fix tests

* Make versioning a little easier

* fix up ci

CONTRIBUTING.md

@@ -0,0 +1,21 @@
+# Installation
+
+This project uses poetry. Create a virtual environment, and run `poetry install`
+
+# Versioning (Maintainers only)
+
+Before merging your changes, make sure to bump the versions.
+
+Make a version bump to `pyproject.toml`. If the underlying dependency on the llamacloud platform OpenAPI
+sdk needs bumping, make sure to bring that in as well. If updating dependencies, run `poetry lock`.
+
+The legacy `llama_parse` package re-exports some of `llama_cloud_services` in the old namespace. The
+versions need to be kept consistent to sidecar it with `llama_cloud_services`. Bump it's version in `llama_parse/pyproject.toml`, and also bump it's dependency version of `llama-cloud-services` to match.
+
+**Note**: Don't worry about updating the `llama_parse/poetry.lock` file when bumping versions. The GitHub action will automatically run `poetry lock` for the llama_parse package during the build process (though it doesn't commit the updated lockfile back to the repo).
+
+You can also do this with `./scripts/version-bump.py set 0.x.x` if you have `uv` installed.
+
+Once the change is merged, push a tag `git tag -a v0.x.x -m 0.x.x` and `git push origin 0.x.x`.
+
+This tagging step can be done with `./scripts/version-bump tag`.

examples/parse/demo_table_extraction.ipynb

@@ -0,0 +1,516 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Table Extraction with LlamaParse\n",
+    "\n",
+    "This notebook will show you how to extract tables and save them as CSV files thanks to LlamaParse advanced parsing capabilities."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**1. Install needed dependencies**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! pip install llama-cloud-services pandas"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**2. Set you LLAMA_CLOUD_API_KEY as env variable**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "LLAMA_CLOUD_API_KEY: ··········\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = getpass(\"LLAMA_CLOUD_API_KEY: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**3. Initialiaze the parser**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_cloud_services import LlamaParse\n",
+    "\n",
+    "parser = LlamaParse(result_type=\"markdown\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**4. Get data**\n",
+    "\n",
+    "This is a PDF with _lots_ of tables!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "--2025-07-16 16:20:41--  https://assets.accessible-digital-documents.com/uploads/2017/01/sample-tables.pdf\n",
+      "Resolving assets.accessible-digital-documents.com (assets.accessible-digital-documents.com)... 3.166.135.2, 3.166.135.62, 3.166.135.51, ...\n",
+      "Connecting to assets.accessible-digital-documents.com (assets.accessible-digital-documents.com)|3.166.135.2|:443... connected.\n",
+      "HTTP request sent, awaiting response... 200 OK\n",
+      "Length: 145494 (142K) [application/pdf]\n",
+      "Saving to: ‘sample-tables.pdf’\n",
+      "\n",
+      "sample-tables.pdf   100%[===================>] 142.08K  --.-KB/s    in 0.04s   \n",
+      "\n",
+      "2025-07-16 16:20:41 (3.72 MB/s) - ‘sample-tables.pdf’ saved [145494/145494]\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "! wget https://assets.accessible-digital-documents.com/uploads/2017/01/sample-tables.pdf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**5. Parse document**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id b53949f7-9017-4b6a-b30c-be6227271ed2\n"
+     ]
+    }
+   ],
+   "source": [
+    "json_result = parser.get_json_result(\"sample-tables.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**6. Get tables!**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tables = parser.get_tables(json_result, \"tables/\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**7. Load tables**\n",
+    "\n",
+    "Let's show one example table!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.google.colaboratory.intrinsic+json": {
+       "summary": "{\n  \"name\": \"display(df\",\n  \"rows\": 8,\n  \"fields\": [\n    {\n      \"column\": \"Rainfall\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"Average\",\n          \"\",\n          \"24 hour high\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Americas\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 908,\n        \"min\": 9,\n        \"max\": 2010,\n        \"num_unique_values\": 8,\n        \"samples\": [\n          104,\n          133,\n          2010\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Asia\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"num_unique_values\": 7,\n        \"samples\": [\n          \"\",\n          201.0,\n          28.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Europe\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"num_unique_values\": 7,\n        \"samples\": [\n          \"\",\n          193.0,\n          29.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Africa\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"num_unique_values\": 7,\n        \"samples\": [\n          \"\",\n          144.0,\n          20.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}",
+       "type": "dataframe"
+      },
+      "text/html": [
+       "\n",
+       "  <div id=\"df-94a74c8f-1062-4a80-8d3f-32f0fbadf7bb\" class=\"colab-df-container\">\n",
+       "    <div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Rainfall</th>\n",
+       "      <th>Americas</th>\n",
+       "      <th>Asia</th>\n",
+       "      <th>Europe</th>\n",
+       "      <th>Africa</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>(inches)</td>\n",
+       "      <td>2010</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Average</td>\n",
+       "      <td>104</td>\n",
+       "      <td>201.0</td>\n",
+       "      <td>193.0</td>\n",
+       "      <td>144.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>24 hour high</td>\n",
+       "      <td>15</td>\n",
+       "      <td>26.0</td>\n",
+       "      <td>27.0</td>\n",
+       "      <td>18.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>12 hour high</td>\n",
+       "      <td>9</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>11.0</td>\n",
+       "      <td>12.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td></td>\n",
+       "      <td>2009</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>Average</td>\n",
+       "      <td>133</td>\n",
+       "      <td>244.0</td>\n",
+       "      <td>155.0</td>\n",
+       "      <td>166.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>24 hour high</td>\n",
+       "      <td>27</td>\n",
+       "      <td>28.0</td>\n",
+       "      <td>29.0</td>\n",
+       "      <td>20.0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>12 hour high</td>\n",
+       "      <td>11</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>13.0</td>\n",
+       "      <td>16.0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>\n",
+       "    <div class=\"colab-df-buttons\">\n",
+       "\n",
+       "  <div class=\"colab-df-container\">\n",
+       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-94a74c8f-1062-4a80-8d3f-32f0fbadf7bb')\"\n",
+       "            title=\"Convert this dataframe to an interactive table.\"\n",
+       "            style=\"display:none;\">\n",
+       "\n",
+       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
+       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
+       "  </svg>\n",
+       "    </button>\n",
+       "\n",
+       "  <style>\n",
+       "    .colab-df-container {\n",
+       "      display:flex;\n",
+       "      gap: 12px;\n",
+       "    }\n",
+       "\n",
+       "    .colab-df-convert {\n",
+       "      background-color: #E8F0FE;\n",
+       "      border: none;\n",
+       "      border-radius: 50%;\n",
+       "      cursor: pointer;\n",
+       "      display: none;\n",
+       "      fill: #1967D2;\n",
+       "      height: 32px;\n",
+       "      padding: 0 0 0 0;\n",
+       "      width: 32px;\n",
+       "    }\n",
+       "\n",
+       "    .colab-df-convert:hover {\n",
+       "      background-color: #E2EBFA;\n",
+       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+       "      fill: #174EA6;\n",
+       "    }\n",
+       "\n",
+       "    .colab-df-buttons div {\n",
+       "      margin-bottom: 4px;\n",
+       "    }\n",
+       "\n",
+       "    [theme=dark] .colab-df-convert {\n",
+       "      background-color: #3B4455;\n",
+       "      fill: #D2E3FC;\n",
+       "    }\n",
+       "\n",
+       "    [theme=dark] .colab-df-convert:hover {\n",
+       "      background-color: #434B5C;\n",
+       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+       "      fill: #FFFFFF;\n",
+       "    }\n",
+       "  </style>\n",
+       "\n",
+       "    <script>\n",
+       "      const buttonEl =\n",
+       "        document.querySelector('#df-94a74c8f-1062-4a80-8d3f-32f0fbadf7bb button.colab-df-convert');\n",
+       "      buttonEl.style.display =\n",
+       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+       "\n",
+       "      async function convertToInteractive(key) {\n",
+       "        const element = document.querySelector('#df-94a74c8f-1062-4a80-8d3f-32f0fbadf7bb');\n",
+       "        const dataTable =\n",
+       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+       "                                                    [key], {});\n",
+       "        if (!dataTable) return;\n",
+       "\n",
+       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
+       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+       "          + ' to learn more about interactive tables.';\n",
+       "        element.innerHTML = '';\n",
+       "        dataTable['output_type'] = 'display_data';\n",
+       "        await google.colab.output.renderOutput(dataTable, element);\n",
+       "        const docLink = document.createElement('div');\n",
+       "        docLink.innerHTML = docLinkHtml;\n",
+       "        element.appendChild(docLink);\n",
+       "      }\n",
+       "    </script>\n",
+       "  </div>\n",
+       "\n",
+       "\n",
+       "    <div id=\"df-54b2aa43-838b-47d3-9209-2fb18153cf87\">\n",
+       "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-54b2aa43-838b-47d3-9209-2fb18153cf87')\"\n",
+       "                title=\"Suggest charts\"\n",
+       "                style=\"display:none;\">\n",
+       "\n",
+       "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
+       "     width=\"24px\">\n",
+       "    <g>\n",
+       "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
+       "    </g>\n",
+       "</svg>\n",
+       "      </button>\n",
+       "\n",
+       "<style>\n",
+       "  .colab-df-quickchart {\n",
+       "      --bg-color: #E8F0FE;\n",
+       "      --fill-color: #1967D2;\n",
+       "      --hover-bg-color: #E2EBFA;\n",
+       "      --hover-fill-color: #174EA6;\n",
+       "      --disabled-fill-color: #AAA;\n",
+       "      --disabled-bg-color: #DDD;\n",
+       "  }\n",
+       "\n",
+       "  [theme=dark] .colab-df-quickchart {\n",
+       "      --bg-color: #3B4455;\n",
+       "      --fill-color: #D2E3FC;\n",
+       "      --hover-bg-color: #434B5C;\n",
+       "      --hover-fill-color: #FFFFFF;\n",
+       "      --disabled-bg-color: #3B4455;\n",
+       "      --disabled-fill-color: #666;\n",
+       "  }\n",
+       "\n",
+       "  .colab-df-quickchart {\n",
+       "    background-color: var(--bg-color);\n",
+       "    border: none;\n",
+       "    border-radius: 50%;\n",
+       "    cursor: pointer;\n",
+       "    display: none;\n",
+       "    fill: var(--fill-color);\n",
+       "    height: 32px;\n",
+       "    padding: 0;\n",
+       "    width: 32px;\n",
+       "  }\n",
+       "\n",
+       "  .colab-df-quickchart:hover {\n",
+       "    background-color: var(--hover-bg-color);\n",
+       "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+       "    fill: var(--button-hover-fill-color);\n",
+       "  }\n",
+       "\n",
+       "  .colab-df-quickchart-complete:disabled,\n",
+       "  .colab-df-quickchart-complete:disabled:hover {\n",
+       "    background-color: var(--disabled-bg-color);\n",
+       "    fill: var(--disabled-fill-color);\n",
+       "    box-shadow: none;\n",
+       "  }\n",
+       "\n",
+       "  .colab-df-spinner {\n",
+       "    border: 2px solid var(--fill-color);\n",
+       "    border-color: transparent;\n",
+       "    border-bottom-color: var(--fill-color);\n",
+       "    animation:\n",
+       "      spin 1s steps(1) infinite;\n",
+       "  }\n",
+       "\n",
+       "  @keyframes spin {\n",
+       "    0% {\n",
+       "      border-color: transparent;\n",
+       "      border-bottom-color: var(--fill-color);\n",
+       "      border-left-color: var(--fill-color);\n",
+       "    }\n",
+       "    20% {\n",
+       "      border-color: transparent;\n",
+       "      border-left-color: var(--fill-color);\n",
+       "      border-top-color: var(--fill-color);\n",
+       "    }\n",
+       "    30% {\n",
+       "      border-color: transparent;\n",
+       "      border-left-color: var(--fill-color);\n",
+       "      border-top-color: var(--fill-color);\n",
+       "      border-right-color: var(--fill-color);\n",
+       "    }\n",
+       "    40% {\n",
+       "      border-color: transparent;\n",
+       "      border-right-color: var(--fill-color);\n",
+       "      border-top-color: var(--fill-color);\n",
+       "    }\n",
+       "    60% {\n",
+       "      border-color: transparent;\n",
+       "      border-right-color: var(--fill-color);\n",
+       "    }\n",
+       "    80% {\n",
+       "      border-color: transparent;\n",
+       "      border-right-color: var(--fill-color);\n",
+       "      border-bottom-color: var(--fill-color);\n",
+       "    }\n",
+       "    90% {\n",
+       "      border-color: transparent;\n",
+       "      border-bottom-color: var(--fill-color);\n",
+       "    }\n",
+       "  }\n",
+       "</style>\n",
+       "\n",
+       "      <script>\n",
+       "        async function quickchart(key) {\n",
+       "          const quickchartButtonEl =\n",
+       "            document.querySelector('#' + key + ' button');\n",
+       "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
+       "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
+       "          try {\n",
+       "            const charts = await google.colab.kernel.invokeFunction(\n",
+       "                'suggestCharts', [key], {});\n",
+       "          } catch (error) {\n",
+       "            console.error('Error during call to suggestCharts:', error);\n",
+       "          }\n",
+       "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
+       "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
+       "        }\n",
+       "        (() => {\n",
+       "          let quickchartButtonEl =\n",
+       "            document.querySelector('#df-54b2aa43-838b-47d3-9209-2fb18153cf87 button');\n",
+       "          quickchartButtonEl.style.display =\n",
+       "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+       "        })();\n",
+       "      </script>\n",
+       "    </div>\n",
+       "\n",
+       "    </div>\n",
+       "  </div>\n"
+      ],
+      "text/plain": [
+       "       Rainfall  Americas   Asia Europe Africa\n",
+       "0      (inches)      2010                     \n",
+       "1       Average       104  201.0  193.0  144.0\n",
+       "2  24 hour high        15   26.0   27.0   18.0\n",
+       "3  12 hour high         9   10.0   11.0   12.0\n",
+       "4                    2009                     \n",
+       "5       Average       133  244.0  155.0  166.0\n",
+       "6  24 hour high        27   28.0   29.0   20.0\n",
+       "7  12 hour high        11   12.0   13.0   16.0"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "from IPython.display import display\n",
+    "\n",
+    "df = pd.read_csv(\n",
+    "    \"/content/tables/table_2025_16_07_16_30_01_569.csv\",\n",
+    ")\n",
+    "display(df.fillna(\"\"))"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

