mirror of
https://github.com/hwchase17/langchain.git
synced 2025-04-27 11:41:51 +00:00
a0c2281540
```python
"""python scripts/update_mypy_ruff.py"""
import glob
import tomllib
from pathlib import Path
import toml
import subprocess
import re
ROOT_DIR = Path(__file__).parents[1]
def main():
for path in glob.glob(str(ROOT_DIR / "libs/**/pyproject.toml"), recursive=True):
print(path)
with open(path, "rb") as f:
pyproject = tomllib.load(f)
try:
pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = (
"^1.10"
)
pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = (
"^0.5"
)
except KeyError:
continue
with open(path, "w") as f:
toml.dump(pyproject, f)
cwd = "/".join(path.split("/")[:-1])
completed = subprocess.run(
"poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color",
cwd=cwd,
shell=True,
capture_output=True,
text=True,
)
logs = completed.stdout.split("\n")
to_ignore = {}
for l in logs:
if re.match("^(.*)\:(\d+)\: error:.*\[(.*)\]", l):
path, line_no, error_type = re.match(
"^(.*)\:(\d+)\: error:.*\[(.*)\]", l
).groups()
if (path, line_no) in to_ignore:
to_ignore[(path, line_no)].append(error_type)
else:
to_ignore[(path, line_no)] = [error_type]
print(len(to_ignore))
for (error_path, line_no), error_types in to_ignore.items():
all_errors = ", ".join(error_types)
full_path = f"{cwd}/{error_path}"
try:
with open(full_path, "r") as f:
file_lines = f.readlines()
except FileNotFoundError:
continue
file_lines[int(line_no) - 1] = (
file_lines[int(line_no) - 1][:-1] + f" # type: ignore[{all_errors}]\n"
)
with open(full_path, "w") as f:
f.write("".join(file_lines))
subprocess.run(
"poetry run ruff format .; poetry run ruff --select I --fix .",
cwd=cwd,
shell=True,
capture_output=True,
text=True,
)
if __name__ == "__main__":
main()
```
108 lines
3.6 KiB
Python
108 lines
3.6 KiB
Python
"""Question answering over a graph."""
|
|
|
|
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,
|
|
GREMLIN_GENERATION_PROMPT,
|
|
)
|
|
from langchain_community.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]}
|