andras/great-ai
andras/great-ai
Watch
1
0
Fork
You've already forked great-ai
 0
Code Issues Pull requests 2 Projects Releases 4 Packages 1 Wiki Activity Actions

Rerender
All checks were successful
Publish documentation to great-ai.schmelczer.dev / publish (push) Successful in 1m10s
Details
Check / Lint, format & type checks (push) Successful in 1m55s
Details
Check / Test on Python 3.12 (push) Successful in 3m8s
Details
Check / Test on Python 3.13 (push) Successful in 2m32s
Details
Check / Notebooks on Python 3.12 (push) Successful in 8m49s
Details
Check / Notebooks on Python 3.13 (push) Successful in 7m53s
Details

Browse source
This commit is contained in:
Andras Schmelczer 2026-10-28 22:53:24 +00:00
commit cf61b38b45
11 changed files with 7062 additions and 267 deletions
Download patch file Download diff file Expand all files Collapse all files

108
docs/examples/scibert/data.ipynb
View file

@ -32,9 +32,16 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 1,
"id": "cell-3",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:59.684612Z",
"iopub.status.busy": "2026-10-28T22:47:59.684455Z",
"iopub.status.idle": "2026-10-28T22:47:59.694166Z",
"shell.execute_reply": "2026-10-28T22:47:59.693485Z"
}
},
"outputs": [
{
"name": "stdout",
@ -85,16 +92,35 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 2,
"id": "cell-5",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:59.695771Z",
"iopub.status.busy": "2026-10-28T22:47:59.695589Z",
"iopub.status.idle": "2026-10-28T22:48:00.795320Z",
"shell.execute_reply": "2026-10-28T22:48:00.795003Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFetching cached versions of summary-train-dataset-small\u001b[0m\n",
"\u001b[38;5;39mFetching cached versions of summary-train-dataset-small\u001b[0m\n",
"\u001b[38;5;39mFetching cached versions of summary-train-dataset-small\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFetching cached versions of summary-train-dataset-small\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFetching cached versions of summary-train-dataset-small\u001b[0m\n"
]
}
@ -116,9 +142,16 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 3,
"id": "cell-7",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:00.796420Z",
"iopub.status.busy": "2026-10-28T22:48:00.796263Z",
"iopub.status.idle": "2026-10-28T22:48:00.798035Z",
"shell.execute_reply": "2026-10-28T22:48:00.797684Z"
}
},
"outputs": [],
"source": [
"y1 = [e[0] for e in evaluations.values() if len(e) == 2]\n",
@ -137,9 +170,16 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 4,
"id": "cell-9",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:00.798711Z",
"iopub.status.busy": "2026-10-28T22:48:00.798654Z",
"iopub.status.idle": "2026-10-28T22:48:00.806309Z",
"shell.execute_reply": "2026-10-28T22:48:00.806045Z"
}
},
"outputs": [
{
"name": "stdout",
@ -170,9 +210,16 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 5,
"id": "cell-11",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:00.807045Z",
"iopub.status.busy": "2026-10-28T22:48:00.806983Z",
"iopub.status.idle": "2026-10-28T22:48:00.808468Z",
"shell.execute_reply": "2026-10-28T22:48:00.808132Z"
}
},
"outputs": [],
"source": [
"X = [s for s in evaluations.keys()]\n",
@ -181,9 +228,16 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 6,
"id": "cell-12",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:00.809082Z",
"iopub.status.busy": "2026-10-28T22:48:00.809029Z",
"iopub.status.idle": "2026-10-28T22:48:00.861903Z",
"shell.execute_reply": "2026-10-28T22:48:00.861397Z"
}
},
"outputs": [
{
"data": {
@ -191,7 +245,7 @@
"array([0.41666667, 0.25 , 0.16666667, 0.41666667, 0.5 ])"
]
},
"execution_count": 7,
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
@ -223,9 +277,16 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 7,
"id": "cell-14",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:00.862626Z",
"iopub.status.busy": "2026-10-28T22:48:00.862564Z",
"iopub.status.idle": "2026-10-28T22:48:00.873305Z",
"shell.execute_reply": "2026-10-28T22:48:00.872879Z"
}
},
"outputs": [
{
"data": {
@ -2150,7 +2211,7 @@
" ('classifier', LinearSVC(random_state=42))])"
]
},
"execution_count": 8,
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
@ -2164,9 +2225,16 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 8,
"id": "cell-15",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:00.874007Z",
"iopub.status.busy": "2026-10-28T22:48:00.873948Z",
"iopub.status.idle": "2026-10-28T22:48:00.920993Z",
"shell.execute_reply": "2026-10-28T22:48:00.920537Z"
}
},
"outputs": [
{
"name": "stdout",

