mirror of
https://github.com/lancedb/lancedb.git
synced 2025-12-25 14:29:56 +00:00
119b928a52
This PR makes incremental changes to the documentation. * Closes #697 * Closes #698 ## Chores - [x] Add dark mode - [x] Fix headers in navbar - [x] Add `extra.css` to customize navbar styles - [x] Customize fonts for prose/code blocks, navbar and admonitions - [x] Inspect all admonition boxes (remove redundant dropdowns) and improve clarity and readability - [x] Ensure that all images in the docs have white background (not transparent) to be viewable in dark mode - [x] Improve code formatting in code blocks to make them consistent with autoformatters (eslint/ruff) - [x] Add bolder weight to h1 headers - [x] Add diagram showing the difference between embedded (OSS) and serverless (Cloud) - [x] Fix [Creating an empty table](https://lancedb.github.io/lancedb/guides/tables/#creating-empty-table) section: right now, the subheaders are not clickable. - [x] In critical data ingestion methods like `table.add` (among others), the type signature often does not match the actual code - [x] Proof-read each documentation section and rewrite as necessary to provide more context, use cases, and explanations so it reads less like reference documentation. This is especially important for CRUD and search sections since those are so central to the user experience. ## Restructure/new content - [x] The section for [Adding data](https://lancedb.github.io/lancedb/guides/tables/#adding-to-a-table) only shows examples for pandas and iterables. We should include pydantic models, arrow tables, etc. - [x] Add conceptual tutorial for IVF-PQ index - [x] Clearly separate vector search, FTS and filtering sections so that these are easier to find - [x] Add docs on refine factor to explain its importance for recall. Closes #716 - [x] Add an FAQ page showing answers to commonly asked questions about LanceDB. Closes #746 - [x] Add simple polars example to the integrations section. Closes #756 and closes #153 - [ ] Add basic docs for the Rust API (more detailed API docs can come later). Closes #781 - [x] Add a section on the various storage options on local vs. cloud (S3, EBS, EFS, local disk, etc.) and the tradeoffs involved. Closes #782 - [x] Revamp filtering docs: add pre-filtering examples and redo headers and update content for SQL filters. Closes #783 and closes #784. - [x] Add docs for data management: compaction, cleaning up old versions and incremental indexing. Closes #785 - [ ] Add a benchmark section that also discusses some best practices. Closes #787 --------- Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com> Co-authored-by: Will Jones <willjones127@gmail.com>
66 lines
1.8 KiB
Python
66 lines
1.8 KiB
Python
import glob
|
|
from typing import Iterator
|
|
from pathlib import Path
|
|
|
|
glob_string = "../src/**/*.md"
|
|
excluded_globs = [
|
|
"../src/fts.md",
|
|
"../src/embedding.md",
|
|
"../src/examples/*.md",
|
|
"../src/integrations/voxel51.md",
|
|
"../src/guides/tables.md",
|
|
"../src/python/duckdb.md",
|
|
"../src/embeddings/*.md",
|
|
"../src/concepts/*.md",
|
|
"../src/ann_indexes.md",
|
|
"../src/basic.md",
|
|
]
|
|
|
|
python_prefix = "py"
|
|
python_file = ".py"
|
|
python_folder = "python"
|
|
|
|
files = glob.glob(glob_string, recursive=True)
|
|
excluded_files = [
|
|
f
|
|
for excluded_glob in excluded_globs
|
|
for f in glob.glob(excluded_glob, recursive=True)
|
|
]
|
|
|
|
|
|
def yield_lines(lines: Iterator[str], prefix: str, suffix: str):
|
|
in_code_block = False
|
|
# Python code has strict indentation
|
|
strip_length = 0
|
|
skip_test = False
|
|
for line in lines:
|
|
if "skip-test" in line:
|
|
skip_test = True
|
|
if line.strip().startswith(prefix + python_prefix):
|
|
in_code_block = True
|
|
strip_length = len(line) - len(line.lstrip())
|
|
elif in_code_block and line.strip().startswith(suffix):
|
|
in_code_block = False
|
|
if not skip_test:
|
|
yield "\n"
|
|
skip_test = False
|
|
elif in_code_block:
|
|
if not skip_test:
|
|
yield line[strip_length:]
|
|
|
|
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:
|
|
print(lines)
|
|
out_path = (
|
|
Path(python_folder)
|
|
/ Path(file).name.strip(".md")
|
|
/ (Path(file).name.strip(".md") + python_file)
|
|
)
|
|
print(out_path)
|
|
out_path.parent.mkdir(exist_ok=True, parents=True)
|
|
with open(out_path, "w") as out:
|
|
out.writelines(lines)
|