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 17:33:27 +00:00
[ build-system ]
requires = [ "poetry-core>=1.0.0" , ]
build-backend = "poetry.core.masonry.api"
mongodb[minor]: MongoDB Partner Package -- Porting MongoDBAtlasVectorSearch (#17652)
This PR migrates the existing MongoDBAtlasVectorSearch abstraction from
the `langchain_community` section to the partners package section of the
codebase.
- [x] Run the partner package script as advised in the partner-packages
documentation.
- [x] Add Unit Tests
- [x] Migrate Integration Tests
- [x] Refactor `MongoDBAtlasVectorStore` (autogenerated) to
`MongoDBAtlasVectorSearch`
- [x] ~Remove~ deprecate the old `langchain_community` VectorStore
references.
## Additional Callouts
- Implemented the `delete` method
- Included any missing async function implementations
- `amax_marginal_relevance_search_by_vector`
- `adelete`
- Added new Unit Tests that test for functionality of
`MongoDBVectorSearch` methods
- Removed [`del
res[self._embedding_key]`](https://github.com/langchain-ai/langchain/blob/e0c81e1cb0ede673a69aae6434e17e34868c3bcc/libs/community/langchain_community/vectorstores/mongodb_atlas.py#L218)
in `_similarity_search_with_score` function as it would make the
`maximal_marginal_relevance` function fail otherwise. The `Document`
needs to store the embedding key in metadata to work.
Checklist:
- [x] PR title: Please title your PR "package: description", where
"package" is whichever of langchain, community, core, experimental, etc.
is being modified. Use "docs: ..." for purely docs changes, "templates:
..." for template changes, "infra: ..." for CI changes.
- Example: "community: add foobar LLM"
- [x] PR message
- [x] Pass lint and test: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified to check that you're
passing lint and testing. See contribution guidelines for more
information on how to write/run tests, lint, etc:
https://python.langchain.com/docs/contributing/
- [x] Add tests and docs: If you're adding a new integration, please
include
1. Existing tests supplied in docs/docs do not change. Updated
docstrings for new functions like `delete`
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory. (This already exists)
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Steven Silvester <steven.silvester@ieee.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-29 23:09:48 +00:00
[ tool . poetry ]
name = "langchain-mongodb"
2024-08-07 20:10:29 +00:00
version = "0.1.8"
mongodb[minor]: MongoDB Partner Package -- Porting MongoDBAtlasVectorSearch (#17652)
This PR migrates the existing MongoDBAtlasVectorSearch abstraction from
the `langchain_community` section to the partners package section of the
codebase.
- [x] Run the partner package script as advised in the partner-packages
documentation.
- [x] Add Unit Tests
- [x] Migrate Integration Tests
- [x] Refactor `MongoDBAtlasVectorStore` (autogenerated) to
`MongoDBAtlasVectorSearch`
- [x] ~Remove~ deprecate the old `langchain_community` VectorStore
references.
## Additional Callouts
- Implemented the `delete` method
- Included any missing async function implementations
- `amax_marginal_relevance_search_by_vector`
- `adelete`
- Added new Unit Tests that test for functionality of
`MongoDBVectorSearch` methods
- Removed [`del
res[self._embedding_key]`](https://github.com/langchain-ai/langchain/blob/e0c81e1cb0ede673a69aae6434e17e34868c3bcc/libs/community/langchain_community/vectorstores/mongodb_atlas.py#L218)
in `_similarity_search_with_score` function as it would make the
`maximal_marginal_relevance` function fail otherwise. The `Document`
needs to store the embedding key in metadata to work.
Checklist:
- [x] PR title: Please title your PR "package: description", where
"package" is whichever of langchain, community, core, experimental, etc.
is being modified. Use "docs: ..." for purely docs changes, "templates:
..." for template changes, "infra: ..." for CI changes.
