github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-08-10 21:35:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[patch]: Update lancedb.py (#21192)

Browse Source 
very minor update in LanceDB integration, 'metric' argument was missing.
This commit is contained in:
Raghav Dixit 2024-05-02 13:06:39 -04:00 committed by GitHub
parent d297d90ad9
commit 7d451d0041
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 28 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
libs/community/langchain_community/vectorstores/lancedb.py
View File

@ -151,10 +151,30 @@ class LanceDB(VectorStore):
self._connection.create_table(self._table_name, data=docs)
return ids
def get_table(self, name: Optional[str] = None) -> Any:
def get_table(
self, name: Optional[str] = None, set_default: Optional[bool] = False
) -> Any:
"""
Fetches a table object from the database.
Args:
name (str, optional): The name of the table to fetch. Defaults to None
and fetches current table object.
set_default (bool, optional): Sets fetched table as the default table.
Defaults to False.
Returns:
Any: The fetched table object.
Raises:
ValueError: If the specified table is not found in the database.
"""
if name is not None:
try:
self._connection.open_table(name)
if set_default:
self._table_name = name
return self._connection.open_table(name)
except Exception:
raise ValueError(f"Table {name} not found in the database")
else:
@ -167,6 +187,7 @@ class LanceDB(VectorStore):
num_partitions: Optional[int] = 256,
num_sub_vectors: Optional[int] = 96,
index_cache_size: Optional[int] = None,
metric: Optional[str] = "L2",
) -> None:
"""
Create a scalar(for non-vector cols) or a vector index on a table.
@ -181,15 +202,18 @@ class LanceDB(VectorStore):
Returns:
None
"""
tbl = self.get_table()
if vector_col:
self._connection.create_index(
tbl.create_index(
metric=metric,
vector_column_name=vector_col,
num_partitions=num_partitions,
num_sub_vectors=num_sub_vectors,
index_cache_size=index_cache_size,
)
elif col_name:
self._connection.create_scalar_index(col_name)
tbl.create_scalar_index(col_name)
else:
raise ValueError("Provide either vector_col or col_name")