如果你在 Colab 中打开这个 Notebook，可能需要先安装 LlamaIndex 🦙。

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

import logging
import sys
import os

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

创建 Pinecone 索引

from pinecone import Pinecone, ServerlessSpec

os.environ["PINECONE_API_KEY"] = "..."
os.environ["OPENAI_API_KEY"] = "sk-proj-..."

api_key = os.environ["PINECONE_API_KEY"]

pc = Pinecone(api_key=api_key)

# delete if needed
# pc.delete_index("quickstart")

# dimensions are for text-embedding-ada-002

pc.create_index(
    name="quickstart",
    dimension=1536,
    metric="euclidean",
    spec=ServerlessSpec(cloud="aws", region="us-east-1"),
)

# If you need to create a PodBased Pinecone index, you could alternatively do this:
#
# from pinecone import Pinecone, PodSpec
#
# pc = Pinecone(api_key='xxx')
#
# pc.create_index(
#    name='my-index',
#    dimension=1536,
#    metric='cosine',
#    spec=PodSpec(
#      environment='us-east1-gcp',
#      pod_type='p1.x1',
#      pods=1
#    )
# )
#

pinecone_index = pc.Index("quickstart")

加载文档，构建 PineconeVectorStore 和 VectorStoreIndex

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.vector_stores.pinecone import PineconeVectorStore
from IPython.display import Markdown, display

下载数据

!mkdir -p 'data/paul_graham/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

# load documents
documents = SimpleDirectoryReader("./data/paul_graham").load_data()

# initialize without metadata filter
from llama_index.core import StorageContext

if "OPENAI_API_KEY" not in os.environ:
    raise EnvironmentError(f"Environment variable OPENAI_API_KEY is not set")

vector_store = PineconeVectorStore(pinecone_index=pinecone_index)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context
)

查询索引

索引可能需要一分钟左右才能就绪！

# set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")

INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"

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

作者在成长过程中从事写作和编程。他们写短篇小说，并尝试在 IBM 1401 计算机上编写程序。后来他们得到了一台微型计算机，并开始更广泛地编程，编写简单游戏和一个文字处理器。

过滤

你也可以直接使用过滤器获取节点列表。

from llama_index.core.vector_stores.types import (
    MetadataFilter,
    MetadataFilters,
    FilterOperator,
    FilterCondition,
)

filter = MetadataFilters(
    filters=[
        MetadataFilter(
            key="file_path",
            value="/Users/loganmarkewich/giant_change/llama_index/docs/examples/vector_stores/data/paul_graham/paul_graham_essay.txt",
            operator=FilterOperator.EQ,
        )
    ],
    condition=FilterCondition.AND,
)

你可以直接使用过滤器获取节点。下面的代码将返回所有匹配该过滤器的节点。

nodes = vector_store.get_nodes(filters=filter, limit=100)
print(len(nodes))

22

你也可以使用 top-k 和过滤器进行获取。

query_engine = index.as_query_engine(similarity_top_k=2, filters=filter)
response = query_engine.query("What did the author do growing up?")
print(len(response.source_nodes))

INFO:httpx:HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
2