llama_cloud_services/beta/agent_data/__init__.py

@@ -5,6 +5,12 @@ from .schema import (
     StatusType,
     ExtractedT,
     AgentDataT,
+    ComparisonOperator,
+    parse_extracted_field_metadata,
+    calculate_overall_confidence,
+    InvalidExtractionData,
+    ExtractedFieldMetadata,
+    ExtractedFieldMetaDataDict,
 )
 from .client import AsyncAgentDataClient
 
@@ -16,4 +22,10 @@ __all__ = [
     "StatusType",
     "ExtractedT",
     "AgentDataT",
+    "ComparisonOperator",
+    "parse_extracted_field_metadata",
+    "calculate_overall_confidence",
+    "InvalidExtractionData",
+    "ExtractedFieldMetadata",
+    "ExtractedFieldMetaDataDict",
 ]

llama_cloud_services/beta/agent_data/client.py

@@ -1,7 +1,6 @@
 import os
-from typing import Dict, Generic, List, Optional, Type
+from typing import Any, Dict, Generic, List, Optional, Type
 
-from llama_cloud import FilterOperation
 from llama_cloud.client import AsyncLlamaCloud
 from tenacity import (
     WrappedFn,
@@ -14,6 +13,7 @@ import httpx
 
 from .schema import (
     AgentDataT,
+    ComparisonOperator,
     TypedAgentData,
     TypedAgentDataItems,
     TypedAggregateGroup,
@@ -42,7 +42,7 @@ def agent_data_retry(func: WrappedFn) -> WrappedFn:
     )(func)
 
 
-def get_default_agent_id() -> Optional[str]:
+def get_default_agent_id() -> str:
     """
     Retrieve the default agent ID from environment variables.
 
@@ -55,7 +55,7 @@ def get_default_agent_id() -> Optional[str]:
         via environment variables instead of passing it explicitly
         to each client instance.
     """
-    return os.getenv("LLAMA_DEPLOY_DEPLOYMENT_NAME")
+    return os.getenv("LLAMA_DEPLOY_DEPLOYMENT_NAME") or "_public"
 
 
 class AsyncAgentDataClient(Generic[AgentDataT]):
@@ -85,7 +85,7 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
         agent_client = AsyncAgentDataClient(
             client=llama_client,
             type=ExtractedPerson,
-            collection_name="extracted_people",
+            collection="extracted_people",
             agent_url_id="person-extraction-agent"
         )
 
@@ -94,8 +94,8 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
         result = await agent_client.create_agent_data(person)
 
         # Search data
-        results = await agent_client.search_agent_data(
-            filter={"age": FilterOperation(gt=25)},
+        results = await agent_client.search(
+            filter={"age": {"gt": 25}},
             order_by="data.name",
             page_size=20
         )
@@ -107,19 +107,20 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
 
     def __init__(
         self,
-        client: AsyncLlamaCloud,
         type: Type[AgentDataT],
-        collection_name: str = "default",
+        collection: str = "default",
         agent_url_id: Optional[str] = None,
+        client: Optional[AsyncLlamaCloud] = None,
+        token: Optional[str] = None,
+        base_url: Optional[str] = None,
     ):
         """
         Initialize the AsyncAgentDataClient.
 
         Args:
-            client: AsyncLlamaCloud client instance for API communication
             type: Pydantic BaseModel class that defines the data structure.
                 All agent data will be validated against this type.
-            collection_name: Named collection within the agent for organizing data.
+            collection: Named collection within the agent for organizing data.
                 Defaults to "default". Collections allow logical separation of
                 different data types or workflows within the same agent.
             agent_url_id: Unique identifier for the agent. This normally appears in the
@@ -127,6 +128,11 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
                 will attempt to use the LLAMA_DEPLOY_DEPLOYMENT_NAME environment
                 variable. Data can only be added to an already existing agent in the
                 platform.
+            client: AsyncLlamaCloud client instance for API communication. If not provided, will
+                construct one from the provided api token and base url
+            token: Llama Cloud API token. Reads from LLAMA_CLOUD_API_KEY if not provided
+            base_url: Llama Cloud API token. Reads from LLAMA_CLOUD_BASE_URL if not provided, and
+                defaults to https://api.cloud.llamaindex.ai
 
         Raises:
             ValueError: If agent_url_id is not provided and the
@@ -138,33 +144,34 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
         """
 
         self.agent_url_id = agent_url_id or get_default_agent_id()
-        if not self.agent_url_id:
-            raise ValueError(
-                "Agent ID is required, or set the LLAMA_DEPLOY_DEPLOYMENT_NAME environment variable"
-            )
 
-        self.collection_name = collection_name
+        self.collection = collection
+        if not client:
+            client = AsyncLlamaCloud(
+                token=token or os.getenv("LLAMA_CLOUD_API_KEY"),
+                base_url=base_url or os.getenv("LLAMA_CLOUD_BASE_URL"),
+            )
         self.client = client
         self.type = type
 
     @agent_data_retry
-    async def get_agent_data(self, item_id: str) -> TypedAgentData[AgentDataT]:
+    async def get_item(self, item_id: str) -> TypedAgentData[AgentDataT]:
         raw_data = await self.client.beta.get_agent_data(
             item_id=item_id,
         )
         return TypedAgentData.from_raw(raw_data, validator=self.type)
 
     @agent_data_retry
-    async def create_agent_data(self, data: AgentDataT) -> TypedAgentData[AgentDataT]:
+    async def create_item(self, data: AgentDataT) -> TypedAgentData[AgentDataT]:
         raw_data = await self.client.beta.create_agent_data(
             agent_slug=self.agent_url_id,
-            collection=self.collection_name,
+            collection=self.collection,
             data=data.model_dump(),
         )
         return TypedAgentData.from_raw(raw_data, validator=self.type)
 
     @agent_data_retry
-    async def update_agent_data(
+    async def update_item(
         self, item_id: str, data: AgentDataT
     ) -> TypedAgentData[AgentDataT]:
         raw_data = await self.client.beta.update_agent_data(
@@ -174,13 +181,13 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
         return TypedAgentData.from_raw(raw_data, validator=self.type)
 
     @agent_data_retry
-    async def delete_agent_data(self, item_id: str) -> None:
+    async def delete_item(self, item_id: str) -> None:
         await self.client.beta.delete_agent_data(item_id=item_id)
 