523
docs/examples/scibert/deploy.ipynb
View file

@ -36,9 +36,16 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 1,
"id": "cell-5",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:09.038647Z",
"iopub.status.busy": "2026-10-28T22:48:09.038493Z",
"iopub.status.idle": "2026-10-28T22:48:09.083813Z",
"shell.execute_reply": "2026-10-28T22:48:09.083283Z"
}
},
"outputs": [],
"source": [
"from typing import List\n",
@ -68,16 +75,126 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": 2,
"id": "cell-7",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:09.084713Z",
"iopub.status.busy": "2026-10-28T22:48:09.084644Z",
"iopub.status.idle": "2026-10-28T22:48:11.256390Z",
"shell.execute_reply": "2026-10-28T22:48:11.256030Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFetching cached versions of scibert-highlights\u001b[0m\n",
"\u001b[38;5;39mLatest version of scibert-highlights is 0 (from versions: 0)\u001b[0m\n",
"\u001b[38;5;226mEnvironment variable ENVIRONMENT is not set, defaulting to development mode ‼️\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mCannot find credentials files, defaulting to using ParallelTinyDbDriver\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mThe selected tracing database (ParallelTinyDbDriver) is not recommended for production\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mCannot find credentials files, defaulting to using LargeFileLocal\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mGreatAI (v0.1.11): configured ✅\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 tracing_database: ParallelTinyDbDriver\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 large_file_implementation: LargeFileLocal\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 is_production: False\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 should_log_exception_stack: True\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 prediction_cache_size: 512\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 dashboard_table_size: 50\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mYou still need to check whether you follow all best practices before trusting your deployment.\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226m> Find out more at https://se-ml.github.io/practices\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFetching cached versions of scibert-highlights\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mLatest version of scibert-highlights is 0 (from versions: 0)\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFile scibert-highlights-0 found in cache\u001b[0m\n"
]
}
@ -114,9 +231,16 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 3,
"id": "cell-9",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:11.257418Z",
"iopub.status.busy": "2026-10-28T22:48:11.257269Z",
"iopub.status.idle": "2026-10-28T22:48:11.289789Z",
"shell.execute_reply": "2026-10-28T22:48:11.289400Z"
}
},
"outputs": [],
"source": [
"from great_ai import GreatAI\n",
@ -155,21 +279,28 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": 4,
"id": "cell-11",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:48:11.290551Z",
"iopub.status.busy": "2026-10-28T22:48:11.290495Z",
"iopub.status.idle": "2026-10-28T22:48:11.803477Z",
"shell.execute_reply": "2026-10-28T22:48:11.803126Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"W1028 12:49:11.667000 52910 torch/distributed/elastic/multiprocessing/redirects.py:35] NOTE: Redirects are currently not supported in MacOs.\n"
"W1028 22:48:11.714000 21400 .venv/lib/python3.13/site-packages/torch/distributed/elastic/multiprocessing/redirects.py:35] NOTE: Redirects are currently not supported in MacOs.\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "6ef4b00220304248a94035042cb5fa15",
"model_id": "494840f6abbc4b7aaad2ce762d1e32e8",
"version_major": 2,
"version_minor": 0
},
@ -234,6 +365,374 @@
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.5"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"state": {
"3db5ee6325b74e25903d2d083b4a79ac": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"494840f6abbc4b7aaad2ce762d1e32e8": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_a60ffd19ff674f3087de262cca2823ea",
"IPY_MODEL_5dc69cd57cac4608a2b0d4b4a9a2150c",
"IPY_MODEL_4cd08817c5684abeb1146d2c8e2a4f95"
],
"layout": "IPY_MODEL_d6a5b48086a84a2291dcfc6991c24af1",
"tabbable": null,
"tooltip": null
}
},
"4cd08817c5684abeb1146d2c8e2a4f95": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_bd3bce93f04348f29314e8437dae3c49",
"placeholder": "​",
"style": "IPY_MODEL_94030007cfed4d96b4bb93184555c8d3",
"tabbable": null,
"tooltip": null,
"value": " 25/25 [00:00<00:00, 7301.55it/s]"
}
},
"5dc69cd57cac4608a2b0d4b4a9a2150c": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_6c5077713e5e47dea8ff3f067b042f73",
"max": 25.0,
"min": 0.0,
"orientation": "horizontal",
"style": "IPY_MODEL_c232499e62a342ac8bc98cf0a598d75e",
"tabbable": null,
"tooltip": null,
"value": 25.0
}
},
"6c5077713e5e47dea8ff3f067b042f73": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"94030007cfed4d96b4bb93184555c8d3": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"a60ffd19ff674f3087de262cca2823ea": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_b8cda8463d0d41269292fab71cd1333f",
"placeholder": "​",
"style": "IPY_MODEL_3db5ee6325b74e25903d2d083b4a79ac",
"tabbable": null,
"tooltip": null,
"value": "Loading weights: 100%"
}
},
"b8cda8463d0d41269292fab71cd1333f": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"bd3bce93f04348f29314e8437dae3c49": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"c232499e62a342ac8bc98cf0a598d75e": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"d6a5b48086a84a2291dcfc6991c24af1": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
}
},
"version_major": 2,
"version_minor": 0
}
}
},
"nbformat": 4,

