j6 ` d dl mZmZmZmZ d dlmZ d dlmZm Z m
Z
dZ dZ dZ
G d dee Zy )
)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 e Zd ZU dZdZeed< eZe ed< dZ
e e ed< e e
Zee ef ed< e e
Zee ef ed< eZe ed < d
Ze ed < d ef fd
Z edd Zdee deee fdZde dee fdZ xZS )IpexLLMBgeEmbeddingsa 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 t | di | ddl}ddlm}m} d| j vrd | j d< | j d d
vr t d | j d d |j | j fd
| j i| j | _ || j | _ || j | _ | j d dk( r.| j j j d | _ d| j v r t | _ yy# t $ r}d}t
d| d| d |d}~ww xY w)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 q/var/www/html/Fitness-lenito-AI-main/venv/lib/python3.12/site-packages/langchain_community/embeddings/ipex_llm.pyr z IpexLLMBgeEmbeddings.__init__C sq
"6" ( S 4,, ,*/D h ' X &n < 1151B1B81L0MQP
@+?? OO
*.*;*;
?C?P?P
$DKK0 $T[[1 X &% / ++**,//6DK DOO #%ED " $A
U
##+* - (z *??
s D) ) E 2EE forbidr )extraprotected_namespacestextsreturnc |D cg c]! }| j |j dd z # }} | j j |fi | j }|j S c c}w )zCompute doc embeddings using a HuggingFace transformer model.
Args:
texts: The list of texts to embed.
Returns:
List of embeddings, one for each text.
)r replacer
encoder tolist)r) r1 t
embeddingss r- embed_documentsz$IpexLLMBgeEmbeddings.embed_documentso sf INN1''!))D#*>>N'T[[''D1C1CD
"" Os &A$textc |j dd } | j j | j |z fi | j }|j S )zCompute query embeddings using a HuggingFace transformer model.
Args:
text: The text to embed.
Returns:
Embeddings for the text.
r4 r5 )r6 r
r7 r r r8 )r) r< embeddings r- embed_queryz IpexLLMBgeEmbeddings.embed_query| sW ||D#&&DKK&& " "T )
-1-?-?
!! ) __name__
__module__ __qualname____doc__r
r __annotations__DEFAULT_BGE_MODELr strr r r
dictr r r DEFAULT_QUERY_BGE_INSTRUCTION_ENr r r r model_configr floatr; r?
__classcell__)r, s @r- r r s !F FC'J' "&L(3-&K#(#>L$sCx.>1$)$$?M4S>?R =s=1 s 4(F (FT H2FL #T#Y #4U 3D #
"
"U
"r@ r N)typingr r r r langchain_core.embeddingsr pydanticr r r
rF rI r( r r r@ r- rP s= - , 0 1 1, ? ! $_ y"9j y"r@