     @agent_data_retry
-    async def search_agent_data(
+    async def search(
         self,
-        filter: Optional[Dict[str, Optional[FilterOperation]]] = None,
+        filter: Optional[Dict[str, Dict[ComparisonOperator, Any]]] = None,
         order_by: Optional[str] = None,
         offset: Optional[int] = None,
         page_size: Optional[int] = None,
@@ -191,11 +198,11 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
         Args:
             filter: Filter conditions to apply to the search. Dict mapping field names to FilterOperation objects. Filters only by data fields
                 Examples:
-                - {"age": FilterOperation(gt=18)} - age greater than 18
-                - {"status": FilterOperation(eq="active")} - status equals "active"
-                - {"tags": FilterOperation(includes=["python", "ml"])} - tags include "python" or "ml"
-                - {"created_at": FilterOperation(gte="2024-01-01")} - created after date
-                - {"score": FilterOperation(lt=100, gte=50)} - score between 50 and 100
+                - {"age": {"gt": 18}} - age greater than 18
+                - {"status": {"eq": "active"}} - status equals "active"
+                - {"tags": {"includes": ["python", "ml"]}} - tags include "python" or "ml"
+                - {"created_at": {"gte": "2024-01-01"}} - created after date
+                - {"score": {"lt": 100, "gte": 50}} - score between 50 and 100
             order_by: Comma delimited list of fields to sort results by. Can order by standard agent fields like created_at, or by data fields. Data fields must be prefixed with "data.". If ordering desceding, use a " desc" suffix.
                 Examples:
                 - "data.name desc, created_at" - sort by name in descending order, and then by creation date
@@ -205,7 +212,7 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
         """
         raw = await self.client.beta.search_agent_data_api_v_1_beta_agent_data_search_post(
             agent_slug=self.agent_url_id,
-            collection=self.collection_name,
+            collection=self.collection,
             filter=filter,
             order_by=order_by,
             offset=offset,
@@ -221,9 +228,9 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
         )
 
     @agent_data_retry
-    async def aggregate_agent_data(
+    async def aggregate(
         self,
-        filter: Optional[Dict[str, Optional[FilterOperation]]] = None,
+        filter: Optional[Dict[str, Dict[ComparisonOperator, Any]]] = None,
         group_by: Optional[List[str]] = None,
         count: Optional[bool] = None,
         first: Optional[bool] = None,
@@ -235,20 +242,20 @@ class AsyncAgentDataClient(Generic[AgentDataT]):
         Aggregate agent data into groups according to the group_by fields.
         Args:
             filter: Filter conditions to apply to the search. Dict mapping field names to FilterOperation objects. Filters only by data fields
-                See search_agent_data for more details on filtering.
+                See search for more details on filtering.
             group_by: List of fields to group by. Groups strictly by equality. Can only group by data fields.
                 Examples:
                 - ["name"] - group by name
                 - ["name", "age"] - group by name and age
             count: Whether to include the count of items in each group.
             first: Whether to include the first item in each group.
-            order_by: Comma delimited list of fields to sort results by. See search_agent_data for more details on ordering.
+            order_by: Comma delimited list of fields to sort results by. See search for more details on ordering.
             offset: Number of groups to skip from the beginning. Defaults to 0.
             page_size: Maximum number of groups to return per page.
         """
         raw = await self.client.beta.aggregate_agent_data_api_v_1_beta_agent_data_aggregate_post(
             agent_slug=self.agent_url_id,
-            collection=self.collection_name,
+            collection=self.collection,
             page_size=page_size,
             filter=filter,
             order_by=order_by,

llama_cloud_services/beta/agent_data/schema.py

@@ -37,9 +37,11 @@ Example Usage:
 """
 
 from datetime import datetime
+import numbers
+from llama_cloud import ExtractRun
 from llama_cloud.types.agent_data import AgentData
 from llama_cloud.types.aggregate_group import AggregateGroup
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, ValidationError
 from typing import (
     Generic,
     List,
@@ -60,7 +62,11 @@ AgentDataT = TypeVar("AgentDataT", bound=BaseModel)
 ExtractedT = TypeVar("ExtractedT", bound=Union[BaseModel, dict])
 
 # Status types for extracted data workflow
-StatusType = Union[Literal["error", "accepted", "rejected", "in_review"], str]
+StatusType = Union[Literal["error", "accepted", "rejected", "pending_review"], str]
+
+ComparisonOperator = Dict[
+    str, Dict[Literal["gt", "gte", "lt", "lte", "eq", "includes"], Any]
+]
 
 
 class TypedAgentData(BaseModel, Generic[AgentDataT]):
@@ -142,7 +148,7 @@ class TypedAgentDataItems(BaseModel, Generic[AgentDataT]):
     Example:
         ```python
         # Search with pagination
-        results = await client.search_agent_data(
+        results = await client.search(
             page_size=10,
             include_total=True
         )
@@ -152,7 +158,7 @@ class TypedAgentDataItems(BaseModel, Generic[AgentDataT]):
 
         if results.has_more:
             # Load next page
-            next_page = await client.search_agent_data(
+            next_page = await client.search(
                 page_size=10,
                 offset=10
             )
@@ -170,6 +176,74 @@ class TypedAgentDataItems(BaseModel, Generic[AgentDataT]):
     )
 
 
+class ExtractedFieldMetadata(BaseModel):
+    """
+    Metadata for an extracted data field, such as confidence, and citation information.
+    """
+
+    confidence: Optional[float] = Field(
+        None,
+        description="The confidence score for the field, combined with parsing confidence if applicable",
+    )
+    extracted_confidence: Optional[float] = Field(
+        None,
+        description="The confidence score for the field based on the extracted text only",
+    )
+    page_number: Optional[int] = Field(
+        None, description="The page number that the field occurred on"
+    )
+    matching_text: Optional[str] = Field(
+        None,
+        description="The original text this field's value was derived from",
+    )
+
+
+ExtractedFieldMetaDataDict = Dict[
+    str, Union[ExtractedFieldMetadata, Dict[str, Any], list[Any]]
+]
+
+
+def parse_extracted_field_metadata(
+    field_metadata: dict[str, Any],
+) -> ExtractedFieldMetaDataDict:
+    """
+    Parse the extracted field metadata into a dictionary of field names to field metadata.
+    """
+    result: ExtractedFieldMetaDataDict = {}
+    for field_name, field_value in field_metadata.items():
+        if isinstance(field_value, ExtractedFieldMetadata):
+            # support running this multiple times
+            result[field_name] = field_value
+        elif isinstance(field_value, dict):
+            if "confidence" in field_value or "citations" in field_value:
+                try:
+                    validated = ExtractedFieldMetadata.model_validate(field_value)
+
+                    # grab the citation from the array. This is just an array for backwards compatibility.
+                    if "citations" in field_value and len(field_value["citations"]) > 0:
+                        first_citation = field_value["citations"][0]
+                        if "page_number" in first_citation and isinstance(
+                            first_citation["page_number"], numbers.Number
+                        ):
+                            validated.page_number = int(first_citation["page_number"])  # type: ignore
+                        if "matching_text" in first_citation and isinstance(
+                            first_citation["matching_text"], str
+                        ):
+                            validated.matching_text = first_citation["matching_text"]
+                    result[field_name] = validated
+                    continue
+                except ValidationError:
+                    pass
+            result[field_name] = parse_extracted_field_metadata(field_value)
+        elif isinstance(field_value, list):
+            result[field_name] = [
+                parse_extracted_field_metadata(item) for item in field_value
+            ]
+        else:
+            result[field_name] = field_value
+    return result
+
+
 class ExtractedData(BaseModel, Generic[ExtractedT]):
     """
     Wrapper for extracted data with workflow status tracking.
@@ -183,9 +257,12 @@ class ExtractedData(BaseModel, Generic[ExtractedT]):
         data: The current state of the data (may differ from original after edits)
         status: Current workflow status (in_review, accepted, rejected, error)
         confidence: Confidence scores for individual fields (if available)
+        file_id: The llamacloud file ID of the file that was used to extract the data
+        file_name: The name of the file that was used to extract the data
+        file_hash: A content hash of the file that was used to extract the data, for de-duplication
 
     Status Workflow:
-        - "in_review": Initial state, awaiting human review
+        - "pending_review": Initial state, awaiting human review
         - "accepted": Data approved and ready for use
         - "rejected": Data rejected, needs re-extraction or manual fix
         - "error": Processing error occurred
@@ -194,8 +271,8 @@ class ExtractedData(BaseModel, Generic[ExtractedT]):
         ```python
         # Create extracted data for review
         extracted = ExtractedData.create(
-            extracted_data=person_data,
-            status="in_review",
+            data=person_data,
+            status="pending_review",
             confidence={"name": 0.95, "age": 0.87}
         )
 
@@ -212,20 +289,39 @@ class ExtractedData(BaseModel, Generic[ExtractedT]):
     data: ExtractedT = Field(
         description="The latest state of the data. Will differ if data has been updated"
     )
-    status: Union[Literal["error", "accepted", "rejected", "in_review"], str] = Field(
-        description="The status of the extracted data"
+    status: StatusType = Field(description="The status of the extracted data")
+    overall_confidence: Optional[float] = Field(
+        None,
+        description="The overall confidence score for the extracted data",
     )
-    confidence: Dict[str, Union[float, Dict]] = Field(
+    field_metadata: ExtractedFieldMetaDataDict = Field(
         default_factory=dict,
-        description="Confidence scores, if any, for each primitive field in the original_data data",
+        description="Page links, and perhaps eventually bounding boxes, for individual fields in the extracted data. Structure is expected to have a ",
+    )
+    file_id: Optional[str] = Field(
+        None, description="The ID of the file that was used to extract the data"
+    )
+    file_name: Optional[str] = Field(
+        None, description="The name of the file that was used to extract the data"
+    )
+    file_hash: Optional[str] = Field(
+        None, description="The hash of the file that was used to extract the data"
+    )
+    metadata: Optional[Dict[str, Any]] = Field(
+        default_factory=dict,
+        description="Additional metadata about the extracted data, such as errors, tokens, etc.",
     )
 
