openGauss 向量数据库

docker run --name opengauss \
  -d \
  -e GS_PASSWORD='MyStrongPass@123' \
  -p 8888:5432 \
  opengauss/opengauss-server:latest

pip install langchain-opengauss

from langchain_opengauss import OpenGauss, OpenGaussSettings

# Configure with schema validation
config = OpenGaussSettings(
    table_name="test_langchain",
    embedding_dimension=384,
    index_type="HNSW",
    distance_strategy="COSINE",
)
vector_store = OpenGauss(embedding=embeddings, config=config)

from langchain_core.documents import Document

document_1 = Document(page_content="foo", metadata={"source": "https://example.com"})

document_2 = Document(page_content="bar", metadata={"source": "https://example.com"})

document_3 = Document(page_content="baz", metadata={"source": "https://example.com"})

documents = [document_1, document_2, document_3]

vector_store.add_documents(documents=documents, ids=["1", "2", "3"])

updated_document = Document(
    page_content="qux", metadata={"source": "https://another-example.com"}
)

# If the id is already exist, will update the document
vector_store.add_documents(document_id="1", document=updated_document)

vector_store.delete(ids=["3"])

results = vector_store.similarity_search(
    query="thud", k=1, filter={"source": "https://another-example.com"}
)
for doc in results:
    print(f"* {doc.page_content} [{doc.metadata}]")

results = vector_store.similarity_search_with_score(
    query="thud", k=1, filter={"source": "https://example.com"}
)
for doc, score in results:
    print(f"* [SIM={score:3f}] {doc.page_content} [{doc.metadata}]")

retriever = vector_store.as_retriever(search_type="mmr", search_kwargs={"k": 1})
retriever.invoke("thud")

import math

lists = min(
    int(math.sqrt(total_rows)) if total_rows > 1e6 else int(total_rows / 1000),
    2000,  # openGauss maximum
)

OpenGaussSettings(min_connections=3, max_connections=20)