mcpField
C
chroma

chroma

github.com/ovachiever数据与数据库5655 次安装48 周前更新
代码仓库

关于 chroma

Chroma 是用于 LLM 应用的开源嵌入数据库，面向构建 RAG、语义搜索和文档检索的开发者。它支持元数据过滤、持久化存储及本地或服务端使用。

主要功能

  1. 01存储文档、嵌入和元数据
  2. 02相似度查询与元数据过滤
  3. 03支持持久化磁盘存储
  4. 04提供多种嵌入函数
  5. 05支持服务端模式
  6. 06提供 LangChain 与 LlamaIndex 集成

适用场景

  1. 01构建 RAG 应用
  2. 02对文档进行语义搜索
  3. 03在笔记本中原型验证
  4. 04保存并筛选带元数据的嵌入

安装

复制下面的命令，在终端中运行。

$npx skills add https://github.com/ovachiever/droid-tings --skill chroma

安装后在 Claude Code 中输入/chroma确认已加载。

附带文件references/integration.md

详细介绍

Chroma - 开源嵌入数据库

用于构建带记忆的大模型应用的 AI 原生数据库。

何时使用 Chroma

在以下情况使用 Chroma：

  • 构建 RAG（检索增强生成）应用
  • 需要本地/可自托管的向量数据库
  • 想要开源解决方案（Apache 2.0）
  • 在 notebook 中进行原型开发
  • 对文档进行语义搜索
  • 存储带元数据的嵌入

指标：

  • 24,300+ GitHub stars
  • 1,900+ forks
  • v1.3.3（稳定版，每周发布）
  • Apache 2.0 许可证

改用以下替代方案：

  • Pinecone：托管云服务，自动扩缩容
  • FAISS：纯相似度搜索，无元数据
  • Weaviate：生产级 ML 原生数据库
  • Qdrant：高性能，基于 Rust

快速开始

安装
# Python
pip install chromadb

# JavaScript/TypeScript
npm install chromadb @chroma-core/default-embed
基本用法（Python）
import chromadb

# Create client
client = chromadb.Client()

# Create collection
collection = client.create_collection(name="my_collection")

# Add documents
collection.add(
    documents=["This is document 1", "This is document 2"],
    metadatas=[{"source": "doc1"}, {"source": "doc2"}],
    ids=["id1", "id2"]
)

# Query
results = collection.query(
    query_texts=["document about topic"],
    n_results=2
)

print(results)

核心操作

1. 创建 collection
# Simple collection
collection = client.create_collection("my_docs")

# With custom embedding function
from chromadb.utils import embedding_functions

openai_ef = embedding_functions.OpenAIEmbeddingFunction(
    api_key="your-key",
    model_name="text-embedding-3-small"
)

collection = client.create_collection(
    name="my_docs",
    embedding_function=openai_ef
)

# Get existing collection
collection = client.get_collection("my_docs")

# Delete collection
client.delete_collection("my_docs")
2. 添加文档
# Add with auto-generated IDs
collection.add(
    documents=["Doc 1", "Doc 2", "Doc 3"],
    metadatas=[
        {"source": "web", "category": "tutorial"},
        {"source": "pdf", "page": 5},
        {"source": "api", "timestamp": "2025-01-01"}
    ],
    ids=["id1", "id2", "id3"]
)

# Add with custom embeddings
collection.add(
    embeddings=[[0.1, 0.2, ...], [0.3, 0.4, ...]],
    documents=["Doc 1", "Doc 2"],
    ids=["id1", "id2"]
)
3. 查询（相似度搜索）
# Basic query
results = collection.query(
    query_texts=["machine learning tutorial"],
    n_results=5
)

# Query with filters
results = collection.query(
    query_texts=["Python programming"],
    n_results=3,
    where={"source": "web"}
)

# Query with metadata filters
results = collection.query(
    query_texts=["advanced topics"],
    where={
        "$and": [
            {"category": "tutorial"},
            {"difficulty": {"$gte": 3}}
        ]
    }
)

# Access results
print(results["documents"])      # List of matching documents
print(results["metadatas"])      # Metadata for each doc
print(results["distances"])      # Similarity scores
print(results["ids"])            # Document IDs
4. 获取文档
# Get by IDs
docs = collection.get(
    ids=["id1", "id2"]
)

# Get with filters
docs = collection.get(
    where={"category": "tutorial"},
    limit=10
)

# Get all documents
docs = collection.get()
5. 更新文档
# Update document content
collection.update(
    ids=["id1"],
    documents=["Updated content"],
    metadatas=[{"source": "updated"}]
)
6. 删除文档
# Delete by IDs
collection.delete(ids=["id1", "id2"])

