extract_run, Person, metadata={"test": "metadata"}
+        )
+
+    # Verify the exception message prominently shows the job error
+    exception = exc_info.value
+    assert exception.extraction_error == job_error_message
+    assert f"Extraction error: {job_error_message}" == str(exception)
+
+    # Verify the invalid_item contains both errors in metadata
+    invalid_data = exception.invalid_item
+    assert invalid_data.metadata.get("job_error") == job_error_message
+    assert "extraction_error" in invalid_data.metadata  # Validation error still present
+    assert "test" in invalid_data.metadata  # Original metadata preserved
+
 
 class Dimensions(BaseModel):
     length: Optional[str] = Field(
@@ -663,3 +707,69 @@ def test_field_conflict_in_schema():
     assert isinstance(
         extracted["majority_opinion"]["reasoning"], ExtractedFieldMetadata
     )
+
+
+def test_parse_extracted_field_metadata_with_bounding_boxes():
+    """Test parse_extracted_field_metadata with bounding boxes and page dimensions."""
+    raw_metadata = {
+        "document_type": {
+            "citation": [
+                {
+                    "page": 1,
+                    "matching_text": "FACTURE ORIGINALE",
+                    "bounding_boxes": [{"x": 77.28, "y": 615.12, "w": 70.6, "h": 7.2}],
+                    "page_dimensions": {"width": 222.24, "height": 736.56},
+                }
+            ],
+            "parsing_confidence": 1.0,
+            "extraction_confidence": 0.7252506422636493,
+            "confidence": 0.7252506422636493,
+        },
+        "summary": {
+            "citation": [
+                {
+                    "page": 1,
+                    "matching_text": "FACTURE ORIGINALE",
+                    "bounding_boxes": [{"x": 77.28, "y": 615.12, "w": 70.6, "h": 7.2}],
+                    "page_dimensions": {"width": 222.24, "height": 736.56},
+                },
+                {
+                    "page": 1,
+                    "matching_text": "Café filtre assiette — $1.90",
+                    "bounding_boxes": [
+                        {"x": 10.56, "y": 172.83, "w": 171.85, "h": 497.01}
+                    ],
+                    "page_dimensions": {"width": 222.24, "height": 736.56},
+                },
+            ],
+            "parsing_confidence": 1.0,
+            "extraction_confidence": 0.5700013128334419,
+            "confidence": 0.5700013128334419,
+        },
+    }
+
+    result = parse_extracted_field_metadata(raw_metadata)
+
+    # Verify document_type citation with bounding boxes
+    assert isinstance(result["document_type"], ExtractedFieldMetadata)
+    assert result["document_type"].parsing_confidence == 1.0
+    assert result["document_type"].extraction_confidence == 0.7252506422636493
+    assert result["document_type"].confidence == 0.7252506422636493
+    assert len(result["document_type"].citation) == 1
+
+    citation = result["document_type"].citation[0]
+    assert citation.page == 1
+    assert citation.matching_text == "FACTURE ORIGINALE"
+    assert len(citation.bounding_boxes) == 1
+    assert citation.bounding_boxes[0] == BoundingBox(x=77.28, y=615.12, w=70.6, h=7.2)
+    assert citation.page_dimensions == PageDimensions(width=222.24, height=736.56)
+
+    # Verify summary citation with multiple bounding boxes
+    assert isinstance(result["summary"], ExtractedFieldMetadata)
+    assert len(result["summary"].citation) == 2
+    assert result["summary"].citation[0].bounding_boxes[0].x == 77.28
+    assert result["summary"].citation[1].bounding_boxes[0].x == 10.56
+
+    # Verify round-trip serialization
+    result2 = parse_extracted_field_metadata(result)
+    assert result2 == result

py/uv.lock

@@ -3,7 +3,8 @@ revision = 3
 requires-python = ">=3.9, <4.0"
 resolution-markers = [
     "python_full_version >= '3.14'",
-    "python_full_version >= '3.11' and python_full_version < '3.14'",
+    "python_full_version >= '3.12' and python_full_version < '3.14'",
+    "python_full_version == '3.11.*'",
     "python_full_version == '3.10.*'",
     "python_full_version < '3.10'",
 ]
@@ -220,7 +221,8 @@ name = "argon2-cffi-bindings"
 version = "25.1.0"
 source = { registry = "https://pypi.org/simple" }
 resolution-markers = [
-    "python_full_version >= '3.11' and python_full_version < '3.14'",
+    "python_full_version >= '3.12' and python_full_version < '3.14'",
+    "python_full_version == '3.11.*'",
     "python_full_version == '3.10.*'",
     "python_full_version < '3.10'",
 ]
@@ -589,7 +591,8 @@ version = "8.2.1"
 source = { registry = "https://pypi.org/simple" }
 resolution-markers = [
     "python_full_version >= '3.14'",
-    "python_full_version >= '3.11' and python_full_version < '3.14'",
+    "python_full_version >= '3.12' and python_full_version < '3.14'",
+    "python_full_version == '3.11.*'",
     "python_full_version == '3.10.*'",
 ]
 dependencies = [
@@ -720,6 +723,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/33/6b/e0547afaf41bf2c42e52430072fa5658766e3d65bd4b03a563d1b6336f57/distlib-0.4.0-py2.py3-none-any.whl", hash = "sha256:9659f7d87e46584a30b5780e43ac7a2143098441670ff0a49d5f9034c54a6c16", size = 469047, upload-time = "2025-07-17T16:51:58.613Z" },
 ]
 
+[[package]]
+name = "et-xmlfile"
+version = "2.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/d3/38/af70d7ab1ae9d4da450eeec1fa3918940a5fafb9055e934af8d6eb0c2313/et_xmlfile-2.0.0.tar.gz", hash = "sha256:dab3f4764309081ce75662649be815c4c9081e88f0837825f90fd28317d4da54", size = 17234, upload-time = "2024-10-25T17:25:40.039Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c1/8b/5fe2cc11fee489817272089c4203e679c63b570a5aaeb18d852ae3cbba6a/et_xmlfile-2.0.0-py3-none-any.whl", hash = "sha256:7a91720bc756843502c3b7504c77b8fe44217c85c537d85037f0f536151b2caa", size = 18059, upload-time = "2024-10-25T17:25:39.051Z" },
+]
+
 [[package]]
 name = "eval-type-backport"
 version = "0.2.2"
@@ -1120,7 +1132,8 @@ version = "8.37.0"
 source = { registry = "https://pypi.org/simple" }
 resolution-markers = [
     "python_full_version >= '3.14'",
-    "python_full_version >= '3.11' and python_full_version < '3.14'",
+    "python_full_version >= '3.12' and python_full_version < '3.14'",
+    "python_full_version == '3.11.*'",
     "python_full_version == '3.10.*'",
 ]
 dependencies = [
@@ -1582,21 +1595,21 @@ wheels = [
 
 [[package]]
 name = "llama-cloud"
-version = "0.1.44"
+version = "0.1.45"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "certifi" },
     { name = "httpx" },
     { name = "pydantic" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/54/eb/16e31fb0fc4df91b08fa19cc3f28ac6e3c7d4df0bcbb71dd2bf596e9586f/llama_cloud-0.1.44.tar.gz", hash = "sha256:276a2b4f94463da037431ca3063331b3b6be398bbfb003113ee76b7c2a873b53", size = 120502, upload-time = "2025-11-04T00:51:58.578Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/e0/b7/3a2a209f1c3fa516de172cb13e03f5a897adea5523f2ee0f544d035e3704/llama_cloud-0.1.45.tar.gz", hash = "sha256:140244008cc5710e31ae97c6043973a3a9969a51b0f38155fa33a8434078e8aa", size = 140968, upload-time = "2025-12-03T02:22:49.484Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/69/0a/fabe54c21d5927d626550cb9560a20e51e42468355f5f0fb300f84806e28/llama_cloud-0.1.44-py3-none-any.whl", hash = "sha256:dfdcc4932353711fc8639f14261cbb54a88139b7790ebdd3ed4fde29bbbc0b88", size = 332779, upload-time = "2025-11-04T00:51:57.371Z" },
+    { url = "https://files.pythonhosted.org/packages/62/1d/466b0df69b81ce9410ad6ec7229a1e6601ff69640f02f246e06cfcc7428c/llama_cloud-0.1.45-py3-none-any.whl", hash = "sha256:500299a6d3f25f97bcf6755d6338523023564fa8f376955c2cf299bbc9561cc2", size = 397184, upload-time = "2025-12-03T02:22:48.335Z" },
 ]
 
 [[package]]
 name = "llama-cloud-services"
-version = "0.6.79"
+version = "0.6.88"
 source = { editable = "." }
 dependencies = [
     { name = "click", version = "8.1.8", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },
@@ -1620,10 +1633,15 @@ dev = [
     { name = "ipython", version = "8.37.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.10'" },
     { name = "jupyter" },
     { name = "mypy" },
+    { name = "openpyxl" },
+    { name = "pandas" },
     { name = "pre-commit" },
+    { name = "pyarrow", version = "21.0.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },
+    { name = "pyarrow", version = "22.0.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.10'" },
     { name = "pydantic-settings" },
     { name = "pytest" },
     { name = "pytest-asyncio" },
+    { name = "pytest-timeout" },
     { name = "pytest-xdist" },
 ]
 
@@ -1631,7 +1649,7 @@ dev = [
 requires-dist = [
     { name = "click", specifier = ">=8.1.7,<9" },
     { name = "eval-type-backport", marker = "python_full_version < '3.10'", specifier = ">=0.2.0,<0.3" },
-    { name = "llama-cloud", specifier = "==0.1.44" },
+    { name = "llama-cloud", specifier = "==0.1.45" },
     { name = "llama-index-core", specifier = ">=0.12.0" },
     { name = "packaging", specifier = ">=23.0" },
     { name = "platformdirs", specifier = ">=4.3.7,<5" },
@@ -1648,10 +1666,14 @@ dev = [
     { name = "ipython", specifier = ">=8.12.3,<9" },
     { name = "jupyter", specifier = ">=1.1.1,<2" },
     { name = "mypy", specifier = ">=1.14.1,<2" },
+    { name = "openpyxl" },
+    { name = "pandas" },
     { name = "pre-commit", specifier = "==3.2.0" },
+    { name = "pyarrow" },
     { name = "pydantic-settings", specifier = ">=2.10.1" },
     { name = "pytest", specifier = ">=8.0.0,<9" },
     { name = "pytest-asyncio" },
+    { name = "pytest-timeout", specifier = ">=2.3.1" },
     { name = "pytest-xdist", specifier = ">=3.6.1,<4" },
 ]
 
@@ -2098,7 +2120,8 @@ version = "3.5"
 source = { registry = "https://pypi.org/simple" }
 resolution-markers = [
     "python_full_version >= '3.14'",
-    "python_full_version >= '3.11' and python_full_version < '3.14'",
+    "python_full_version >= '3.12' and python_full_version < '3.14'",
+    "python_full_version == '3.11.*'",
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/6c/4f/ccdb8ad3a38e583f214547fd2f7ff1fc160c43a75af88e6aec213404b96a/networkx-3.5.tar.gz", hash = "sha256:d4c6f9cf81f52d69230866796b82afbccdec3db7ae4fbd1b65ea750feed50037", size = 2471065, upload-time = "2025-05-29T11:35:07.804Z" }
 wheels = [
@@ -2284,7 +2307,8 @@ version = "2.3.2"
 source = { registry = "https://pypi.org/simple" }
 resolution-markers = [
     "python_full_version >= '3.14'",
-    "python_full_version >= '3.11' and python_full_version < '3.14'",
+    "python_full_version >= '3.12' and python_full_version < '3.14'",
+    "python_full_version == '3.11.*'",
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/37/7d/3fec4199c5ffb892bed55cff901e4f39a58c81df9c44c280499e92cad264/numpy-2.3.2.tar.gz", hash = "sha256:e0486a11ec30cdecb53f184d496d1c6a20786c81e55e41640270130056f8ee48", size = 20489306, upload-time = "2025-07-24T21:32:07.553Z" }
 wheels = [
@@ -2363,6 +2387,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/78/e3/6690b3f85a05506733c7e90b577e4762517404ea78bab2ca3a5cb1aeb78d/numpy-2.3.2-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:6936aff90dda378c09bea075af0d9c675fe3a977a9d2402f95a87f440f59f619", size = 12977811, upload-time = "2025-07-24T21:29:18.234Z" },
 ]
 