1286
docs/examples/scibert/train.ipynb
View file

File diff suppressed because it is too large Load diff

350
docs/examples/simple-mag/train.ipynb
View file

@ -24,15 +24,21 @@
"\n",
"Use Python 3.12 or 3.13 and install this checkout with `uv pip install --editable '.[notebooks]'`.\n",
"See **Run notebooks locally** in the repository README for the kernel, execution order,\n",
"and full-data options. Run related notebooks from the same working directory\n",
"to share the default `.cache/` model store and `tracing_database.json` database.\n"
"and full-data options. Generated figures are saved in the working directory.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"id": "4a11c71a",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:48.995471Z",
"iopub.status.busy": "2026-10-28T22:47:48.995236Z",
"iopub.status.idle": "2026-10-28T22:47:49.001740Z",
"shell.execute_reply": "2026-10-28T22:47:49.000980Z"
}
},
"outputs": [],
"source": [
"from docs.notebook_support import DATA_DIR, FULL_RUN, mag_lines"
@ -42,14 +48,219 @@
"cell_type": "code",
"execution_count": 2,
"id": "cell-3",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:49.003739Z",
"iopub.status.busy": "2026-10-28T22:47:49.003565Z",
"iopub.status.idle": "2026-10-28T22:47:52.423523Z",
"shell.execute_reply": "2026-10-28T22:47:52.422483Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 700/700 [00:01<00:00, 627.30it/s]\n",
"100%|██████████| 210/210 [00:01<00:00, 196.84it/s]\n"
"\r",
" 0%| | 0/700 [00:00<?, ?it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 0%| | 1/700 [00:00<01:25, 8.16it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 10%|█ | 71/700 [00:00<00:01, 359.30it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 20%|██ | 141/700 [00:00<00:01, 463.46it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 188/700 [00:00<00:01, 464.19it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 34%|███▎ | 235/700 [00:00<00:01, 439.26it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 40%|████ | 281/700 [00:00<00:00, 420.43it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 50%|█████ | 351/700 [00:00<00:00, 474.65it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 60%|██████ | 421/700 [00:00<00:00, 516.09it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 80%|████████ | 561/700 [00:01<00:00, 701.71it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 90%|█████████ | 631/700 [00:01<00:00, 672.36it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 700/700 [00:01<00:00, 588.38it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 0%| | 0/210 [00:00<?, ?it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 0%| | 1/210 [00:00<00:27, 7.68it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 6%|▌ | 12/210 [00:00<00:03, 60.95it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 16%|█▌ | 34/210 [00:00<00:01, 126.17it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 27%|██▋ | 56/210 [00:00<00:00, 157.44it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 37%|███▋ | 78/210 [00:00<00:00, 173.66it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 48%|████▊ | 100/210 [00:00<00:00, 183.94it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 58%|█████▊ | 122/210 [00:00<00:00, 192.70it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 69%|██████▊ | 144/210 [00:00<00:00, 196.32it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 84%|████████▍ | 177/210 [00:00<00:00, 226.84it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 95%|█████████▌| 200/210 [00:01<00:00, 225.06it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 210/210 [00:01<00:00, 190.69it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n"
]
}
],
@ -80,7 +291,14 @@
"cell_type": "code",
"execution_count": 3,
"id": "cell-4",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:52.426201Z",
"iopub.status.busy": "2026-10-28T22:47:52.425143Z",
"iopub.status.idle": "2026-10-28T22:47:52.585612Z",
"shell.execute_reply": "2026-10-28T22:47:52.585283Z"
}
},
"outputs": [
{
"data": {
@ -119,7 +337,14 @@
"cell_type": "code",
"execution_count": 4,
"id": "cell-5",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:52.586376Z",
"iopub.status.busy": "2026-10-28T22:47:52.586316Z",
"iopub.status.idle": "2026-10-28T22:47:52.593735Z",
"shell.execute_reply": "2026-10-28T22:47:52.593353Z"
}
},
"outputs": [],
"source": [
"from sklearn.naive_bayes import MultinomialNB\n",
@ -140,7 +365,14 @@
"cell_type": "code",
