mirror of
https://github.com/lancedb/lancedb.git
synced 2026-10-31 07:46:51 +00:00
Wyatt Alt
b4cbaf2f67
The Functions page only showed a plain function, so it never said where a class's `__init__` runs. Users loading a large model need to know it is not the client: registration reads the signature and ships the source. This adds a section on class Functions: `__init__` runs once per instance on the worker, then `__call__` per row or batch and `close()` on retirement, state is per instance, and `__init__` parameters are initialization fields set per binding. The example's test asserts that registering the class does not construct it.
23 lines
2.1 KiB
Plaintext
23 lines
2.1 KiB
Plaintext
{/* Auto-generated by scripts/mdx_snippets_gen.py. Do not edit manually. */}
|
|
|
|
export const PyFunctionApply = "from lancedb import col\n\ntable.add_columns({\"doubled\": version(value=col(\"value\"))})\n";
|
|
|
|
export const PyFunctionClassApply = "from lancedb import col\n\napplication = embedder(text=col(\"text\"), model=\"all-mpnet-base-v2\")\n";
|
|
|
|
export const PyFunctionClassDefine = "@udf(pip=[\"sentence-transformers\"])\nclass embed:\n def __init__(self, model: str = \"all-MiniLM-L6-v2\"):\n # Runs on the worker, once per instance: only the worker needs the package.\n from sentence_transformers import SentenceTransformer\n\n self.model = SentenceTransformer(model)\n\n def __call__(self, text: str) -> list[float]:\n return self.model.encode(text).tolist()\n\n def close(self):\n del self.model\n";
|
|
|
|
export const PyFunctionConnect = "import os\n\nimport lancedb\n\ndb = lancedb.connect(\n uri=os.environ[\"LANCEDB_URI\"], # db://your-database\n api_key=os.environ[\"LANCEDB_API_KEY\"],\n region=os.environ.get(\"LANCEDB_REGION\", \"us-east-1\"),\n host_override=os.environ[\"LANCEDB_HOST_OVERRIDE\"],\n)\n";
|
|
|
|
export const PyFunctionCreateTable = "import pyarrow as pa\n\nschema = pa.schema([pa.field(\"value\", pa.float64(), nullable=False)])\ntable = db.create_table(\n \"function_demo\",\n [{\"value\": 1.0}, {\"value\": 2.0}, {\"value\": 3.0}],\n schema=schema,\n)\n";
|
|
|
|
export const PyFunctionDefine = "from lancedb import udf\n\n\n@udf\ndef double(value: float) -> float:\n return value * 2\n";
|
|
|
|
export const PyFunctionInspect = "rows = table.search().select([\"value\", \"doubled\"]).to_list()\nprint(sorted((row[\"value\"], row[\"doubled\"]) for row in rows))\n# [(1.0, 2.0), (2.0, 4.0), (3.0, 6.0)]\n";
|
|
|
|
export const PyFunctionLocalCall = "print(double(1.5))\n# 3.0\n";
|
|
|
|
export const PyFunctionRefresh = "refresh = table.refresh_column_async(\"doubled\")\nresult = refresh.wait()\nprint(result.rows_assigned)\n# 3\n";
|
|
|
|
export const PyFunctionRegister = "job = db.create_function_async(double)\nversion = job.wait()\n";
|
|
|