mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-08 08:38:48 +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()
```
97 lines
3.3 KiB
Python
97 lines
3.3 KiB
Python
"""Util that calls Outline."""
|
|
|
|
import logging
|
|
from typing import Any, Dict, List, Optional
|
|
|
|
import requests
|
|
from langchain_core.documents import Document
|
|
from langchain_core.pydantic_v1 import BaseModel, root_validator
|
|
from langchain_core.utils import get_from_dict_or_env
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
OUTLINE_MAX_QUERY_LENGTH = 300
|
|
|
|
|
|
class OutlineAPIWrapper(BaseModel):
|
|
"""Wrapper around OutlineAPI.
|
|
|
|
This wrapper will use the Outline API to query the documents of your instance.
|
|
By default it will return the document content of the top-k results.
|
|
It limits the document content by doc_content_chars_max.
|
|
"""
|
|
|
|
top_k_results: int = 3
|
|
load_all_available_meta: bool = False
|
|
doc_content_chars_max: int = 4000
|
|
outline_instance_url: Optional[str] = None
|
|
outline_api_key: Optional[str] = None
|
|
outline_search_endpoint: str = "/api/documents.search"
|
|
|
|
@root_validator(pre=True)
|
|
def validate_environment(cls, values: Dict) -> Dict:
|
|
"""Validate that instance url and api key exists in environment."""
|
|
outline_instance_url = get_from_dict_or_env(
|
|
values, "outline_instance_url", "OUTLINE_INSTANCE_URL"
|
|
)
|
|
values["outline_instance_url"] = outline_instance_url
|
|
|
|
outline_api_key = get_from_dict_or_env(
|
|
values, "outline_api_key", "OUTLINE_API_KEY"
|
|
)
|
|
values["outline_api_key"] = outline_api_key
|
|
|
|
return values
|
|
|
|
def _result_to_document(self, outline_res: Any) -> Document:
|
|
main_meta = {
|
|
"title": outline_res["document"]["title"],
|
|
"source": self.outline_instance_url + outline_res["document"]["url"],
|
|
}
|
|
add_meta = (
|
|
{
|
|
"id": outline_res["document"]["id"],
|
|
"ranking": outline_res["ranking"],
|
|
"collection_id": outline_res["document"]["collectionId"],
|
|
"parent_document_id": outline_res["document"]["parentDocumentId"],
|
|
"revision": outline_res["document"]["revision"],
|
|
"created_by": outline_res["document"]["createdBy"]["name"],
|
|
}
|
|
if self.load_all_available_meta
|
|
else {}
|
|
)
|
|
doc = Document(
|
|
page_content=outline_res["document"]["text"][: self.doc_content_chars_max],
|
|
metadata={
|
|
**main_meta,
|
|
**add_meta,
|
|
},
|
|
)
|
|
return doc
|
|
|
|
def _outline_api_query(self, query: str) -> List:
|
|
raw_result = requests.post(
|
|
f"{self.outline_instance_url}{self.outline_search_endpoint}",
|
|
data={"query": query, "limit": self.top_k_results},
|
|
headers={"Authorization": f"Bearer {self.outline_api_key}"},
|
|
)
|
|
|
|
if not raw_result.ok:
|
|
raise ValueError("Outline API returned an error: ", raw_result.text)
|
|
|
|
return raw_result.json()["data"]
|
|
|
|
def run(self, query: str) -> List[Document]:
|
|
"""
|
|
Run Outline search and get the document content plus the meta information.
|
|
|
|
Returns: a list of documents.
|
|
|
|
"""
|
|
results = self._outline_api_query(query[:OUTLINE_MAX_QUERY_LENGTH])
|
|
docs = []
|
|
for result in results[: self.top_k_results]:
|
|
if doc := self._result_to_document(result):
|
|
docs.append(doc)
|
|
return docs
|