mirror of
https://github.com/lancedb/lancedb.git
synced 2026-10-15 16:22:27 +00:00
Jack Ye
b21fb2a4dc
The pages describing this code lived in lancedb/docs, a repository with ten stars that neither contributing guide mentioned. A user who hit a wrong page while reading the source had to find a separate, near-invisible repository to fix it. These 102 pages now sit beside the code, and a documentation fix is a pull request in the repository the reader already had open. `docs/web` is a complete Mintlify site: `cd docs/web && mint dev` serves it with no other checkout. Enterprise pages stay private and are merged in when the published site is assembled, so links into them do not resolve here — every open-source page does. `docs/web-tests` holds the tests the code examples are extracted from. They ran against a published wheel before; here they can run against this repository's own SDK, so an example that stops compiling fails the pull request that broke it rather than being noticed later. Both directories sit beside `docs/src` and are invisible to it: mkdocs reads `docs_dir: src`, so the SDK reference builds and deploys exactly as before.
8 lines
2.0 KiB
Plaintext
8 lines
2.0 KiB
Plaintext
{/* Auto-generated by scripts/mdx_snippets_gen.py. Do not edit manually. */}
|
|
|
|
export const PyCamelotBatches = "import json\nfrom collections.abc import Iterator\nfrom pathlib import Path\n\n\ndef validated_batches(\n input_path: Path, batch_size: int\n) -> Iterator[list[dict]]:\n raw_records = json.loads(input_path.read_text())\n asset_root = input_path.parent.parent\n batch: list[dict] = []\n\n for raw in raw_records:\n payload = dict(raw)\n image_path = asset_root / payload.pop(\"img\")\n payload[\"image_filename\"] = image_path.name\n payload[\"image\"] = image_path.read_bytes()\n\n character = Character.model_validate(payload)\n batch.append(character.model_dump(mode=\"python\"))\n\n if len(batch) == batch_size:\n yield batch\n batch = []\n\n if batch:\n yield batch\n";
|
|
|
|
export const PyCamelotOssIngestion = "import lancedb\n\n\ndef ingest_oss(\n input_path: Path,\n uri: str = \"data/camelot.lancedb\",\n table_name: str = \"camelot_multimodal\",\n batch_size: int = 64,\n):\n db = lancedb.connect(uri)\n if table_name in db.list_tables():\n raise ValueError(\n f\"Table {table_name!r} already exists. Choose a fresh table name.\"\n )\n\n table = db.create_table(table_name, schema=Character)\n for batch in validated_batches(input_path, batch_size):\n table.add(batch)\n\n table.optimize()\n return table\n\n\nif __name__ == \"__main__\":\n ingest_oss(Path(\"data/camelot.json\"))\n";
|
|
|
|
export const PyCamelotSchema = "from lancedb.pydantic import LanceModel\nfrom pydantic import ConfigDict\n\n\nclass Stats(LanceModel):\n model_config = ConfigDict(strict=True, extra=\"forbid\")\n\n strength: int\n courage: int\n magic: int\n wisdom: int\n\n\nclass Character(LanceModel):\n model_config = ConfigDict(strict=True, extra=\"forbid\")\n\n id: int\n name: str\n role: str\n description: str\n stats: Stats\n image_filename: str\n image: bytes\n";
|