+[[package]]
+name = "openpyxl"
+version = "3.1.5"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "et-xmlfile" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/3d/f9/88d94a75de065ea32619465d2f77b29a0469500e99012523b91cc4141cd1/openpyxl-3.1.5.tar.gz", hash = "sha256:cf0e3cf56142039133628b5acffe8ef0c12bc902d2aadd3e0fe5878dc08d1050", size = 186464, upload-time = "2024-06-28T14:03:44.161Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c0/da/977ded879c29cbd04de313843e76868e6e13408a94ed6b987245dc7c8506/openpyxl-3.1.5-py2.py3-none-any.whl", hash = "sha256:5282c12b107bffeef825f4617dc029afaf41d0ea60823bbb665ef3079dc79de2", size = 250910, upload-time = "2024-06-28T14:03:41.161Z" },
+]
+
 [[package]]
 name = "orderly-set"
 version = "5.5.0"
@@ -2390,6 +2426,76 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/20/12/38679034af332785aac8774540895e234f4d07f7545804097de4b666afd8/packaging-25.0-py3-none-any.whl", hash = "sha256:29572ef2b1f17581046b3a2227d5c611fb25ec70ca1ba8554b24b0e69331a484", size = 66469, upload-time = "2025-04-19T11:48:57.875Z" },
 ]
 
