梯度嵌入¶

Gradient提供了嵌入模型，可以很容易地与LlamaIndex集成。下面是如何在LlamaIndex中使用它的示例。

In [ ]:

%pip install llama-index-llms-gradient
%pip install llama-index-embeddings-gradient

%pip install llama-index-llms-gradient %pip install llama-index-embeddings-gradient

In [ ]:

# 安装所需的包

%pip install llama-index --quiet
%pip install gradientai --quiet

# 安装所需的包 %pip install llama-index --quiet %pip install gradientai --quiet

Gradient需要访问令牌和工作空间ID进行授权。它们可以从以下位置获取：

• Gradient UI，或
• Gradient CLI 使用 gradient env 命令。

In [ ]:

import os

os.environ["GRADIENT_ACCESS_TOKEN"] = "{GRADIENT_ACCESS_TOKEN}"
os.environ["GRADIENT_WORKSPACE_ID"] = "{GRADIENT_WORKSPACE_ID}"

import os os.environ["GRADIENT_ACCESS_TOKEN"] = "{GRADIENT_ACCESS_TOKEN}" os.environ["GRADIENT_WORKSPACE_ID"] = "{GRADIENT_WORKSPACE_ID}"

In [ ]:

from llama_index.llms.gradient import GradientBaseModelLLM

# 注意：我们在这里使用一个基本模型，您也可以插入您微调过的模型。
llm = GradientBaseModelLLM(
    base_model_slug="llama2-7b-chat",
    max_tokens=400,
)

from llama_index.llms.gradient import GradientBaseModelLLM # 注意：我们在这里使用一个基本模型，您也可以插入您微调过的模型。 llm = GradientBaseModelLLM( base_model_slug="llama2-7b-chat", max_tokens=400, )

下载数据¶

In [ ]:

!mkdir -p 'data/paul_graham/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

!mkdir -p 'data/paul_graham/' !wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

加载文档¶

In [ ]:

from llama_index.core import SimpleDirectoryReader

documents = SimpleDirectoryReader("./data/paul_graham").load_data()
print(f"Loaded {len(documents)} document(s).")

from llama_index.core import SimpleDirectoryReader documents = SimpleDirectoryReader("./data/paul_graham").load_data() print(f"Loaded {len(documents)} document(s).")

配置梯度嵌入¶

在使用深度学习模型时，梯度嵌入是一种有用的技术，它可以帮助我们理解模型的行为。在这个示例中，我们将学习如何配置梯度嵌入。

In [ ]:

from llama_index.embeddings.gradient import GradientEmbedding
from llama_index.core import Settings

embed_model = GradientEmbedding(
    gradient_access_token=os.environ["GRADIENT_ACCESS_TOKEN"],
    gradient_workspace_id=os.environ["GRADIENT_WORKSPACE_ID"],
    gradient_model_slug="bge-large",
)

Settings.embed_model = embed_model
Settings.llm = llm
Settings.chunk_size = 1024

from llama_index.embeddings.gradient import GradientEmbedding from llama_index.core import Settings embed_model = GradientEmbedding( gradient_access_token=os.environ["GRADIENT_ACCESS_TOKEN"], gradient_workspace_id=os.environ["GRADIENT_WORKSPACE_ID"], gradient_model_slug="bge-large", ) Settings.embed_model = embed_model Settings.llm = llm Settings.chunk_size = 1024

设置查询索引¶

In [ ]:

from llama_index.core import VectorStoreIndex

index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()

from llama_index.core import VectorStoreIndex index = VectorStoreIndex.from_documents(documents) query_engine = index.as_query_engine()

In [ ]:

response = query_engine.query(
    "What did the author do after his time at Y Combinator?"
)
print(response)

response = query_engine.query( "What did the author do after his time at Y Combinator?" ) print(response)