Qdrant Reader¶

In [ ]:

%pip install llama-index-readers-qdrant

In [ ]:

import logging
import sys

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

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

In [ ]:

from llama_index.readers.qdrant import QdrantReader

In [ ]:

reader = QdrantReader(host="localhost")

In [ ]:

# 查询向量是查询的嵌入表示
# 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, ...]

In [ ]:

# 注意：必需参数为 collection_name, query_vector。
# 请参阅 Python 客户端：https://github.com/qdrant/qdrant_client
# 了解更多细节。
documents = reader.load_data(
    collection_name="demo", query_vector=query_vector, limit=5
)

创建索引¶

In [ ]:

index = SummaryIndex.from_documents(documents)

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("<query_text>")

In [ ]:

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