+[[package]]
+name = "pandas"
+version = "2.3.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "numpy", version = "2.0.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },
+    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version == '3.10.*'" },
+    { name = "numpy", version = "2.3.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11'" },
+    { name = "python-dateutil" },
+    { name = "pytz" },
+    { name = "tzdata" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/33/01/d40b85317f86cf08d853a4f495195c73815fdf205eef3993821720274518/pandas-2.3.3.tar.gz", hash = "sha256:e05e1af93b977f7eafa636d043f9f94c7ee3ac81af99c13508215942e64c993b", size = 4495223, upload-time = "2025-09-29T23:34:51.853Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3d/f7/f425a00df4fcc22b292c6895c6831c0c8ae1d9fac1e024d16f98a9ce8749/pandas-2.3.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:376c6446ae31770764215a6c937f72d917f214b43560603cd60da6408f183b6c", size = 11555763, upload-time = "2025-09-29T23:16:53.287Z" },
+    { url = "https://files.pythonhosted.org/packages/13/4f/66d99628ff8ce7857aca52fed8f0066ce209f96be2fede6cef9f84e8d04f/pandas-2.3.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e19d192383eab2f4ceb30b412b22ea30690c9e618f78870357ae1d682912015a", size = 10801217, upload-time = "2025-09-29T23:17:04.522Z" },
+    { url = "https://files.pythonhosted.org/packages/1d/03/3fc4a529a7710f890a239cc496fc6d50ad4a0995657dccc1d64695adb9f4/pandas-2.3.3-cp310-cp310-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5caf26f64126b6c7aec964f74266f435afef1c1b13da3b0636c7518a1fa3e2b1", size = 12148791, upload-time = "2025-09-29T23:17:18.444Z" },
+    { url = "https://files.pythonhosted.org/packages/40/a8/4dac1f8f8235e5d25b9955d02ff6f29396191d4e665d71122c3722ca83c5/pandas-2.3.3-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:dd7478f1463441ae4ca7308a70e90b33470fa593429f9d4c578dd00d1fa78838", size = 12769373, upload-time = "2025-09-29T23:17:35.846Z" },
+    { url = "https://files.pythonhosted.org/packages/df/91/82cc5169b6b25440a7fc0ef3a694582418d875c8e3ebf796a6d6470aa578/pandas-2.3.3-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:4793891684806ae50d1288c9bae9330293ab4e083ccd1c5e383c34549c6e4250", size = 13200444, upload-time = "2025-09-29T23:17:49.341Z" },
+    { url = "https://files.pythonhosted.org/packages/10/ae/89b3283800ab58f7af2952704078555fa60c807fff764395bb57ea0b0dbd/pandas-2.3.3-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:28083c648d9a99a5dd035ec125d42439c6c1c525098c58af0fc38dd1a7a1b3d4", size = 13858459, upload-time = "2025-09-29T23:18:03.722Z" },
+    { url = "https://files.pythonhosted.org/packages/85/72/530900610650f54a35a19476eca5104f38555afccda1aa11a92ee14cb21d/pandas-2.3.3-cp310-cp310-win_amd64.whl", hash = "sha256:503cf027cf9940d2ceaa1a93cfb5f8c8c7e6e90720a2850378f0b3f3b1e06826", size = 11346086, upload-time = "2025-09-29T23:18:18.505Z" },
+    { url = "https://files.pythonhosted.org/packages/c1/fa/7ac648108144a095b4fb6aa3de1954689f7af60a14cf25583f4960ecb878/pandas-2.3.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:602b8615ebcc4a0c1751e71840428ddebeb142ec02c786e8ad6b1ce3c8dec523", size = 11578790, upload-time = "2025-09-29T23:18:30.065Z" },
+    { url = "https://files.pythonhosted.org/packages/9b/35/74442388c6cf008882d4d4bdfc4109be87e9b8b7ccd097ad1e7f006e2e95/pandas-2.3.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:8fe25fc7b623b0ef6b5009149627e34d2a4657e880948ec3c840e9402e5c1b45", size = 10833831, upload-time = "2025-09-29T23:38:56.071Z" },
+    { url = "https://files.pythonhosted.org/packages/fe/e4/de154cbfeee13383ad58d23017da99390b91d73f8c11856f2095e813201b/pandas-2.3.3-cp311-cp311-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b468d3dad6ff947df92dcb32ede5b7bd41a9b3cceef0a30ed925f6d01fb8fa66", size = 12199267, upload-time = "2025-09-29T23:18:41.627Z" },
+    { url = "https://files.pythonhosted.org/packages/bf/c9/63f8d545568d9ab91476b1818b4741f521646cbdd151c6efebf40d6de6f7/pandas-2.3.3-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b98560e98cb334799c0b07ca7967ac361a47326e9b4e5a7dfb5ab2b1c9d35a1b", size = 12789281, upload-time = "2025-09-29T23:18:56.834Z" },
+    { url = "https://files.pythonhosted.org/packages/f2/00/a5ac8c7a0e67fd1a6059e40aa08fa1c52cc00709077d2300e210c3ce0322/pandas-2.3.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:1d37b5848ba49824e5c30bedb9c830ab9b7751fd049bc7914533e01c65f79791", size = 13240453, upload-time = "2025-09-29T23:19:09.247Z" },
+    { url = "https://files.pythonhosted.org/packages/27/4d/5c23a5bc7bd209231618dd9e606ce076272c9bc4f12023a70e03a86b4067/pandas-2.3.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:db4301b2d1f926ae677a751eb2bd0e8c5f5319c9cb3f88b0becbbb0b07b34151", size = 13890361, upload-time = "2025-09-29T23:19:25.342Z" },
+    { url = "https://files.pythonhosted.org/packages/8e/59/712db1d7040520de7a4965df15b774348980e6df45c129b8c64d0dbe74ef/pandas-2.3.3-cp311-cp311-win_amd64.whl", hash = "sha256:f086f6fe114e19d92014a1966f43a3e62285109afe874f067f5abbdcbb10e59c", size = 11348702, upload-time = "2025-09-29T23:19:38.296Z" },
+    { url = "https://files.pythonhosted.org/packages/9c/fb/231d89e8637c808b997d172b18e9d4a4bc7bf31296196c260526055d1ea0/pandas-2.3.3-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:6d21f6d74eb1725c2efaa71a2bfc661a0689579b58e9c0ca58a739ff0b002b53", size = 11597846, upload-time = "2025-09-29T23:19:48.856Z" },
+    { url = "https://files.pythonhosted.org/packages/5c/bd/bf8064d9cfa214294356c2d6702b716d3cf3bb24be59287a6a21e24cae6b/pandas-2.3.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:3fd2f887589c7aa868e02632612ba39acb0b8948faf5cc58f0850e165bd46f35", size = 10729618, upload-time = "2025-09-29T23:39:08.659Z" },
+    { url = "https://files.pythonhosted.org/packages/57/56/cf2dbe1a3f5271370669475ead12ce77c61726ffd19a35546e31aa8edf4e/pandas-2.3.3-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ecaf1e12bdc03c86ad4a7ea848d66c685cb6851d807a26aa245ca3d2017a1908", size = 11737212, upload-time = "2025-09-29T23:19:59.765Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/63/cd7d615331b328e287d8233ba9fdf191a9c2d11b6af0c7a59cfcec23de68/pandas-2.3.3-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b3d11d2fda7eb164ef27ffc14b4fcab16a80e1ce67e9f57e19ec0afaf715ba89", size = 12362693, upload-time = "2025-09-29T23:20:14.098Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/de/8b1895b107277d52f2b42d3a6806e69cfef0d5cf1d0ba343470b9d8e0a04/pandas-2.3.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:a68e15f780eddf2b07d242e17a04aa187a7ee12b40b930bfdd78070556550e98", size = 12771002, upload-time = "2025-09-29T23:20:26.76Z" },
+    { url = "https://files.pythonhosted.org/packages/87/21/84072af3187a677c5893b170ba2c8fbe450a6ff911234916da889b698220/pandas-2.3.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:371a4ab48e950033bcf52b6527eccb564f52dc826c02afd9a1bc0ab731bba084", size = 13450971, upload-time = "2025-09-29T23:20:41.344Z" },
+    { url = "https://files.pythonhosted.org/packages/86/41/585a168330ff063014880a80d744219dbf1dd7a1c706e75ab3425a987384/pandas-2.3.3-cp312-cp312-win_amd64.whl", hash = "sha256:a16dcec078a01eeef8ee61bf64074b4e524a2a3f4b3be9326420cabe59c4778b", size = 10992722, upload-time = "2025-09-29T23:20:54.139Z" },
+    { url = "https://files.pythonhosted.org/packages/cd/4b/18b035ee18f97c1040d94debd8f2e737000ad70ccc8f5513f4eefad75f4b/pandas-2.3.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:56851a737e3470de7fa88e6131f41281ed440d29a9268dcbf0002da5ac366713", size = 11544671, upload-time = "2025-09-29T23:21:05.024Z" },
+    { url = "https://files.pythonhosted.org/packages/31/94/72fac03573102779920099bcac1c3b05975c2cb5f01eac609faf34bed1ca/pandas-2.3.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:bdcd9d1167f4885211e401b3036c0c8d9e274eee67ea8d0758a256d60704cfe8", size = 10680807, upload-time = "2025-09-29T23:21:15.979Z" },
+    { url = "https://files.pythonhosted.org/packages/16/87/9472cf4a487d848476865321de18cc8c920b8cab98453ab79dbbc98db63a/pandas-2.3.3-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e32e7cc9af0f1cc15548288a51a3b681cc2a219faa838e995f7dc53dbab1062d", size = 11709872, upload-time = "2025-09-29T23:21:27.165Z" },
+    { url = "https://files.pythonhosted.org/packages/15/07/284f757f63f8a8d69ed4472bfd85122bd086e637bf4ed09de572d575a693/pandas-2.3.3-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:318d77e0e42a628c04dc56bcef4b40de67918f7041c2b061af1da41dcff670ac", size = 12306371, upload-time = "2025-09-29T23:21:40.532Z" },
+    { url = "https://files.pythonhosted.org/packages/33/81/a3afc88fca4aa925804a27d2676d22dcd2031c2ebe08aabd0ae55b9ff282/pandas-2.3.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:4e0a175408804d566144e170d0476b15d78458795bb18f1304fb94160cabf40c", size = 12765333, upload-time = "2025-09-29T23:21:55.77Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/0f/b4d4ae743a83742f1153464cf1a8ecfafc3ac59722a0b5c8602310cb7158/pandas-2.3.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:93c2d9ab0fc11822b5eece72ec9587e172f63cff87c00b062f6e37448ced4493", size = 13418120, upload-time = "2025-09-29T23:22:10.109Z" },
+    { url = "https://files.pythonhosted.org/packages/4f/c7/e54682c96a895d0c808453269e0b5928a07a127a15704fedb643e9b0a4c8/pandas-2.3.3-cp313-cp313-win_amd64.whl", hash = "sha256:f8bfc0e12dc78f777f323f55c58649591b2cd0c43534e8355c51d3fede5f4dee", size = 10993991, upload-time = "2025-09-29T23:25:04.889Z" },
+    { url = "https://files.pythonhosted.org/packages/f9/ca/3f8d4f49740799189e1395812f3bf23b5e8fc7c190827d55a610da72ce55/pandas-2.3.3-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:75ea25f9529fdec2d2e93a42c523962261e567d250b0013b16210e1d40d7c2e5", size = 12048227, upload-time = "2025-09-29T23:22:24.343Z" },
+    { url = "https://files.pythonhosted.org/packages/0e/5a/f43efec3e8c0cc92c4663ccad372dbdff72b60bdb56b2749f04aa1d07d7e/pandas-2.3.3-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:74ecdf1d301e812db96a465a525952f4dde225fdb6d8e5a521d47e1f42041e21", size = 11411056, upload-time = "2025-09-29T23:22:37.762Z" },
+    { url = "https://files.pythonhosted.org/packages/46/b1/85331edfc591208c9d1a63a06baa67b21d332e63b7a591a5ba42a10bb507/pandas-2.3.3-cp313-cp313t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6435cb949cb34ec11cc9860246ccb2fdc9ecd742c12d3304989017d53f039a78", size = 11645189, upload-time = "2025-09-29T23:22:51.688Z" },
+    { url = "https://files.pythonhosted.org/packages/44/23/78d645adc35d94d1ac4f2a3c4112ab6f5b8999f4898b8cdf01252f8df4a9/pandas-2.3.3-cp313-cp313t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:900f47d8f20860de523a1ac881c4c36d65efcb2eb850e6948140fa781736e110", size = 12121912, upload-time = "2025-09-29T23:23:05.042Z" },
+    { url = "https://files.pythonhosted.org/packages/53/da/d10013df5e6aaef6b425aa0c32e1fc1f3e431e4bcabd420517dceadce354/pandas-2.3.3-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:a45c765238e2ed7d7c608fc5bc4a6f88b642f2f01e70c0c23d2224dd21829d86", size = 12712160, upload-time = "2025-09-29T23:23:28.57Z" },
+    { url = "https://files.pythonhosted.org/packages/bd/17/e756653095a083d8a37cbd816cb87148debcfcd920129b25f99dd8d04271/pandas-2.3.3-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:c4fc4c21971a1a9f4bdb4c73978c7f7256caa3e62b323f70d6cb80db583350bc", size = 13199233, upload-time = "2025-09-29T23:24:24.876Z" },
+    { url = "https://files.pythonhosted.org/packages/04/fd/74903979833db8390b73b3a8a7d30d146d710bd32703724dd9083950386f/pandas-2.3.3-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:ee15f284898e7b246df8087fc82b87b01686f98ee67d85a17b7ab44143a3a9a0", size = 11540635, upload-time = "2025-09-29T23:25:52.486Z" },
+    { url = "https://files.pythonhosted.org/packages/21/00/266d6b357ad5e6d3ad55093a7e8efc7dd245f5a842b584db9f30b0f0a287/pandas-2.3.3-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:1611aedd912e1ff81ff41c745822980c49ce4a7907537be8692c8dbc31924593", size = 10759079, upload-time = "2025-09-29T23:26:33.204Z" },
+    { url = "https://files.pythonhosted.org/packages/ca/05/d01ef80a7a3a12b2f8bbf16daba1e17c98a2f039cbc8e2f77a2c5a63d382/pandas-2.3.3-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6d2cefc361461662ac48810cb14365a365ce864afe85ef1f447ff5a1e99ea81c", size = 11814049, upload-time = "2025-09-29T23:27:15.384Z" },
+    { url = "https://files.pythonhosted.org/packages/15/b2/0e62f78c0c5ba7e3d2c5945a82456f4fac76c480940f805e0b97fcbc2f65/pandas-2.3.3-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ee67acbbf05014ea6c763beb097e03cd629961c8a632075eeb34247120abcb4b", size = 12332638, upload-time = "2025-09-29T23:27:51.625Z" },
+    { url = "https://files.pythonhosted.org/packages/c5/33/dd70400631b62b9b29c3c93d2feee1d0964dc2bae2e5ad7a6c73a7f25325/pandas-2.3.3-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:c46467899aaa4da076d5abc11084634e2d197e9460643dd455ac3db5856b24d6", size = 12886834, upload-time = "2025-09-29T23:28:21.289Z" },
+    { url = "https://files.pythonhosted.org/packages/d3/18/b5d48f55821228d0d2692b34fd5034bb185e854bdb592e9c640f6290e012/pandas-2.3.3-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:6253c72c6a1d990a410bc7de641d34053364ef8bcd3126f7e7450125887dffe3", size = 13409925, upload-time = "2025-09-29T23:28:58.261Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/3d/124ac75fcd0ecc09b8fdccb0246ef65e35b012030defb0e0eba2cbbbe948/pandas-2.3.3-cp314-cp314-win_amd64.whl", hash = "sha256:1b07204a219b3b7350abaae088f451860223a52cfb8a6c53358e7948735158e5", size = 11109071, upload-time = "2025-09-29T23:32:27.484Z" },
+    { url = "https://files.pythonhosted.org/packages/89/9c/0e21c895c38a157e0faa1fb64587a9226d6dd46452cac4532d80c3c4a244/pandas-2.3.3-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:2462b1a365b6109d275250baaae7b760fd25c726aaca0054649286bcfbb3e8ec", size = 12048504, upload-time = "2025-09-29T23:29:31.47Z" },
+    { url = "https://files.pythonhosted.org/packages/d7/82/b69a1c95df796858777b68fbe6a81d37443a33319761d7c652ce77797475/pandas-2.3.3-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:0242fe9a49aa8b4d78a4fa03acb397a58833ef6199e9aa40a95f027bb3a1b6e7", size = 11410702, upload-time = "2025-09-29T23:29:54.591Z" },
+    { url = "https://files.pythonhosted.org/packages/f9/88/702bde3ba0a94b8c73a0181e05144b10f13f29ebfc2150c3a79062a8195d/pandas-2.3.3-cp314-cp314t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a21d830e78df0a515db2b3d2f5570610f5e6bd2e27749770e8bb7b524b89b450", size = 11634535, upload-time = "2025-09-29T23:30:21.003Z" },
+    { url = "https://files.pythonhosted.org/packages/a4/1e/1bac1a839d12e6a82ec6cb40cda2edde64a2013a66963293696bbf31fbbb/pandas-2.3.3-cp314-cp314t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2e3ebdb170b5ef78f19bfb71b0dc5dc58775032361fa188e814959b74d726dd5", size = 12121582, upload-time = "2025-09-29T23:30:43.391Z" },
+    { url = "https://files.pythonhosted.org/packages/44/91/483de934193e12a3b1d6ae7c8645d083ff88dec75f46e827562f1e4b4da6/pandas-2.3.3-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:d051c0e065b94b7a3cea50eb1ec32e912cd96dba41647eb24104b6c6c14c5788", size = 12699963, upload-time = "2025-09-29T23:31:10.009Z" },
+    { url = "https://files.pythonhosted.org/packages/70/44/5191d2e4026f86a2a109053e194d3ba7a31a2d10a9c2348368c63ed4e85a/pandas-2.3.3-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:3869faf4bd07b3b66a9f462417d0ca3a9df29a9f6abd5d0d0dbab15dac7abe87", size = 13202175, upload-time = "2025-09-29T23:31:59.173Z" },
+    { url = "https://files.pythonhosted.org/packages/56/b4/52eeb530a99e2a4c55ffcd352772b599ed4473a0f892d127f4147cf0f88e/pandas-2.3.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:c503ba5216814e295f40711470446bc3fd00f0faea8a086cbc688808e26f92a2", size = 11567720, upload-time = "2025-09-29T23:33:06.209Z" },
+    { url = "https://files.pythonhosted.org/packages/48/4a/2d8b67632a021bced649ba940455ed441ca854e57d6e7658a6024587b083/pandas-2.3.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:a637c5cdfa04b6d6e2ecedcb81fc52ffb0fd78ce2ebccc9ea964df9f658de8c8", size = 10810302, upload-time = "2025-09-29T23:33:35.846Z" },
+    { url = "https://files.pythonhosted.org/packages/13/e6/d2465010ee0569a245c975dc6967b801887068bc893e908239b1f4b6c1ac/pandas-2.3.3-cp39-cp39-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:854d00d556406bffe66a4c0802f334c9ad5a96b4f1f868adf036a21b11ef13ff", size = 12154874, upload-time = "2025-09-29T23:33:49.939Z" },
+    { url = "https://files.pythonhosted.org/packages/1f/18/aae8c0aa69a386a3255940e9317f793808ea79d0a525a97a903366bb2569/pandas-2.3.3-cp39-cp39-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:bf1f8a81d04ca90e32a0aceb819d34dbd378a98bf923b6398b9a3ec0bf44de29", size = 12790141, upload-time = "2025-09-29T23:34:05.655Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/26/617f98de789de00c2a444fbe6301bb19e66556ac78cff933d2c98f62f2b4/pandas-2.3.3-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:23ebd657a4d38268c7dfbdf089fbc31ea709d82e4923c5ffd4fbd5747133ce73", size = 13208697, upload-time = "2025-09-29T23:34:21.835Z" },
+    { url = "https://files.pythonhosted.org/packages/b9/fb/25709afa4552042bd0e15717c75e9b4a2294c3dc4f7e6ea50f03c5136600/pandas-2.3.3-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:5554c929ccc317d41a5e3d1234f3be588248e61f08a74dd17c9eabb535777dc9", size = 13879233, upload-time = "2025-09-29T23:34:35.079Z" },
+    { url = "https://files.pythonhosted.org/packages/98/af/7be05277859a7bc399da8ba68b88c96b27b48740b6cf49688899c6eb4176/pandas-2.3.3-cp39-cp39-win_amd64.whl", hash = "sha256:d3e28b3e83862ccf4d85ff19cf8c20b2ae7e503881711ff2d534dc8f761131aa", size = 11359119, upload-time = "2025-09-29T23:34:46.339Z" },
+]
+
 [[package]]
 name = "pandocfilters"
 version = "1.5.1"
@@ -2735,6 +2841,122 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/8e/37/efad0257dc6e593a18957422533ff0f87ede7c9c6ea010a2177d738fb82f/pure_eval-0.2.3-py3-none-any.whl", hash = "sha256:1db8e35b67b3d218d818ae653e27f06c3aa420901fa7b081ca98cbedc874e0d0", size = 11842, upload-time = "2024-07-21T12:58:20.04Z" },
 ]
 
