DashVector 读取器¶

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

In [ ]

%pip install llama-index-readers-dashvector

%pip install llama-index-readers-dashvector

In [ ]

!pip install llama-index

!pip install llama-index

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 [ ]

api_key = os.environ["DASHVECTOR_API_KEY"]

api_key = os.environ["DASHVECTOR_API_KEY"]

In [ ]

from llama_index.readers.dashvector import DashVectorReader

reader = DashVectorReader(api_key=api_key)

from llama_index.readers.dashvector import DashVectorReader reader = DashVectorReader(api_key=api_key)

In [ ]

import numpy as np

# the query_vector is an embedding representation of your query_vector
query_vector = [n1, n2, n3, ...]

import numpy as np # the query_vector 是您的查询向量的嵌入表示 query_vector = [n1, n2, n3, ...]

In [ ]

# NOTE: Required args are index_name, id_to_text_map, vector.
# In addition, we can pass through the metadata filter that meet the SQL syntax.
# See the Python client: https://pypi.ac.cn/project/dashvector/ for more details.
documents = reader.load_data(
    collection_name="quickstart",
    topk=3,
    vector=query_vector,
    filter="key = 'value'",
    output_fields=["key1", "key2"],
)

# 注意：必需参数为 index_name, id_to_text_map, vector。 # 此外，我们可以传递符合 SQL 语法的元数据过滤器。 # 更多详情请参阅 Python 客户端：https://pypi.ac.cn/project/dashvector/。 documents = reader.load_data( collection_name="quickstart", topk=3, vector=query_vector, filter="key = 'value'", output_fields=["key1", "key2"], )

创建索引¶

In [ ]

from llama_index.core import ListIndex
from IPython.display import Markdown, display

index = ListIndex.from_documents(documents)

from llama_index.core import ListIndex from IPython.display import Markdown, display index = ListIndex.from_documents(documents)

In [ ]

# set Logging to DEBUG for more detailed outputs
query_engine = index.as_query_engine()
response = query_engine.query("<query_text>")

# 将日志级别设置为 DEBUG 以获取更详细的输出 query_engine = index.as_query_engine() response = query_engine.query("")

In [ ]

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

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