Skip to main content
Google BigQuery 是一个无服务器、高性价比的企业级数据仓库，支持跨云运行并可随数据规模弹性扩展。BigQuery 是 Google Cloud Platform 的组成部分。
以每行一个文档的方式加载 BigQuery 查询结果。 
pip install -qU langchain-google-community[bigquery]

from langchain_google_community import BigQueryLoader

BASE_QUERY = """
SELECT
  id,
  dna_sequence,
  organism
FROM (
  SELECT
    ARRAY (
    SELECT
      AS STRUCT 1 AS id, "ATTCGA" AS dna_sequence, "Lokiarchaeum sp. (strain GC14_75)." AS organism
    UNION ALL
    SELECT
      AS STRUCT 2 AS id, "AGGCGA" AS dna_sequence, "Heimdallarchaeota archaeon (strain LC_2)." AS organism
    UNION ALL
    SELECT
      AS STRUCT 3 AS id, "TCCGGA" AS dna_sequence, "Acidianus hospitalis (strain W1)." AS organism) AS new_array),
  UNNEST(new_array)
"""

​
基本用法

loader = BigQueryLoader(BASE_QUERY)

data = loader.load()

print(data)

[Document(page_content='id: 1\ndna_sequence: ATTCGA\norganism: Lokiarchaeum sp. (strain GC14_75).', lookup_str='', metadata={}, lookup_index=0), Document(page_content='id: 2\ndna_sequence: AGGCGA\norganism: Heimdallarchaeota archaeon (strain LC_2).', lookup_str='', metadata={}, lookup_index=0), Document(page_content='id: 3\ndna_sequence: TCCGGA\norganism: Acidianus hospitalis (strain W1).', lookup_str='', metadata={}, lookup_index=0)]

​
指定内容列与元数据列

loader = BigQueryLoader(
    BASE_QUERY,
    page_content_columns=["dna_sequence", "organism"],
    metadata_columns=["id"],
)

data = loader.load()

print(data)

[Document(page_content='dna_sequence: ATTCGA\norganism: Lokiarchaeum sp. (strain GC14_75).', lookup_str='', metadata={'id': 1}, lookup_index=0), Document(page_content='dna_sequence: AGGCGA\norganism: Heimdallarchaeota archaeon (strain LC_2).', lookup_str='', metadata={'id': 2}, lookup_index=0), Document(page_content='dna_sequence: TCCGGA\norganism: Acidianus hospitalis (strain W1).', lookup_str='', metadata={'id': 3}, lookup_index=0)]

​
向元数据中添加来源信息

# Note that the `id` column is being returned twice, with one instance aliased as `source`
ALIASED_QUERY = """
SELECT
  id,
  dna_sequence,
  organism,
  id as source
FROM (
  SELECT
    ARRAY (
    SELECT
      AS STRUCT 1 AS id, "ATTCGA" AS dna_sequence, "Lokiarchaeum sp. (strain GC14_75)." AS organism
    UNION ALL
    SELECT
      AS STRUCT 2 AS id, "AGGCGA" AS dna_sequence, "Heimdallarchaeota archaeon (strain LC_2)." AS organism
    UNION ALL
    SELECT
      AS STRUCT 3 AS id, "TCCGGA" AS dna_sequence, "Acidianus hospitalis (strain W1)." AS organism) AS new_array),
  UNNEST(new_array)
"""

loader = BigQueryLoader(ALIASED_QUERY, metadata_columns=["source"])

data = loader.load()

print(data)

[Document(page_content='id: 1\ndna_sequence: ATTCGA\norganism: Lokiarchaeum sp. (strain GC14_75).\nsource: 1', lookup_str='', metadata={'source': 1}, lookup_index=0), Document(page_content='id: 2\ndna_sequence: AGGCGA\norganism: Heimdallarchaeota archaeon (strain LC_2).\nsource: 2', lookup_str='', metadata={'source': 2}, lookup_index=0), Document(page_content='id: 3\ndna_sequence: TCCGGA\norganism: Acidianus hospitalis (strain W1).\nsource: 3', lookup_str='', metadata={'source': 3}, lookup_index=0)]
在 GitHub 上编辑此页面 或 提交 Issue。
通过 MCP 将这些文档连接到 Claude、VSCode 等工具，获取实时解答。