+[[package]]
+name = "pyarrow"
+version = "21.0.0"
+source = { registry = "https://pypi.org/simple" }
+resolution-markers = [
+    "python_full_version < '3.10'",
+]
+sdist = { url = "https://files.pythonhosted.org/packages/ef/c2/ea068b8f00905c06329a3dfcd40d0fcc2b7d0f2e355bdb25b65e0a0e4cd4/pyarrow-21.0.0.tar.gz", hash = "sha256:5051f2dccf0e283ff56335760cbc8622cf52264d67e359d5569541ac11b6d5bc", size = 1133487, upload-time = "2025-07-18T00:57:31.761Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/17/d9/110de31880016e2afc52d8580b397dbe47615defbf09ca8cf55f56c62165/pyarrow-21.0.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:e563271e2c5ff4d4a4cbeb2c83d5cf0d4938b891518e676025f7268c6fe5fe26", size = 31196837, upload-time = "2025-07-18T00:54:34.755Z" },
+    { url = "https://files.pythonhosted.org/packages/df/5f/c1c1997613abf24fceb087e79432d24c19bc6f7259cab57c2c8e5e545fab/pyarrow-21.0.0-cp310-cp310-macosx_12_0_x86_64.whl", hash = "sha256:fee33b0ca46f4c85443d6c450357101e47d53e6c3f008d658c27a2d020d44c79", size = 32659470, upload-time = "2025-07-18T00:54:38.329Z" },
+    { url = "https://files.pythonhosted.org/packages/3e/ed/b1589a777816ee33ba123ba1e4f8f02243a844fed0deec97bde9fb21a5cf/pyarrow-21.0.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:7be45519b830f7c24b21d630a31d48bcebfd5d4d7f9d3bdb49da9cdf6d764edb", size = 41055619, upload-time = "2025-07-18T00:54:42.172Z" },
+    { url = "https://files.pythonhosted.org/packages/44/28/b6672962639e85dc0ac36f71ab3a8f5f38e01b51343d7aa372a6b56fa3f3/pyarrow-21.0.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:26bfd95f6bff443ceae63c65dc7e048670b7e98bc892210acba7e4995d3d4b51", size = 42733488, upload-time = "2025-07-18T00:54:47.132Z" },
+    { url = "https://files.pythonhosted.org/packages/f8/cc/de02c3614874b9089c94eac093f90ca5dfa6d5afe45de3ba847fd950fdf1/pyarrow-21.0.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:bd04ec08f7f8bd113c55868bd3fc442a9db67c27af098c5f814a3091e71cc61a", size = 43329159, upload-time = "2025-07-18T00:54:51.686Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/3e/99473332ac40278f196e105ce30b79ab8affab12f6194802f2593d6b0be2/pyarrow-21.0.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:9b0b14b49ac10654332a805aedfc0147fb3469cbf8ea951b3d040dab12372594", size = 45050567, upload-time = "2025-07-18T00:54:56.679Z" },
+    { url = "https://files.pythonhosted.org/packages/7b/f5/c372ef60593d713e8bfbb7e0c743501605f0ad00719146dc075faf11172b/pyarrow-21.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:9d9f8bcb4c3be7738add259738abdeddc363de1b80e3310e04067aa1ca596634", size = 26217959, upload-time = "2025-07-18T00:55:00.482Z" },
+    { url = "https://files.pythonhosted.org/packages/94/dc/80564a3071a57c20b7c32575e4a0120e8a330ef487c319b122942d665960/pyarrow-21.0.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:c077f48aab61738c237802836fc3844f85409a46015635198761b0d6a688f87b", size = 31243234, upload-time = "2025-07-18T00:55:03.812Z" },
+    { url = "https://files.pythonhosted.org/packages/ea/cc/3b51cb2db26fe535d14f74cab4c79b191ed9a8cd4cbba45e2379b5ca2746/pyarrow-21.0.0-cp311-cp311-macosx_12_0_x86_64.whl", hash = "sha256:689f448066781856237eca8d1975b98cace19b8dd2ab6145bf49475478bcaa10", size = 32714370, upload-time = "2025-07-18T00:55:07.495Z" },
+    { url = "https://files.pythonhosted.org/packages/24/11/a4431f36d5ad7d83b87146f515c063e4d07ef0b7240876ddb885e6b44f2e/pyarrow-21.0.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:479ee41399fcddc46159a551705b89c05f11e8b8cb8e968f7fec64f62d91985e", size = 41135424, upload-time = "2025-07-18T00:55:11.461Z" },
+    { url = "https://files.pythonhosted.org/packages/74/dc/035d54638fc5d2971cbf1e987ccd45f1091c83bcf747281cf6cc25e72c88/pyarrow-21.0.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:40ebfcb54a4f11bcde86bc586cbd0272bac0d516cfa539c799c2453768477569", size = 42823810, upload-time = "2025-07-18T00:55:16.301Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/3b/89fced102448a9e3e0d4dded1f37fa3ce4700f02cdb8665457fcc8015f5b/pyarrow-21.0.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:8d58d8497814274d3d20214fbb24abcad2f7e351474357d552a8d53bce70c70e", size = 43391538, upload-time = "2025-07-18T00:55:23.82Z" },
+    { url = "https://files.pythonhosted.org/packages/fb/bb/ea7f1bd08978d39debd3b23611c293f64a642557e8141c80635d501e6d53/pyarrow-21.0.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:585e7224f21124dd57836b1530ac8f2df2afc43c861d7bf3d58a4870c42ae36c", size = 45120056, upload-time = "2025-07-18T00:55:28.231Z" },
+    { url = "https://files.pythonhosted.org/packages/6e/0b/77ea0600009842b30ceebc3337639a7380cd946061b620ac1a2f3cb541e2/pyarrow-21.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:555ca6935b2cbca2c0e932bedd853e9bc523098c39636de9ad4693b5b1df86d6", size = 26220568, upload-time = "2025-07-18T00:55:32.122Z" },
+    { url = "https://files.pythonhosted.org/packages/ca/d4/d4f817b21aacc30195cf6a46ba041dd1be827efa4a623cc8bf39a1c2a0c0/pyarrow-21.0.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:3a302f0e0963db37e0a24a70c56cf91a4faa0bca51c23812279ca2e23481fccd", size = 31160305, upload-time = "2025-07-18T00:55:35.373Z" },
+    { url = "https://files.pythonhosted.org/packages/a2/9c/dcd38ce6e4b4d9a19e1d36914cb8e2b1da4e6003dd075474c4cfcdfe0601/pyarrow-21.0.0-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:b6b27cf01e243871390474a211a7922bfbe3bda21e39bc9160daf0da3fe48876", size = 32684264, upload-time = "2025-07-18T00:55:39.303Z" },
+    { url = "https://files.pythonhosted.org/packages/4f/74/2a2d9f8d7a59b639523454bec12dba35ae3d0a07d8ab529dc0809f74b23c/pyarrow-21.0.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:e72a8ec6b868e258a2cd2672d91f2860ad532d590ce94cdf7d5e7ec674ccf03d", size = 41108099, upload-time = "2025-07-18T00:55:42.889Z" },
+    { url = "https://files.pythonhosted.org/packages/ad/90/2660332eeb31303c13b653ea566a9918484b6e4d6b9d2d46879a33ab0622/pyarrow-21.0.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:b7ae0bbdc8c6674259b25bef5d2a1d6af5d39d7200c819cf99e07f7dfef1c51e", size = 42829529, upload-time = "2025-07-18T00:55:47.069Z" },
+    { url = "https://files.pythonhosted.org/packages/33/27/1a93a25c92717f6aa0fca06eb4700860577d016cd3ae51aad0e0488ac899/pyarrow-21.0.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:58c30a1729f82d201627c173d91bd431db88ea74dcaa3885855bc6203e433b82", size = 43367883, upload-time = "2025-07-18T00:55:53.069Z" },
+    { url = "https://files.pythonhosted.org/packages/05/d9/4d09d919f35d599bc05c6950095e358c3e15148ead26292dfca1fb659b0c/pyarrow-21.0.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:072116f65604b822a7f22945a7a6e581cfa28e3454fdcc6939d4ff6090126623", size = 45133802, upload-time = "2025-07-18T00:55:57.714Z" },
+    { url = "https://files.pythonhosted.org/packages/71/30/f3795b6e192c3ab881325ffe172e526499eb3780e306a15103a2764916a2/pyarrow-21.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:cf56ec8b0a5c8c9d7021d6fd754e688104f9ebebf1bf4449613c9531f5346a18", size = 26203175, upload-time = "2025-07-18T00:56:01.364Z" },
+    { url = "https://files.pythonhosted.org/packages/16/ca/c7eaa8e62db8fb37ce942b1ea0c6d7abfe3786ca193957afa25e71b81b66/pyarrow-21.0.0-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:e99310a4ebd4479bcd1964dff9e14af33746300cb014aa4a3781738ac63baf4a", size = 31154306, upload-time = "2025-07-18T00:56:04.42Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/e8/e87d9e3b2489302b3a1aea709aaca4b781c5252fcb812a17ab6275a9a484/pyarrow-21.0.0-cp313-cp313-macosx_12_0_x86_64.whl", hash = "sha256:d2fe8e7f3ce329a71b7ddd7498b3cfac0eeb200c2789bd840234f0dc271a8efe", size = 32680622, upload-time = "2025-07-18T00:56:07.505Z" },
+    { url = "https://files.pythonhosted.org/packages/84/52/79095d73a742aa0aba370c7942b1b655f598069489ab387fe47261a849e1/pyarrow-21.0.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:f522e5709379d72fb3da7785aa489ff0bb87448a9dc5a75f45763a795a089ebd", size = 41104094, upload-time = "2025-07-18T00:56:10.994Z" },
+    { url = "https://files.pythonhosted.org/packages/89/4b/7782438b551dbb0468892a276b8c789b8bbdb25ea5c5eb27faadd753e037/pyarrow-21.0.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:69cbbdf0631396e9925e048cfa5bce4e8c3d3b41562bbd70c685a8eb53a91e61", size = 42825576, upload-time = "2025-07-18T00:56:15.569Z" },
+    { url = "https://files.pythonhosted.org/packages/b3/62/0f29de6e0a1e33518dec92c65be0351d32d7ca351e51ec5f4f837a9aab91/pyarrow-21.0.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:731c7022587006b755d0bdb27626a1a3bb004bb56b11fb30d98b6c1b4718579d", size = 43368342, upload-time = "2025-07-18T00:56:19.531Z" },
+    { url = "https://files.pythonhosted.org/packages/90/c7/0fa1f3f29cf75f339768cc698c8ad4ddd2481c1742e9741459911c9ac477/pyarrow-21.0.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:dc56bc708f2d8ac71bd1dcb927e458c93cec10b98eb4120206a4091db7b67b99", size = 45131218, upload-time = "2025-07-18T00:56:23.347Z" },
+    { url = "https://files.pythonhosted.org/packages/01/63/581f2076465e67b23bc5a37d4a2abff8362d389d29d8105832e82c9c811c/pyarrow-21.0.0-cp313-cp313-win_amd64.whl", hash = "sha256:186aa00bca62139f75b7de8420f745f2af12941595bbbfa7ed3870ff63e25636", size = 26087551, upload-time = "2025-07-18T00:56:26.758Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/ab/357d0d9648bb8241ee7348e564f2479d206ebe6e1c47ac5027c2e31ecd39/pyarrow-21.0.0-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:a7a102574faa3f421141a64c10216e078df467ab9576684d5cd696952546e2da", size = 31290064, upload-time = "2025-07-18T00:56:30.214Z" },
+    { url = "https://files.pythonhosted.org/packages/3f/8a/5685d62a990e4cac2043fc76b4661bf38d06efed55cf45a334b455bd2759/pyarrow-21.0.0-cp313-cp313t-macosx_12_0_x86_64.whl", hash = "sha256:1e005378c4a2c6db3ada3ad4c217b381f6c886f0a80d6a316fe586b90f77efd7", size = 32727837, upload-time = "2025-07-18T00:56:33.935Z" },
+    { url = "https://files.pythonhosted.org/packages/fc/de/c0828ee09525c2bafefd3e736a248ebe764d07d0fd762d4f0929dbc516c9/pyarrow-21.0.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:65f8e85f79031449ec8706b74504a316805217b35b6099155dd7e227eef0d4b6", size = 41014158, upload-time = "2025-07-18T00:56:37.528Z" },
+    { url = "https://files.pythonhosted.org/packages/6e/26/a2865c420c50b7a3748320b614f3484bfcde8347b2639b2b903b21ce6a72/pyarrow-21.0.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:3a81486adc665c7eb1a2bde0224cfca6ceaba344a82a971ef059678417880eb8", size = 42667885, upload-time = "2025-07-18T00:56:41.483Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/f9/4ee798dc902533159250fb4321267730bc0a107d8c6889e07c3add4fe3a5/pyarrow-21.0.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:fc0d2f88b81dcf3ccf9a6ae17f89183762c8a94a5bdcfa09e05cfe413acf0503", size = 43276625, upload-time = "2025-07-18T00:56:48.002Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/da/e02544d6997037a4b0d22d8e5f66bc9315c3671371a8b18c79ade1cefe14/pyarrow-21.0.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:6299449adf89df38537837487a4f8d3bd91ec94354fdd2a7d30bc11c48ef6e79", size = 44951890, upload-time = "2025-07-18T00:56:52.568Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/4e/519c1bc1876625fe6b71e9a28287c43ec2f20f73c658b9ae1d485c0c206e/pyarrow-21.0.0-cp313-cp313t-win_amd64.whl", hash = "sha256:222c39e2c70113543982c6b34f3077962b44fca38c0bd9e68bb6781534425c10", size = 26371006, upload-time = "2025-07-18T00:56:56.379Z" },
+    { url = "https://files.pythonhosted.org/packages/3e/cc/ce4939f4b316457a083dc5718b3982801e8c33f921b3c98e7a93b7c7491f/pyarrow-21.0.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:a7f6524e3747e35f80744537c78e7302cd41deee8baa668d56d55f77d9c464b3", size = 31211248, upload-time = "2025-07-18T00:56:59.7Z" },
+    { url = "https://files.pythonhosted.org/packages/1f/c2/7a860931420d73985e2f340f06516b21740c15b28d24a0e99a900bb27d2b/pyarrow-21.0.0-cp39-cp39-macosx_12_0_x86_64.whl", hash = "sha256:203003786c9fd253ebcafa44b03c06983c9c8d06c3145e37f1b76a1f317aeae1", size = 32676896, upload-time = "2025-07-18T00:57:03.884Z" },
+    { url = "https://files.pythonhosted.org/packages/68/a8/197f989b9a75e59b4ca0db6a13c56f19a0ad8a298c68da9cc28145e0bb97/pyarrow-21.0.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:3b4d97e297741796fead24867a8dabf86c87e4584ccc03167e4a811f50fdf74d", size = 41067862, upload-time = "2025-07-18T00:57:07.587Z" },
+    { url = "https://files.pythonhosted.org/packages/fa/82/6ecfa89487b35aa21accb014b64e0a6b814cc860d5e3170287bf5135c7d8/pyarrow-21.0.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:898afce396b80fdda05e3086b4256f8677c671f7b1d27a6976fa011d3fd0a86e", size = 42747508, upload-time = "2025-07-18T00:57:13.917Z" },
+    { url = "https://files.pythonhosted.org/packages/3b/b7/ba252f399bbf3addc731e8643c05532cf32e74cebb5e32f8f7409bc243cf/pyarrow-21.0.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:067c66ca29aaedae08218569a114e413b26e742171f526e828e1064fcdec13f4", size = 43345293, upload-time = "2025-07-18T00:57:19.828Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/0a/a20819795bd702b9486f536a8eeb70a6aa64046fce32071c19ec8230dbaa/pyarrow-21.0.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:0c4e75d13eb76295a49e0ea056eb18dbd87d81450bfeb8afa19a7e5a75ae2ad7", size = 45060670, upload-time = "2025-07-18T00:57:24.477Z" },
+    { url = "https://files.pythonhosted.org/packages/10/15/6b30e77872012bbfe8265d42a01d5b3c17ef0ac0f2fae531ad91b6a6c02e/pyarrow-21.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:cdc4c17afda4dab2a9c0b79148a43a7f4e1094916b3e18d8975bfd6d6d52241f", size = 26227521, upload-time = "2025-07-18T00:57:29.119Z" },
+]
+
+[[package]]
+name = "pyarrow"
+version = "22.0.0"
+source = { registry = "https://pypi.org/simple" }
+resolution-markers = [
+    "python_full_version >= '3.14'",
+    "python_full_version >= '3.12' and python_full_version < '3.14'",
+    "python_full_version == '3.11.*'",
+    "python_full_version == '3.10.*'",
+]
+sdist = { url = "https://files.pythonhosted.org/packages/30/53/04a7fdc63e6056116c9ddc8b43bc28c12cdd181b85cbeadb79278475f3ae/pyarrow-22.0.0.tar.gz", hash = "sha256:3d600dc583260d845c7d8a6db540339dd883081925da2bd1c5cb808f720b3cd9", size = 1151151, upload-time = "2025-10-24T12:30:00.762Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d9/9b/cb3f7e0a345353def531ca879053e9ef6b9f38ed91aebcf68b09ba54dec0/pyarrow-22.0.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:77718810bd3066158db1e95a63c160ad7ce08c6b0710bc656055033e39cdad88", size = 34223968, upload-time = "2025-10-24T10:03:31.21Z" },
+    { url = "https://files.pythonhosted.org/packages/6c/41/3184b8192a120306270c5307f105b70320fdaa592c99843c5ef78aaefdcf/pyarrow-22.0.0-cp310-cp310-macosx_12_0_x86_64.whl", hash = "sha256:44d2d26cda26d18f7af7db71453b7b783788322d756e81730acb98f24eb90ace", size = 35942085, upload-time = "2025-10-24T10:03:38.146Z" },
+    { url = "https://files.pythonhosted.org/packages/d9/3d/a1eab2f6f08001f9fb714b8ed5cfb045e2fe3e3e3c0c221f2c9ed1e6d67d/pyarrow-22.0.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:b9d71701ce97c95480fecb0039ec5bb889e75f110da72005743451339262f4ce", size = 44964613, upload-time = "2025-10-24T10:03:46.516Z" },
+    { url = "https://files.pythonhosted.org/packages/46/46/a1d9c24baf21cfd9ce994ac820a24608decf2710521b29223d4334985127/pyarrow-22.0.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:710624ab925dc2b05a6229d47f6f0dac1c1155e6ed559be7109f684eba048a48", size = 47627059, upload-time = "2025-10-24T10:03:55.353Z" },
+    { url = "https://files.pythonhosted.org/packages/3a/4c/f711acb13075c1391fd54bc17e078587672c575f8de2a6e62509af026dcf/pyarrow-22.0.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:f963ba8c3b0199f9d6b794c90ec77545e05eadc83973897a4523c9e8d84e9340", size = 47947043, upload-time = "2025-10-24T10:04:05.408Z" },
+    { url = "https://files.pythonhosted.org/packages/4e/70/1f3180dd7c2eab35c2aca2b29ace6c519f827dcd4cfeb8e0dca41612cf7a/pyarrow-22.0.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:bd0d42297ace400d8febe55f13fdf46e86754842b860c978dfec16f081e5c653", size = 50206505, upload-time = "2025-10-24T10:04:15.786Z" },
+    { url = "https://files.pythonhosted.org/packages/80/07/fea6578112c8c60ffde55883a571e4c4c6bc7049f119d6b09333b5cc6f73/pyarrow-22.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:00626d9dc0f5ef3a75fe63fd68b9c7c8302d2b5bbc7f74ecaedba83447a24f84", size = 28101641, upload-time = "2025-10-24T10:04:22.57Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/b7/18f611a8cdc43417f9394a3ccd3eace2f32183c08b9eddc3d17681819f37/pyarrow-22.0.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:3e294c5eadfb93d78b0763e859a0c16d4051fc1c5231ae8956d61cb0b5666f5a", size = 34272022, upload-time = "2025-10-24T10:04:28.973Z" },
+    { url = "https://files.pythonhosted.org/packages/26/5c/f259e2526c67eb4b9e511741b19870a02363a47a35edbebc55c3178db22d/pyarrow-22.0.0-cp311-cp311-macosx_12_0_x86_64.whl", hash = "sha256:69763ab2445f632d90b504a815a2a033f74332997052b721002298ed6de40f2e", size = 35995834, upload-time = "2025-10-24T10:04:35.467Z" },
+    { url = "https://files.pythonhosted.org/packages/50/8d/281f0f9b9376d4b7f146913b26fac0aa2829cd1ee7e997f53a27411bbb92/pyarrow-22.0.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:b41f37cabfe2463232684de44bad753d6be08a7a072f6a83447eeaf0e4d2a215", size = 45030348, upload-time = "2025-10-24T10:04:43.366Z" },
+    { url = "https://files.pythonhosted.org/packages/f5/e5/53c0a1c428f0976bf22f513d79c73000926cb00b9c138d8e02daf2102e18/pyarrow-22.0.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:35ad0f0378c9359b3f297299c3309778bb03b8612f987399a0333a560b43862d", size = 47699480, upload-time = "2025-10-24T10:04:51.486Z" },
+    { url = "https://files.pythonhosted.org/packages/95/e1/9dbe4c465c3365959d183e6345d0a8d1dc5b02ca3f8db4760b3bc834cf25/pyarrow-22.0.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:8382ad21458075c2e66a82a29d650f963ce51c7708c7c0ff313a8c206c4fd5e8", size = 48011148, upload-time = "2025-10-24T10:04:59.585Z" },
+    { url = "https://files.pythonhosted.org/packages/c5/b4/7caf5d21930061444c3cf4fa7535c82faf5263e22ce43af7c2759ceb5b8b/pyarrow-22.0.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:1a812a5b727bc09c3d7ea072c4eebf657c2f7066155506ba31ebf4792f88f016", size = 50276964, upload-time = "2025-10-24T10:05:08.175Z" },
+    { url = "https://files.pythonhosted.org/packages/ae/f3/cec89bd99fa3abf826f14d4e53d3d11340ce6f6af4d14bdcd54cd83b6576/pyarrow-22.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:ec5d40dd494882704fb876c16fa7261a69791e784ae34e6b5992e977bd2e238c", size = 28106517, upload-time = "2025-10-24T10:05:14.314Z" },
+    { url = "https://files.pythonhosted.org/packages/af/63/ba23862d69652f85b615ca14ad14f3bcfc5bf1b99ef3f0cd04ff93fdad5a/pyarrow-22.0.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:bea79263d55c24a32b0d79c00a1c58bb2ee5f0757ed95656b01c0fb310c5af3d", size = 34211578, upload-time = "2025-10-24T10:05:21.583Z" },
+    { url = "https://files.pythonhosted.org/packages/b1/d0/f9ad86fe809efd2bcc8be32032fa72e8b0d112b01ae56a053006376c5930/pyarrow-22.0.0-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:12fe549c9b10ac98c91cf791d2945e878875d95508e1a5d14091a7aaa66d9cf8", size = 35989906, upload-time = "2025-10-24T10:05:29.485Z" },
+    { url = "https://files.pythonhosted.org/packages/b4/a8/f910afcb14630e64d673f15904ec27dd31f1e009b77033c365c84e8c1e1d/pyarrow-22.0.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:334f900ff08ce0423407af97e6c26ad5d4e3b0763645559ece6fbf3747d6a8f5", size = 45021677, upload-time = "2025-10-24T10:05:38.274Z" },
+    { url = "https://files.pythonhosted.org/packages/13/95/aec81f781c75cd10554dc17a25849c720d54feafb6f7847690478dcf5ef8/pyarrow-22.0.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:c6c791b09c57ed76a18b03f2631753a4960eefbbca80f846da8baefc6491fcfe", size = 47726315, upload-time = "2025-10-24T10:05:47.314Z" },
+    { url = "https://files.pythonhosted.org/packages/bb/d4/74ac9f7a54cfde12ee42734ea25d5a3c9a45db78f9def949307a92720d37/pyarrow-22.0.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:c3200cb41cdbc65156e5f8c908d739b0dfed57e890329413da2748d1a2cd1a4e", size = 47990906, upload-time = "2025-10-24T10:05:58.254Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/71/fedf2499bf7a95062eafc989ace56572f3343432570e1c54e6599d5b88da/pyarrow-22.0.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:ac93252226cf288753d8b46280f4edf3433bf9508b6977f8dd8526b521a1bbb9", size = 50306783, upload-time = "2025-10-24T10:06:08.08Z" },
+    { url = "https://files.pythonhosted.org/packages/68/ed/b202abd5a5b78f519722f3d29063dda03c114711093c1995a33b8e2e0f4b/pyarrow-22.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:44729980b6c50a5f2bfcc2668d36c569ce17f8b17bccaf470c4313dcbbf13c9d", size = 27972883, upload-time = "2025-10-24T10:06:14.204Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/d6/d0fac16a2963002fc22c8fa75180a838737203d558f0ed3b564c4a54eef5/pyarrow-22.0.0-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:e6e95176209257803a8b3d0394f21604e796dadb643d2f7ca21b66c9c0b30c9a", size = 34204629, upload-time = "2025-10-24T10:06:20.274Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/9c/1d6357347fbae062ad3f17082f9ebc29cc733321e892c0d2085f42a2212b/pyarrow-22.0.0-cp313-cp313-macosx_12_0_x86_64.whl", hash = "sha256:001ea83a58024818826a9e3f89bf9310a114f7e26dfe404a4c32686f97bd7901", size = 35985783, upload-time = "2025-10-24T10:06:27.301Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/c0/782344c2ce58afbea010150df07e3a2f5fdad299cd631697ae7bd3bac6e3/pyarrow-22.0.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:ce20fe000754f477c8a9125543f1936ea5b8867c5406757c224d745ed033e691", size = 45020999, upload-time = "2025-10-24T10:06:35.387Z" },
+    { url = "https://files.pythonhosted.org/packages/1b/8b/5362443737a5307a7b67c1017c42cd104213189b4970bf607e05faf9c525/pyarrow-22.0.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:e0a15757fccb38c410947df156f9749ae4a3c89b2393741a50521f39a8cf202a", size = 47724601, upload-time = "2025-10-24T10:06:43.551Z" },
+    { url = "https://files.pythonhosted.org/packages/69/4d/76e567a4fc2e190ee6072967cb4672b7d9249ac59ae65af2d7e3047afa3b/pyarrow-22.0.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:cedb9dd9358e4ea1d9bce3665ce0797f6adf97ff142c8e25b46ba9cdd508e9b6", size = 48001050, upload-time = "2025-10-24T10:06:52.284Z" },
+    { url = "https://files.pythonhosted.org/packages/01/5e/5653f0535d2a1aef8223cee9d92944cb6bccfee5cf1cd3f462d7cb022790/pyarrow-22.0.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:252be4a05f9d9185bb8c18e83764ebcfea7185076c07a7a662253af3a8c07941", size = 50307877, upload-time = "2025-10-24T10:07:02.405Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/f8/1d0bd75bf9328a3b826e24a16e5517cd7f9fbf8d34a3184a4566ef5a7f29/pyarrow-22.0.0-cp313-cp313-win_amd64.whl", hash = "sha256:a4893d31e5ef780b6edcaf63122df0f8d321088bb0dee4c8c06eccb1ca28d145", size = 27977099, upload-time = "2025-10-24T10:08:07.259Z" },
+    { url = "https://files.pythonhosted.org/packages/90/81/db56870c997805bf2b0f6eeeb2d68458bf4654652dccdcf1bf7a42d80903/pyarrow-22.0.0-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:f7fe3dbe871294ba70d789be16b6e7e52b418311e166e0e3cba9522f0f437fb1", size = 34336685, upload-time = "2025-10-24T10:07:11.47Z" },
+    { url = "https://files.pythonhosted.org/packages/1c/98/0727947f199aba8a120f47dfc229eeb05df15bcd7a6f1b669e9f882afc58/pyarrow-22.0.0-cp313-cp313t-macosx_12_0_x86_64.whl", hash = "sha256:ba95112d15fd4f1105fb2402c4eab9068f0554435e9b7085924bcfaac2cc306f", size = 36032158, upload-time = "2025-10-24T10:07:18.626Z" },
+    { url = "https://files.pythonhosted.org/packages/96/b4/9babdef9c01720a0785945c7cf550e4acd0ebcd7bdd2e6f0aa7981fa85e2/pyarrow-22.0.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:c064e28361c05d72eed8e744c9605cbd6d2bb7481a511c74071fd9b24bc65d7d", size = 44892060, upload-time = "2025-10-24T10:07:26.002Z" },
+    { url = "https://files.pythonhosted.org/packages/f8/ca/2f8804edd6279f78a37062d813de3f16f29183874447ef6d1aadbb4efa0f/pyarrow-22.0.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:6f9762274496c244d951c819348afbcf212714902742225f649cf02823a6a10f", size = 47504395, upload-time = "2025-10-24T10:07:34.09Z" },
+    { url = "https://files.pythonhosted.org/packages/b9/f0/77aa5198fd3943682b2e4faaf179a674f0edea0d55d326d83cb2277d9363/pyarrow-22.0.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:a9d9ffdc2ab696f6b15b4d1f7cec6658e1d788124418cb30030afbae31c64746", size = 48066216, upload-time = "2025-10-24T10:07:43.528Z" },
+    { url = "https://files.pythonhosted.org/packages/79/87/a1937b6e78b2aff18b706d738c9e46ade5bfcf11b294e39c87706a0089ac/pyarrow-22.0.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:ec1a15968a9d80da01e1d30349b2b0d7cc91e96588ee324ce1b5228175043e95", size = 50288552, upload-time = "2025-10-24T10:07:53.519Z" },
+    { url = "https://files.pythonhosted.org/packages/60/ae/b5a5811e11f25788ccfdaa8f26b6791c9807119dffcf80514505527c384c/pyarrow-22.0.0-cp313-cp313t-win_amd64.whl", hash = "sha256:bba208d9c7decf9961998edf5c65e3ea4355d5818dd6cd0f6809bec1afb951cc", size = 28262504, upload-time = "2025-10-24T10:08:00.932Z" },
+    { url = "https://files.pythonhosted.org/packages/bd/b0/0fa4d28a8edb42b0a7144edd20befd04173ac79819547216f8a9f36f9e50/pyarrow-22.0.0-cp314-cp314-macosx_12_0_arm64.whl", hash = "sha256:9bddc2cade6561f6820d4cd73f99a0243532ad506bc510a75a5a65a522b2d74d", size = 34224062, upload-time = "2025-10-24T10:08:14.101Z" },
+    { url = "https://files.pythonhosted.org/packages/0f/a8/7a719076b3c1be0acef56a07220c586f25cd24de0e3f3102b438d18ae5df/pyarrow-22.0.0-cp314-cp314-macosx_12_0_x86_64.whl", hash = "sha256:e70ff90c64419709d38c8932ea9fe1cc98415c4f87ea8da81719e43f02534bc9", size = 35990057, upload-time = "2025-10-24T10:08:21.842Z" },
+    { url = "https://files.pythonhosted.org/packages/89/3c/359ed54c93b47fb6fe30ed16cdf50e3f0e8b9ccfb11b86218c3619ae50a8/pyarrow-22.0.0-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:92843c305330aa94a36e706c16209cd4df274693e777ca47112617db7d0ef3d7", size = 45068002, upload-time = "2025-10-24T10:08:29.034Z" },
+    { url = "https://files.pythonhosted.org/packages/55/fc/4945896cc8638536ee787a3bd6ce7cec8ec9acf452d78ec39ab328efa0a1/pyarrow-22.0.0-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:6dda1ddac033d27421c20d7a7943eec60be44e0db4e079f33cc5af3b8280ccde", size = 47737765, upload-time = "2025-10-24T10:08:38.559Z" },
+    { url = "https://files.pythonhosted.org/packages/cd/5e/7cb7edeb2abfaa1f79b5d5eb89432356155c8426f75d3753cbcb9592c0fd/pyarrow-22.0.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:84378110dd9a6c06323b41b56e129c504d157d1a983ce8f5443761eb5256bafc", size = 48048139, upload-time = "2025-10-24T10:08:46.784Z" },
+    { url = "https://files.pythonhosted.org/packages/88/c6/546baa7c48185f5e9d6e59277c4b19f30f48c94d9dd938c2a80d4d6b067c/pyarrow-22.0.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:854794239111d2b88b40b6ef92aa478024d1e5074f364033e73e21e3f76b25e0", size = 50314244, upload-time = "2025-10-24T10:08:55.771Z" },
+    { url = "https://files.pythonhosted.org/packages/3c/79/755ff2d145aafec8d347bf18f95e4e81c00127f06d080135dfc86aea417c/pyarrow-22.0.0-cp314-cp314-win_amd64.whl", hash = "sha256:b883fe6fd85adad7932b3271c38ac289c65b7337c2c132e9569f9d3940620730", size = 28757501, upload-time = "2025-10-24T10:09:59.891Z" },
+    { url = "https://files.pythonhosted.org/packages/0e/d2/237d75ac28ced3147912954e3c1a174df43a95f4f88e467809118a8165e0/pyarrow-22.0.0-cp314-cp314t-macosx_12_0_arm64.whl", hash = "sha256:7a820d8ae11facf32585507c11f04e3f38343c1e784c9b5a8b1da5c930547fe2", size = 34355506, upload-time = "2025-10-24T10:09:02.953Z" },
+    { url = "https://files.pythonhosted.org/packages/1e/2c/733dfffe6d3069740f98e57ff81007809067d68626c5faef293434d11bd6/pyarrow-22.0.0-cp314-cp314t-macosx_12_0_x86_64.whl", hash = "sha256:c6ec3675d98915bf1ec8b3c7986422682f7232ea76cad276f4c8abd5b7319b70", size = 36047312, upload-time = "2025-10-24T10:09:10.334Z" },
+    { url = "https://files.pythonhosted.org/packages/7c/2b/29d6e3782dc1f299727462c1543af357a0f2c1d3c160ce199950d9ca51eb/pyarrow-22.0.0-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:3e739edd001b04f654b166204fc7a9de896cf6007eaff33409ee9e50ceaff754", size = 45081609, upload-time = "2025-10-24T10:09:18.61Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/42/aa9355ecc05997915af1b7b947a7f66c02dcaa927f3203b87871c114ba10/pyarrow-22.0.0-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:7388ac685cab5b279a41dfe0a6ccd99e4dbf322edfb63e02fc0443bf24134e91", size = 47703663, upload-time = "2025-10-24T10:09:27.369Z" },
+    { url = "https://files.pythonhosted.org/packages/ee/62/45abedde480168e83a1de005b7b7043fd553321c1e8c5a9a114425f64842/pyarrow-22.0.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:f633074f36dbc33d5c05b5dc75371e5660f1dbf9c8b1d95669def05e5425989c", size = 48066543, upload-time = "2025-10-24T10:09:34.908Z" },
+    { url = "https://files.pythonhosted.org/packages/84/e9/7878940a5b072e4f3bf998770acafeae13b267f9893af5f6d4ab3904b67e/pyarrow-22.0.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:4c19236ae2402a8663a2c8f21f1870a03cc57f0bef7e4b6eb3238cc82944de80", size = 50288838, upload-time = "2025-10-24T10:09:44.394Z" },
+    { url = "https://files.pythonhosted.org/packages/7b/03/f335d6c52b4a4761bcc83499789a1e2e16d9d201a58c327a9b5cc9a41bd9/pyarrow-22.0.0-cp314-cp314t-win_amd64.whl", hash = "sha256:0c34fe18094686194f204a3b1787a27456897d8a2d62caf84b61e8dfbc0252ae", size = 29185594, upload-time = "2025-10-24T10:09:53.111Z" },
+]
+
 [[package]]
 name = "pycparser"
 version = "2.22"
@@ -2923,6 +3145,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c7/9d/bf86eddabf8c6c9cb1ea9a869d6873b46f105a5d292d3a6f7071f5b07935/pytest_asyncio-1.1.0-py3-none-any.whl", hash = "sha256:5fe2d69607b0bd75c656d1211f969cadba035030156745ee09e7d71740e58ecf", size = 15157, upload-time = "2025-07-16T04:29:24.929Z" },
 ]
 
