Aleph Alpha Embeddings¶
如果您在colab上打开这个笔记本,您可能需要安装LlamaIndex 🦙。
In [ ]:
Copied!
%pip install llama-index-embeddings-alephalpha
%pip install llama-index-embeddings-alephalpha
In [ ]:
Copied!
!pip install llama-index
!pip install llama-index
In [ ]:
Copied!
# 使用您的AA令牌进行初始化
import os
os.environ["AA_TOKEN"] = "your_token_here"
# 使用您的AA令牌进行初始化
import os
os.environ["AA_TOKEN"] = "your_token_here"
使用luminous-base
嵌入。¶
- representation="Document":用于存储在向量数据库中的文本(文档)。
- representation="Query":用于搜索查询,以找到向量数据库中最相关的文档。
- representation="Symmetric":用于聚类、分类、异常检测或可视化任务。
In [ ]:
Copied!
来自llama_index.embeddings.alephalpha的AlephAlphaEmbedding
# 要自定义您的令牌,请执行以下操作
# 否则,它将查找您的环境变量中的AA_TOKEN
# embed_model = AlephAlpha(token="<aa_token>")
# 使用representation='query'
embed_model = AlephAlphaEmbedding(
model="luminous-base",
representation="Query",
)
embeddings = embed_model.get_text_embedding("Hello Aleph Alpha!")
print(len(embeddings))
print(embeddings[:5])
来自llama_index.embeddings.alephalpha的AlephAlphaEmbedding
# 要自定义您的令牌,请执行以下操作
# 否则,它将查找您的环境变量中的AA_TOKEN
# embed_model = AlephAlpha(token="")
# 使用representation='query'
embed_model = AlephAlphaEmbedding(
model="luminous-base",
representation="Query",
)
embeddings = embed_model.get_text_embedding("Hello Aleph Alpha!")
print(len(embeddings))
print(embeddings[:5])
representation_enum: SemanticRepresentation.Query 5120 [0.14257812, 2.59375, 0.33203125, -0.33789062, -0.94140625]
In [ ]:
Copied!
# 使用 representation='Document'
embed_model = AlephAlphaEmbedding(
model="luminous-base",
representation="Document",
)
embeddings = embed_model.get_text_embedding("你好 Aleph Alpha!")
print(len(embeddings))
print(embeddings[:5])
# 使用 representation='Document'
embed_model = AlephAlphaEmbedding(
model="luminous-base",
representation="Document",
)
embeddings = embed_model.get_text_embedding("你好 Aleph Alpha!")
print(len(embeddings))
print(embeddings[:5])
representation_enum: SemanticRepresentation.Document 5120 [0.14257812, 2.59375, 0.33203125, -0.33789062, -0.94140625]