104 使用Cohere Rerank优化LlamaIndex查询

使用Cohere Rerank优化LlamaIndex查询

欢迎来到这篇技术博客！今天我们将探讨如何使用Cohere Rerank优化LlamaIndex的查询结果。如果你在Colab上打开这个Notebook，你可能需要安装LlamaIndex。

%pip install llama-index > /dev/null
%pip install llama-index-postprocessor-cohere-rerank > /dev/null

下载数据

首先，我们需要下载一些示例数据。这里我们使用Paul Graham的散文作为示例。

!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'

加载文档并构建索引

接下来，我们加载文档并构建向量索引。

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

# 加载文档
documents = SimpleDirectoryReader("./data/paul_graham/").load_data()

# 构建索引
index = VectorStoreIndex.from_documents(documents=documents)

使用Cohere Rerank优化查询结果

我们将使用Cohere Rerank来优化查询结果。首先，我们需要设置Cohere API密钥。

import os
from llama_index.postprocessor.cohere_rerank import CohereRerank

api_key = os.environ["COHERE_API_KEY"]
cohere_rerank = CohereRerank(api_key=api_key, top_n=2)

然后，我们创建一个查询引擎，并使用Cohere Rerank作为节点后处理器。

query_engine = index.as_query_engine(
    similarity_top_k=10,
    node_postprocessors=[cohere_rerank],
)

response = query_engine.query(
    "What did Sam Altman do in this essay?",
)

from llama_index.core.response.pprint_utils import pprint_response
pprint_response(response, show_source=True)

直接检索最相似的节点

作为对比，我们也可以直接检索最相似的节点，而不使用Cohere Rerank。

query_engine = index.as_query_engine(
    similarity_top_k=2,
)

response = query_engine.query(
    "What did Sam Altman do in this essay?",
)

pprint_response(response, show_source=True)

结果对比

使用Cohere Rerank优化后的查询结果更加相关和准确。以下是优化后的查询结果：

Final Response: Sam Altman was asked if he wanted to be the president
of Y Combinator. Initially, he declined as he wanted to start a
startup focused on making nuclear reactors. However, after persistent
persuasion, he eventually agreed to become the president of Y
Combinator starting with the winter 2014 batch.
______________________________________________________________________
Source Node 1/2
Node ID: 7ecf4eb2-215d-45e4-ba08-44d9219c7fa6
Similarity: 0.93033177
Text: When I was dealing with some urgent problem during YC, there was
about a 60% chance it had to do with HN, and a 40% chance it had do
with everything else combined. [17]  As well as HN, I wrote all of
YC's internal software in Arc. But while I continued to work a good
deal in Arc, I gradually stopped working on Arc, partly because I
didn't have t...
______________________________________________________________________
Source Node 2/2
Node ID: 88be17e9-e0a0-49e1-9ff8-f2b7aa7493ed
Similarity: 0.86269903
Text: Up till that point YC had been controlled by the original LLC we
four had started. But we wanted YC to last for a long time, and to do
that it couldn't be controlled by the founders. So if Sam said yes,
we'd let him reorganize YC. Robert and I would retire, and Jessica and
Trevor would become ordinary partners.  When we asked Sam if he wanted
to...

而直接检索最相似节点的结果可能不太相关，甚至可能出现幻觉（hallucination）。

总结

通过使用Cohere Rerank，我们可以在查询时进一步优化结果的相关性和准确性。这种方法特别适用于需要高精度查询结果的场景。希望这篇博客能帮助你更好地理解和应用Cohere Rerank。

如果你有任何问题或需要进一步的帮助，请随时在评论区留言。感谢阅读！