+[[package]]
+name = "pytest-timeout"
+version = "2.4.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pytest" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/ac/82/4c9ecabab13363e72d880f2fb504c5f750433b2b6f16e99f4ec21ada284c/pytest_timeout-2.4.0.tar.gz", hash = "sha256:7e68e90b01f9eff71332b25001f85c75495fc4e3a836701876183c4bcfd0540a", size = 17973, upload-time = "2025-05-05T19:44:34.99Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/fa/b6/3127540ecdf1464a00e5a01ee60a1b09175f6913f0644ac748494d9c4b21/pytest_timeout-2.4.0-py3-none-any.whl", hash = "sha256:c42667e5cdadb151aeb5b26d114aff6bdf5a907f176a007a30b940d3d865b5c2", size = 14382, upload-time = "2025-05-05T19:44:33.502Z" },
+]
+
 [[package]]
 name = "pytest-xdist"
 version = "3.8.0"
@@ -2969,6 +3203,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/08/20/0f2523b9e50a8052bc6a8b732dfc8568abbdc42010aef03a2d750bdab3b2/python_json_logger-3.3.0-py3-none-any.whl", hash = "sha256:dd980fae8cffb24c13caf6e158d3d61c0d6d22342f932cb6e9deedab3d35eec7", size = 15163, upload-time = "2025-03-07T07:08:25.627Z" },
 ]
 
