Spaces:
Runtime error
Runtime error
File size: 3,710 Bytes
129cd69 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 |
"""Question answering over a graph."""
from __future__ import annotations
from typing import Any, Dict, List, Optional
from langchain_core.language_models import BaseLanguageModel
from langchain_core.prompts import BasePromptTemplate
from langchain_core.pydantic_v1 import Field
from langchain.callbacks.manager import CallbackManagerForChainRun
from langchain.chains.base import Chain
from langchain.chains.graph_qa.prompts import (
CYPHER_QA_PROMPT,
GREMLIN_GENERATION_PROMPT,
)
from langchain.chains.llm import LLMChain
from langchain.graphs.hugegraph import HugeGraph
class HugeGraphQAChain(Chain):
"""Chain for question-answering against a graph by generating gremlin statements.
*Security note*: Make sure that the database connection uses credentials
that are narrowly-scoped to only include necessary permissions.
Failure to do so may result in data corruption or loss, since the calling
code may attempt commands that would result in deletion, mutation
of data if appropriately prompted or reading sensitive data if such
data is present in the database.
The best way to guard against such negative outcomes is to (as appropriate)
limit the permissions granted to the credentials used with this tool.
See https://python.langchain.com/docs/security for more information.
"""
graph: HugeGraph = Field(exclude=True)
gremlin_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]:
"""Input keys.
:meta private:
"""
return [self.input_key]
@property
def output_keys(self) -> List[str]:
"""Output keys.
:meta private:
"""
_output_keys = [self.output_key]
return _output_keys
@classmethod
def from_llm(
cls,
llm: BaseLanguageModel,
*,
qa_prompt: BasePromptTemplate = CYPHER_QA_PROMPT,
gremlin_prompt: BasePromptTemplate = GREMLIN_GENERATION_PROMPT,
**kwargs: Any,
) -> HugeGraphQAChain:
"""Initialize from LLM."""
qa_chain = LLMChain(llm=llm, prompt=qa_prompt)
gremlin_generation_chain = LLMChain(llm=llm, prompt=gremlin_prompt)
return cls(
qa_chain=qa_chain,
gremlin_generation_chain=gremlin_generation_chain,
**kwargs,
)
def _call(
self,
inputs: Dict[str, Any],
run_manager: Optional[CallbackManagerForChainRun] = None,
) -> Dict[str, str]:
"""Generate gremlin statement, use it to look up in db and answer question."""
_run_manager = run_manager or CallbackManagerForChainRun.get_noop_manager()
callbacks = _run_manager.get_child()
question = inputs[self.input_key]
generated_gremlin = self.gremlin_generation_chain.run(
{"question": question, "schema": self.graph.get_schema}, callbacks=callbacks
)
_run_manager.on_text("Generated gremlin:", end="\n", verbose=self.verbose)
_run_manager.on_text(
generated_gremlin, color="green", end="\n", verbose=self.verbose
)
context = self.graph.query(generated_gremlin)
_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]}
|