互惠重排融合检索器¶

在本示例中，我们将演示如何合并来自多个查询和多个索引的检索结果。

检索到的节点将按照这篇论文中提出的互惠重排融合算法进行重新排序。该算法提供了一种高效的重排方法，无需过多计算或依赖外部模型。

特别感谢 GitHub 用户 @Raduaschl 提供的示例实现。

In [ ]:

%pip install llama-index-llms-openai
%pip install llama-index-retrievers-bm25

%pip install llama-index-llms-openai %pip install llama-index-retrievers-bm25

In [ ]:

import os
import openai

os.environ["OPENAI_API_KEY"] = "sk-..."
openai.api_key = os.environ["OPENAI_API_KEY"]

import os import openai os.environ["OPENAI_API_KEY"] = "sk-..." openai.api_key = os.environ["OPENAI_API_KEY"]

安装¶

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

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'

--2024-02-12 17:59:58--  https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 2606:50c0:8003::154, 2606:50c0:8001::154, 2606:50c0:8002::154, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|2606:50c0:8003::154|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 75042 (73K) [text/plain]
Saving to: ‘data/paul_graham/paul_graham_essay.txt’

data/paul_graham/pa 100%[===================>]  73.28K   327KB/s    in 0.2s    

2024-02-12 17:59:59 (327 KB/s) - ‘data/paul_graham/paul_graham_essay.txt’ saved [75042/75042]

In [ ]:

from llama_index.core import SimpleDirectoryReader

documents = SimpleDirectoryReader("./data/paul_graham/").load_data()

from llama_index.core import SimpleDirectoryReader documents = SimpleDirectoryReader("./data/paul_graham/").load_data()

接下来，我们将为文档建立一个向量索引。

In [ ]:

from llama_index.core import VectorStoreIndex
from llama_index.core.node_parser import SentenceSplitter

splitter = SentenceSplitter(chunk_size=256)

index = VectorStoreIndex.from_documents(documents, transformations=[splitter])

from llama_index.core import VectorStoreIndex from llama_index.core.node_parser import SentenceSplitter splitter = SentenceSplitter(chunk_size=256) index = VectorStoreIndex.from_documents(documents, transformations=[splitter])

创建混合融合检索器¶

在此步骤中，我们将索引与基于BM25的检索器进行融合。这种组合使我们能够同时捕捉输入查询中的语义关联和关键词。

由于这两种检索器都会计算相关性分数，我们可以使用互惠重排序算法对节点重新排序，而无需借助额外模型或过多计算资源。

该配置还会执行4次查询：第一次使用原始查询，随后生成3个额外查询。

默认情况下，系统使用以下提示模板生成附加查询：

QUERY_GEN_PROMPT = (
    "You are a helpful assistant that generates multiple search queries based on a "
    "single input query. Generate {num_queries} search queries, one on each line, "
    "related to the following input query:\n"
    "Query: {query}\n"
    "Queries:\n"
)

首先，我们创建检索器。每个检索器将获取前 2 个最相似的节点：

In [ ]:

from llama_index.retrievers.bm25 import BM25Retriever

vector_retriever = index.as_retriever(similarity_top_k=2)

bm25_retriever = BM25Retriever.from_defaults(
    docstore=index.docstore, similarity_top_k=2
)

from llama_index.retrievers.bm25 import BM25Retriever vector_retriever = index.as_retriever(similarity_top_k=2) bm25_retriever = BM25Retriever.from_defaults( docstore=index.docstore, similarity_top_k=2 )

接下来，我们可以创建融合检索器，它将从两个检索器返回的4个节点中筛选出相似度最高的前2个节点：

In [ ]:

from llama_index.core.retrievers import QueryFusionRetriever

retriever = QueryFusionRetriever(
    [vector_retriever, bm25_retriever],
    similarity_top_k=2,
    num_queries=4,  # set this to 1 to disable query generation
    mode="reciprocal_rerank",
    use_async=True,
    verbose=True,
    # query_gen_prompt="...",  # we could override the query generation prompt here
)

from llama_index.core.retrievers import QueryFusionRetriever retriever = QueryFusionRetriever( [vector_retriever, bm25_retriever], similarity_top_k=2, num_queries=4, # set this to 1 to disable query generation mode="reciprocal_rerank", use_async=True, verbose=True, # query_gen_prompt="...", # we could override the query generation prompt here )