+[[package]]
+name = "pytz"
+version = "2025.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f8/bf/abbd3cdfb8fbc7fb3d4d38d320f2441b1e7cbe29be4f23797b4a2b5d8aac/pytz-2025.2.tar.gz", hash = "sha256:360b9e3dbb49a209c21ad61809c7fb453643e048b38924c765813546746e81c3", size = 320884, upload-time = "2025-03-25T02:25:00.538Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/81/c4/34e93fe5f5429d7570ec1fa436f1986fb1f00c3e0f43a589fe2bbcd22c3f/pytz-2025.2-py2.py3-none-any.whl", hash = "sha256:5ddf76296dd8c44c26eb8f4b6f35488f3ccbf6fbbd7adee0b7262d43f0ec2f00", size = 509225, upload-time = "2025-03-25T02:24:58.468Z" },
+]
+
 [[package]]
 name = "pywin32"
 version = "311"
@@ -3860,6 +4103,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/17/69/cd203477f944c353c31bade965f880aa1061fd6bf05ded0726ca845b6ff7/typing_inspection-0.4.1-py3-none-any.whl", hash = "sha256:389055682238f53b04f7badcb49b989835495a96700ced5dab2d8feae4b26f51", size = 14552, upload-time = "2025-05-21T18:55:22.152Z" },
 ]
 