"execution_count": 5,
"id": "cell-6",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:52.594535Z",
"iopub.status.busy": "2026-10-28T22:47:52.594460Z",
"iopub.status.idle": "2026-10-28T22:47:53.535898Z",
"shell.execute_reply": "2026-10-28T22:47:53.535480Z"
}
},
"outputs": [
{
"name": "stdout",
@ -190,10 +422,10 @@
" <tbody>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.004115</td>\n",
" <td>0.000260</td>\n",
" <td>0.001606</td>\n",
" <td>0.000055</td>\n",
" <td>0.003533</td>\n",
" <td>0.000225</td>\n",
" <td>0.001693</td>\n",
" <td>0.000093</td>\n",
" <td>1.0</td>\n",
" <td>True</td>\n",
" <td>0.9</td>\n",
@ -208,10 +440,10 @@
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>0.004385</td>\n",
" <td>0.000527</td>\n",
" <td>0.001801</td>\n",
" <td>0.000060</td>\n",
" <td>0.003541</td>\n",
" <td>0.000153</td>\n",
" <td>0.001560</td>\n",
" <td>0.000040</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>0.9</td>\n",
@ -226,10 +458,10 @@
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.009770</td>\n",
" <td>0.003560</td>\n",
" <td>0.002647</td>\n",
" <td>0.000300</td>\n",
" <td>0.008523</td>\n",
" <td>0.003302</td>\n",
" <td>0.002370</td>\n",
" <td>0.000126</td>\n",
" <td>0.5</td>\n",
" <td>True</td>\n",
" <td>0.9</td>\n",
@ -244,10 +476,10 @@
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.005172</td>\n",
" <td>0.000944</td>\n",
" <td>0.001999</td>\n",
" <td>0.000186</td>\n",
" <td>0.003354</td>\n",
" <td>0.000213</td>\n",
" <td>0.001738</td>\n",
" <td>0.000117</td>\n",
" <td>0.5</td>\n",
" <td>False</td>\n",
" <td>0.9</td>\n",
@ -262,10 +494,10 @@
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.004092</td>\n",
" <td>0.001210</td>\n",
" <td>0.002313</td>\n",
" <td>0.000227</td>\n",
" <td>0.003001</td>\n",
" <td>0.000492</td>\n",
" <td>0.001699</td>\n",
" <td>0.000205</td>\n",
" <td>0.5</td>\n",
" <td>True</td>\n",
" <td>0.9</td>\n",
@ -280,10 +512,10 @@
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.003984</td>\n",
" <td>0.000263</td>\n",
" <td>0.001870</td>\n",
" <td>0.000106</td>\n",
" <td>0.002694</td>\n",
" <td>0.000210</td>\n",
" <td>0.001664</td>\n",
" <td>0.000100</td>\n",
" <td>0.5</td>\n",
" <td>False</td>\n",
" <td>0.9</td>\n",
@ -298,10 +530,10 @@
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>0.002690</td>\n",
" <td>0.000284</td>\n",
" <td>0.001573</td>\n",
" <td>0.000183</td>\n",
" <td>0.002624</td>\n",
" <td>0.000035</td>\n",
" <td>0.002088</td>\n",
" <td>0.000339</td>\n",
" <td>1.0</td>\n",
" <td>True</td>\n",
" <td>0.9</td>\n",
@ -316,10 +548,10 @@
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>0.003193</td>\n",
" <td>0.000383</td>\n",
" <td>0.001686</td>\n",
" <td>0.000183</td>\n",
" <td>0.002653</td>\n",
" <td>0.000031</td>\n",
" <td>0.001487</td>\n",
" <td>0.000070</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>0.9</td>\n",
@ -338,14 +570,14 @@
],
"text/plain": [
" mean_fit_time std_fit_time mean_score_time std_score_time \\\n",
"4 0.004115 0.000260 0.001606 0.000055 \n",
"6 0.004385 0.000527 0.001801 0.000060 \n",
"0 0.009770 0.003560 0.002647 0.000300 \n",
"2 0.005172 0.000944 0.001999 0.000186 \n",
"1 0.004092 0.001210 0.002313 0.000227 \n",
"3 0.003984 0.000263 0.001870 0.000106 \n",
"5 0.002690 0.000284 0.001573 0.000183 \n",
"7 0.003193 0.000383 0.001686 0.000183 \n",
"4 0.003533 0.000225 0.001693 0.000093 \n",
"6 0.003541 0.000153 0.001560 0.000040 \n",
"0 0.008523 0.003302 0.002370 0.000126 \n",
"2 0.003354 0.000213 0.001738 0.000117 \n",
"1 0.003001 0.000492 0.001699 0.000205 \n",
"3 0.002694 0.000210 0.001664 0.000100 \n",
"5 0.002624 0.000035 0.002088 0.000339 \n",
"7 0.002653 0.000031 0.001487 0.000070 \n",
"\n",
" param_classifier__alpha param_classifier__fit_prior \\\n",
"4 1.0 True \n",
@ -430,7 +662,14 @@
"cell_type": "code",
"execution_count": 6,
"id": "cell-7",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:53.536912Z",
"iopub.status.busy": "2026-10-28T22:47:53.536844Z",
"iopub.status.idle": "2026-10-28T22:47:53.592995Z",
"shell.execute_reply": "2026-10-28T22:47:53.592634Z"
}
},
"outputs": [
{
"data": {
@ -2714,7 +2953,14 @@
"cell_type": "code",
"execution_count": 7,
"id": "cell-8",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:53.594117Z",
"iopub.status.busy": "2026-10-28T22:47:53.594030Z",
"iopub.status.idle": "2026-10-28T22:47:56.661828Z",
"shell.execute_reply": "2026-10-28T22:47:56.661325Z"
}
},
"outputs": [
{
"name": "stdout",

