dh6 ` S SK JrJrJrJr S SKJr S SKJrJ r J
r
Sr Sr Sr
" S S\\5 rg )
)AnyDictListOptional)
Embeddings) BaseModel
ConfigDictFieldzBAAI/bge-small-en-v1.5z9Represent this question for searching relevant passages: u9 为这个句子生成表示以用于检索相关文章：c ^ \ rS rSr% SrSr\\S' \r \
\S' Sr \ \
\S' \
" \S9r\\
\4 \S' \
" \S9r\\
\4 \S ' \r\
\S
' S r\
\S ' S
\4U 4S jjr\" SSS9rS\\
S\\\ 4S jrS\
S\\ 4S jrSr U =r $ )IpexLLMBgeEmbeddings aD Wrapper around the BGE embedding model
with IPEX-LLM optimizations on Intel CPUs and GPUs.
To use, you should have the ``ipex-llm``
and ``sentence_transformers`` package installed. Refer to
`here `_
for installation on Intel CPU.
Example on Intel CPU:
.. code-block:: python
from langchain_community.embeddings import IpexLLMBgeEmbeddings
embedding_model = IpexLLMBgeEmbeddings(
model_name="BAAI/bge-large-en-v1.5",
model_kwargs={},
encode_kwargs={"normalize_embeddings": True},
)
Refer to
`here `_
for installation on Intel GPU.
Example on Intel GPU:
.. code-block:: python
from langchain_community.embeddings import IpexLLMBgeEmbeddings
embedding_model = IpexLLMBgeEmbeddings(
model_name="BAAI/bge-large-en-v1.5",
model_kwargs={"device": "xpu"},
encode_kwargs={"normalize_embeddings": True},
)
Nclient
model_name cache_folder)default_factory model_kwargs
encode_kwargsquery_instruction embed_instructionkwargsc > [ TU ] " S0 UD6 SSKnSSKJnJn SU R ; a S U R S' U R S S
; a [ S U R S S 35 eUR " U R 4S
U R 0U R D6U l U" U R 5 U l U" U R 5 U l U R S S:X a. U R R 5 R S5 U l SU R ; a [ U l gg! [ a nSn[
SU SU S35 UeSnAff = f)z$Initialize the sentence_transformer.r N)_optimize_post
_optimize_prezChttps://python.langchain.com/v0.1/docs/integrations/text_embedding/zDCould not import ipex_llm or sentence_transformers. Please refer to zD/ipex_llm/ for install required packages on Intel CPU. And refer to z;/ipex_llm_gpu/ for install required packages on Intel GPU. devicecpu)r xpuzXIpexLLMBgeEmbeddings currently only supports device to be 'cpu' or 'xpu', but you have: .r r z-zh )super__init__sentence_transformers ipex_llm.transformers.convertr r ImportErrorr
ValueErrorSentenceTransformerr r r halfto DEFAULT_QUERY_BGE_INSTRUCTION_ZHr )selfr r" r r excbase_url __class__s _/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/embeddings/ipex_llm.pyr! IpexLLMBgeEmbeddings.__init__C sm
"6" ( S 4,, ,*/D h ' X &n < 1151B1B81L0MQP
,?? OO
*.*;*;
?C?P?P
$DKK0 $T[[1 X &% / ++**,//6DK DOO #%ED " $A
U
##+* - (z *??
s D1 1
E;EEforbidr )extraprotected_namespacestextsreturnc U Vs/ sH! o R UR SS5 - PM# nnU R R " U40 U R D6nUR 5 $ s snf )zCompute doc embeddings using a HuggingFace transformer model.
Args:
texts: The list of texts to embed.
Returns:
List of embeddings, one for each text.
)r replacer encoder tolist)r* r3 t
embeddingss r. embed_documents$IpexLLMBgeEmbeddings.embed_documentso sb INN1''!))D#*>>N[[''D1C1CD
"" Os 'A%textc UR SS5 nU R R " U R U- 40 U R D6nUR 5 $ )zCompute query embeddings using a HuggingFace transformer model.
Args:
text: The text to embed.
Returns:
Embeddings for the text.
r6 r7 )r8 r r9 r r r: )r* r? embeddings r. embed_query IpexLLMBgeEmbeddings.embed_query| sU ||D#&KK&& " "T )
-1-?-?
!! )r r ) __name__
__module__ __qualname____firstlineno____doc__r r __annotations__DEFAULT_BGE_MODELr strr r r
dictr r r DEFAULT_QUERY_BGE_INSTRUCTION_ENr r r! r model_configr floatr= rB __static_attributes__
__classcell__)r- s @r. r r s !F FC'J' "&L(3-&K#(#>L$sCx.>1$)$$?M4S>?R =s=1 s 4(F (FT H2FL #T#Y #4U 3D #
"
"U
"
"rD r N)typingr r r r langchain_core.embeddingsr pydanticr r r
rK rN r) r r rD r. rV s= - , 0 1 1, ? ! $_ y"9j y"rD