# Delete with filter
collection.delete(
    where={"source": "outdated"}
)

持久化存储

# Persist to disk
client = chromadb.PersistentClient(path="./chroma_db")

collection = client.create_collection("my_docs")
collection.add(documents=["Doc 1"], ids=["id1"])

# Data persisted automatically
# Reload later with same path
client = chromadb.PersistentClient(path="./chroma_db")
collection = client.get_collection("my_docs")

嵌入函数

默认（Sentence Transformers）
# Uses sentence-transformers by default
collection = client.create_collection("my_docs")
# Default model: all-MiniLM-L6-v2
OpenAI
from chromadb.utils import embedding_functions

openai_ef = embedding_functions.OpenAIEmbeddingFunction(
    api_key="your-key",
    model_name="text-embedding-3-small"
)

collection = client.create_collection(
    name="openai_docs",
    embedding_function=openai_ef
)
HuggingFace
huggingface_ef = embedding_functions.HuggingFaceEmbeddingFunction(
    api_key="your-key",
    model_name="sentence-transformers/all-mpnet-base-v2"
)

collection = client.create_collection(
    name="hf_docs",
    embedding_function=huggingface_ef
)
自定义嵌入函数
from chromadb import Documents, EmbeddingFunction, Embeddings

class MyEmbeddingFunction(EmbeddingFunction):
    def __call__(self, input: Documents) -> Embeddings:
        # Your embedding logic
        return embeddings

my_ef = MyEmbeddingFunction()
collection = client.create_collection(
    name="custom_docs",
    embedding_function=my_ef
)

元数据过滤

# Exact match
results = collection.query(
    query_texts=["query"],
    where={"category": "tutorial"}
)

# Comparison operators
results = collection.query(
    query_texts=["query"],
    where={"page": {"$gt": 10}}  # $gt, $gte, $lt, $lte, $ne
)

# Logical operators
results = collection.query(
    query_texts=["query"],
    where={
        "$and": [
            {"category": "tutorial"},
            {"difficulty": {"$lte": 3}}
        ]
    }  # Also: $or
)

# Contains
results = collection.query(
    query_texts=["query"],
    where={"tags": {"$in": ["python", "ml"]}}
)

LangChain 集成

from langchain_chroma import Chroma
from langchain_openai import OpenAIEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter

# Split documents
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000)
docs = text_splitter.split_documents(documents)

# Create Chroma vector store
vectorstore = Chroma.from_documents(
    documents=docs,
    embedding=OpenAIEmbeddings(),
    persist_directory="./chroma_db"
)

# Query
results = vectorstore.similarity_search("machine learning", k=3)

# As retriever
retriever = vectorstore.as_retriever(search_kwargs={"k": 5})

LlamaIndex 集成

from llama_index.vector_stores.chroma import ChromaVectorStore
from llama_index.core import VectorStoreIndex, StorageContext
import chromadb

# Initialize Chroma
db = chromadb.PersistentClient(path="./chroma_db")
collection = db.get_or_create_collection("my_collection")

# Create vector store
vector_store = ChromaVectorStore(chroma_collection=collection)
storage_context = StorageContext.from_defaults(vector_store=vector_store)

# Create index
index = VectorStoreIndex.from_documents(
    documents,
    storage_context=storage_context
)

# Query
query_engine = index.as_query_engine()
response = query_engine.query("What is machine learning?")

服务模式

# Run Chroma server
# Terminal: chroma run --path ./chroma_db --port 8000

# Connect to server
import chromadb
from chromadb.config import Settings

client = chromadb.HttpClient(
    host="localhost",
    port=8000,
    settings=Settings(anonymized_telemetry=False)
)

# Use as normal
collection = client.get_or_create_collection("my_docs")

最佳实践

  1. 使用持久化客户端 - 重启时不会丢失数据
  2. 添加元数据 - 支持过滤和跟踪
  3. 批量操作 - 一次性添加多个文档
  4. 选择合适的嵌入模型 - 平衡速度与质量
  5. 使用过滤器 - 缩小搜索范围
  6. 唯一 ID - 避免冲突
  7. 定期备份 - 复制 chroma_db 目录
  8. 监控 collection 大小 - 按需扩容
  9. 测试嵌入函数 - 确保质量
  10. 生产环境使用服务模式 - 更适合多用户

性能

操作延迟说明
添加 100 个文档约 1-3s含嵌入
查询（top 10）约 50-200ms取决于 collection 大小
元数据过滤约 10-50ms索引得当则很快

资源

评论

支持 Markdown