     @classmethod
     def create(
         cls,
-        extracted_data: ExtractedT,
-        status: StatusType = "in_review",
-        confidence: Optional[Dict[str, Union[float, Dict]]] = None,
+        data: ExtractedT,
+        status: StatusType = "pending_review",
+        field_metadata: ExtractedFieldMetaDataDict = {},
+        file_id: Optional[str] = None,
+        file_name: Optional[str] = None,
+        file_hash: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ) -> "ExtractedData[ExtractedT]":
         """
         Create a new ExtractedData instance with sensible defaults.
@@ -233,18 +329,128 @@ class ExtractedData(BaseModel, Generic[ExtractedT]):
         Args:
             extracted_data: The extracted data payload
             status: Initial workflow status
-            confidence: Optional confidence scores for fields
+            field_metadata: Optional confidence scores, citations, and other metadata for fields
+            file_id: The llamacloud file ID of the file that was used to extract the data
+            file_name: The name of the file that was used to extract the data
+            file_hash: A content hash of the file that was used to extract the data, for de-duplication
+            metadata: Arbitrary additional application-specific data about the extracted data
 
         Returns:
             New ExtractedData instance ready for storage
         """
+        normalized_field_metadata = parse_extracted_field_metadata(field_metadata)
         return cls(
-            original_data=extracted_data,
-            data=extracted_data,
+            original_data=data,
+            data=data,
             status=status,
-            confidence=confidence or {},
+            field_metadata=normalized_field_metadata,
+            overall_confidence=calculate_overall_confidence(normalized_field_metadata),
+            file_id=file_id,
+            file_name=file_name,
+            file_hash=file_hash,
+            metadata=metadata or {},
         )
 
+    @classmethod
+    def from_extraction_result(
+        cls,
+        result: ExtractRun,
+        schema: Type[ExtractedT],
+        file_hash: Optional[str] = None,
+        file_name: Optional[str] = None,
+        file_id: Optional[str] = None,
+        status: StatusType = "pending_review",
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> "ExtractedData[ExtractedT]":
+        """
+        Create an ExtractedData instance from an extraction result.
+        """
+        file_id = file_id or result.file.id
+        file_name = file_name or result.file.name
+
+        try:
+            field_metadata = parse_extracted_field_metadata(
+                result.extraction_metadata.get("field_metadata", {})
+            )
+        except ValidationError:
+            field_metadata = {}
+
+        try:
+            data = schema.model_validate(result.data)  # type: ignore
+            return cls.create(
+                data=data,
+                status=status,
+                field_metadata=field_metadata,
+                file_id=file_id,
+                file_name=file_name,
+                file_hash=file_hash,
+                metadata=metadata or {},
+            )
+        except ValidationError as e:
+            invalid_item = ExtractedData[Dict[str, Any]].create(
+                data=result.data or {},
+                status="error",
+                field_metadata=field_metadata,
+                metadata={"extraction_error": str(e), **(metadata or {})},
+                file_id=file_id,
+                file_name=file_name,
+                file_hash=file_hash,
+            )
+            raise InvalidExtractionData(invalid_item) from e
+
+
+class InvalidExtractionData(Exception):
+    """
+    Exception raised when the extracted data does not conform to the schema.
+    """
+
+    def __init__(self, invalid_item: ExtractedData[Dict[str, Any]]):
+        self.invalid_item = invalid_item
+        super().__init__("Not able to parse the extracted data, parsed invalid format")
+
+
+def calculate_overall_confidence(
+    metadata: ExtractedFieldMetaDataDict,
+) -> Optional[float]:
+    """
+    Calculate the overall confidence score for the extracted data.
+    """
+    numerator, denominator = _calculate_overall_confidence_recursive(metadata)
+    if denominator == 0:
+        return None
+    return numerator / denominator
+
+
+def _calculate_overall_confidence_recursive(
+    confidence: Union[ExtractedFieldMetadata, Dict[str, Any], list[Any]],
+) -> tuple[float, int]:
+    """
+    Calculate the overall confidence score for the extracted data.
+    """
+    if isinstance(confidence, ExtractedFieldMetadata):
+        if confidence.confidence is not None:
+            return confidence.confidence, 1
+        else:
+            return 0, 0
+    if isinstance(confidence, dict):
+        numerator: float = 0
+        denominator: int = 0
+        for value in confidence.values():
+            num, den = _calculate_overall_confidence_recursive(value)
+            numerator += num
+            denominator += den
+        return numerator, denominator
+    elif isinstance(confidence, list):
+        numerator = 0
+        denominator = 0
+        for value in confidence:
+            num, den = _calculate_overall_confidence_recursive(value)
+            numerator += num
+            denominator += den
+        return numerator, denominator
+    else:
+        return 0, 0
+
 
 class TypedAggregateGroup(BaseModel, Generic[AgentDataT]):
     """

llama_cloud_services/extract/extract.py

@@ -137,15 +137,9 @@ def run_in_thread(
 
 
 def _extraction_config_warning(config: ExtractConfig) -> None:
-    if config.use_reasoning:
+    if config.cite_sources or config.confidence_scores:
         warnings.warn(
-            "`use_reasoning` is an experimental feature. Results will be available in "
-            "the `extraction_metadata` field for the extraction run.",
-            ExperimentalWarning,
-        )
-    if config.cite_sources:
-        warnings.warn(
-            "`cite_sources` is an experimental feature. This may greatly increase the "
+            "`cite_sources`/`confidence_scores` could greatly increase the "
             "size of the response, and slow down the extraction. Results will be "
             "available in the `extraction_metadata` field for the extraction run.",
             ExperimentalWarning,

llama_cloud_services/parse/base.py

@@ -37,6 +37,7 @@ from llama_cloud_services.parse.utils import (
     nest_asyncio_msg,
     make_api_request,
     partition_pages,
+    extract_tables_from_json_results,
 )
 
 # can put in a path to the file or the file bytes itself
@@ -324,6 +325,10 @@ class LlamaParse(BasePydanticReader):
         default=None,
         description="The maximum number of pages to extract text from documents. If set to 0 or not set, all pages will be that should be extracted will be extracted (can work in combination with targetPages).",
     )
+    merge_tables_across_pages_in_markdown: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will merge tables across pages in the markdown output. This is useful for documents with tables that span across multiple pages.",
+    )
     output_pdf_of_document: Optional[bool] = Field(
         default=False,
         description="If set to true, the parser will also output a PDF of the document. (except for spreadsheets)",
@@ -376,6 +381,10 @@ class LlamaParse(BasePydanticReader):
         default=False,
         description="Preserve grid alignment across page in text mode.",
     )
+    preserve_very_small_text: Optional[bool] = Field(
+        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).",
+    )
     replace_failed_page_mode: Optional[FailedPageMode] = Field(
         default=None,
         description="The mode to use to replace the failed page, see FailedPageMode enum for possible value. If set, the parser will replace the failed page with the specified mode. If not set, the default mode (raw_text) will be used.",
@@ -859,6 +868,11 @@ class LlamaParse(BasePydanticReader):
         if self.page_prefix is not None:
             data["page_prefix"] = self.page_prefix
 
+        if self.merge_tables_across_pages_in_markdown:
+            data[
+                "merge_tables_across_pages_in_markdown"
+            ] = self.merge_tables_across_pages_in_markdown
+
         if self.hide_headers:
             data["hide_headers"] = self.hide_headers
 
@@ -902,6 +916,9 @@ class LlamaParse(BasePydanticReader):
                 "preserve_layout_alignment_across_pages"
             ] = self.preserve_layout_alignment_across_pages
 
+        if self.preserve_very_small_text:
+            data["preserve_very_small_text"] = self.preserve_very_small_text
+
         if self.preset is not None:
             data["preset"] = self.preset
 
@@ -1611,6 +1628,16 @@ class LlamaParse(BasePydanticReader):
             else:
                 raise e
 
+    def get_tables(self, json_results: List[dict], download_path: str) -> List[str]:
+        if not os.path.exists(download_path):
+            os.makedirs(download_path)
+        return extract_tables_from_json_results(json_results, download_path)
+
+    async def aget_tables(
+        self, json_result: List[dict], download_path: str
+    ) -> List[str]:
+        return await asyncio.to_thread(self.get_tables, json_result, download_path)
+
     async def aget_xlsx(
         self, json_result: List[dict], download_path: str
     ) -> List[dict]:
@@ -1677,3 +1704,79 @@ class LlamaParse(BasePydanticReader):
                 sub_docs.append(sub_doc)
 
         return sub_docs
+
+    async def aget_result(
+        self, job_id: Union[str, List[str]]
+    ) -> Union[JobResult, List[JobResult]]:
+        """
+        Return JobResult object for previously parsed job(s).
+
+        If the job is still pending, the result will not be returned until it is completed.
+
+        Args:
+            job_id: Job ID or list of multiple Job IDs to be retrieved.
+
+        Returns:
+            JobResult object or list of JobResult objects if multiple job IDs were provided.
+        """
+        if isinstance(job_id, str):
+            result = await self._get_job_result(
+                job_id, ResultType.JSON.value, verbose=self.verbose
+            )
+            return JobResult(
+                job_id=job_id,
+                file_name="",
+                job_result=result,
+                api_key=self.api_key,
+                base_url=self.base_url,
+                client=self.aclient,
+                page_separator=self.page_separator or _DEFAULT_SEPARATOR,
+            )
+        elif isinstance(job_id, list):
+            results = []
+            jobs = [
+                self._get_job_result(id_, ResultType.JSON.value, verbose=self.verbose)
+                for id_ in job_id
+            ]
+            results = await run_jobs(
+                jobs,
+                workers=self.num_workers,
+                desc="Getting job results",
+                show_progress=self.show_progress,
+            )
+            return [
+                JobResult(
+                    job_id=job_id[i],
+                    file_name="",
+                    job_result=result,
+                    api_key=self.api_key,
+                    base_url=self.base_url,
+                    client=self.aclient,
+                    page_separator=self.page_separator or _DEFAULT_SEPARATOR,
+                )
+                for i, result in enumerate(results)
+            ]
+        else:
+            raise ValueError("The input job_id must be a string or a list of strings.")
+
+    def get_result(
+        self, job_id: Union[str, List[str]]
+    ) -> Union[JobResult, List[JobResult]]:
+        """
+        Return JobResult object for previously parsed job(s).
+
+        If the job is still pending, the result will not be returned until it is completed.
+
+        Args:
+            job_id: Job ID or list of multiple Job IDs to be retrieved.
+
+        Returns:
+            JobResult object or list of JobResult objects if multiple job IDs were provided.
+        """
+        try:
+            return asyncio_run(self.aget_result(job_id))
+        except RuntimeError as e:
+            if nest_asyncio_err in str(e):
+                raise RuntimeError(nest_asyncio_msg)
+            else:
+                raise e

llama_cloud_services/parse/types.py

@@ -295,13 +295,64 @@ class JobResult(BaseModel):
     async def aget_markdown_nodes(self, split_by_page: bool = False) -> List[TextNode]:
         """
         Get the markdown nodes from the job.
-
         Args:
             split_by_page: Whether to split the pages into separate documents
         """
         documents = await self.aget_markdown_documents(split_by_page)
         return [TextNode(text=doc.text, metadata=doc.metadata) for doc in documents]
 