150
docs/examples/simple/data.ipynb
View file

@ -35,9 +35,16 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"id": "a800dc4d",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:31.221616Z",
"iopub.status.busy": "2026-10-28T22:47:31.221419Z",
"iopub.status.idle": "2026-10-28T22:47:31.227624Z",
"shell.execute_reply": "2026-10-28T22:47:31.226922Z"
}
},
"outputs": [],
"source": [
"from docs.notebook_support import DATA_DIR, FULL_RUN, mag_lines"
@ -47,7 +54,14 @@
"cell_type": "code",
"execution_count": 2,
"id": "cell-3",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:31.229286Z",
"iopub.status.busy": "2026-10-28T22:47:31.229129Z",
"iopub.status.idle": "2026-10-28T22:47:31.231400Z",
"shell.execute_reply": "2026-10-28T22:47:31.230864Z"
}
},
"outputs": [],
"source": [
"PER_LABEL = None if FULL_RUN else 60"
@ -57,7 +71,14 @@
"cell_type": "code",
"execution_count": 3,
"id": "cell-4",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:31.232556Z",
"iopub.status.busy": "2026-10-28T22:47:31.232454Z",
"iopub.status.idle": "2026-10-28T22:47:31.318875Z",
"shell.execute_reply": "2026-10-28T22:47:31.318472Z"
}
},
"outputs": [
{
"name": "stdout",
@ -90,7 +111,14 @@
"cell_type": "code",
"execution_count": 4,
"id": "cell-6",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:31.319705Z",
"iopub.status.busy": "2026-10-28T22:47:31.319649Z",
"iopub.status.idle": "2026-10-28T22:47:32.655835Z",
"shell.execute_reply": "2026-10-28T22:47:32.655342Z"
}
},
"outputs": [],
"source": [
"from great_ai.utilities import clean\n",
@ -106,7 +134,14 @@
"cell_type": "code",
"execution_count": 5,
"id": "cell-7",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:32.656875Z",
"iopub.status.busy": "2026-10-28T22:47:32.656706Z",
"iopub.status.idle": "2026-10-28T22:47:32.658407Z",
"shell.execute_reply": "2026-10-28T22:47:32.657982Z"
}
},
"outputs": [],
"source": [
"X, y = zip(*preprocessed_data) # X is the input, y is the expected output"
@ -129,8 +164,107 @@
"cell_type": "code",
"execution_count": 6,
"id": "cell-9",
"metadata": {},
"outputs": [],
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:32.659171Z",
"iopub.status.busy": "2026-10-28T22:47:32.659099Z",
"iopub.status.idle": "2026-10-28T22:47:32.670028Z",
"shell.execute_reply": "2026-10-28T22:47:32.669511Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mEnvironment variable ENVIRONMENT is not set, defaulting to development mode ‼️\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mCannot find credentials files, defaulting to using ParallelTinyDbDriver\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mThe selected tracing database (ParallelTinyDbDriver) is not recommended for production\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mCannot find credentials files, defaulting to using LargeFileLocal\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mGreatAI (v0.1.11): configured ✅\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 tracing_database: ParallelTinyDbDriver\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 large_file_implementation: LargeFileLocal\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 is_production: False\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 should_log_exception_stack: True\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 prediction_cache_size: 512\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 dashboard_table_size: 50\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mYou still need to check whether you follow all best practices before trusting your deployment.\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226m> Find out more at https://se-ml.github.io/practices\u001b[0m\n"
]
}
],
"source": [
"import random\n",
"from great_ai import add_ground_truth, delete_ground_truth\n",

223
docs/examples/simple/deploy.ipynb
View file

@ -34,17 +34,133 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 1,
"id": "cell-3",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:38.748279Z",
"iopub.status.busy": "2026-10-28T22:47:38.748156Z",
"iopub.status.idle": "2026-10-28T22:47:40.219787Z",
"shell.execute_reply": "2026-10-28T22:47:40.219011Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFetching cached versions of small-domain-prediction\u001b[0m\n",
"\u001b[38;5;39mLatest version of small-domain-prediction is 0 (from versions: 0)\u001b[0m\n",
"\u001b[38;5;39mFile small-domain-prediction-0 found in cache\u001b[0m\n",
"\u001b[38;5;226mEnvironment variable ENVIRONMENT is not set, defaulting to development mode ‼️\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mCannot find credentials files, defaulting to using ParallelTinyDbDriver\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mThe selected tracing database (ParallelTinyDbDriver) is not recommended for production\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mCannot find credentials files, defaulting to using LargeFileLocal\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mGreatAI (v0.1.11): configured ✅\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 tracing_database: ParallelTinyDbDriver\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 large_file_implementation: LargeFileLocal\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 is_production: False\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 should_log_exception_stack: True\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 prediction_cache_size: 512\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 dashboard_table_size: 50\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mYou still need to check whether you follow all best practices before trusting your deployment.\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226m> Find out more at https://se-ml.github.io/practices\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFetching cached versions of small-domain-prediction\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mLatest version of small-domain-prediction is 0 (from versions: 0)\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFile small-domain-prediction-0 found in cache\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFile small-domain-prediction-0 found in cache\u001b[0m\n"
]
}
@ -139,15 +255,95 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 2,
"id": "cell-5",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:40.220877Z",
"iopub.status.busy": "2026-10-28T22:47:40.220772Z",
"iopub.status.idle": "2026-10-28T22:47:41.416823Z",
"shell.execute_reply": "2026-10-28T22:47:41.416155Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 84/84 [00:01<00:00, 81.74it/s] "
"\r",
" 0%| | 0/84 [00:00<?, ?it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 1%| | 1/84 [00:00<00:21, 3.81it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 13%|█▎ | 11/84 [00:00<00:01, 36.69it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 25%|██▌ | 21/84 [00:00<00:01, 54.23it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 37%|███▋ | 31/84 [00:00<00:00, 63.01it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 49%|████▉ | 41/84 [00:00<00:00, 69.13it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 61%|██████ | 51/84 [00:00<00:00, 73.60it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 85%|████████▍ | 71/84 [00:01<00:00, 94.70it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
" 96%|█████████▋| 81/84 [00:01<00:00, 91.80it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"100%|██████████| 84/84 [00:01<00:00, 73.28it/s]"
]
},
{
@ -231,9 +427,16 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 3,
"id": "98ae85f1",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:41.418358Z",
"iopub.status.busy": "2026-10-28T22:47:41.418224Z",
"iopub.status.idle": "2026-10-28T22:47:41.457910Z",
"shell.execute_reply": "2026-10-28T22:47:41.457489Z"
}
},
"outputs": [
{
"name": "stdout",

