Skip to main content
Open In ColabOpen on GitHub

Galaxia 检索器

Galaxia 是 GraphRAG 解决方案，可以自动化文档处理、知识库（Graph 语言模型）创建和检索：galaxia-rag

要使用Galaxia，请先上传文本并在此处创建图语言模型：smabbler-cloud

在模型构建并激活后，您将能够使用此集成来检索所需的内容。

The module repository is located here: github

集成细节​

检索器Self-host云开发解决方案包
Galaxia Retriever❌✅langchain-galaxia-retriever

设置​

在您能够获取任何内容之前，您需要在这里创建您的图语言模型：smabbler-cloud

按照以下3个简单的步骤： rag-指令

记得在构建模型后激活它！

安装​

retriever 是在以下包中实现的：pypi

%pip install -qU langchain-galaxia-retriever

Instantiation​

from langchain_galaxia_retriever.retriever import GalaxiaRetriever

gr = GalaxiaRetriever(
    api_url="beta.api.smabbler.com",
    api_key="<key>",  # you can find it here: https://beta.cloud.smabbler.com/user/account
    knowledge_base_id="<knowledge_base_id>",  # you can find it in https://beta.cloud.smabbler.com , in the model table
    n_retries=10,
    wait_time=5,
)

用法​

result = gr.invoke("<test question>")
print(result)

使用在链中​

from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough

prompt = ChatPromptTemplate.from_template(
    """Answer the question based only on the context provided.

Context: {context}

Question: {question}"""
)


def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)


chain = (
    {"context": gr | format_docs, "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)
chain.invoke("<test question>")

API 参考​

有关 Galaxia Retriever 的更多信息，请在 GitHub 上查看其实现 GitHub