Together AI 嵌入模型¶

本笔记本演示如何使用 Together AI 进行嵌入操作。Together AI 提供多种最先进的嵌入模型访问权限。

访问 https://together.ai 并注册获取 API 密钥。

安装¶

如果您在 Colab 上打开此 Notebook，可能需要安装 LlamaIndex 🦙。

In [ ]:

%pip install llama-index-embeddings-together

%pip install llama-index-embeddings-together

In [ ]:

!pip install llama-index

!pip install llama-index

In [ ]:

# You can set the API key in the embeddings or env
# import os
# os.environ["TOEGETHER_API_KEY"] = "your-api-key"

from llama_index.embeddings.together import TogetherEmbedding

embed_model = TogetherEmbedding(
    model_name="togethercomputer/m2-bert-80M-8k-retrieval", api_key="..."
)

# You can set the API key in the embeddings or env # import os # os.environ["TOEGETHER_API_KEY"] = "your-api-key" from llama_index.embeddings.together import TogetherEmbedding embed_model = TogetherEmbedding( model_name="togethercomputer/m2-bert-80M-8k-retrieval", api_key="..." )

获取嵌入向量¶

In [ ]:

embeddings = embed_model.get_text_embedding("hello world")

embeddings = embed_model.get_text_embedding("hello world")

In [ ]:

print(len(embeddings))

print(len(embeddings))

768

In [ ]:

print(embeddings[:5])

print(embeddings[:5])

[-0.11657876, -0.012690996, 0.24342081, 0.32781482, 0.022501636]