Qdrant 读取器¶

输入 [ ]

%pip install llama-index-readers-qdrant

%pip install llama-index-readers-qdrant

输入 [ ]

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))

如果您正在 Colab 中打开此 Notebook，您可能需要安装 LlamaIndex 🦙。

输入 [ ]

!pip install llama-index

!pip install llama-index

输入 [ ]

from llama_index.readers.qdrant import QdrantReader

from llama_index.readers.qdrant import QdrantReader

输入 [ ]

reader = QdrantReader(host="localhost")

reader = QdrantReader(host="localhost")

输入 [ ]

# the query_vector is an embedding representation of your query_vector
# Example query vector:
#   query_vector=[0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3]

query_vector = [n1, n2, n3, ...]

# query_vector 是你的查询向量的嵌入表示 # 示例查询向量： # query_vector=[0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3, 0.3] query_vector = [n1, n2, n3, ...]

输入 [ ]

# NOTE: Required args are collection_name, query_vector.
# See the Python client: https://github.com/qdrant/qdrant_client
# for more details.
documents = reader.load_data(
    collection_name="demo", query_vector=query_vector, limit=5
)

# 注意：必需的参数是 collection_name, query_vector. # 更多详情请参阅 Python 客户端：https://github.com/qdrant/qdrant_client documents = reader.load_data( collection_name="demo", query_vector=query_vector, limit=5 )

创建索引¶

输入 [ ]

index = SummaryIndex.from_documents(documents)

index = SummaryIndex.from_documents(documents)

输入 [ ]

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

# 将 Logging 设置为 DEBUG 以获取更详细的输出 query_engine = index.as_query_engine() response = query_engine.query("")

输入 [ ]

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

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