- Example: "community: add foobar LLM"
- [x] PR message
- [x] Pass lint and test: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified to check that you're
passing lint and testing. See contribution guidelines for more
information on how to write/run tests, lint, etc:
https://python.langchain.com/docs/contributing/
- [x] Add tests and docs: If you're adding a new integration, please
include
1. Existing tests supplied in docs/docs do not change. Updated
docstrings for new functions like `delete`
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory. (This already exists)
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Steven Silvester <steven.silvester@ieee.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-29 23:09:48 +00:00
description = "An integration package connecting MongoDB and LangChain"
authors = [ ]
readme = "README.md"
repository = "https://github.com/langchain-ai/langchain"
license = "MIT"
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 17:33:27 +00:00
[ tool . mypy ]
disallow_untyped_defs = "True"
mongodb[minor]: MongoDB Partner Package -- Porting MongoDBAtlasVectorSearch (#17652)
This PR migrates the existing MongoDBAtlasVectorSearch abstraction from
the `langchain_community` section to the partners package section of the
codebase.
- [x] Run the partner package script as advised in the partner-packages
documentation.
- [x] Add Unit Tests
- [x] Migrate Integration Tests
- [x] Refactor `MongoDBAtlasVectorStore` (autogenerated) to
`MongoDBAtlasVectorSearch`
- [x] ~Remove~ deprecate the old `langchain_community` VectorStore
references.
## Additional Callouts
- Implemented the `delete` method
- Included any missing async function implementations
- `amax_marginal_relevance_search_by_vector`
- `adelete`
- Added new Unit Tests that test for functionality of
`MongoDBVectorSearch` methods
- Removed [`del
res[self._embedding_key]`](https://github.com/langchain-ai/langchain/blob/e0c81e1cb0ede673a69aae6434e17e34868c3bcc/libs/community/langchain_community/vectorstores/mongodb_atlas.py#L218)
in `_similarity_search_with_score` function as it would make the
`maximal_marginal_relevance` function fail otherwise. The `Document`
needs to store the embedding key in metadata to work.
Checklist:
- [x] PR title: Please title your PR "package: description", where
"package" is whichever of langchain, community, core, experimental, etc.
is being modified. Use "docs: ..." for purely docs changes, "templates:
..." for template changes, "infra: ..." for CI changes.
- Example: "community: add foobar LLM"
- [x] PR message
- [x] Pass lint and test: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified to check that you're
passing lint and testing. See contribution guidelines for more
information on how to write/run tests, lint, etc:
https://python.langchain.com/docs/contributing/
- [x] Add tests and docs: If you're adding a new integration, please
include
1. Existing tests supplied in docs/docs do not change. Updated
docstrings for new functions like `delete`
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory. (This already exists)
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Steven Silvester <steven.silvester@ieee.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-29 23:09:48 +00:00
[ tool . poetry . urls ]
"Source Code" = "https://github.com/langchain-ai/langchain/tree/master/libs/partners/mongodb"
2024-07-22 20:59:13 +00:00
"Release Notes" = "https://github.com/langchain-ai/langchain/releases?q=tag%3A%22langchain-mongodb%3D%3D0%22&expanded=true"
mongodb[minor]: MongoDB Partner Package -- Porting MongoDBAtlasVectorSearch (#17652)
This PR migrates the existing MongoDBAtlasVectorSearch abstraction from
the `langchain_community` section to the partners package section of the
codebase.
- [x] Run the partner package script as advised in the partner-packages
documentation.
- [x] Add Unit Tests
- [x] Migrate Integration Tests
- [x] Refactor `MongoDBAtlasVectorStore` (autogenerated) to
`MongoDBAtlasVectorSearch`
- [x] ~Remove~ deprecate the old `langchain_community` VectorStore
references.
## Additional Callouts
- Implemented the `delete` method
- Included any missing async function implementations
- `amax_marginal_relevance_search_by_vector`
- `adelete`
- Added new Unit Tests that test for functionality of
`MongoDBVectorSearch` methods
- Removed [`del
res[self._embedding_key]`](https://github.com/langchain-ai/langchain/blob/e0c81e1cb0ede673a69aae6434e17e34868c3bcc/libs/community/langchain_community/vectorstores/mongodb_atlas.py#L218)
in `_similarity_search_with_score` function as it would make the
`maximal_marginal_relevance` function fail otherwise. The `Document`
needs to store the embedding key in metadata to work.
Checklist:
- [x] PR title: Please title your PR "package: description", where
"package" is whichever of langchain, community, core, experimental, etc.
is being modified. Use "docs: ..." for purely docs changes, "templates:
..." for template changes, "infra: ..." for CI changes.