+[[package]]
+name = "tzdata"
+version = "2025.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/95/32/1a225d6164441be760d75c2c42e2780dc0873fe382da3e98a2e1e48361e5/tzdata-2025.2.tar.gz", hash = "sha256:b60a638fcc0daffadf82fe0f57e53d06bdec2f36c4df66280ae79bce6bd6f2b9", size = 196380, upload-time = "2025-03-23T13:54:43.652Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/5c/23/c7abc0ca0a1526a0774eca151daeb8de62ec457e77262b66b359c3c7679e/tzdata-2025.2-py2.py3-none-any.whl", hash = "sha256:1a403fada01ff9221ca8044d701868fa132215d84beb92242d9acd2147f667a8", size = 347839, upload-time = "2025-03-23T13:54:41.845Z" },
+]
+
 [[package]]
 name = "uri-template"
 version = "1.3.0"

ts/llama_cloud_services/CHANGELOG.md

@@ -1,5 +1,44 @@
 # llama-cloud-services
 
+## 0.5.3
+
+### Patch Changes
+
+- d7864af: bugfixes in retry logic for LlamaExtract and LlamaClassify
+
+## 0.5.2
+
+### Patch Changes
+
+- 997bcc8: Add types for bounding boxes
+
+## 0.5.1
+
+### Patch Changes
+
+- d5b18a0: Fix publishing
+
+## 0.5.0
+
+### Minor Changes
+
+- 576c3d9: feat: support zod v4 & v3
+
+  Adds support for zod v4 while maintaining backward compatibility with v3.
+  - Updated zod peer dependency to accept both v3 and v4: `^3.25.76 || ^4.0.0`
+  - Migrated all import statements to use `zod/v4` import path for compatibility
+
+### Patch Changes
+
+- c8321d2: Improve parse results polling
+- 576c3d9: Support zod v3 an v4
+
+## 0.4.3
+
+### Patch Changes
+
+- 71db318: Add tier and version
+
 ## 0.4.2
 
 ### Patch Changes

ts/llama_cloud_services/package.json

@@ -1,12 +1,12 @@
 {
   "name": "llama-cloud-services",
-  "version": "0.4.2",
+  "version": "0.5.3",
   "type": "module",
   "license": "MIT",
   "scripts": {
     "get-openapi": "node ./scripts/get-openapi.js",
     "generate": "./node_modules/.bin/openapi-ts",
-    "build": "pnpm run generate && bunchee",
+    "build": "bunchee",
     "dev": "bunchee --watch",
     "lint": "eslint src/ --ignore-pattern client/*.ts --no-warn-ignored",
     "format": "prettier --write ./src/ tests/",
@@ -116,9 +116,9 @@
     "@eslint/js": "^9.32.0",
     "@hey-api/client-fetch": "^0.10.1",
     "@hey-api/openapi-ts": "^0.67.5",
-    "@llamaindex/core": "^0.6.19",
+    "@llamaindex/core": "^0.6.22",
     "@llamaindex/env": "^0.1.30",
-    "@llamaindex/workflow-core": "^0.4.1",
+    "@llamaindex/workflow-core": "^1.3.3",
     "@types/node": "^20.19.9",
     "@typescript-eslint/eslint-plugin": "^8.38.0",
     "@typescript-eslint/parser": "^8.38.0",
@@ -131,18 +131,19 @@
     "turbo": "^2.5.5",
     "typescript": "^5.8.3",
     "typescript-eslint": "^8.38.0",
-    "vitest": "^2.0.0"
+    "vitest": "^2.0.0",
+    "zod": "^4.1.13"
   },
   "peerDependencies": {
     "@llamaindex/core": "^0.6.19",
     "@llamaindex/env": "^0.1.30",
-    "@llamaindex/workflow-core": "^0.4.1"
+    "@llamaindex/workflow-core": "^1.3.3",
+    "zod": "^3.25.0 || ^4.0.0"
   },
   "dependencies": {
     "ajv": "^8.17.1",
     "file-type": "^21.0.0",
-    "p-retry": "^6.2.1",
-    "zod": "^3.25.76"
+    "p-retry": "^6.2.1"
   },
   "packageManager": "pnpm@10.8.1"
 }

ts/llama_cloud_services/src/LLamaCloudFileService.ts

@@ -1,7 +1,7 @@
 import {
   addFilesToPipelineApiApiV1PipelinesPipelineIdFilesPut,
   getPipelineFileStatusApiV1PipelinesPipelineIdFilesFileIdStatusGet,
-  listPipelineFilesApiV1PipelinesPipelineIdFilesGet,
+  listPipelineFiles2ApiV1PipelinesPipelineIdFiles2Get,
   listProjectsApiV1ProjectsGet,
   readFileContentApiV1FilesIdContentGet,
   searchPipelinesApiV1PipelinesGet,
@@ -97,21 +97,20 @@ export class LLamaCloudFileService {
    */
   public static async getFileUrl(pipelineId: string, filename: string) {
     initService();
-    const { data: allPipelineFiles } =
-      await listPipelineFilesApiV1PipelinesPipelineIdFilesGet({
-        path: {
-          pipeline_id: pipelineId,
-        },
-        throwOnError: true,
-      });
-    const file = allPipelineFiles.find((file) => file.name === filename);
+    const response = await listPipelineFiles2ApiV1PipelinesPipelineIdFiles2Get({
+      path: {
+        pipeline_id: pipelineId,
+      },
+      throwOnError: true,
+    });
+    const file = response.data.files.find((file) => file.name === filename);
     if (!file?.file_id) return null;
     const { data: fileContent } = await readFileContentApiV1FilesIdContentGet({
       path: {
         id: file.file_id,
       },
       query: {
-        project_id: file.project_id,
+        project_id: file.project_id || null,
       },
       throwOnError: true,
     });

ts/llama_cloud_services/src/beta/agent/index.ts

@@ -2,11 +2,14 @@ export { AgentClient, createAgentDataClient } from "./client";
 
 export type {
   AggregateAgentDataOptions,
+  BoundingBox,
   ComparisonOperator,
   ExtractedData,
   ExtractedFieldMetadata,
   ExtractedFieldMetadataDict,
+  FieldCitation,
   FilterOperation,
+  PageDimensions,
   SearchAgentDataOptions,
   StatusType,
   TypedAgentData,

ts/llama_cloud_services/src/beta/agent/types.ts

@@ -28,6 +28,44 @@ export type ComparisonOperator =
  */
 export type FilterOperation = RawFilterOperation;
 
+/**
+ * Bounding box coordinates for a citation location on a page
+ */
+export interface BoundingBox {
+  /** X coordinate of the bounding box origin */
+  x: number;
+  /** Y coordinate of the bounding box origin */
+  y: number;
+  /** Width of the bounding box */
+  w: number;
+  /** Height of the bounding box */
+  h: number;
+}
+
+/**
+ * Dimensions of a page in the source document
+ */
+export interface PageDimensions {
+  /** Width of the page */
+  width: number;
+  /** Height of the page */
+  height: number;
+}
+
+/**
+ * Citation information for an extracted field
+ */
+export interface FieldCitation {
+  /** The page number that the field occurred on */
+  page?: number;
+  /** The original text this field's value was derived from */
+  matching_text?: string;
+  /** Bounding boxes indicating where the citation appears on the page */
+  bounding_boxes?: BoundingBox[];
+  /** Dimensions of the page containing the citation */
+  page_dimensions?: PageDimensions;
+}
+
 /**
  * Metadata for an extracted field, including confidence and citation information
  */
@@ -38,16 +76,11 @@ export interface ExtractedFieldMetadata {
   confidence?: number;
   /** The confidence score for the field based on the extracted text only */
   extraction_confidence?: number;
+  /** The confidence score for the field based on the parsing/OCR quality */
+  parsing_confidence?: number;
   citation?: FieldCitation[];
 }
 
-export interface FieldCitation {
-  /** The page number that the field occurred on */
-  page?: number;
-  /** The original text this field's value was derived from */
-  matching_text?: string;
-}
-
 /**
  * Dictionary mapping field names to their metadata
  * Values can be ExtractedFieldMetadata objects, nested dictionaries, or arrays

ts/llama_cloud_services/src/classify.ts

@@ -108,20 +108,19 @@ async function pollForJobCompletion({
     }
     const response =
       await getClassifyJobApiV1ClassifierJobsClassifyJobIdGet(jobOptions);
-    if (!response.response.ok) {
-      numIterations++;
-    }
     if (typeof response.data != "undefined") {
       status = response.data.status as StatusEnum;
       if (status == StatusEnum.CANCELLED || status == StatusEnum.ERROR) {
-        throw new Error("There was an error during the classification job.");
-      } else if (status == StatusEnum.SUCCESS) {
+        throw new Error("There was an error extracting data from your file.");
+      } else if (
+        status == StatusEnum.SUCCESS ||
+        status == StatusEnum.PARTIAL_SUCCESS
+      ) {
         return true;
-      } else {
-        numIterations++;
-        await sleep(interval * 1000);
       }
     }
+    numIterations++;
+    await sleep(interval * 1000);
   }
 }
 
@@ -169,7 +168,7 @@ async function getJobResult({
       retries++;
       await sleep(retryInterval * 1000);
     }
-    if (typeof response.data != "undefined") {
+    if (response.response.ok && typeof response.data != "undefined") {
       return response.data as ClassifyJobResults;
     } else {
       throw new Error(

ts/llama_cloud_services/src/events.ts

@@ -1,6 +1,6 @@
 import { workflowEvent } from "@llamaindex/workflow-core";
 import { zodEvent } from "@llamaindex/workflow-core/util/zod";
-import { z } from "zod";
+import { z } from "zod/v4";
 import { parseFormSchema } from "./schema";
 
 export const uploadEvent = zodEvent(

ts/llama_cloud_services/src/extract.ts

@@ -296,20 +296,16 @@ async function pollForJobCompletion(
       return false;
     }
     const response = await getJobApiV1ExtractionJobsJobIdGet(jobOptions);
-    if (!response.response.ok) {
-      numIterations++;
-    }
     if (typeof response.data != "undefined") {
       status = response.data.status as StatusEnum;
       if (status == StatusEnum.CANCELLED || status == StatusEnum.ERROR) {
         throw new Error("There was an error extracting data from your file.");
       } else if (status == StatusEnum.SUCCESS) {
         return true;
-      } else {
-        numIterations++;
-        await sleep(interval * 1000);
       }
     }
+    numIterations++;
+    await sleep(interval * 1000);
   }
 }
 
