Chroma¶

Chroma 是一个面向AI的原生开源向量数据库，专注于提升开发者的生产力和开发体验。Chroma采用Apache 2.0许可证。

     

• 官方网站
• 文档
• Twitter
• Discord

Chroma具备完整的类型注解、全面的测试覆盖和详尽的文档说明。

安装命令：

pip install chromadb

Chroma支持多种运行模式，以下是与LlamaIndex集成的示例：

• 内存模式 - 在Python脚本或Jupyter笔记本中运行
• 持久化内存模式 - 在脚本或笔记本中运行并支持磁盘存储/加载
• Docker容器模式 - 作为服务在本地或云端运行

与其他数据库类似，您可以执行以下操作：

• .add 添加数据
• .get 获取数据
• .update 更新数据
• .upsert 更新或插入数据
• .delete 删除数据
• .peek 查看数据
• .query 执行相似性搜索

完整文档请参阅文档中心。

基础示例¶

在这个基础示例中，我们将保罗·格雷厄姆的文章分割成多个文本块，使用开源嵌入模型进行向量化处理，将其加载到 Chroma 中，然后执行查询操作。

如果您在 Colab 上打开此 Notebook，可能需要安装 LlamaIndex 🦙。

In [ ]:

%pip install llama-index-vector-stores-chroma
%pip install llama-index-embeddings-huggingface

%pip install llama-index-vector-stores-chroma %pip install llama-index-embeddings-huggingface

In [ ]:

!pip install llama-index

!pip install llama-index

创建 Chroma 索引¶

In [ ]:

# !pip install llama-index chromadb --quiet
# !pip install chromadb
# !pip install sentence-transformers
# !pip install pydantic==1.10.11

# !pip install llama-index chromadb --quiet # !pip install chromadb # !pip install sentence-transformers # !pip install pydantic==1.10.11

In [ ]:

# import
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.vector_stores.chroma import ChromaVectorStore
from llama_index.core import StorageContext
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from IPython.display import Markdown, display
import chromadb

# import from llama_index.core import VectorStoreIndex, SimpleDirectoryReader from llama_index.vector_stores.chroma import ChromaVectorStore from llama_index.core import StorageContext from llama_index.embeddings.huggingface import HuggingFaceEmbedding from IPython.display import Markdown, display import chromadb

In [ ]:

# set up OpenAI
import os
import getpass

os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")
import openai

openai.api_key = os.environ["OPENAI_API_KEY"]

# set up OpenAI import os import getpass os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:") import openai openai.api_key = os.environ["OPENAI_API_KEY"]

下载数据

In [ ]:

!mkdir -p 'data/paul_graham/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

!mkdir -p 'data/paul_graham/' !wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

In [ ]:

# create client and a new collection
chroma_client = chromadb.EphemeralClient()
chroma_collection = chroma_client.create_collection("quickstart")

# define embedding function
embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-base-en-v1.5")

# load documents
documents = SimpleDirectoryReader("./data/paul_graham/").load_data()

# set up ChromaVectorStore and load in data
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context, embed_model=embed_model
)

# Query Data
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
display(Markdown(f"<b>{response}</b>"))

# create client and a new collection chroma_client = chromadb.EphemeralClient() chroma_collection = chroma_client.create_collection("quickstart") # define embedding function embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-base-en-v1.5") # load documents documents = SimpleDirectoryReader("./data/paul_graham/").load_data() # set up ChromaVectorStore and load in data vector_store = ChromaVectorStore(chroma_collection=chroma_collection) storage_context = StorageContext.from_defaults(vector_store=vector_store) index = VectorStoreIndex.from_documents( documents, storage_context=storage_context, embed_model=embed_model ) # Query Data query_engine = index.as_query_engine() response = query_engine.query("What did the author do growing up?") display(Markdown(f"{response}"))

/Users/loganmarkewich/llama_index/llama-index/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm
/Users/loganmarkewich/llama_index/llama-index/lib/python3.9/site-packages/bitsandbytes/cextension.py:34: UserWarning: The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers, 8-bit multiplication, and GPU quantization are unavailable.
  warn("The installed version of bitsandbytes was compiled without GPU support. "

'NoneType' object has no attribute 'cadam32bit_grad_fp32'

The author worked on writing and programming growing up. They wrote short stories and tried writing programs on an IBM 1401 computer. Later, they got a microcomputer and started programming more extensively.

基础示例（包含磁盘存储功能）¶

延续前一个示例，若需将数据保存至磁盘，只需初始化 Chroma 客户端并传入目标存储目录即可。

注意：Chroma 会尽力自动将数据保存到磁盘，但多个内存中的客户端可能互相覆盖数据。最佳实践是同一路径下始终只运行一个客户端实例。

In [ ]:

# save to disk

db = chromadb.PersistentClient(path="./chroma_db")
chroma_collection = db.get_or_create_collection("quickstart")
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
storage_context = StorageContext.from_defaults(vector_store=vector_store)

index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context, embed_model=embed_model
)

# load from disk
db2 = chromadb.PersistentClient(path="./chroma_db")
chroma_collection = db2.get_or_create_collection("quickstart")
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
index = VectorStoreIndex.from_vector_store(
    vector_store,
    embed_model=embed_model,
)

# Query Data from the persisted index
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
display(Markdown(f"<b>{response}</b>"))

