DeepInfra¶

通过此集成，您可以使用 DeepInfra 的嵌入模型为文本数据获取嵌入向量。这里是嵌入模型的链接。

首先，您需要在 DeepInfra 网站 上注册并获取 API 令牌。您可以从模型卡片中复制 model_ids，然后开始在代码中使用它们。

安装¶

In [ ]:

!pip install llama-index llama-index-embeddings-deepinfra

!pip install llama-index llama-index-embeddings-deepinfra

初始化¶

In [ ]:

from dotenv import load_dotenv, find_dotenv
from llama_index.embeddings.deepinfra import DeepInfraEmbeddingModel

_ = load_dotenv(find_dotenv())

model = DeepInfraEmbeddingModel(
    model_id="BAAI/bge-large-en-v1.5",  # Use custom model ID
    api_token="YOUR_API_TOKEN",  # Optionally provide token here
    normalize=True,  # Optional normalization
    text_prefix="text: ",  # Optional text prefix
    query_prefix="query: ",  # Optional query prefix
)

from dotenv import load_dotenv, find_dotenv from llama_index.embeddings.deepinfra import DeepInfraEmbeddingModel _ = load_dotenv(find_dotenv()) model = DeepInfraEmbeddingModel( model_id="BAAI/bge-large-en-v1.5", # Use custom model ID api_token="YOUR_API_TOKEN", # Optionally provide token here normalize=True, # Optional normalization text_prefix="text: ", # Optional text prefix query_prefix="query: ", # Optional query prefix )

同步请求¶

获取文本嵌入向量¶

In [ ]:

response = model.get_text_embedding("hello world")
print(response)

response = model.get_text_embedding("hello world") print(response)

批量请求¶

In [ ]:

texts = ["hello world", "goodbye world"]
response_batch = model.get_text_embedding_batch(texts)
print(response_batch)

texts = ["hello world", "goodbye world"] response_batch = model.get_text_embedding_batch(texts) print(response_batch)

查询请求¶

In [ ]:

query_response = model.get_query_embedding("hello world")
print(query_response)

query_response = model.get_query_embedding("hello world") print(query_response)

异步请求¶

获取文本嵌入向量¶

In [ ]:

async def main():
    text = "hello world"
    async_response = await model.aget_text_embedding(text)
    print(async_response)


if __name__ == "__main__":
    import asyncio

    asyncio.run(main())

async def main(): text = "hello world" async_response = await model.aget_text_embedding(text) print(async_response) if __name__ == "__main__": import asyncio asyncio.run(main())

如有任何问题或反馈，请通过 feedback@deepinfra.com 联系我们。