@@ -350,7 +346,7 @@ async function getJobResult(
       retries++;
       await sleep(retryInterval * 1000);
     }
-    if (typeof response.data != "undefined") {
+    if (response.response.ok && typeof response.data != "undefined") {
       return {
         data: response.data.data,
         extractionMetadata: response.data.extraction_metadata,

ts/llama_cloud_services/src/query-tool.ts

@@ -2,7 +2,7 @@ import type { JSONValue } from "@llamaindex/core/global";
 import type { ToolMetadata } from "@llamaindex/core/llms";
 import type { BaseQueryEngine } from "@llamaindex/core/query-engine";
 import { tool } from "@llamaindex/core/tools";
-import { z } from "zod";
+import { z } from "zod/v4";
 
 const DEFAULT_NAME = "llama_cloud_index_tool";
 const DEFAULT_DESCRIPTION =
@@ -21,9 +21,7 @@ export function createQueryEngineTool(
     name: metadata?.name ?? DEFAULT_NAME,
     description: metadata?.description ?? DEFAULT_DESCRIPTION,
     parameters: z.object({
-      query: z.string({
-        description: "The query to search for",
-      }),
+      query: z.string().describe("The query to search for"),
     }),
     execute: async ({ query }) => {
       const response = await queryEngine.query({ query });

ts/llama_cloud_services/src/reader.ts

@@ -1,9 +1,10 @@
 /* eslint-disable @typescript-eslint/no-explicit-any */
 import { type Client, createClient, createConfig } from "@hey-api/client-fetch";
+import { type FailedAttemptError } from "p-retry";
 import { Document, FileReader } from "@llamaindex/core/schema";
 import { fs, getEnv, path } from "@llamaindex/env";
 import {
-  type BodyUploadFileApiParsingUploadPost,
+  type BodyUploadFileApiV1ParsingUploadPost,
   type FailPageMode,
   type ParserLanguages,
   type ParsingMode,
@@ -32,6 +33,33 @@ type WriteStream = {
 // eslint-disable-next-line no-var
 var process: any;
 
+function handleFailedAttempt(
+  error: FailedAttemptError,
+  jobId: string,
+  verbose: boolean,
+) {
+  // Retry only on 5XX or socket errors.
+  const status = (error.cause as any)?.response?.status;
+  if (
+    !(
+      (status && status >= 500 && status < 600) ||
+      ((error.cause as any)?.code &&
+        ((error.cause as any).code === "ECONNRESET" ||
+          (error.cause as any).code === "ETIMEDOUT" ||
+          (error.cause as any).code === "ECONNREFUSED")) ||
+      (status && status === 404)
+    )
+  ) {
+    throw error;
+  }
+
+  if (verbose) {
+    console.warn(
+      `Attempting to get job ${jobId} result (attempt ${error.attemptNumber}) failed. Retrying...`,
+    );
+  }
+}
+
 /**
  * Represents a reader for parsing files using the LlamaParse API.
  * See https://github.com/run-llama/llama_parse
@@ -186,6 +214,18 @@ export class LlamaParseReader extends FileReader {
   page_footer_suffix?: string | undefined;
   merge_tables_across_pages_in_markdown?: boolean | undefined;
   extract_printed_page_number?: boolean | undefined;
+  tier?: string | undefined;
+  version?: string | undefined;
+  layout_aware?: boolean | undefined;
+  line_level_bounding_box?: boolean | undefined;
+  specialized_image_parsing?: boolean | undefined;
+  aggressive_table_extraction?: boolean | undefined;
+  preserve_very_small_text?: boolean | undefined;
+  spreadsheet_force_formula_computation?: boolean | undefined;
+  inline_images_in_markdown?: boolean | undefined;
+  keep_page_separator_when_merging_tables?: boolean | undefined;
+  remove_hidden_text?: boolean | undefined;
+  presentation_out_of_bounds_content?: boolean | undefined;
 
   constructor(
     params: Partial<Omit<LlamaParseReader, "language" | "apiKey">> & {
@@ -383,11 +423,27 @@ export class LlamaParseReader extends FileReader {
       merge_tables_across_pages_in_markdown:
         this.merge_tables_across_pages_in_markdown,
       extract_printed_page_number: this.extract_printed_page_number,
+      tier: this.tier,
+      version: this.version,
+      layout_aware: this.layout_aware,
+      line_level_bounding_box: this.line_level_bounding_box,
+      specialized_image_parsing: this.specialized_image_parsing,
+      aggressive_table_extraction: this.aggressive_table_extraction,
+      preserve_very_small_text: this.preserve_very_small_text,
+      spreadsheet_force_formula_computation:
+        this.spreadsheet_force_formula_computation,
+      inline_images_in_markdown: this.inline_images_in_markdown,
+      webhook_configurations: undefined,
+      keep_page_separator_when_merging_tables:
+        this.keep_page_separator_when_merging_tables,
+      remove_hidden_text: this.remove_hidden_text,
+      presentation_out_of_bounds_content:
+        this.presentation_out_of_bounds_content,
     } satisfies {
-      [Key in keyof BodyUploadFileApiParsingUploadPost]-?:
-        | BodyUploadFileApiParsingUploadPost[Key]
+      [Key in keyof BodyUploadFileApiV1ParsingUploadPost]-?:
+        | BodyUploadFileApiV1ParsingUploadPost[Key]
         | undefined;
-    } as unknown as BodyUploadFileApiParsingUploadPost;
+    } as unknown as BodyUploadFileApiV1ParsingUploadPost;
 
     const response = await uploadFileApiV1ParsingUploadPost({
       client: this.#client,
@@ -439,26 +495,8 @@ export class LlamaParseReader extends FileReader {
             }),
           {
             retries: this.maxErrorCount,
-            onFailedAttempt: (error) => {
-              // Retry only on 5XX or socket errors.
-              const status = (error.cause as any)?.response?.status;
-              if (
-                !(
-                  (status && status >= 500 && status < 600) ||
-                  ((error.cause as any)?.code &&
-                    ((error.cause as any).code === "ECONNRESET" ||
-                      (error.cause as any).code === "ETIMEDOUT" ||
-                      (error.cause as any).code === "ECONNREFUSED"))
-                )
-              ) {
-                throw error;
-              }
-              if (this.verbose) {
-                console.warn(
-                  `Attempting to get job ${jobId} result (attempt ${error.attemptNumber}) failed. Retrying...`,
-                );
-              }
-            },
+            onFailedAttempt: (error) =>
+              handleFailedAttempt(error, jobId, this.verbose),
           },
         );
       } catch (e: any) {
@@ -471,49 +509,69 @@ export class LlamaParseReader extends FileReader {
       const status = (data as Record<string, unknown>)["status"];
 
       if (status === "SUCCESS") {
-        let resultData;
         switch (resultType) {
           case "json": {
-            resultData =
-              await getJobJsonResultApiV1ParsingJobJobIdResultJsonGet({
-                client: this.#client,
-                throwOnError: true,
-                path: { job_id: jobId },
-                query: {
-                  organization_id: this.organization_id ?? null,
-                },
-                signal: AbortSignal.timeout(this.maxTimeout * 1000),
-              });
-            break;
+            const resultData = await pRetry(
+              () =>
+                getJobJsonResultApiV1ParsingJobJobIdResultJsonGet({
+                  client: this.#client,
+                  throwOnError: true,
+                  path: { job_id: jobId },
+                  query: {
+                    organization_id: this.organization_id ?? null,
+                  },
+                  signal: AbortSignal.timeout(this.maxTimeout * 1000),
+                }),
+              {
+                retries: this.maxErrorCount,
+                onFailedAttempt: (error) =>
+                  handleFailedAttempt(error, jobId, this.verbose),
+              },
+            );
+            return resultData.data;
           }
           case "markdown": {
-            resultData =
-              await getJobResultApiV1ParsingJobJobIdResultMarkdownGet({
-                client: this.#client,
-                throwOnError: true,
-                path: { job_id: jobId },
-                query: {
-                  organization_id: this.organization_id ?? null,
-                },
-                signal: AbortSignal.timeout(this.maxTimeout * 1000),
-              });
-            break;
+            const resultData = await pRetry(
+              () =>
+                getJobResultApiV1ParsingJobJobIdResultMarkdownGet({
+                  client: this.#client,
+                  throwOnError: true,
+                  path: { job_id: jobId },
+                  query: {
+                    organization_id: this.organization_id ?? null,
+                  },
+                  signal: AbortSignal.timeout(this.maxTimeout * 1000),
+                }),
+              {
+                retries: this.maxErrorCount,
+                onFailedAttempt: (error) =>
+                  handleFailedAttempt(error, jobId, this.verbose),
+              },
+            );
+            return resultData.data;
           }
           case "text": {
-            resultData =
-              await getJobTextResultApiV1ParsingJobJobIdResultTextGet({
-                client: this.#client,
-                throwOnError: true,
-                path: { job_id: jobId },
-                query: {
-                  organization_id: this.organization_id ?? null,
-                },
-                signal: AbortSignal.timeout(this.maxTimeout * 1000),
-              });
-            break;
+            const resultData = await pRetry(
+              () =>
+                getJobTextResultApiV1ParsingJobJobIdResultTextGet({
+                  client: this.#client,
+                  throwOnError: true,
+                  path: { job_id: jobId },
+                  query: {
+                    organization_id: this.organization_id ?? null,
+                  },
+                  signal: AbortSignal.timeout(this.maxTimeout * 1000),
+                }),
+              {
+                retries: this.maxErrorCount,
+                onFailedAttempt: (error) =>
+                  handleFailedAttempt(error, jobId, this.verbose),
+              },
+            );
+
+            return resultData.data;
           }
         }
-        return resultData.data;
       } else if (status === "PENDING") {
         if (this.verbose && tries % 10 === 0) {
           this.stdout?.write(".");

ts/llama_cloud_services/src/schema.ts

@@ -1,6 +1,6 @@
 import { FailPageMode, ParserLanguages, ParsingMode } from "./client";
 
-import { z } from "zod";
+import { z } from "zod/v4";
 
 type Language = ParserLanguages;
 const VALUES: [Language, ...Language[]] = [
@@ -52,9 +52,10 @@ export const parseFormSchema = z.object({
   html_remove_navigation_elements: z.boolean().optional(),
   http_proxy: z
     .string()
-    .url(
-      'Set a valid URL for the HTTP proxy, e.g., "http://proxy.example.com:8080"',
-    )
+    .url({
+      error:
+        'Set a valid URL for the HTTP proxy, e.g., "http://proxy.example.com:8080"',
+    })
     .refine(
       (url) => {
         try {
@@ -67,7 +68,7 @@ export const parseFormSchema = z.object({
         }
       },
       {
-        message: "Invalid HTTP proxy URL",
+        error: "Invalid HTTP proxy URL",
       },
     )
     .optional(),
@@ -100,7 +101,7 @@ export const parseFormSchema = z.object({
   vendor_multimodal_model_name: z.string().optional(),
   model: z.string().optional(),
   webhook_url: z.string().url().optional(),
-  parse_mode: z.nativeEnum(ParsingMode).nullable().optional(),
+  parse_mode: z.enum(ParsingMode).nullable().optional(),
   system_prompt: z.string().optional(),
   system_prompt_append: z.string().optional(),
   user_prompt: z.string().optional(),
@@ -129,7 +130,7 @@ export const parseFormSchema = z.object({
   compact_markdown_table: z.boolean().optional(),
   markdown_table_multiline_header_separator: z.string().optional(),
   page_error_tolerance: z.number().min(0).max(1).optional(),
-  replace_failed_page_mode: z.nativeEnum(FailPageMode).nullable().optional(),
+  replace_failed_page_mode: z.enum(FailPageMode).nullable().optional(),
   replace_failed_page_with_error_message_prefix: z.string().optional(),
   replace_failed_page_with_error_message_suffix: z.string().optional(),
 });