txtai 向量存储¶

如果您在colab上打开这个笔记本，您可能需要安装LlamaIndex 🦙。

In [ ]:

%pip install llama-index-vector-stores-txtai

%pip install llama-index-vector-stores-txtai

In [ ]:

!pip install llama-index

!pip install llama-index

创建一个Faiss索引¶

In [ ]:

import logging
import sys

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

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

In [ ]:

import txtai# 创建txtai ann索引txtai_index = txtai.ann.ANNFactory.create({"backend": "numpy"})

import txtai# 创建txtai ann索引txtai_index = txtai.ann.ANNFactory.create({"backend": "numpy"})

加载文档，构建VectorStoreIndex¶

In [ ]:

from llama_index.core import (
    SimpleDirectoryReader,
    load_index_from_storage,
    VectorStoreIndex,
    StorageContext,
)
from llama_index.vector_stores.txtai import TxtaiVectorStore
from IPython.display import Markdown, display

from llama_index.core import ( SimpleDirectoryReader, load_index_from_storage, VectorStoreIndex, StorageContext, ) from llama_index.vector_stores.txtai import TxtaiVectorStore from IPython.display import Markdown, display

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'

In [ ]:

# 加载文档documents = SimpleDirectoryReader("./data/paul_graham/").load_data()

# 加载文档documents = SimpleDirectoryReader("./data/paul_graham/").load_data()

In [ ]:

vector_store = TxtaiVectorStore(txtai_index=txtai_index)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context
)

vector_store = TxtaiVectorStore(txtai_index=txtai_index) storage_context = StorageContext.from_defaults(vector_store=vector_store) index = VectorStoreIndex.from_documents( documents, storage_context=storage_context )

In [ ]:

# 将索引保存到磁盘index.storage_context.persist()

# 将索引保存到磁盘index.storage_context.persist()

In [ ]:

# 从磁盘加载索引vector_store = TxtaiVectorStore.from_persist_dir("./storage")storage_context = StorageContext.from_defaults(    vector_store=vector_store, persist_dir="./storage")index = load_index_from_storage(storage_context=storage_context)

# 从磁盘加载索引vector_store = TxtaiVectorStore.from_persist_dir("./storage")storage_context = StorageContext.from_defaults( vector_store=vector_store, persist_dir="./storage")index = load_index_from_storage(storage_context=storage_context)

# 查询索引

这个代码段演示了如何查询列表中特定元素的索引。

In [ ]:

# 将日志级别设置为DEBUG，以获得更详细的输出query_engine = index.as_query_engine()response = query_engine.query("作者在成长过程中做了什么？")

# 将日志级别设置为DEBUG，以获得更详细的输出query_engine = index.as_query_engine()response = query_engine.query("作者在成长过程中做了什么？")

In [ ]:

display(Markdown(f"<b>{response}</b>"))

display(Markdown(f"{response}"))

In [ ]:

# 将日志级别设置为DEBUG，以获得更详细的输出query_engine = index.as_query_engine()response = query_engine.query(    "作者在Y Combinator结束后做了什么？")

# 将日志级别设置为DEBUG，以获得更详细的输出query_engine = index.as_query_engine()response = query_engine.query( "作者在Y Combinator结束后做了什么？")

In [ ]:

display(Markdown(f"<b>{response}</b>"))

display(Markdown(f"{response}"))