116
docs/examples/simple/stacked-bars.ipynb
View file

@ -15,10 +15,109 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 1,
"id": "cell-2",
"metadata": {},
"outputs": [],
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:46.557024Z",
"iopub.status.busy": "2026-10-28T22:47:46.556756Z",
"iopub.status.idle": "2026-10-28T22:47:47.930475Z",
"shell.execute_reply": "2026-10-28T22:47:47.930111Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mEnvironment variable ENVIRONMENT is not set, defaulting to development mode ‼️\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mCannot find credentials files, defaulting to using ParallelTinyDbDriver\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mThe selected tracing database (ParallelTinyDbDriver) is not recommended for production\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mCannot find credentials files, defaulting to using LargeFileLocal\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mGreatAI (v0.1.11): configured ✅\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 tracing_database: ParallelTinyDbDriver\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 large_file_implementation: LargeFileLocal\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 is_production: False\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 should_log_exception_stack: True\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 prediction_cache_size: 512\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 dashboard_table_size: 50\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mYou still need to check whether you follow all best practices before trusting your deployment.\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226m> Find out more at https://se-ml.github.io/practices\u001b[0m\n"
]
}
],
"source": [
"from great_ai import query_ground_truth\n",
"\n",
@ -29,9 +128,16 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 2,
"id": "cell-3",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:47.931724Z",
"iopub.status.busy": "2026-10-28T22:47:47.931557Z",
"iopub.status.idle": "2026-10-28T22:47:48.314653Z",
"shell.execute_reply": "2026-10-28T22:47:48.314283Z"
}
},
"outputs": [
{
"data": {

