feat: expose storage options in LanceDB (#1204)

Exposes `storage_options` in LanceDB. This is provided for Python async,
Node `lancedb`, and Node `vectordb` (and Rust of course). Python
synchronous is omitted because it's not compatible with the PyArrow
filesystems we use there currently. In the future, we will move the sync
API to wrap the async one, and then it will get support for
`storage_options`.

1. Fixes #1168
2. Closes #1165
3. Closes #1082
4. Closes #439
5. Closes #897
6. Closes #642
7. Closes #281
8. Closes #114
9. Closes #990
10. Deprecating `awsCredentials` and `awsRegion`. Users are encouraged
to use `storageOptions` instead.
This commit is contained in:
Will Jones
2024-04-10 10:12:04 -07:00
committed by GitHub
parent 25dea4e859
commit 1d23af213b
31 changed files with 3128 additions and 262 deletions
+14 -1
View File
@@ -1,5 +1,5 @@
import glob
from typing import Iterator
from typing import Iterator, List
from pathlib import Path
glob_string = "../src/**/*.md"
@@ -50,11 +50,24 @@ def yield_lines(lines: Iterator[str], prefix: str, suffix: str):
yield line[strip_length:]
def wrap_async(lines: List[str]) -> List[str]:
# Indent all the lines
lines = [" " + line for line in lines]
# Put all lines in `async def main():`
lines = ["async def main():\n"] + lines
# Put `import asyncio\n asyncio.run(main())` at the end
lines = lines + ["\n", "import asyncio\n", "asyncio.run(main())\n"]
return lines
for file in filter(lambda file: file not in excluded_files, files):
with open(file, "r") as f:
lines = list(yield_lines(iter(f), "```", "```"))
if len(lines) > 0:
if any("await" in line for line in lines):
lines = wrap_async(lines)
print(lines)
out_path = (
Path(python_folder)