当前位置：首页 > news >正文

chromadb向量数据库使用（1）

news 2025/9/7 1:05:56

完整代码

import chromadb
chroma_client = chromadb.Client()

collection = chroma_client.create_collection(name="my_collection")

collection.add(documents=["This is a document about pineapple","This is a document about oranges"],ids=["id1", "id2"]
)

results = collection.query(query_texts=["This is a query document about hawaii"], n_results=2 
)
print(results)

{'ids': [['id1', 'id2']], 'embeddings': None, 'documents': [['This is a document about pineapple', 'This is a document about oranges']], 'uris': None, 'data': None, 'metadatas': [[None, None]], 'distances': [[1.0404009819030762, 1.2430799007415771]], 'included': [<IncludeEnum.distances: 'distances'>, <IncludeEnum.documents: 'documents'>, <IncludeEnum.metadatas: 'metadatas'>]}

import chromadb
chroma_client = chromadb.Client()collection = chroma_client.get_or_create_collection(name="my_collection")collection.upsert(documents=["This is a document about pineapple","This is a document about oranges"],ids=["id1", "id2"]
)results = collection.query(query_texts=["..."], n_results=2 
)print(results)

{'ids': [['id2', 'id1']], 'embeddings': None, 'documents': [['This is a document about oranges', 'This is a document about pineapple']], 'uris': None, 'data': None, 'metadatas': [[None, None]], 'distances': [[1.8110723495483398, 1.846815824508667]], 'included': [<IncludeEnum.distances: 'distances'>, <IncludeEnum.documents: 'documents'>, <IncludeEnum.metadatas: 'metadatas'>]}

代码解释

以下是逐行代码的中文解释：

# 导入ChromaDB客户端库
import chromadb# 创建ChromaDB客户端实例（默认使用内存存储）
chroma_client = chromadb.Client()# 创建名为"my_collection"的集合（类似数据库表）
collection = chroma_client.create_collection(name="my_collection")# 向集合添加文档数据
collection.add(documents=["This is a document about pineapple",  # 文档1：关于菠萝"This is a document about oranges"     # 文档2：关于橙子],ids=["id1", "id2"]  # 为每个文档指定唯一ID
)# 执行相似性查询
results = collection.query(query_texts=["This is a query document about hawaii"],  # 查询文本（夏威夷相关）n_results=2  # 返回最相似的2个结果
)# 打印查询结果（包含相似文档及其距离分数）
print(results)

# 获取或创建集合（如果已存在则直接获取）
collection = chroma_client.get_or_create_collection(name="my_collection")# 使用upsert方法添加/更新文档（存在则更新，不存在则插入）
collection.upsert(documents=["This is a document about pineapple",  # 文档内容与之前相同"This is a document about oranges"],ids=["id1", "id2"]  # 使用相同ID
)# 执行空查询（使用"..."作为占位符）
results = collection.query(query_texts=["..."],  # 无效查询文本示例n_results=2
)# 打印不同查询条件的结果对比
print(results)