263
docs/examples/simple/train.ipynb
View file

@ -32,9 +32,16 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"id": "d8ae0655",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:33.469672Z",
"iopub.status.busy": "2026-10-28T22:47:33.469359Z",
"iopub.status.idle": "2026-10-28T22:47:33.475106Z",
"shell.execute_reply": "2026-10-28T22:47:33.473998Z"
}
},
"outputs": [],
"source": [
"from docs.notebook_support import FULL_RUN"
@ -44,8 +51,107 @@
"cell_type": "code",
"execution_count": 2,
"id": "cell-3",
"metadata": {},
"outputs": [],
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:33.476993Z",
"iopub.status.busy": "2026-10-28T22:47:33.476853Z",
"iopub.status.idle": "2026-10-28T22:47:34.629711Z",
"shell.execute_reply": "2026-10-28T22:47:34.629235Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mEnvironment variable ENVIRONMENT is not set, defaulting to development mode ‼️\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mCannot find credentials files, defaulting to using ParallelTinyDbDriver\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mThe selected tracing database (ParallelTinyDbDriver) is not recommended for production\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mCannot find credentials files, defaulting to using LargeFileLocal\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mGreatAI (v0.1.11): configured ✅\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 tracing_database: ParallelTinyDbDriver\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 large_file_implementation: LargeFileLocal\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 is_production: False\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 should_log_exception_stack: True\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 prediction_cache_size: 512\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 dashboard_table_size: 50\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mYou still need to check whether you follow all best practices before trusting your deployment.\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226m> Find out more at https://se-ml.github.io/practices\u001b[0m\n"
]
}
],
"source": [
"from great_ai import query_ground_truth\n",
"\n",
@ -61,7 +167,14 @@
"cell_type": "code",
"execution_count": 3,
"id": "cell-4",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:34.630652Z",
"iopub.status.busy": "2026-10-28T22:47:34.630494Z",
"iopub.status.idle": "2026-10-28T22:47:34.675524Z",
"shell.execute_reply": "2026-10-28T22:47:34.675167Z"
}
},
"outputs": [
{
"data": {
@ -107,7 +220,14 @@
"cell_type": "code",
"execution_count": 4,
"id": "cell-6",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:34.676373Z",
"iopub.status.busy": "2026-10-28T22:47:34.676316Z",
"iopub.status.idle": "2026-10-28T22:47:34.683015Z",
"shell.execute_reply": "2026-10-28T22:47:34.682660Z"
}
},
"outputs": [],
"source": [
"from sklearn.naive_bayes import MultinomialNB\n",
@ -128,7 +248,14 @@
"cell_type": "code",
"execution_count": 5,
"id": "cell-7",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:34.683793Z",
"iopub.status.busy": "2026-10-28T22:47:34.683737Z",
"iopub.status.idle": "2026-10-28T22:47:35.666188Z",
"shell.execute_reply": "2026-10-28T22:47:35.665816Z"
}
},
"outputs": [
{
"name": "stdout",
@ -178,10 +305,10 @@
" <tbody>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0.002468</td>\n",
" <td>0.000398</td>\n",
" <td>0.001431</td>\n",
" <td>0.000171</td>\n",
" <td>0.002220</td>\n",
" <td>0.000173</td>\n",
" <td>0.001228</td>\n",
" <td>0.000017</td>\n",
" <td>0.5</td>\n",
" <td>False</td>\n",
" <td>0.9</td>\n",
@ -196,10 +323,10 @@
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>0.002088</td>\n",
" <td>0.000166</td>\n",
" <td>0.001113</td>\n",
" <td>0.000053</td>\n",
" <td>0.002214</td>\n",
" <td>0.000084</td>\n",
" <td>0.001206</td>\n",
" <td>0.000011</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>0.9</td>\n",
@ -214,10 +341,10 @@
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.010547</td>\n",
" <td>0.005423</td>\n",
" <td>0.001438</td>\n",
" <td>0.000207</td>\n",
" <td>0.008167</td>\n",
" <td>0.004108</td>\n",
" <td>0.001306</td>\n",
" <td>0.000036</td>\n",
" <td>0.5</td>\n",
" <td>True</td>\n",
" <td>0.9</td>\n",
@ -232,10 +359,10 @@
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0.002662</td>\n",
" <td>0.000426</td>\n",
" <td>0.001162</td>\n",
" <td>0.000068</td>\n",
" <td>0.002201</td>\n",
" <td>0.000114</td>\n",
" <td>0.001167</td>\n",
" <td>0.000094</td>\n",
" <td>1.0</td>\n",
" <td>True</td>\n",
" <td>0.9</td>\n",
@ -250,10 +377,10 @@
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>0.001664</td>\n",
" <td>0.000016</td>\n",
" <td>0.001354</td>\n",
" <td>0.000081</td>\n",
" <td>0.001697</td>\n",
" <td>0.000039</td>\n",
" <td>0.001383</td>\n",
" <td>0.000154</td>\n",
" <td>0.5</td>\n",
" <td>False</td>\n",
" <td>0.9</td>\n",
@ -268,10 +395,10 @@
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>0.002125</td>\n",
" <td>0.000228</td>\n",
" <td>0.001368</td>\n",
" <td>0.000247</td>\n",
" <td>0.001766</td>\n",
" <td>0.000113</td>\n",
" <td>0.001158</td>\n",
" <td>0.000053</td>\n",
" <td>1.0</td>\n",
" <td>False</td>\n",
" <td>0.9</td>\n",
@ -286,10 +413,10 @@
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.001997</td>\n",
" <td>0.000104</td>\n",
" <td>0.001105</td>\n",
" <td>0.000051</td>\n",
" <td>0.001895</td>\n",
" <td>0.000174</td>\n",
" <td>0.001272</td>\n",
" <td>0.000105</td>\n",
" <td>0.5</td>\n",
" <td>True</td>\n",
" <td>0.9</td>\n",
@ -304,10 +431,10 @@
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>0.002135</td>\n",
" <td>0.000251</td>\n",
" <td>0.001422</td>\n",
" <td>0.000479</td>\n",
" <td>0.001901</td>\n",
" <td>0.000075</td>\n",
" <td>0.001156</td>\n",
" <td>0.000107</td>\n",
" <td>1.0</td>\n",
" <td>True</td>\n",
" <td>0.9</td>\n",
@ -326,14 +453,14 @@
],
"text/plain": [
" mean_fit_time std_fit_time mean_score_time std_score_time \\\n",
"2 0.002468 0.000398 0.001431 0.000171 \n",
"6 0.002088 0.000166 0.001113 0.000053 \n",
"0 0.010547 0.005423 0.001438 0.000207 \n",
"4 0.002662 0.000426 0.001162 0.000068 \n",
"3 0.001664 0.000016 0.001354 0.000081 \n",
"7 0.002125 0.000228 0.001368 0.000247 \n",
"1 0.001997 0.000104 0.001105 0.000051 \n",
"5 0.002135 0.000251 0.001422 0.000479 \n",
"2 0.002220 0.000173 0.001228 0.000017 \n",
"6 0.002214 0.000084 0.001206 0.000011 \n",
"0 0.008167 0.004108 0.001306 0.000036 \n",
"4 0.002201 0.000114 0.001167 0.000094 \n",
"3 0.001697 0.000039 0.001383 0.000154 \n",
"7 0.001766 0.000113 0.001158 0.000053 \n",
"1 0.001895 0.000174 0.001272 0.000105 \n",
"5 0.001901 0.000075 0.001156 0.000107 \n",
"\n",
" param_classifier__alpha param_classifier__fit_prior \\\n",
"2 0.5 False \n",
@ -419,7 +546,14 @@
"cell_type": "code",
"execution_count": 6,
"id": "cell-8",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:35.667075Z",
"iopub.status.busy": "2026-10-28T22:47:35.667011Z",
"iopub.status.idle": "2026-10-28T22:47:35.717496Z",
"shell.execute_reply": "2026-10-28T22:47:35.716936Z"
}
},
"outputs": [
{
"data": {
@ -2711,15 +2845,40 @@
"cell_type": "code",
"execution_count": 7,
"id": "cell-10",
"metadata": {},
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:35.718404Z",
"iopub.status.busy": "2026-10-28T22:47:35.718242Z",
"iopub.status.idle": "2026-10-28T22:47:35.738575Z",
"shell.execute_reply": "2026-10-28T22:47:35.738292Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFetching cached versions of small-domain-prediction\u001b[0m\n",
"\u001b[38;5;39mFetching cached versions of small-domain-prediction\u001b[0m\n",
"\u001b[38;5;39mFetching cached versions of small-domain-prediction\u001b[0m\n",
"\u001b[38;5;39mFetching cached versions of small-domain-prediction\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFetching cached versions of small-domain-prediction\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFetching cached versions of small-domain-prediction\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mModel small-domain-prediction uploaded with version 0\u001b[0m\n"
]
},