# save to disk db = chromadb.PersistentClient(path="./chroma_db") chroma_collection = db.get_or_create_collection("quickstart") vector_store = ChromaVectorStore(chroma_collection=chroma_collection) storage_context = StorageContext.from_defaults(vector_store=vector_store) index = VectorStoreIndex.from_documents( documents, storage_context=storage_context, embed_model=embed_model ) # load from disk db2 = chromadb.PersistentClient(path="./chroma_db") chroma_collection = db2.get_or_create_collection("quickstart") vector_store = ChromaVectorStore(chroma_collection=chroma_collection) index = VectorStoreIndex.from_vector_store( vector_store, embed_model=embed_model, ) # Query Data from the persisted index query_engine = index.as_query_engine() response = query_engine.query("What did the author do growing up?") display(Markdown(f"{response}"))

The author worked on writing and programming growing up. They wrote short stories and tried writing programs on an IBM 1401 computer. Later, they got a microcomputer and started programming games and a word processor.

基础示例（使用 Docker 容器）¶

您也可以单独在 Docker 容器中运行 Chroma 服务端，创建一个客户端与之连接，然后将其传递给 LlamaIndex。

以下是克隆、构建和运行 Docker 镜像的方法：

git clone git@github.com:chroma-core/chroma.git
docker-compose up -d --build

In [ ]:

# create the chroma client and add our data
import chromadb

remote_db = chromadb.HttpClient()
chroma_collection = remote_db.get_or_create_collection("quickstart")
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
storage_context = StorageContext.from_defaults(vector_store=vector_store)

index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context, embed_model=embed_model
)

# create the chroma client and add our data import chromadb remote_db = chromadb.HttpClient() chroma_collection = remote_db.get_or_create_collection("quickstart") vector_store = ChromaVectorStore(chroma_collection=chroma_collection) storage_context = StorageContext.from_defaults(vector_store=vector_store) index = VectorStoreIndex.from_documents( documents, storage_context=storage_context, embed_model=embed_model )

In [ ]:

# Query Data from the Chroma Docker index
query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
display(Markdown(f"<b>{response}</b>"))

# Query Data from the Chroma Docker index query_engine = index.as_query_engine() response = query_engine.query("What did the author do growing up?") display(Markdown(f"{response}"))

Growing up, the author wrote short stories, programmed on an IBM 1401, and wrote programs on a TRS-80 microcomputer. He also took painting classes at Harvard and worked as a de facto studio assistant for a painter. He also tried to start a company to put art galleries online, and wrote software to build online stores.

更新与删除¶

在构建实际应用的过程中，除了添加数据外，您还需要更新和删除数据。

Chroma 要求用户提供 ids 以简化此处的记录工作。ids 可以是文件名，也可以是组合哈希值如 filename_paragraphNumber 等。

以下是一个展示各种操作的基础示例：

In [ ]:

doc_to_update = chroma_collection.get(limit=1)
doc_to_update["metadatas"][0] = {
    **doc_to_update["metadatas"][0],
    **{"author": "Paul Graham"},
}
chroma_collection.update(
    ids=[doc_to_update["ids"][0]], metadatas=[doc_to_update["metadatas"][0]]
)
updated_doc = chroma_collection.get(limit=1)
print(updated_doc["metadatas"][0])

# delete the last document
print("count before", chroma_collection.count())
chroma_collection.delete(ids=[doc_to_update["ids"][0]])
print("count after", chroma_collection.count())

doc_to_update = chroma_collection.get(limit=1) doc_to_update["metadatas"][0] = { **doc_to_update["metadatas"][0], **{"author": "Paul Graham"}, } chroma_collection.update( ids=[doc_to_update["ids"][0]], metadatas=[doc_to_update["metadatas"][0]] ) updated_doc = chroma_collection.get(limit=1) print(updated_doc["metadatas"][0]) # delete the last document print("count before", chroma_collection.count()) chroma_collection.delete(ids=[doc_to_update["ids"][0]]) print("count after", chroma_collection.count())

{'_node_content': '{"id_": "be08c8bc-f43e-4a71-ba64-e525921a8319", "embedding": null, "metadata": {}, "excluded_embed_metadata_keys": [], "excluded_llm_metadata_keys": [], "relationships": {"1": {"node_id": "2cbecdbb-0840-48b2-8151-00119da0995b", "node_type": null, "metadata": {}, "hash": "4c702b4df575421e1d1af4b1fd50511b226e0c9863dbfffeccb8b689b8448f35"}, "3": {"node_id": "6a75604a-fa76-4193-8f52-c72a7b18b154", "node_type": null, "metadata": {}, "hash": "d6c408ee1fbca650fb669214e6f32ffe363b658201d31c204e85a72edb71772f"}}, "hash": "b4d0b960aa09e693f9dc0d50ef46a3d0bf5a8fb3ac9f3e4bcf438e326d17e0d8", "text": "", "start_char_idx": 0, "end_char_idx": 4050, "text_template": "{metadata_str}\\n\\n{content}", "metadata_template": "{key}: {value}", "metadata_seperator": "\\n"}', 'author': 'Paul Graham', 'doc_id': '2cbecdbb-0840-48b2-8151-00119da0995b', 'document_id': '2cbecdbb-0840-48b2-8151-00119da0995b', 'ref_doc_id': '2cbecdbb-0840-48b2-8151-00119da0995b'}
count before 20
count after 19