ModelScope 嵌入模型¶

在本笔记本中，我们将展示如何在LlamaIndex中使用ModelScope Embeddings。查看ModelScope官网。

若在Colab中打开此笔记本，您需要安装LlamaIndex 🦙和modelscope。

In [ ]:

!pip install llama-index-embeddings-modelscope

!pip install llama-index-embeddings-modelscope

基本用法¶

In [ ]:

import sys
from llama_index.embeddings.modelscope.base import ModelScopeEmbedding

model = ModelScopeEmbedding(
    model_name="iic/nlp_gte_sentence-embedding_chinese-base",
    model_revision="master",
)

rsp = model.get_query_embedding("Hello, who are you?")
print(rsp)

rsp = model.get_text_embedding("Hello, who are you?")
print(rsp)

import sys from llama_index.embeddings.modelscope.base import ModelScopeEmbedding model = ModelScopeEmbedding( model_name="iic/nlp_gte_sentence-embedding_chinese-base", model_revision="master", ) rsp = model.get_query_embedding("Hello, who are you?") print(rsp) rsp = model.get_text_embedding("Hello, who are you?") print(rsp)

批量生成嵌入向量¶

In [ ]:

from llama_index.embeddings.modelscope.base import ModelScopeEmbedding

model = ModelScopeEmbedding(
    model_name="iic/nlp_gte_sentence-embedding_chinese-base",
    model_revision="master",
)

rsp = model.get_text_embedding_batch(
    ["Hello, who are you?", "I am a student."]
)
print(rsp)

from llama_index.embeddings.modelscope.base import ModelScopeEmbedding model = ModelScopeEmbedding( model_name="iic/nlp_gte_sentence-embedding_chinese-base", model_revision="master", ) rsp = model.get_text_embedding_batch( ["Hello, who are you?", "I am a student."] ) print(rsp)