VearchDemo

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 openai
from IPython.display import Markdown, display
from llama_index import SimpleDirectoryReader, StorageContext, VectorStoreIndex

openai.api_key = ""

import openai from IPython.display import Markdown, display from llama_index import SimpleDirectoryReader, StorageContext, VectorStoreIndex openai.api_key = ""

In [ ]

!mkdir -p 'data/paul_graham/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt'
# load documents
documents = SimpleDirectoryReader("./data/paul_graham/").load_data()
print("Document ID:", len(documents), documents[0].doc_id)

!mkdir -p 'data/paul_graham/' !wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt' # load documents documents = SimpleDirectoryReader("./data/paul_graham/").load_data() print("文档 ID:", len(documents), documents[0].doc_id)

Document ID: 1 8d84aefd-ca73-4c1e-b83d-141c1b1b3ba6

In [ ]

from llama_index import ServiceContext
from llama_index.embeddings import HuggingFaceEmbedding
from llama_index.vector_stores import VearchVectorStore

"""
vearch cluster
"""
vector_store = VearchVectorStore(
    path_or_url="http://liama-index-router.vectorbase.svc.sq01.n.jd.local",
    table_name="liama_index_test2",
    db_name="liama_index",
    flag=1,
)

"""
vearch standalone
"""
# vector_store = VearchVectorStore(
#         path_or_url = '/data/zhx/zhx/liama_index/knowledge_base/liama_index_teststandalone',
#         # path_or_url = 'http://liama-index-router.vectorbase.svc.sq01.n.jd.local',
#         table_name = 'liama_index_teststandalone',
#         db_name = 'liama_index',
#         flag = 0)

embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")
service_context = ServiceContext.from_defaults(embed_model=embed_model)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context, service_context=service_context
)

from llama_index import ServiceContext from llama_index.embeddings import HuggingFaceEmbedding from llama_index.vector_stores import VearchVectorStore """ vearch cluster """ vector_store = VearchVectorStore( path_or_url="http://liama-index-router.vectorbase.svc.sq01.n.jd.local", table_name="liama_index_test2", db_name="liama_index", flag=1, ) """ vearch standalone """ # vector_store = VearchVectorStore( # path_or_url = '/data/zhx/zhx/liama_index/knowledge_base/liama_index_teststandalone', # # path_or_url = 'http://liama-index-router.vectorbase.svc.sq01.n.jd.local', # table_name = 'liama_index_teststandalone', # db_name = 'liama_index', # flag = 0) embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5") service_context = ServiceContext.from_defaults(embed_model=embed_model) storage_context = StorageContext.from_defaults(vector_store=vector_store) index = VectorStoreIndex.from_documents( documents, storage_context=storage_context, service_context=service_context )

Loading checkpoint shards:   0%|          | 0/7 [00:00<?, ?it/s]

In [ ]

query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
display(Markdown(f"<b>{response}</b>"))

query_engine = index.as_query_engine() response = query_engine.query("作者在成长过程中做了什么？") display(Markdown(f"{response}"))

作者没有提供任何关于其成长经历的信息。

In [ ]

query_engine = index.as_query_engine()
response = query_engine.query(
    "What did the author do after his time at Y Combinator?"
)
display(Markdown(f"<b>{response}</b>"))

query_engine = index.as_query_engine() response = query_engine.query( "作者在 Y Combinator 之后做了什么？" ) display(Markdown(f"{response}"))

作者在继续为 Y Combinator 工作的同时，用 Arc 写了 Y Combinator 所有的内部软件，但后来停止了 Arc 的工作，专注于写文章和为 Y Combinator 工作。2012 年，作者的母亲中风，作者意识到 Y Combinator 占用了他太多时间，决定将其交给其他人。作者向 Robert Morris 提出了这个建议，后者主动建议作者确保 Y Combinator 不是作者做的最后一件酷事。作者最终在 2013 年决定将 Y Combinator 的领导权交给 Sam Altman。