rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-01-13 23:32:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Qian/query option doc (#615)

Browse Source 
- API documentation improvement for queries (table.search)
- a small bug fix for the remote API on create_table

![image](https://github.com/lancedb/lancedb/assets/1305083/712e9bd3-deb8-4d81-8cd0-d8e98ef68f4e)

![image](https://github.com/lancedb/lancedb/assets/1305083/ba22125a-8c36-4e34-a07f-e39f0136e62c)
This commit is contained in:
QianZhu
2023-10-31 19:50:05 -07:00
committed by GitHub
parent b2b70ea399
commit 7eec2b8f9a
6 changed files with 210 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
python/lancedb/context.py
View File

@@ -84,7 +84,9 @@ def contextualize(raw_df: "pd.DataFrame") -> Contextualizer:
context windows that don't cross document boundaries. In this case, we can
pass ``document_id`` as the group by.
>>> contextualize(data).window(4).stride(2).text_col('token').groupby('document_id').to_pandas()
>>> (contextualize(data)
... .window(4).stride(2).text_col('token').groupby('document_id')
... .to_pandas())
token document_id
0 The quick brown fox 1
2 brown fox jumped over 1
@@ -92,18 +94,24 @@ def contextualize(raw_df: "pd.DataFrame") -> Contextualizer:
6 the lazy dog 1
9 I love sandwiches 2
``min_window_size`` determines the minimum size of the context windows that are generated
This can be used to trim the last few context windows which have size less than
``min_window_size``. By default context windows of size 1 are skipped.
``min_window_size`` determines the minimum size of the context windows
that are generated.This can be used to trim the last few context windows
which have size less than ``min_window_size``.
By default context windows of size 1 are skipped.
>>> contextualize(data).window(6).stride(3).text_col('token').groupby('document_id').to_pandas()
>>> (contextualize(data)
... .window(6).stride(3).text_col('token').groupby('document_id')
... .to_pandas())
token document_id
0 The quick brown fox jumped over 1
3 fox jumped over the lazy dog 1
6 the lazy dog 1
9 I love sandwiches 2
>>> contextualize(data).window(6).stride(3).min_window_size(4).text_col('token').groupby('document_id').to_pandas()
>>> (contextualize(data)
... .window(6).stride(3).min_window_size(4).text_col('token')
... .groupby('document_id')
... .to_pandas())
token document_id
0 The quick brown fox jumped over 1
3 fox jumped over the lazy dog 1
@@ -113,7 +121,9 @@ def contextualize(raw_df: "pd.DataFrame") -> Contextualizer:
class Contextualizer:
"""Create context windows from a DataFrame. See [lancedb.context.contextualize][]."""
"""Create context windows from a DataFrame.
See [lancedb.context.contextualize][].
"""
def __init__(self, raw_df):
self._text_col = None
@@ -183,7 +193,7 @@ class Contextualizer:
deprecated_in="0.3.1",
removed_in="0.4.0",
current_version=__version__,
details="Use the bar function instead",
details="Use to_pandas() instead",
)
def to_df(self) -> "pd.DataFrame":
return self.to_pandas()