+    def get_markdown(self) -> str:
+        """
+        Get the raw parsed markdown from the job, distinct from the markdown documents.
+        This does not include page separators, e.g. if merge_tables_across_pages_in_markdown is True
+        """
+        return asyncio_run(self.aget_markdown())
+
+    async def aget_markdown(self) -> str:
+        """
+        Get the raw parsed markdown from the job, distinct from the markdown documents.
+        This does not include page separators, e.g. if merge_tables_across_pages_in_markdown is True
+        """
+        url = f"{self._base_url}/api/v1/parsing/job/{self.job_id}/result/raw/markdown"
+        response = await make_api_request(self._client, "GET", url)
+        return response.content.decode("utf-8")
+
+    def get_text(self) -> str:
+        """
+        Get the raw parsed text from the job.
+        """
+        return asyncio_run(self.aget_text())
+
+    async def aget_text(self) -> str:
+        """
+        Get the raw parsed text from the job.
+        """
+        url = f"{self._base_url}/api/v1/parsing/job/{self.job_id}/result/raw/text"
+        response = await make_api_request(self._client, "GET", url)
+        return response.content.decode("utf-8")
+
+    def get_json(self) -> Dict[str, Any]:
+        """
+        Get the full parsed JSON result from the job.
+
+        Note:
+            This is not the same as JobResult.json(), which is a
+            JSON serialized version of the JobResult Page Documents.
+        """
+        return asyncio_run(self.aget_json())
+
+    async def aget_json(self) -> Dict[str, Any]:
+        """
+        Get the full parsed JSON result from the job.
+
+        Note:
+            This is not the same as JobResult.json(), which is a
+            JSON serialized version of the JobResult Page Documents.
+        """
+        url = f"{self._base_url}/api/v1/parsing/job/{self.job_id}/result/json"
+        response = await make_api_request(self._client, "GET", url)
+        return response.json()
+
     async def _get_image_document_with_bytes(
         self, image: ImageItem, page: Page
     ) -> ImageDocument:

llama_cloud_services/parse/utils.py

@@ -1,7 +1,10 @@
 import httpx
 import itertools
 import logging
+import os
 from enum import Enum
+from pathlib import Path
+from datetime import datetime
 from tenacity import (
     retry,
     stop_after_attempt,
@@ -9,7 +12,7 @@ from tenacity import (
     retry_if_exception,
     before_sleep_log,
 )
-from typing import Any, Iterable, Iterator, Optional
+from typing import Any, Iterable, Iterator, Optional, List, cast
 
 logger = logging.getLogger(__name__)
 
@@ -351,3 +354,30 @@ def partition_pages(
             yield ",".join(targets)
         else:
             return
+
+
+def extract_tables_from_json_results(
+    json_results: List[dict], download_path: str
+) -> List[str]:
+    tables = []
+    for json_result in json_results:
+        pages = json_result["pages"]
+        for page in pages:
+            page = cast(dict, page)
+            items = page.get("items", [])
+            if items:
+                for i, item in enumerate(items):
+                    item = cast(dict, item)
+                    if item.get("type", "") == "table" and item.get("csv", ""):
+                        savepath = os.path.join(
+                            download_path,
+                            f"table_{datetime.now().strftime('%Y_%d_%m_%H_%M_%S_%f')[:-3]}.csv",
+                        )
+                        if Path(savepath).exists():
+                            savepath = (
+                                savepath.replace(".csv", "_")[0] + str(i) + ".csv"
+                            )
+                        with open(savepath, "w") as f:
+                            f.write(item["csv"])
+                        tables.append(savepath)
+    return tables

llama_parse/poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.1.3 and should not be changed by hand.
 
 [[package]]
 name = "aiohappyeyeballs"
@@ -257,7 +257,7 @@ version = "2025.1.31"
 description = "Python package for providing Mozilla's CA Bundle."
 optional = false
 python-versions = ">=3.6"
-groups = ["main", "dev"]
+groups = ["main"]
 files = [
     {file = "certifi-2025.1.31-py3-none-any.whl", hash = "sha256:ca78db4565a652026a4db2bcdf68f2fb589ea80d0be70e03929ed730746b84fe"},
     {file = "certifi-2025.1.31.tar.gz", hash = "sha256:3d5da6925056f6f18f119200434a4780a94263f10d1c21d032a6f6b2baa20651"},
@@ -350,7 +350,7 @@ version = "3.4.1"
 description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
 optional = false
 python-versions = ">=3.7"
-groups = ["main", "dev"]
+groups = ["main"]
 files = [
     {file = "charset_normalizer-3.4.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:91b36a978b5ae0ee86c394f5a54d6ef44db1de0815eb43de826d41d21e4af3de"},
     {file = "charset_normalizer-3.4.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7461baadb4dc00fd9e0acbe254e3d7d2112e7f92ced2adc96e54ef6501c5f176"},
@@ -593,7 +593,7 @@ description = "Like `typing._eval_type`, but lets older Python versions use newe
 optional = false
 python-versions = ">=3.8"
 groups = ["main"]
-markers = "python_version < \"3.10\""
+markers = "python_version == \"3.9\""
 files = [
     {file = "eval_type_backport-0.2.2-py3-none-any.whl", hash = "sha256:cb6ad7c393517f476f96d456d0412ea80f0a8cf96f6892834cd9340149111b0a"},
     {file = "eval_type_backport-0.2.2.tar.gz", hash = "sha256:f0576b4cf01ebb5bd358d02314d31846af5e07678387486e2c798af0e7d849c1"},
@@ -896,7 +896,7 @@ version = "0.16.0"
 description = "A pure-Python, bring-your-own-I/O implementation of HTTP/1.1"
 optional = false
 python-versions = ">=3.8"
-groups = ["main", "dev"]
+groups = ["main"]
 files = [
     {file = "h11-0.16.0-py3-none-any.whl", hash = "sha256:63cf8bbe7522de3bf65932fda1d9c2772064ffb3dae62d55932da54b31cb6c86"},
     {file = "h11-0.16.0.tar.gz", hash = "sha256:4e35b956cf45792e4caa5885e69fba00bdbc6ffafbfa020300e549b208ee5ff1"},
@@ -955,7 +955,7 @@ version = "3.10"
 description = "Internationalized Domain Names in Applications (IDNA)"
 optional = false
 python-versions = ">=3.6"
-groups = ["main", "dev"]
+groups = ["main"]
 files = [
     {file = "idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3"},
     {file = "idna-3.10.tar.gz", hash = "sha256:12f65c9b470abda6dc35cf8e63cc574b1c52b11df2c86030af0ac09b01b13ea9"},
@@ -971,7 +971,7 @@ description = "Read metadata from Python packages"
 optional = false
 python-versions = ">=3.9"
 groups = ["dev"]
-markers = "python_version < \"3.10\""
+markers = "python_version == \"3.9\""
 files = [
     {file = "importlib_metadata-8.6.1-py3-none-any.whl", hash = "sha256:02a89390c1e15fdfdc0d7c6b25cb3e62650d0494005c97d6f148bf5b9787525e"},
     {file = "importlib_metadata-8.6.1.tar.gz", hash = "sha256:310b41d755445d74569f993ccfc22838295d9fe005425094fad953d7f15c8580"},
@@ -1170,14 +1170,14 @@ test = ["ipykernel", "pre-commit", "pytest (<8)", "pytest-cov", "pytest-timeout"
 
 [[package]]
 name = "llama-cloud"
-version = "0.1.23"
+version = "0.1.34"
 description = ""
 optional = false
 python-versions = "<4,>=3.8"
 groups = ["main"]
 files = [
-    {file = "llama_cloud-0.1.23-py3-none-any.whl", hash = "sha256:ce95b0705d85c99b3b27b0af0d16a17d9a81b14c96bf13c1063a1bd13d8d0446"},
-    {file = "llama_cloud-0.1.23.tar.gz", hash = "sha256:3d84a24a860f046d39a106c06742ec0ea39a574ac42bbf91706fe025f44e233e"},
+    {file = "llama_cloud-0.1.34-py3-none-any.whl", hash = "sha256:9b06fb109b1d9f652095a11732ae3dbe84e48cc00c580b2eeb19e71e901267be"},
+    {file = "llama_cloud-0.1.34.tar.gz", hash = "sha256:6866e4bab47d2c1840bdf169c13c06176931c1d30697ac1fa71bab7942a041e9"},
 ]
 
 [package.dependencies]
@@ -1187,24 +1187,25 @@ pydantic = ">=1.10"
 
 [[package]]
 name = "llama-cloud-services"
-version = "0.6.30"
+version = "0.6.48"
 description = "Tailored SDK clients for LlamaCloud services."
 optional = false
 python-versions = "<4.0,>=3.9"
 groups = ["main"]
 files = [
-    {file = "llama_cloud_services-0.6.30-py3-none-any.whl", hash = "sha256:4d5817a9841fc3ba3409865c52d082090f4ef827931f0e5e4a89f5818c0d4e36"},
-    {file = "llama_cloud_services-0.6.30.tar.gz", hash = "sha256:2cb5004d13127aac52888ae9b3d70f899d598633520b2a2542bb62682d08d776"},
+    {file = "llama_cloud_services-0.6.48-py3-none-any.whl", hash = "sha256:5faadcfa270f3be516dd7d3568cbb54b3014b2c8878c5bd7d3252ab1bd635869"},
+    {file = "llama_cloud_services-0.6.48.tar.gz", hash = "sha256:64fe8d8ce7434d6a481646c35be55973ae10765d20b6be0067a262e6be61f2df"},
 ]
 
 [package.dependencies]
 click = ">=8.1.7,<9.0.0"
 eval-type-backport = {version = ">=0.2.0,<0.3.0", markers = "python_version < \"3.10\""}
-llama-cloud = "0.1.23"
+llama-cloud = "0.1.34"
 llama-index-core = ">=0.12.0"
 platformdirs = ">=4.3.7,<5.0.0"
 pydantic = ">=2.8,<2.10 || >2.10"
 python-dotenv = ">=1.0.1,<2.0.0"
+tenacity = ">=8.5.0,<10.0"
 
