Source code for langchain_community.chains.graph_qa.nebulagraph

"""在图上的问答。"""
from __future__ import annotations

from typing import Any, Dict, List, Optional

from langchain.chains.base import Chain
from langchain.chains.llm import LLMChain
from langchain_core.callbacks import CallbackManagerForChainRun
from langchain_core.language_models import BaseLanguageModel
from langchain_core.prompts import BasePromptTemplate
from langchain_core.pydantic_v1 import Field

from langchain_community.chains.graph_qa.prompts import (
    CYPHER_QA_PROMPT,
    NGQL_GENERATION_PROMPT,
)
from langchain_community.graphs.nebula_graph import NebulaGraph


class NebulaGraphQAChain(Chain):
    """用于通过生成nGQL语句针对图进行问答的链。

    *安全提示*: 确保数据库连接使用的凭据范围狭窄，仅包括必要的权限。
        如果未这样做，可能会导致数据损坏或丢失，因为调用代码可能尝试执行会导致删除、变异数据（如果适当提示）或读取敏感数据（如果数据库中存在此类数据）的命令。
        防范这些负面结果的最佳方法是（根据需要）限制授予此工具使用的凭据的权限。

        有关更多信息，请参阅 https://python.langchain.com/docs/security。"""

    graph: NebulaGraph = Field(exclude=True)
    ngql_generation_chain: LLMChain
    qa_chain: LLMChain
    input_key: str = "query"  #: :meta private:
    output_key: str = "result"  #: :meta private:

    @property
    def input_keys(self) -> List[str]:
        """返回输入的键。

:元数据 私有:
"""
        return [self.input_key]

    @property
    def output_keys(self) -> List[str]:
        """返回输出键。

:元数据 私有:
"""
        _output_keys = [self.output_key]
        return _output_keys

    @classmethod
    def from_llm(
        cls,
        llm: BaseLanguageModel,
        *,
        qa_prompt: BasePromptTemplate = CYPHER_QA_PROMPT,
        ngql_prompt: BasePromptTemplate = NGQL_GENERATION_PROMPT,
        **kwargs: Any,
    ) -> NebulaGraphQAChain:
        """从LLM初始化。"""
        qa_chain = LLMChain(llm=llm, prompt=qa_prompt)
        ngql_generation_chain = LLMChain(llm=llm, prompt=ngql_prompt)

        return cls(
            qa_chain=qa_chain,
            ngql_generation_chain=ngql_generation_chain,
            **kwargs,
        )

    def _call(
        self,
        inputs: Dict[str, Any],
        run_manager: Optional[CallbackManagerForChainRun] = None,
    ) -> Dict[str, str]:
        """生成nGQL语句，使用它在数据库中查找并回答问题。"""
        _run_manager = run_manager or CallbackManagerForChainRun.get_noop_manager()
        callbacks = _run_manager.get_child()
        question = inputs[self.input_key]

        generated_ngql = self.ngql_generation_chain.run(
            {"question": question, "schema": self.graph.get_schema}, callbacks=callbacks
        )

        _run_manager.on_text("Generated nGQL:", end="\n", verbose=self.verbose)
        _run_manager.on_text(
            generated_ngql, color="green", end="\n", verbose=self.verbose
        )
        context = self.graph.query(generated_ngql)

        _run_manager.on_text("Full Context:", end="\n", verbose=self.verbose)
        _run_manager.on_text(
            str(context), color="green", end="\n", verbose=self.verbose
        )

        result = self.qa_chain(
            {"question": question, "context": context},
            callbacks=callbacks,
        )
        return {self.output_key: result[self.qa_chain.output_key]}