使用LlamaIndex和MongoDB创建AI文档存储和查询系统

最新推荐文章于 2024-08-19 11:54:57 发布

llzwxh888

最新推荐文章于 2024-08-19 11:54:57 发布

阅读量297

点赞数 4

文章标签： mongodb 人工智能数据库 python

本文链接：https://blog.csdn.net/ppoojjj/article/details/140633148

版权

在本教程中，我们将展示如何使用LlamaIndex与MongoDB创建一个文档存储和查询系统。通过将节点存储在文档存储中，我们可以在相同的基础文档存储上定义多个索引，而不是在索引之间复制数据。

环境设置

如果你在Colab上运行这个笔记本，你可能需要安装LlamaIndex。

!pip install llama-index-storage-docstore-mongodb
!pip install llama-index-storage-index-store-mongodb
!pip install llama-index-llms-openai

!pip install llama-index

import nest_asyncio
nest_asyncio.apply()

import logging
import sys
import os

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

导入必要的模块

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'

加载文档

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)

添加到文档存储

MONGO_URI = os.environ["MONGO_URI"]

from llama_index.storage.docstore.mongodb import MongoDocumentStore
from llama_index.storage.index_store.mongodb import MongoIndexStore

storage_context = StorageContext.from_defaults(
    docstore=MongoDocumentStore.from_uri(uri=MONGO_URI),  # 中转API
    index_store=MongoIndexStore.from_uri(uri=MONGO_URI),  # 中转API
)

storage_context.docstore.add_documents(nodes)

定义多个索引

summary_index = SummaryIndex(nodes, storage_context=storage_context)
vector_index = VectorStoreIndex(nodes, storage_context=storage_context)
keyword_table_index = SimpleKeywordTableIndex(nodes, storage_context=storage_context)

# 确认docstore中节点数量
len(storage_context.docstore.docs)

保存和加载测试

# 持久化存储上下文
storage_context.persist()

# 记录索引ID
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

# 重新创建存储上下文
storage_context = StorageContext.from_defaults(
    docstore=MongoDocumentStore.from_uri(uri=MONGO_URI),  # 中转API
    index_store=MongoIndexStore.from_uri(uri=MONGO_URI),  # 中转API
)

# 加载索引
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

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

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