本指南将展示如何直接使用由 Google Firestore 支持的 DocumentStore 抽象层。通过将节点放入文档存储中，您可以在相同的底层文档存储上定义多个索引，而无需在不同索引之间复制数据。

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

In [ ]

已复制！

%pip install llama-index-storage-docstore-firestore
%pip install llama-index-storage-kvstore-firestore
%pip install llama-index-storage-index-store-firestore
%pip install llama-index-llms-openai

!pip install llama-index

已复制！

!pip install llama-index

import nest_asyncio nest_asyncio.apply()

已复制！

import nest_asyncio

nest_asyncio.apply()

import logging import sys logging.basicConfig(stream=sys.stdout, level=logging.INFO) logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

已复制！

import logging
import sys

logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

from llama_index.core import SimpleDirectoryReader, StorageContext from llama_index.core import VectorStoreIndex, SimpleKeywordTableIndex from llama_index.core import SummaryIndex from llama_index.core import ComposableGraph from llama_index.llms.openai import OpenAI from llama_index.core.response.notebook_utils import display_response from llama_index.core import Settings

已复制！

from llama_index.core import SimpleDirectoryReader, StorageContext
from llama_index.core import VectorStoreIndex, SimpleKeywordTableIndex
from llama_index.core import SummaryIndex
from llama_index.core import ComposableGraph
from llama_index.llms.openai import OpenAI
from llama_index.core.response.notebook_utils import display_response
from llama_index.core import Settings

下载数据¶

!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'

已复制！

!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¶

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

已复制！

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

解析为节点¶

from llama_index.core.node_parser import SentenceSplitter nodes = SentenceSplitter().get_nodes_from_documents(documents)

已复制！

from llama_index.core.node_parser import SentenceSplitter

nodes = SentenceSplitter().get_nodes_from_documents(documents)

添加到文档存储¶

from llama_index.storage.kvstore.firestore import FirestoreKVStore from llama_index.storage.docstore.firestore import FirestoreDocumentStore from llama_index.storage.index_store.firestore import FirestoreIndexStore

已复制！

from llama_index.storage.kvstore.firestore import FirestoreKVStore
from llama_index.storage.docstore.firestore import FirestoreDocumentStore
from llama_index.storage.index_store.firestore import FirestoreIndexStore

kvstore = FirestoreKVStore() storage_context = StorageContext.from_defaults( docstore=FirestoreDocumentStore(kvstore), index_store=FirestoreIndexStore(kvstore), )

已复制！

kvstore = FirestoreKVStore()

storage_context = StorageContext.from_defaults(
    docstore=FirestoreDocumentStore(kvstore),
    index_store=FirestoreIndexStore(kvstore),
)

storage_context.docstore.add_documents(nodes)

已复制！

storage_context.docstore.add_documents(nodes)

定义多个索引¶

每个索引使用相同的底层节点。

summary_index = SummaryIndex(nodes, storage_context=storage_context)

已复制！

summary_index = SummaryIndex(nodes, storage_context=storage_context)

vector_index = VectorStoreIndex(nodes, storage_context=storage_context)

已复制！

vector_index = VectorStoreIndex(nodes, storage_context=storage_context)

keyword_table_index = SimpleKeywordTableIndex( nodes, storage_context=storage_context )

已复制！

keyword_table_index = SimpleKeywordTableIndex(
    nodes, storage_context=storage_context
)

# NOTE: the docstore still has the same nodes len(storage_context.docstore.docs)

已复制！

# NOTE: the docstore still has the same nodes
len(storage_context.docstore.docs)

测试保存和加载¶

# NOTE: docstore and index_store is persisted in Firestore by default # NOTE: here only need to persist simple vector store to disk storage_context.persist()

已复制！

# NOTE: docstore and index_store is persisted in Firestore by default
# NOTE: here only need to persist simple vector store to disk
storage_context.persist()

# note down index IDs list_id = summary_index.index_id vector_id = vector_index.index_id keyword_id = keyword_table_index.index_id

已复制！

# note down index IDs
list_id = summary_index.index_id
vector_id = vector_index.index_id
keyword_id = keyword_table_index.index_id

from llama_index.core import load_index_from_storage kvstore = FirestoreKVStore() # re-create storage context storage_context = StorageContext.from_defaults( docstore=FirestoreDocumentStore(kvstore), index_store=FirestoreIndexStore(kvstore), ) # load indices summary_index = load_index_from_storage( storage_context=storage_context, index_id=list_id ) vector_index = load_index_from_storage( storage_context=storage_context, vector_id=vector_id ) keyword_table_index = load_index_from_storage( storage_context=storage_context, keyword_id=keyword_id )

已复制！

from llama_index.core import load_index_from_storage

kvstore = FirestoreKVStore()

# re-create storage context
storage_context = StorageContext.from_defaults(
    docstore=FirestoreDocumentStore(kvstore),
    index_store=FirestoreIndexStore(kvstore),
)

# load indices
summary_index = load_index_from_storage(
    storage_context=storage_context, index_id=list_id
)
vector_index = load_index_from_storage(
    storage_context=storage_context, vector_id=vector_id
)
keyword_table_index = load_index_from_storage(
    storage_context=storage_context, keyword_id=keyword_id
)

测试一些查询¶

chatgpt = OpenAI(temperature=0, model="gpt-3.5-turbo") Settings.llm = chatgpt Settings.chunk_size = 1024

已复制！

chatgpt = OpenAI(temperature=0, model="gpt-3.5-turbo")
Settings.llm = chatgpt
Settings.chunk_size = 1024

query_engine = summary_index.as_query_engine() list_response = query_engine.query("What is a summary of this document?")

已复制！

query_engine = summary_index.as_query_engine()
list_response = query_engine.query("What is a summary of this document?")

display_response(list_response)

已复制！

display_response(list_response)

query_engine = vector_index.as_query_engine() vector_response = query_engine.query("What did the author do growing up?")

已复制！

query_engine = vector_index.as_query_engine()
vector_response = query_engine.query("What did the author do growing up?")

display_response(vector_response)

已复制！

display_response(vector_response)

query_engine = keyword_table_index.as_query_engine() keyword_response = query_engine.query( "What did the author do after his time at YC?" )

已复制！

query_engine = keyword_table_index.as_query_engine()
keyword_response = query_engine.query(
    "What did the author do after his time at YC?"
)

display_response(keyword_response)

已复制！

display_response(keyword_response)

返回顶部