9.1. 常用¶

Faiss: Faiss 是一个Facebook开发的开源向量索引库，它提供了一些非常快速和高效的近似最近邻搜索算法。虽然它本身不是一个数据库系统，但可以与其他数据库集成，以支持向量检索。
Weaviate: https://weaviate.io/
Annoy: Annoy 是一个小巧而快速的库，专门用于近似最近邻搜索。虽然它不是一个数据库，但你可以将其用于构建自定义向量索引。
Pinecone: https://www.pinecone.io/
- Langchain AI Handbook: https://www.pinecone.io/learn/langchain/

9.1.1. Chroma¶

Chroma(Chroma is the open-source embedding database. Chroma makes it easy to build LLM apps by making knowledge, facts, and skills pluggable for LLMs): https://docs.trychroma.com/

quickstart:

# 1. Install
pip install chromadb

# 2. Get the Chroma Client
import chromadb
chroma_client = chromadb.Client()

# 3. Create a collection
collection = chroma_client.create_collection(name="my_collection")

# 4. Add some text documents to the collection
collection.add(
    documents=["This is a document", "This is another document"],
    metadatas=[{"source": "my_source"}, {"source": "my_source"}],
    ids=["id1", "id2"]
)
# or
collection.add(
    embeddings=[[1.2, 2.3, 4.5], [6.7, 8.2, 9.2]],
    documents=["This is a document", "This is another document"],
    metadatas=[{"source": "my_source"}, {"source": "my_source"}],
    ids=["id1", "id2"]
)

# 5. Query the collection
results = collection.query(
    query_texts=["This is a query document"],
    n_results=2
)