 [[package]]
 name = "llama-index-core"
@@ -2473,7 +2474,7 @@ version = "2.32.4"
 description = "Python HTTP for Humans."
 optional = false
 python-versions = ">=3.8"
-groups = ["main", "dev"]
+groups = ["main"]
 files = [
     {file = "requests-2.32.4-py3-none-any.whl", hash = "sha256:27babd3cda2a6d50b30443204ee89830707d396671944c998b5975b031ac2b2c"},
     {file = "requests-2.32.4.tar.gz", hash = "sha256:27d0316682c8a29834d3264820024b62a36942083d52caf2f14c0591336d3422"},
@@ -2807,7 +2808,7 @@ files = [
     {file = "typing_extensions-4.13.2-py3-none-any.whl", hash = "sha256:a439e7c04b49fec3e5d3e2beaa21755cadbbdc391694e28ccdd36ca4a1408f8c"},
     {file = "typing_extensions-4.13.2.tar.gz", hash = "sha256:e6c81219bd689f51865d9e372991c540bda33a0379d5573cddb9a3a23f7caaef"},
 ]
-markers = {dev = "python_version < \"3.10\""}
+markers = {dev = "python_version == \"3.9\""}
 
 [[package]]
 name = "typing-inspect"
@@ -2846,7 +2847,7 @@ version = "2.4.0"
 description = "HTTP library with thread-safe connection pooling, file post, and more."
 optional = false
 python-versions = ">=3.9"
-groups = ["main", "dev"]
+groups = ["main"]
 files = [
     {file = "urllib3-2.4.0-py3-none-any.whl", hash = "sha256:4e16665048960a0900c702d4a66415956a584919c03361cac9f1df5c5dd7e813"},
     {file = "urllib3-2.4.0.tar.gz", hash = "sha256:414bc6535b787febd7567804cc015fee39daab8ad86268f1310a9250697de466"},
@@ -3068,7 +3069,7 @@ description = "Backport of pathlib-compatible object wrapper for zip files"
 optional = false
 python-versions = ">=3.9"
 groups = ["dev"]
-markers = "python_version < \"3.10\""
+markers = "python_version == \"3.9\""
 files = [
     {file = "zipp-3.21.0-py3-none-any.whl", hash = "sha256:ac1bbe05fd2991f160ebce24ffbac5f6d11d83dc90891255885223d42b3cd931"},
     {file = "zipp-3.21.0.tar.gz", hash = "sha256:2c9958f6430a2040341a52eb608ed6dd93ef4392e02ffe219417c1b28b5dd1f4"},
@@ -3085,4 +3086,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<4.0"
-content-hash = "1be767f62c8a8e1c9acb76347055a837ea2c44130004703361d0303b049bede7"
+content-hash = "0b5ab34c44ce7802b02e01b6535b9bb0e08f99f26a43a76be88534dd8a417666"

llama_parse/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "llama-parse"
-version = "0.6.44"
+version = "0.6.53"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <logan@llamaindex.ai>"]
 license = "MIT"
@@ -13,7 +13,7 @@ packages = [{include = "llama_parse"}]
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
-llama-cloud-services = ">=0.6.44"
+llama-cloud-services = ">=0.6.53"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.0.0"

poetry.lock

@@ -1925,14 +1925,14 @@ rapidfuzz = ">=3.9.0,<4.0.0"
 
 [[package]]
 name = "llama-cloud"
-version = "0.1.33"
+version = "0.1.35"
 description = ""
 optional = false
 python-versions = "<4,>=3.8"
 groups = ["main"]
 files = [
-    {file = "llama_cloud-0.1.33-py3-none-any.whl", hash = "sha256:35b7d4a30b013f0a343f7e09126b531c697d65bffd4eb4d2d79bf7d65f256178"},
-    {file = "llama_cloud-0.1.33.tar.gz", hash = "sha256:a0bb900d5a6e86f8c767b48686c5253679ad7ca1b57612dc39b0767e57ad3d78"},
+    {file = "llama_cloud-0.1.35-py3-none-any.whl", hash = "sha256:b7abab4423118e6f638d2f326749e7a07c6426543bea6da99b623c715b22af71"},
+    {file = "llama_cloud-0.1.35.tar.gz", hash = "sha256:200349d5d57424d7461f304cdb1355a58eea3e6ca1e6b0d75c66b2e937216983"},
 ]
 
 [package.dependencies]
@@ -4623,4 +4623,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<4.0"
-content-hash = "487717a0bbe7ff67360e3e9f187e15a33c77e4942a7c909cb37b95425a81544c"
+content-hash = "025b27407a221b35c3d970294ba1fd734d77a7742d41a317d6b62e08022376ae"

pyproject.toml

@@ -8,7 +8,7 @@ python_version = "3.10"
 
 [tool.poetry]
 name = "llama-cloud-services"
-version = "0.6.44"
+version = "0.6.53"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = ["Logan Markewich <logan@runllama.ai>"]
 license = "MIT"
@@ -18,7 +18,7 @@ packages = [{include = "llama_cloud_services"}]
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
 llama-index-core = ">=0.12.0"
-llama-cloud = "==0.1.33"
+llama-cloud = "==0.1.35"
 pydantic = ">=2.8,!=2.10"
 click = "^8.1.7"
 python-dotenv = "^1.0.1"

scripts/version-bump.py

@@ -0,0 +1,147 @@
+#!/usr/bin/env -S uv run --script
+# /// script
+# dependencies = ["click", "tomlkit"]
+# ///
+
+import click
+import subprocess
+import sys
+import tomlkit
+from pathlib import Path
+
+
+def get_current_versions() -> tuple[str, str, str]:
+    """Get current versions from both pyproject.toml files."""
+    # Read main pyproject.toml
+    main_content = Path("pyproject.toml").read_text()
+    main_doc = tomlkit.parse(main_content)
+    main_version = main_doc["tool"]["poetry"]["version"]
+
+    # Read llama_parse/pyproject.toml
+    llama_parse_content = Path("llama_parse/pyproject.toml").read_text()
+    llama_parse_doc = tomlkit.parse(llama_parse_content)
+    llama_parse_version = llama_parse_doc["tool"]["poetry"]["version"]
+    dependency_version = llama_parse_doc["tool"]["poetry"]["dependencies"][
+        "llama-cloud-services"
+    ]
+
+    return str(main_version), str(llama_parse_version), str(dependency_version)
+
+
+def validate_versions(
+    main_version: str, llama_parse_version: str, dependency_version: str
+) -> list[str]:
+    """Validate that versions are consistent and return warnings."""
+    warnings = []
+
+    if main_version != llama_parse_version:
+        warnings.append(
+            f"Version mismatch: main={main_version}, llama_parse={llama_parse_version}"
+        )
+
+    # Extract version from dependency string (e.g., ">=0.6.51" -> "0.6.51")
+    if dependency_version and dependency_version.startswith(">="):
+        dep_ver = dependency_version[2:]
+        if dep_ver != main_version:
+            warnings.append(
+                f"Dependency version mismatch: dependency={dep_ver}, main={main_version}"
+            )
+
+    return warnings
+
+
+def set_version(version: str) -> None:
+    """Set version across all pyproject.toml files using tomlkit to preserve formatting."""
+    # Update main pyproject.toml
+    main_content = Path("pyproject.toml").read_text()
+    main_doc = tomlkit.parse(main_content)
+    main_doc["tool"]["poetry"]["version"] = version
+    Path("pyproject.toml").write_text(tomlkit.dumps(main_doc))
+
+    # Update llama_parse/pyproject.toml
+    llama_parse_content = Path("llama_parse/pyproject.toml").read_text()
+    llama_parse_doc = tomlkit.parse(llama_parse_content)
+    llama_parse_doc["tool"]["poetry"]["version"] = version
+    llama_parse_doc["tool"]["poetry"]["dependencies"][
+        "llama-cloud-services"
+    ] = f">={version}"
+    Path("llama_parse/pyproject.toml").write_text(tomlkit.dumps(llama_parse_doc))
+
+    click.echo(f"Updated all versions to {version}")
+
+
+def get_current_branch() -> str:
+    """Get the current git branch."""
+    result = subprocess.run(
+        ["git", "branch", "--show-current"], capture_output=True, text=True, check=True
+    )
+    return result.stdout.strip()
+
+
+def create_and_push_tag(version: str) -> None:
+    """Create a git tag and push it."""
+    current_branch = get_current_branch()
+    if current_branch != "main":
+        click.echo(
+            f"Error: Not on main branch (currently on {current_branch})", err=True
+        )
+        sys.exit(1)
+
+    tag_name = f"v{version}"
+
+    # Create tag
+    subprocess.run(["git", "tag", tag_name], check=True)
+    click.echo(f"Created tag {tag_name}")
+
+    # Push tag
+    subprocess.run(["git", "push", "origin", tag_name], check=True)
+    click.echo(f"Pushed tag {tag_name}")
+
+
+@click.group()
+def cli() -> None:
+    """Version management for llama-cloud-services."""
+    pass
+
+
+@cli.command()
+def get() -> None:
+    """Get current versions and show validation warnings."""
+    main_version, llama_parse_version, dependency_version = get_current_versions()
+
+    click.echo("Current versions:")
+    click.echo(f"  llama-cloud-services: {main_version}")
+    click.echo(f"  llama-parse: {llama_parse_version}")
+    click.echo(f"  dependency reference: {dependency_version}")
+
+    warnings = validate_versions(main_version, llama_parse_version, dependency_version)
+    if warnings:
+        click.echo("\nValidation warnings:")
+        for warning in warnings:
+            click.echo(f"  ⚠️  {warning}")
+    else:
+        click.echo("\n✅ All versions are consistent")
+
+
+@cli.command()
+@click.argument("version")
+def set(version: str) -> None:
+    """Set version across all pyproject.toml files."""
+    set_version(version)
+
+
+@cli.command()
+@click.option(
+    "--version", help="Version to tag (uses current version if not specified)"
+)
+def tag(version: str | None = None) -> None:
+    """Create and push a git tag for the current version."""
+    if not version:
+        main_version, _, _ = get_current_versions()
+        version = main_version
+
+    create_and_push_tag(version)
+
+
+if __name__ == "__main__":
+    cli()

tests/beta/agent_data/test_agent_data_client.py

@@ -48,8 +48,8 @@ class TestData(BaseModel):
 # Skip all tests if API key is not set
 @pytest.mark.asyncio
 @pytest.mark.skipif(
-    not LLAMA_CLOUD_API_KEY or not LLAMA_DEPLOY_DEPLOYMENT_NAME,
-    reason="LLAMA_CLOUD_API_KEY or LLAMA_DEPLOY_DEPLOYMENT_NAME not set",
+    not LLAMA_CLOUD_API_KEY,
+    reason="LLAMA_CLOUD_API_KEY not set",
 )
 async def test_agent_data_crud_operations():
     """Test basic CRUD operations for agent data with automatic cleanup"""
@@ -67,7 +67,7 @@ async def test_agent_data_crud_operations():
     agent_data_client = AsyncAgentDataClient(
         client=client,
         type=TestData,
-        collection_name=f"test-collection-{test_id[:8]}",
+        collection=f"test-collection-{test_id[:8]}",
         agent_url_id=LLAMA_DEPLOY_DEPLOYMENT_NAME,
     )
 
