Skip to main content
Open In ColabOpen on GitHub

AstraDB

DataStax Astra DB is a serverless AI-ready database built on Apache Cassandra® and made conveniently available through an easy-to-use JSON API.

概览

Astra DB 文档加载器返回从 Astra DB 集合中读取的 Langchain Document 对象列表。

加载器接受以下参数:

  • api_endpoint: Astra DB API 端点。看起来像 https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com
  • token: Astra DB 令牌。看起来像 AstraCS:aBcD0123...
  • collection_name : AstraDB 集合名称
  • namespace: (可选)AstraDB 命名空间(在 Astra DB 中称为keyspace
  • filter_criteria: (可选)用于查找查询的过滤器
  • projection: (可选)在 find 查询中使用的投影
  • limit: (可选)要检索的最大文档数
  • extraction_function: (可选)一个将 AstraDB 文档转换为 LangChain page_content 字符串的函数。默认值为 json.dumps

加载器为其读取的文档设置以下元数据:

metadata={
"namespace": "...",
"api_endpoint": "...",
"collection": "..."
}

设置

!pip install "langchain-astradb>=0.6,<0.7"

使用文档加载器加载文档

from langchain_astradb import AstraDBLoader
API 参考:AstraDBLoader

API 参考: AstraDBLoader

from getpass import getpass

ASTRA_DB_API_ENDPOINT = input("ASTRA_DB_API_ENDPOINT = ")
ASTRA_DB_APPLICATION_TOKEN = getpass("ASTRA_DB_APPLICATION_TOKEN = ")
ASTRA_DB_API_ENDPOINT =  https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com
ASTRA_DB_APPLICATION_TOKEN = ········
loader = AstraDBLoader(
api_endpoint=ASTRA_DB_API_ENDPOINT,
token=ASTRA_DB_APPLICATION_TOKEN,
collection_name="movie_reviews",
projection={"title": 1, "reviewtext": 1},
limit=10,
)
docs = loader.load()
docs[0]
Document(metadata={'namespace': 'default_keyspace', 'api_endpoint': 'https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com', 'collection': 'movie_reviews'}, page_content='{"_id": "659bdffa16cbc4586b11a423", "title": "Dangerous Men", "reviewtext": "\\"Dangerous Men,\\" the picture\'s production notes inform, took 26 years to reach the big screen. After having seen it, I wonder: What was the rush?"}')