Skip to content

correct return type for encoding #1119

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
dream-tentacle wants to merge 1 commit into
base: master
Choose a base branch
from
Open

correct return type for encoding #1119

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions FlagEmbedding/flag_models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -237,7 +237,7 @@ def __init__(
def encode_queries(self, queries: Union[List[str], str],
batch_size: int = 256,
max_length: int = 512,
convert_to_numpy: bool = True) -> np.ndarray:
convert_to_numpy: bool = True) -> Union[np.ndarray, torch.Tensor]:
'''
This function will be used for retrieval task
if there is a instruction for queries, we will add it to the query text
Expand All @@ -252,7 +252,7 @@ def encode_corpus(self,
corpus: Union[List[str], str],
batch_size: int = 256,
max_length: int = 512,
convert_to_numpy: bool = True) -> np.ndarray:
convert_to_numpy: bool = True) -> Union[np.ndarray, torch.Tensor]:
'''
This function will be used for retrieval task
encode corpus for retrieval task
Expand All @@ -264,7 +264,7 @@ def encode(self,
sentences: Union[List[str], str],
batch_size: int = 256,
max_length: int = 512,
convert_to_numpy: bool = True) -> np.ndarray:
convert_to_numpy: bool = True) -> Union[np.ndarray, torch.Tensor]:
if self.num_gpus > 0:
batch_size = batch_size * self.num_gpus
self.model.eval()
Expand Down Expand Up @@ -341,7 +341,7 @@ def __init__(
def encode_queries(self, queries: Union[List[str], str],
batch_size: int = 256,
max_length: int = 512,
convert_to_numpy: bool = True) -> np.ndarray:
convert_to_numpy: bool = True) -> Union[np.ndarray, torch.Tensor]:
'''
This function will be used for retrieval task
if there is a instruction for queries, we will add it to the query text
Expand All @@ -350,7 +350,7 @@ def encode_queries(self, queries: Union[List[str], str],
if isinstance(queries, str):
input_texts = self.query_instruction_for_retrieval + queries
else:
input_texts = ['{}{}'.format(self.query_instruction_for_retrieval, q) for q in queries]
input_texts = [(self.query_instruction_for_retrieval + q) for q in queries]
else:
input_texts = queries
return self.encode(input_texts, batch_size=batch_size, max_length=max_length, convert_to_numpy=convert_to_numpy)
Expand All @@ -359,7 +359,7 @@ def encode_corpus(self,
corpus: Union[List[str], str],
batch_size: int = 256,
max_length: int = 512,
convert_to_numpy: bool = True) -> np.ndarray:
convert_to_numpy: bool = True) -> Union[np.ndarray, torch.Tensor]:
'''
This function will be used for retrieval task
encode corpus for retrieval task
Expand All @@ -371,7 +371,7 @@ def encode(self,
sentences: Union[List[str], str],
batch_size: int = 256,
max_length: int = 512,
convert_to_numpy: bool = True) -> np.ndarray:
convert_to_numpy: bool = True) -> Union[np.ndarray, torch.Tensor]:
if self.num_gpus > 0:
batch_size = batch_size * self.num_gpus
self.model.eval()
Expand Down
2 changes: 1 addition & 1 deletion Tutorials/1_Embedding/1.2.1_BGE_Series.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -266,7 +266,7 @@
"```\n",
"LLMEmbedder.encode_keys(keys, batch_size=256, max_length=512, task='qa')\n",
"```\n",
"Similarly, *encode_keys()* also calls *_encode()* and automatically add instructions according to given task."
"Similarly, *encode_keys()* also calls *_encode()* and automatically add instructions according to the given task."
]
},
{
Expand Down