@@ -77,21 +77,21 @@ async def test_agent_data_crud_operations():
     created_item = None
     try:
         # Test CREATE
-        created_item = await agent_data_client.create_agent_data(test_data)
+        created_item = await agent_data_client.create_item(test_data)
         assert created_item.data.name == "test-item"
         assert created_item.data.test_id == test_id
         assert created_item.data.value == 42
         assert created_item.id is not None
 
         # Test READ
-        retrieved_item = await agent_data_client.get_agent_data(created_item.id)
+        retrieved_item = await agent_data_client.get_item(created_item.id)
         assert retrieved_item.id == created_item.id
         assert retrieved_item.data.name == "test-item"
         assert retrieved_item.data.test_id == test_id
         assert retrieved_item.data.value == 42
 
         # Test SEARCH
-        search_results = await agent_data_client.search_agent_data(
+        search_results = await agent_data_client.search(
             filter={"test_id": {"eq": test_id}}, page_size=10, include_total=True
         )
         assert len(search_results.items) == 1
@@ -99,7 +99,7 @@ async def test_agent_data_crud_operations():
         assert search_results.total == 1
 
         # Test AGGREGATE
-        aggregate_results = await agent_data_client.aggregate_agent_data(
+        aggregate_results = await agent_data_client.aggregate(
             group_by=["test_id"], count=True
         )
         assert len(aggregate_results.items) == 1
@@ -108,7 +108,7 @@ async def test_agent_data_crud_operations():
 
         # Test UPDATE
         updated_data = TestData(name="updated-item", test_id=test_id, value=84)
-        updated_item = await agent_data_client.update_agent_data(
+        updated_item = await agent_data_client.update_item(
             created_item.id, updated_data
         )
         assert updated_item.data.name == "updated-item"
@@ -116,7 +116,7 @@ async def test_agent_data_crud_operations():
         assert updated_item.id == created_item.id
 
         # Verify update persisted
-        verified_item = await agent_data_client.get_agent_data(created_item.id)
+        verified_item = await agent_data_client.get_item(created_item.id)
         assert verified_item.data.name == "updated-item"
         assert verified_item.data.value == 84
 
@@ -124,6 +124,6 @@ async def test_agent_data_crud_operations():
         # Clean up test data
         if created_item is not None:
             try:
-                await agent_data_client.delete_agent_data(created_item.id)
+                await agent_data_client.delete_item(created_item.id)
             except Exception as e:
                 print(f"Warning: Failed to cleanup test data {created_item.id}: {e}")

tests/beta/agent_data/test_agent_data_schema.py

@@ -2,14 +2,19 @@ from datetime import datetime
 from typing import Any, Dict
 
 import pytest
+from llama_cloud import ExtractRun, File
 from llama_cloud.types.agent_data import AgentData
 from llama_cloud.types.aggregate_group import AggregateGroup
 from pydantic import BaseModel, ValidationError
 
 from llama_cloud_services.beta.agent_data.schema import (
     ExtractedData,
+    ExtractedFieldMetadata,
+    InvalidExtractionData,
     TypedAgentData,
     TypedAggregateGroup,
+    calculate_overall_confidence,
+    parse_extracted_field_metadata,
 )
 
 
@@ -70,15 +75,22 @@ def test_extracted_data_create_method():
     extracted = ExtractedData.create(person)
     assert extracted.original_data == person
     assert extracted.data == person
-    assert extracted.status == "in_review"
-    assert extracted.confidence == {}
+    assert extracted.status == "pending_review"
+    assert extracted.field_metadata == {}
+    assert extracted.overall_confidence is None
 
-    # Test with custom values
+    # Test with custom values using ExtractedFieldMetadata
+    field_metadata = {
+        "name": ExtractedFieldMetadata(confidence=0.99, page_number=1),
+        "age": ExtractedFieldMetadata(confidence=0.85, page_number=1),
+    }
     extracted_custom = ExtractedData.create(
-        person, status="accepted", confidence={"name": 0.99}
+        person, status="accepted", field_metadata=field_metadata
     )
     assert extracted_custom.status == "accepted"
-    assert extracted_custom.confidence["name"] == 0.99
+    assert extracted_custom.field_metadata["name"].confidence == 0.99
+    assert extracted_custom.field_metadata["age"].confidence == 0.85
+    assert extracted_custom.overall_confidence == pytest.approx((0.99 + 0.85) / 2)
 
