Bagatur
a0c2281540
infra: update mypy 1.10, ruff 0.5 ( #23721 )
...
```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()
```
2024-07-03 10:33:27 -07:00
Luis Antonio Vieira Junior
67c880af74
community[patch]: adding linearization config to AmazonTextractPDFLoader ( #17489 )
...
- **Description:** Adding an optional parameter `linearization_config`
to the `AmazonTextractPDFLoader` so the caller can define how the output
will be linearized, instead of forcing a predefined set of linearization
configs. It will still have a default configuration as this will be an
optional parameter.
- **Issue:** #17457
- **Dependencies:** The same ones that already exist for
`AmazonTextractPDFLoader`
- **Twitter handle:** [@lvieirajr19](https://twitter.com/lvieirajr19 )
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-03-08 17:25:22 -08:00
Bagatur
fa5d49f2c1
docs, experimental[patch], langchain[patch], community[patch]: update storage imports ( #15429 )
...
ran
```bash
g grep -l "langchain.vectorstores" | xargs -L 1 sed -i '' "s/langchain\.vectorstores/langchain_community.vectorstores/g"
g grep -l "langchain.document_loaders" | xargs -L 1 sed -i '' "s/langchain\.document_loaders/langchain_community.document_loaders/g"
g grep -l "langchain.chat_loaders" | xargs -L 1 sed -i '' "s/langchain\.chat_loaders/langchain_community.chat_loaders/g"
g grep -l "langchain.document_transformers" | xargs -L 1 sed -i '' "s/langchain\.document_transformers/langchain_community.document_transformers/g"
g grep -l "langchain\.graphs" | xargs -L 1 sed -i '' "s/langchain\.graphs/langchain_community.graphs/g"
g grep -l "langchain\.memory\.chat_message_histories" | xargs -L 1 sed -i '' "s/langchain\.memory\.chat_message_histories/langchain_community.chat_message_histories/g"
gco master libs/langchain/tests/unit_tests/*/test_imports.py
gco master libs/langchain/tests/unit_tests/**/test_public_api.py
```
2024-01-02 16:47:11 -05:00
Bagatur
ed58eeb9c5
community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community ( #14463 )
...
Moved the following modules to new package langchain-community in a backwards compatible fashion:
```
mv langchain/langchain/adapters community/langchain_community
mv langchain/langchain/callbacks community/langchain_community/callbacks
mv langchain/langchain/chat_loaders community/langchain_community
mv langchain/langchain/chat_models community/langchain_community
mv langchain/langchain/document_loaders community/langchain_community
mv langchain/langchain/docstore community/langchain_community
mv langchain/langchain/document_transformers community/langchain_community
mv langchain/langchain/embeddings community/langchain_community
mv langchain/langchain/graphs community/langchain_community
mv langchain/langchain/llms community/langchain_community
mv langchain/langchain/memory/chat_message_histories community/langchain_community
mv langchain/langchain/retrievers community/langchain_community
mv langchain/langchain/storage community/langchain_community
mv langchain/langchain/tools community/langchain_community
mv langchain/langchain/utilities community/langchain_community
mv langchain/langchain/vectorstores community/langchain_community
mv langchain/langchain/agents/agent_toolkits community/langchain_community
mv langchain/langchain/cache.py community/langchain_community
mv langchain/langchain/adapters community/langchain_community
mv langchain/langchain/callbacks community/langchain_community/callbacks
mv langchain/langchain/chat_loaders community/langchain_community
mv langchain/langchain/chat_models community/langchain_community
mv langchain/langchain/document_loaders community/langchain_community
mv langchain/langchain/docstore community/langchain_community
mv langchain/langchain/document_transformers community/langchain_community
mv langchain/langchain/embeddings community/langchain_community
mv langchain/langchain/graphs community/langchain_community
mv langchain/langchain/llms community/langchain_community
mv langchain/langchain/memory/chat_message_histories community/langchain_community
mv langchain/langchain/retrievers community/langchain_community
mv langchain/langchain/storage community/langchain_community
mv langchain/langchain/tools community/langchain_community
mv langchain/langchain/utilities community/langchain_community
mv langchain/langchain/vectorstores community/langchain_community
mv langchain/langchain/agents/agent_toolkits community/langchain_community
mv langchain/langchain/cache.py community/langchain_community
```
Moved the following to core
```
mv langchain/langchain/utils/json_schema.py core/langchain_core/utils
mv langchain/langchain/utils/html.py core/langchain_core/utils
mv langchain/langchain/utils/strings.py core/langchain_core/utils
cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py
rm langchain/langchain/utils/env.py
```
See .scripts/community_split/script_integrations.sh for all changes
2023-12-11 13:53:30 -08:00
