Dynamo DB Docstore演示¶

本指南向您展示如何直接使用由DynamoDB支持的DocumentStore抽象。通过将节点放入文档存储，您可以在同一底层文档存储上定义多个索引，而不是在不同索引之间重复数据。

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

In [ ]

%pip install llama-index-storage-docstore-dynamodb
%pip install llama-index-storage-index-store-dynamodb
%pip install llama-index-vector-stores-dynamodb
%pip install llama-index-llms-openai

%pip install llama-index-storage-docstore-dynamodb %pip install llama-index-storage-index-store-dynamodb %pip install llama-index-vector-stores-dynamodb %pip install llama-index-llms-openai

In [ ]

!pip install llama-index

!pip install llama-index

In [ ]

import nest_asyncio

nest_asyncio.apply()

import nest_asyncio nest_asyncio.apply()

In [ ]

import logging
import sys
import os

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

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

In [ ]

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

from llama_index.core import SimpleDirectoryReader, StorageContext from llama_index.core import VectorStoreIndex, SimpleKeywordTableIndex from llama_index.core import SummaryIndex 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¶

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 [ ]

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

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

解析为节点¶

In [ ]

from llama_index.core.node_parser import SentenceSplitter

nodes = SentenceSplitter().get_nodes_from_documents(documents)

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

添加到文档存储¶

In [ ]

TABLE_NAME = os.environ["DYNAMODB_TABLE_NAME"]

TABLE_NAME = os.environ["DYNAMODB_TABLE_NAME"]

In [ ]

from llama_index.storage.docstore.dynamodb import DynamoDBDocumentStore
from llama_index.storage.index_store.dynamodb import DynamoDBIndexStore
from llama_index.vector_stores.dynamodb import DynamoDBVectorStore

from llama_index.storage.docstore.dynamodb import DynamoDBDocumentStore from llama_index.storage.index_store.dynamodb import DynamoDBIndexStore from llama_index.vector_stores.dynamodb import DynamoDBVectorStore

In [ ]

storage_context = StorageContext.from_defaults(
    docstore=DynamoDBDocumentStore.from_table_name(table_name=TABLE_NAME),
    index_store=DynamoDBIndexStore.from_table_name(table_name=TABLE_NAME),
    vector_store=DynamoDBVectorStore.from_table_name(table_name=TABLE_NAME),
)

storage_context = StorageContext.from_defaults( docstore=DynamoDBDocumentStore.from_table_name(table_name=TABLE_NAME), index_store=DynamoDBIndexStore.from_table_name(table_name=TABLE_NAME), vector_store=DynamoDBVectorStore.from_table_name(table_name=TABLE_NAME), )

In [ ]

storage_context.docstore.add_documents(nodes)

storage_context.docstore.add_documents(nodes)

定义并添加多个索引¶

每个索引使用相同的底层节点。

In [ ]

# https://gpt-index.readthedocs.io/en/stable/api_reference/indices/list.html
summary_index = SummaryIndex(nodes, storage_context=storage_context)

# https://gpt-index.readthedocs.io/en/stable/api_reference/indices/list.html summary_index = SummaryIndex(nodes, storage_context=storage_context)

In [ ]

# https://gpt-index.readthedocs.io/en/stable/api_reference/indices/vector_store.html
vector_index = VectorStoreIndex(nodes, storage_context=storage_context)

# https://gpt-index.readthedocs.io/en/stable/api_reference/indices/vector_store.html vector_index = VectorStoreIndex(nodes, storage_context=storage_context)

In [ ]

# https://gpt-index.readthedocs.io/en/stable/api_reference/indices/table.html
keyword_table_index = SimpleKeywordTableIndex(
    nodes, storage_context=storage_context
)

# https://gpt-index.readthedocs.io/en/stable/api_reference/indices/table.html keyword_table_index = SimpleKeywordTableIndex( nodes, storage_context=storage_context )

In [ ]

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

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

测试保存和加载¶

In [ ]

# NOTE: docstore, index_store, and vector_index is persisted in DynamoDB by default when they are created
# NOTE: You can also persist simple vector store to disk by using the command below
storage_context.persist()

# NOTE: docstore, index_store, and vector_index is persisted in DynamoDB by default when they are created # NOTE: You can also persist simple vector store to disk by using the command below storage_context.persist()

In [ ]

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

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

In [ ]

from llama_index.core import load_index_from_storage

# re-create storage context
storage_context = StorageContext.from_defaults(
    docstore=DynamoDBDocumentStore.from_table_name(table_name=TABLE_NAME),
    index_store=DynamoDBIndexStore.from_table_name(table_name=TABLE_NAME),
    vector_store=DynamoDBVectorStore.from_table_name(table_name=TABLE_NAME),
)

summary_index = load_index_from_storage(
    storage_context=storage_context, index_id=list_id
)
keyword_table_index = load_index_from_storage(
    storage_context=storage_context, index_id=keyword_id
)

# You need to add "vector_store=DynamoDBVectorStore.from_table_name(table_name=TABLE_NAME)" to StorageContext to load vector index from DynamoDB
vector_index = load_index_from_storage(
    storage_context=storage_context, index_id=vector_id
)

from llama_index.core import load_index_from_storage # re-create storage context storage_context = StorageContext.from_defaults( docstore=DynamoDBDocumentStore.from_table_name(table_name=TABLE_NAME), index_store=DynamoDBIndexStore.from_table_name(table_name=TABLE_NAME), vector_store=DynamoDBVectorStore.from_table_name(table_name=TABLE_NAME), ) summary_index = load_index_from_storage( storage_context=storage_context, index_id=list_id ) keyword_table_index = load_index_from_storage( storage_context=storage_context, index_id=keyword_id ) # You need to add "vector_store=DynamoDBVectorStore.from_table_name(table_name=TABLE_NAME)" to StorageContext to load vector index from DynamoDB vector_index = load_index_from_storage( storage_context=storage_context, index_id=vector_id )

测试一些查询¶

In [ ]

chatgpt = OpenAI(temperature=0, model="gpt-3.5-turbo")

Settings.llm = chatgpt
Settings.chunk_size = 1024

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

In [ ]

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

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

In [ ]

display_response(list_response)

display_response(list_response)

In [ ]

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

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

In [ ]

display_response(vector_response)

display_response(vector_response)

In [ ]

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

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

In [ ]

display_response(keyword_response)

display_response(keyword_response)