简单融合检索器¶

本示例将演示如何合并来自多个查询和多个索引的检索结果。

检索到的节点将作为所有查询和索引中的 top-k 结果返回，同时还会处理节点的去重问题。

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"]

安装配置¶

在本笔记本中，我们将使用文档中两个非常相似的页面，每个页面分别存储在不同的索引中。

In [ ]:

from llama_index.core import SimpleDirectoryReader

documents_1 = SimpleDirectoryReader(
    input_files=["../../community/integrations/vector_stores.md"]
).load_data()
documents_2 = SimpleDirectoryReader(
    input_files=["../../module_guides/storing/vector_stores.md"]
).load_data()

from llama_index.core import SimpleDirectoryReader documents_1 = SimpleDirectoryReader( input_files=["../../community/integrations/vector_stores.md"] ).load_data() documents_2 = SimpleDirectoryReader( input_files=["../../module_guides/storing/vector_stores.md"] ).load_data()

In [ ]:

from llama_index.core import VectorStoreIndex

index_1 = VectorStoreIndex.from_documents(documents_1)
index_2 = VectorStoreIndex.from_documents(documents_2)

from llama_index.core import VectorStoreIndex index_1 = VectorStoreIndex.from_documents(documents_1) index_2 = VectorStoreIndex.from_documents(documents_2)

融合索引！¶

在此步骤中，我们将多个索引融合为一个统一的检索器。该检索器还会通过生成与原始问题相关的额外查询来增强查询效果，并汇总检索结果。

此配置将执行4次查询：一次使用原始查询，另外生成3个相关查询。

默认情况下，系统使用以下提示模板生成额外查询：

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"
)

In [ ]:

from llama_index.core.retrievers import QueryFusionRetriever

retriever = QueryFusionRetriever(
    [index_1.as_retriever(), index_2.as_retriever()],
    similarity_top_k=2,
    num_queries=4,  # set this to 1 to disable query generation
    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( [index_1.as_retriever(), index_2.as_retriever()], similarity_top_k=2, num_queries=4, # set this to 1 to disable query generation 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("How do I setup a chroma vector store?")

nodes_with_scores = retriever.retrieve("How do I setup a chroma vector store?")

Generated queries:
1. What are the steps to set up a chroma vector store?
2. Best practices for configuring a chroma vector store
3. Troubleshooting common issues when setting up a chroma vector store

In [ ]:

for node in nodes_with_scores:
    print(f"Score: {node.score:.2f} - {node.text[:100]}...")

for node in nodes_with_scores: print(f"Score: {node.score:.2f} - {node.text[:100]}...")

Score: 0.78 - # Vector Stores

Vector stores contain embedding vectors of ingested document chunks
(and sometimes ...
Score: 0.78 - # Using Vector Stores

LlamaIndex offers multiple integration points with vector stores / vector dat...

在查询引擎中使用！¶

现在，我们可以将检索器接入查询引擎，用于合成自然语言响应。

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(
    "How do I setup a chroma vector store? Can you give an example?"
)

response = query_engine.query( "How do I setup a chroma vector store? Can you give an example?" )

Generated queries:
1. How to set up a chroma vector store?
2. Step-by-step guide for creating a chroma vector store.
3. Examples of chroma vector store setups and configurations.

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: To set up a Chroma vector store, you need to follow these steps:

1. Import the necessary libraries:

import chromadb
from llama_index.vector_stores.chroma import ChromaVectorStore

2. Create a Chroma client:

chroma_client = chromadb.EphemeralClient()
chroma_collection = chroma_client.create_collection("quickstart")

3. Construct the vector store:

vector_store = ChromaVectorStore(chroma_collection=chroma_collection)

Here's an example of how to set up a Chroma vector store using the above steps:

import chromadb
from llama_index.vector_stores.chroma import ChromaVectorStore

# Creating a Chroma client
# EphemeralClient operates purely in-memory, PersistentClient will also save to disk
chroma_client = chromadb.EphemeralClient()
chroma_collection = chroma_client.create_collection("quickstart")

# construct vector store
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)

This example demonstrates how to create a Chroma client, create a collection named "quickstart", and then construct a Chroma vector store using that collection.