1231
docs/surveys/surveys.ipynb
View file

File diff suppressed because one or more lines are too long

192
docs/tutorial/deploy.ipynb
View file

@ -27,9 +27,136 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"execution_count": 1,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:27.038586Z",
"iopub.status.busy": "2026-10-28T22:47:27.038390Z",
"iopub.status.idle": "2026-10-28T22:47:28.222141Z",
"shell.execute_reply": "2026-10-28T22:47:28.221742Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mEnvironment variable ENVIRONMENT is not set, defaulting to development mode ‼️\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mCannot find credentials files, defaulting to using ParallelTinyDbDriver\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mThe selected tracing database (ParallelTinyDbDriver) is not recommended for production\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mCannot find credentials files, defaulting to using LargeFileLocal\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mGreatAI (v0.1.11): configured ✅\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 tracing_database: ParallelTinyDbDriver\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 large_file_implementation: LargeFileLocal\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 is_production: False\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 should_log_exception_stack: True\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 prediction_cache_size: 512\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39m 🔩 dashboard_table_size: 50\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226mYou still need to check whether you follow all best practices before trusting your deployment.\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;226m> Find out more at https://se-ml.github.io/practices\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFetching cached versions of my-domain-predictor\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mLatest version of my-domain-predictor is 0 (from versions: 0)\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFile my-domain-predictor-0 found in cache\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\u001b[38;5;39mFile my-domain-predictor-0 found in cache\u001b[0m\n"
]
}
],
"source": [
"from great_ai import GreatAI, use_model\n",
"from great_ai.utilities import clean\n",
@ -45,9 +172,36 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"execution_count": 2,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:28.223068Z",
"iopub.status.busy": "2026-10-28T22:47:28.222987Z",
"iopub.status.idle": "2026-10-28T22:47:28.234820Z",
"shell.execute_reply": "2026-10-28T22:47:28.234515Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"Trace[str]({'created': '2026-10-28T22:47:28.223376',\n",
" 'exception': None,\n",
" 'feedback': None,\n",
" 'logged_values': { 'arg:sentence:length': 29,\n",
" 'arg:sentence:value': 'Mountains are just big rocks.'},\n",
" 'models': [{'key': 'my-domain-predictor', 'version': 0}],\n",
" 'original_execution_time_ms': 7.958,\n",
" 'output': 'sociology',\n",
" 'tags': ['predict_domain', 'online', 'development'],\n",
" 'trace_id': 'b48540f9-3162-47de-b035-bf11cc4d1581'})"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"predict_domain(\"Mountains are just big rocks.\")"
],
@ -74,9 +228,24 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"execution_count": 3,
"metadata": {
"execution": {
"iopub.execute_input": "2026-10-28T22:47:28.235605Z",
"iopub.status.busy": "2026-10-28T22:47:28.235548Z",
"iopub.status.idle": "2026-10-28T22:47:28.266237Z",
"shell.execute_reply": "2026-10-28T22:47:28.265852Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"sociology\n"
]
}
],
"source": [
"from fastapi.testclient import TestClient\n",
"\n",
@ -114,15 +283,16 @@
"name": "great-ai-local"
},
"language_info": {
"name": "python",
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3"
"pygments_lexer": "ipython3",
"version": "3.13.5"
}
},
"nbformat": 4,

2887
docs/tutorial/train.ipynb
View file

File diff suppressed because one or more lines are too long