Chroma¶

Chroma 是一个以人工智能为基础的开源向量数据库，专注于开发者的生产力和幸福感。Chroma 使用 Apache 2.0 许可证。

Chroma 是完全类型化、经过充分测试和充分文档化的。

使用以下命令安装 Chroma：

pip install chromadb

Chroma 可以以各种模式运行。请参见下面的示例，每个示例都与 LangChain 集成。

in-memory - 在 Python 脚本或 Jupyter 笔记本中
in-memory with persistance - 在脚本或笔记本中，并保存/加载到磁盘
在 Docker 容器中 - 作为在本地计算机或云中运行的服务器

与任何其他数据库一样，您可以：

.add
.get
.update
.upsert
.delete
.peek
和 .query 运行相似性搜索。

在文档中查看完整文档。

基本示例¶

在这个基本示例中，我们将保罗·格雷厄姆的文章分成片段，使用开源嵌入模型进行嵌入，将其加载到 Chroma 中，然后进行查询。

如果您在colab上打开这个笔记本，您可能需要安装LlamaIndex 🦙。

In [ ]:

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

In [ ]:

!pip install llama-index

创建色度指数¶

In [ ]:

# !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

In [ ]:

# 设置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'

In [ ]:

# 创建客户端和新的集合
chroma_client = chromadb.EphemeralClient()
chroma_collection = chroma_client.create_collection("quickstart")

# 定义嵌入函数
embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-base-en-v1.5")

# 加载文档
documents = SimpleDirectoryReader("./data/paul_graham/").load_data()

# 设置ChromaVectorStore并加载数据
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
)

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

/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.

基本示例（包括保存到磁盘）¶

在扩展前面的示例时，如果你想要保存到磁盘，只需初始化Chroma客户端并传递要保存数据的目录即可。

注意：Chroma会尽最大努力自动将数据保存到磁盘，但是多个内存中的客户端可能会互相干扰彼此的工作。作为最佳实践，任何时候只能有一个客户端在运行指定的路径下。

In [ ]:

# 保存到磁盘

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
)

# 从磁盘加载

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,
)

# 从持久化索引查询数据
query_engine = index.as_query_engine()
response = query_engine.query("作者在成长过程中做了什么？")
display(Markdown(f"<b>{response}</b>"))

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.

基本示例（使用Docker容器）¶

您还可以在单独的Docker容器中运行Chroma服务器，创建一个客户端来连接它，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 [ ]:

# 创建chroma客户端并添加我们的数据
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 [ ]:

# 从Chroma Docker索引中查询数据
query_engine = index.as_query_engine()
response = query_engine.query("作者在成长过程中做了什么？")
display(Markdown(f"<b>{response}</b>"))

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.

更新和删除¶

在构建真实应用程序时，您希望不仅仅是添加数据，还要能够更新和删除数据。

Chroma要求用户提供ids来简化这里的簿记工作。ids可以是文件名，也可以是类似于filename_paragraphNumber的组合哈希值。

下面是一个基本示例，展示了如何进行各种操作：

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])

# 删除最后一个文档
print("删除前计数", chroma_collection.count())
chroma_collection.delete(ids=[doc_to_update["ids"][0]])
print("删除后计数", 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