In [ ]:

# apply nested async to run in a notebook
import nest_asyncio

nest_asyncio.apply()

# apply nested async to run in a notebook import nest_asyncio nest_asyncio.apply()

In [ ]:

nodes_with_scores = retriever.retrieve(
    "What happened at Interleafe and Viaweb?"
)

nodes_with_scores = retriever.retrieve( "What happened at Interleafe and Viaweb?" )

Generated queries:
1. What were the major events or milestones in the history of Interleafe and Viaweb?
2. Can you provide a timeline of the key developments and achievements of Interleafe and Viaweb?
3. What were the successes and failures of Interleafe and Viaweb as companies?

In [ ]:

for node in nodes_with_scores:
    print(f"Score: {node.score:.2f} - {node.text}...\n-----\n")

for node in nodes_with_scores: print(f"Score: {node.score:.2f} - {node.text}...\n-----\n")

Score: 0.03 - The UI was horrible, but it proved you could build a whole store through the browser, without any client software or typing anything into the command line on the server.

Now we felt like we were really onto something. I had visions of a whole new generation of software working this way. You wouldn't need versions, or ports, or any of that crap. At Interleaf there had been a whole group called Release Engineering that seemed to be at least as big as the group that actually wrote the software. Now you could just update the software right on the server.

We started a new company we called Viaweb, after the fact that our software worked via the web, and we got $10,000 in seed funding from Idelle's husband Julian. In return for that and doing the initial legal work and giving us business advice, we gave him 10% of the company. Ten years later this deal became the model for Y Combinator's. We knew founders needed something like this, because we'd needed it ourselves....
-----

Score: 0.03 - Now we felt like we were really onto something. I had visions of a whole new generation of software working this way. You wouldn't need versions, or ports, or any of that crap. At Interleaf there had been a whole group called Release Engineering that seemed to be at least as big as the group that actually wrote the software. Now you could just update the software right on the server.

We started a new company we called Viaweb, after the fact that our software worked via the web, and we got $10,000 in seed funding from Idelle's husband Julian. In return for that and doing the initial legal work and giving us business advice, we gave him 10% of the company. Ten years later this deal became the model for Y Combinator's. We knew founders needed something like this, because we'd needed it ourselves.

At this stage I had a negative net worth, because the thousand dollars or so I had in the bank was more than counterbalanced by what I owed the government in taxes. (Had I diligently set aside the proper proportion of the money I'd made consulting for Interleaf?...
-----

如我们所见，两个返回的节点都正确提及了 Viaweb 和 Interleaf！

在查询引擎中使用！¶

现在，我们可以将检索器接入查询引擎，从而生成自然语言响应。

In [ ]:

from llama_index.core.query_engine import RetrieverQueryEngine

query_engine = RetrieverQueryEngine.from_args(retriever)

from llama_index.core.query_engine import RetrieverQueryEngine query_engine = RetrieverQueryEngine.from_args(retriever)

In [ ]:

response = query_engine.query("What happened at Interleafe and Viaweb?")

response = query_engine.query("What happened at Interleafe and Viaweb?")

Generated queries:
1. What were the major events or milestones in the history of Interleafe and Viaweb?
2. Can you provide a timeline of the key developments and achievements of Interleafe and Viaweb?
3. What were the outcomes or impacts of Interleafe and Viaweb on the respective industries they operated in?

In [ ]:

from llama_index.core.response.notebook_utils import display_response

display_response(response)

from llama_index.core.response.notebook_utils import display_response display_response(response)

Final Response: At Interleaf, there was a group called Release Engineering that was as big as the group that actually wrote the software. This suggests that there was a significant focus on managing versions and ports of the software. However, at Viaweb, the founders realized that they could update the software directly on the server, eliminating the need for versions and ports. They started Viaweb, a company that built software that worked via the web. They received $10,000 in seed funding and gave 10% of the company to Julian, who provided the funding and business advice. This deal later became the model for Y Combinator's.