 
 def test_extracted_data_with_dict():
@@ -107,3 +119,303 @@ def test_typed_aggregate_group_from_raw():
     assert typed_group.count == 25
     assert typed_group.first_item.name == "Tech Corp"
     assert typed_group.first_item.employees == 500
+
+
+def test_calculate_overall_confidence_simple_flat():
+    """Test calculate_overall_confidence with simple flat dictionary of ExtractedFieldMetadata."""
+    field_metadata = {
+        "name": ExtractedFieldMetadata(confidence=0.9),
+        "age": ExtractedFieldMetadata(confidence=0.8),
+        "email": ExtractedFieldMetadata(confidence=0.95),
+    }
+    result = calculate_overall_confidence(field_metadata)
+    expected = (0.9 + 0.8 + 0.95) / 3
+    assert result == pytest.approx(expected, rel=1e-9)
+
+
+def test_calculate_overall_confidence_nested():
+    """Test calculate_overall_confidence with nested dictionary structure."""
+    field_metadata = {
+        "person": {
+            "name": ExtractedFieldMetadata(confidence=0.9),
+            "age": ExtractedFieldMetadata(confidence=0.8),
+        },
+        "contact": {
+            "email": ExtractedFieldMetadata(confidence=0.95),
+            "phone": ExtractedFieldMetadata(confidence=0.85),
+        },
+        "score": ExtractedFieldMetadata(confidence=0.7),
+    }
+    result = calculate_overall_confidence(field_metadata)
+    # Should average all leaf values: (0.9 + 0.8 + 0.95 + 0.85 + 0.7) / 5
+    expected = (0.9 + 0.8 + 0.95 + 0.85 + 0.7) / 5
+    assert result == pytest.approx(expected, rel=1e-9)
+
+
+def test_calculate_overall_confidence_with_lists():
+    """Test calculate_overall_confidence with lists of ExtractedFieldMetadata and nested structures."""
+    field_metadata = {
+        "scores": [
+            ExtractedFieldMetadata(confidence=0.9),
+            ExtractedFieldMetadata(confidence=0.8),
+            ExtractedFieldMetadata(confidence=0.95),
+        ],
+        "nested_data": [
+            {
+                "field1": ExtractedFieldMetadata(confidence=0.7),
+                "field2": ExtractedFieldMetadata(confidence=0.6),
+            },
+            {
+                "field1": ExtractedFieldMetadata(confidence=0.8),
+                "field2": ExtractedFieldMetadata(confidence=0.9),
+            },
+        ],
+        "single_value": ExtractedFieldMetadata(confidence=0.85),
+    }
+    result = calculate_overall_confidence(field_metadata)
+    # Should count: [0.9, 0.8, 0.95] + [0.7, 0.6, 0.8, 0.9] + [0.85] = 8 values
+    expected = (0.9 + 0.8 + 0.95 + 0.7 + 0.6 + 0.8 + 0.9 + 0.85) / 8
+    assert result == pytest.approx(expected, rel=1e-9)
+
+
+def test_calculate_overall_confidence_invalid_types():
+    """Test calculate_overall_confidence with invalid/mixed types alongside valid ExtractedFieldMetadata."""
+    field_metadata = {
+        "valid_metadata": ExtractedFieldMetadata(confidence=0.8),
+        "valid_metadata_no_confidence": ExtractedFieldMetadata(),  # No confidence
+        "valid_list": [
+            ExtractedFieldMetadata(confidence=0.5),
+            ExtractedFieldMetadata(confidence=0.6),
+        ],
+        "invalid_string": "not_a_number",
+        "invalid_list_mixed": [
+            ExtractedFieldMetadata(confidence=0.7),
+            "invalid",
+            ExtractedFieldMetadata(confidence=0.8),
+        ],
+        "invalid_none": None,
+        "random_dict": {"a": 1, "b": 2},
+    }
+    result = calculate_overall_confidence(field_metadata)
+    expected = (0.8 + 0.5 + 0.6 + 0.7 + 0.8) / 5
+    assert result == pytest.approx(expected, rel=1e-9)
+
+
+def test_calculate_overall_confidence_empty():
+    """Test calculate_overall_confidence with empty inputs."""
+    # Empty dict
+    assert calculate_overall_confidence({}) is None
+
+    # Empty list
+    assert calculate_overall_confidence([]) is None
+
+    # Dict with only invalid values
+    field_metadata_invalid = {"invalid": "not_a_number", "also_invalid": None}
+    assert calculate_overall_confidence(field_metadata_invalid) is None
+
+    # List with only invalid values
+    field_metadata_invalid_list = ["invalid", None, {}]
+    assert calculate_overall_confidence(field_metadata_invalid_list) is None
+
+    # Dict with ExtractedFieldMetadata but no confidence values
+    field_metadata_no_confidence = {
+        "field1": ExtractedFieldMetadata(),
+        "field2": ExtractedFieldMetadata(),
+    }
+    assert calculate_overall_confidence(field_metadata_no_confidence) is None
+
+
+def test_parse_extracted_field_metadata():
+    """Test parse_extracted_field_metadata with legacy citation format."""
+    raw_metadata = {
+        "name": {
+            "confidence": 0.95,
+            "citations": [{"page_number": 1, "matching_text": "John Smith"}],
+        },
+        "age": {
+            "confidence": 0.87,
+            "citations": [
+                {
+                    "page_number": 2.0,  # Float page number
+                    "matching_text": "25 years old",
+                }
+            ],
+        },
+        "email": {
+            "confidence": 0.92,
+            "citations": [],  # Empty citations
+        },
+    }
+
+    result = parse_extracted_field_metadata(raw_metadata)
+    result2 = parse_extracted_field_metadata(result)
+    assert result2 == result
+
+    # name should have parsed citation data
+    assert isinstance(result["name"], ExtractedFieldMetadata)
+    assert result["name"].confidence == 0.95
+    assert result["name"].page_number == 1
+    assert result["name"].matching_text == "John Smith"
+
+    # age should handle float page number
+    assert isinstance(result["age"], ExtractedFieldMetadata)
+    assert result["age"].confidence == 0.87
+    assert result["age"].page_number == 2  # Should be converted to int
+    assert result["age"].matching_text == "25 years old"
+
+    # email should handle empty citations
+    assert isinstance(result["email"], ExtractedFieldMetadata)
+    assert result["email"].confidence == 0.92
+
+
+def create_file(
+    id: str = "file-456",
+    name: str = "resume.pdf",
+    external_file_id: str = "external-file-id",
+    project_id: str = "project-123",
+) -> File:
+    return File.parse_obj(
+        {
+            "id": id,
+            "name": name,
+            "external_file_id": external_file_id,
+            "project_id": project_id,
+        }
+    )
+
+
+def create_extract_run(
+    id: str = "extract-123",
+    data: Dict[str, Any] = {"name": "John Doe", "age": 30, "email": "john@example.com"},
+    extraction_metadata: Dict[str, Any] = {
+        "name": {
+            "confidence": 0.95,
+            "citations": [{"page_number": 1, "matching_text": "John Doe"}],
+        },
+        "age": {"confidence": 0.87},
+        "email": {
+            "confidence": 0.92,
+            "citations": [{"page_number": 1, "matching_text": "john@example.com"}],
+        },
+    },
+    data_schema: Dict[str, Any] = {},
+    file: File = create_file(),
+) -> ExtractRun:
+    return ExtractRun.parse_obj(
+        {
+            "id": id,
+            "data": data,
+            "extraction_metadata": {
+                "field_metadata": extraction_metadata,
+            },
+            "data_schema": data_schema,
+            "file": file,
+            "extraction_agent_id": "extraction-agent-123",
+            "config": {},
+            "status": "SUCCESS",
+            "from_ui": False,
+        }
+    )
+
+
+def test_extracted_data_from_extraction_result_success():
+    """Test ExtractedData.from_extraction_result with valid data."""
+    # Create mock ExtractRun with valid data
+    extract_run = create_extract_run(
+        file=create_file(id="file-456", name="resume.pdf"),
+    )
+
+    # Create with file object
+    extracted: ExtractedData[Person] = ExtractedData.from_extraction_result(
+        extract_run,
+        Person,
+        file_hash="abc123",
+        status="accepted",
+    )
+
+    # Verify the extracted data
+    assert isinstance(extracted.data, Person)
+    assert extracted.data.name == "John Doe"
+    assert extracted.data.age == 30
+    assert extracted.data.email == "john@example.com"
+    assert extracted.status == "accepted"
+    assert extracted.file_id == "file-456"
+    assert extracted.file_name == "resume.pdf"
+    assert extracted.file_hash == "abc123"
+
+    # Verify field metadata was parsed
+    assert isinstance(extracted.field_metadata["name"], ExtractedFieldMetadata)
+    assert extracted.field_metadata["name"].confidence == 0.95
+    assert extracted.field_metadata["name"].page_number == 1
+    assert extracted.field_metadata["name"].matching_text == "John Doe"
+
+    # Verify overall confidence was calculated
+    expected_confidence = (0.95 + 0.87 + 0.92) / 3
+    assert extracted.overall_confidence == pytest.approx(expected_confidence)
+
+
+def test_extracted_data_from_extraction_result_with_file_params():
+    """Test ExtractedData.from_extraction_result with explicit file parameters."""
+    extract_run = create_extract_run(
+        file=create_file(id="original-file", name="original.pdf"),
+    )
+
+    # Override file parameters
+    extracted: ExtractedData[Person] = ExtractedData.from_extraction_result(
+        extract_run,
+        Person,
+        file_id="custom-file-id",  # Should override file.id
+        file_name="custom-name.pdf",  # Should override file.name
+        file_hash="custom-hash",
+        metadata={"source": "api_test"},
+    )
+
+    assert extracted.file_id == "custom-file-id"  # Overridden
+    assert extracted.file_name == "custom-name.pdf"  # Overridden
+    assert extracted.file_hash == "custom-hash"
+    assert extracted.metadata["source"] == "api_test"
+
+
+def test_extracted_data_from_extraction_result_invalid_data():
+    """Test ExtractedData.from_extraction_result with invalid data raises custom exception."""
+    # Create ExtractRun with data that doesn't match Person schema
+    extract_run = create_extract_run(
+        data={
+            "name": "Valid Name",
+            "age": "not_a_number",
+            "missing_email": True,
+        },  # Invalid age, missing email
+        extraction_metadata={
+            "name": {"confidence": 0.9},
+        },
+        data_schema={},
+        file=create_file(id="error-file", name="bad_data.pdf"),
+    )
+
+    # Should raise InvalidExtractionData with ExtractedData containing error info
+    with pytest.raises(InvalidExtractionData) as exc_info:
+        ExtractedData.from_extraction_result(
+            extract_run, Person, metadata={"test": "metadata"}
+        )
+
+    # Verify the exception contains the invalid ExtractedData
+    invalid_data = exc_info.value.invalid_item
+    assert isinstance(invalid_data, ExtractedData)
+    assert invalid_data.status == "error"
+    assert invalid_data.data == {
+        "name": "Valid Name",
+        "age": "not_a_number",
+        "missing_email": True,
+    }
+    assert invalid_data.file_id == "error-file"
+    assert invalid_data.file_name == "bad_data.pdf"
+
+    # Check error metadata was added
+    assert "extraction_error" in invalid_data.metadata
+    assert "test" in invalid_data.metadata  # Original metadata preserved
+    assert "2 validation errors" in invalid_data.metadata["extraction_error"]
+
+    # Verify field metadata was still parsed (before validation failed)
+    assert isinstance(invalid_data.field_metadata["name"], ExtractedFieldMetadata)
+    assert invalid_data.field_metadata["name"].confidence == 0.9
+    assert invalid_data.overall_confidence == 0.9

tests/extract/test_extract_e2e.py

@@ -8,6 +8,7 @@ import uuid
 from llama_cloud.types import ExtractConfig, ExtractMode
 from deepdiff import DeepDiff
 from tests.extract.util import json_subset_match_score, load_test_dotenv
+from .conftest import register_agent_for_cleanup
 
 load_test_dotenv()
 
@@ -115,13 +116,11 @@ def extraction_agent(test_case: TestCase, extractor: LlamaExtract):
 
     # Create new agent
     agent = extractor.create_agent(agent_name, schema, config=test_case.config)
-    yield agent
 
-    # Cleanup after test
-    try:
-        extractor.delete_agent(agent.id)
-    except Exception as e:
-        print(f"Warning: Failed to delete agent {agent.id}: {str(e)}")
+    # Register agent for cleanup at the end of the test session
+    register_agent_for_cleanup(agent.id)
+
+    yield agent
 
 
 @pytest.mark.skipif(
@@ -130,7 +129,7 @@ def extraction_agent(test_case: TestCase, extractor: LlamaExtract):
 )
 @pytest.mark.parametrize("test_case", get_test_cases(), ids=lambda x: x.name)
 def test_extraction(test_case: TestCase, extraction_agent: ExtractionAgent) -> None:
-    result = extraction_agent.extract(test_case.input_file).data
+    result = extraction_agent.extract(test_case.input_file).data  # type: ignore
     with open(test_case.expected_output, "r") as f:
         expected = json.load(f)
     # TODO: fix the saas_slide test

tests/parse/test_llama_parse.py

@@ -193,3 +193,12 @@ async def test_multiple_page_markdown(
     result = await markdown_parser.aload_data(filepath)
     assert len(result) == expected
     assert all(len(doc.text) > 0 for doc in result)
+
+
+@pytest.mark.asyncio
+async def test_get_result(markdown_parser: LlamaParse) -> None:
+    filepath = "tests/test_files/attention_is_all_you_need.pdf"
+    expected = await markdown_parser.aparse(filepath)
+    result = await markdown_parser.aget_result(expected.job_id)
+    assert result.job_id == expected.job_id
+    assert len(result.pages) == len(expected.pages)

tests/parse/test_llama_parse_result.py

@@ -83,6 +83,12 @@ async def test_basic_parse_result(file_path: str, partition_pages: Optional[int]
     assert image_documents[0].image is not None
     assert len(image_documents[0].resolve_image().getvalue()) > 0
 
+    assert len(await result.aget_text()) > 0
+    assert len(await result.aget_markdown()) > 0
+    json = await result.aget_json()
+    assert json.get("job_metadata")
+    assert len(json.get("pages", [])) == len(result.pages)
+
 
 @pytest.mark.asyncio
 @pytest.mark.skip(

tests/parse/test_utils.py

@@ -1,7 +1,30 @@
 import pytest
 
+from pathlib import Path
+from llama_cloud_services.parse.utils import (
+    expand_target_pages,
+    partition_pages,
+    extract_tables_from_json_results,
+)
+from typing import List
 
-from llama_cloud_services.parse.utils import expand_target_pages, partition_pages
+
+@pytest.fixture()
+def pseudo_json_results() -> List[dict]:
+    return [
+        {
+            "pages": [
+                {
+                    "items": [
+                        {
+                            "type": "table",
+                            "csv": "Name,Age,Height (cm)\nAnna,12,140\nBob,22,175\nClaire,33,173\nDenis,44,185\n",
+                        }
+                    ]
+                }
+            ]
+        }
+    ]
 
 
 def test_expand_target_pages() -> None:
@@ -28,3 +51,12 @@ def test_partion_pages() -> None:
     assert result == ["0,2-3", "5,8"]
     result = list(partition_pages(pages, 3, max_pages=10))
     assert result == ["0,2-3", "5,8-9", "10"]
+
+
+def test_table_extraction(pseudo_json_results: List[dict], tmpdir: Path) -> None:
+    tables = extract_tables_from_json_results(pseudo_json_results, tmpdir)
+    assert len(tables) == 1
+    for table in tables:
+        assert Path(table).exists()
+        with open(table) as t:
+            assert t.read() == pseudo_json_results[0]["pages"][0]["items"][0]["csv"]