- Example: "community: add foobar LLM"
- [x] PR message
- [x] Pass lint and test: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified to check that you're
passing lint and testing. See contribution guidelines for more
information on how to write/run tests, lint, etc:
https://python.langchain.com/docs/contributing/
- [x] Add tests and docs: If you're adding a new integration, please
include
1. Existing tests supplied in docs/docs do not change. Updated
docstrings for new functions like `delete`
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory. (This already exists)
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Steven Silvester <steven.silvester@ieee.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-29 23:09:48 +00:00
[ tool . poetry . dependencies ]
python = ">=3.8.1,<4.0"
pymongo = ">=4.6.1,<5.0"
2024-07-18 18:13:27 +00:00
langchain-core = "^0.2.21"
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 17:33:27 +00:00
[ [ tool . poetry . dependencies . numpy ] ]
version = "^1"
python = "<3.12"
[ [ tool . poetry . dependencies . numpy ] ]
version = "^1.26.0"
python = ">=3.12"
[ tool . ruff . lint ]
select = [ "E" , "F" , "I" , ]
[ tool . coverage . run ]
omit = [ "tests/*" , ]
[ tool . pytest . ini_options ]
addopts = "--snapshot-warn-unused --strict-markers --strict-config --durations=5"
markers = [ "requires: mark tests as requiring a specific library" , "asyncio: mark tests as requiring asyncio" , "compile: mark placeholder test used to compile integration tests without running them" , ]
asyncio_mode = "auto"
mongodb[minor]: MongoDB Partner Package -- Porting MongoDBAtlasVectorSearch (#17652)
This PR migrates the existing MongoDBAtlasVectorSearch abstraction from
the `langchain_community` section to the partners package section of the
codebase.
- [x] Run the partner package script as advised in the partner-packages
documentation.
- [x] Add Unit Tests
- [x] Migrate Integration Tests
- [x] Refactor `MongoDBAtlasVectorStore` (autogenerated) to
`MongoDBAtlasVectorSearch`
- [x] ~Remove~ deprecate the old `langchain_community` VectorStore
references.
## Additional Callouts
- Implemented the `delete` method
- Included any missing async function implementations
- `amax_marginal_relevance_search_by_vector`
- `adelete`
- Added new Unit Tests that test for functionality of
`MongoDBVectorSearch` methods
- Removed [`del
res[self._embedding_key]`](https://github.com/langchain-ai/langchain/blob/e0c81e1cb0ede673a69aae6434e17e34868c3bcc/libs/community/langchain_community/vectorstores/mongodb_atlas.py#L218)
in `_similarity_search_with_score` function as it would make the
`maximal_marginal_relevance` function fail otherwise. The `Document`
needs to store the embedding key in metadata to work.
Checklist:
- [x] PR title: Please title your PR "package: description", where
"package" is whichever of langchain, community, core, experimental, etc.
is being modified. Use "docs: ..." for purely docs changes, "templates:
..." for template changes, "infra: ..." for CI changes.
- Example: "community: add foobar LLM"
- [x] PR message
- [x] Pass lint and test: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified to check that you're
passing lint and testing. See contribution guidelines for more
information on how to write/run tests, lint, etc:
https://python.langchain.com/docs/contributing/
- [x] Add tests and docs: If you're adding a new integration, please
include
1. Existing tests supplied in docs/docs do not change. Updated
docstrings for new functions like `delete`
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory. (This already exists)
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Steven Silvester <steven.silvester@ieee.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-29 23:09:48 +00:00
[ tool . poetry . group . test ]
optional = true
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 17:33:27 +00:00
[ tool . poetry . group . codespell ]
optional = true
[ tool . poetry . group . test_integration ]
optional = true
[ tool . poetry . group . lint ]
optional = true
[ tool . poetry . group . dev ]
optional = true
mongodb[minor]: MongoDB Partner Package -- Porting MongoDBAtlasVectorSearch (#17652)
This PR migrates the existing MongoDBAtlasVectorSearch abstraction from
the `langchain_community` section to the partners package section of the
codebase.
- [x] Run the partner package script as advised in the partner-packages
documentation.
- [x] Add Unit Tests
- [x] Migrate Integration Tests
- [x] Refactor `MongoDBAtlasVectorStore` (autogenerated) to
`MongoDBAtlasVectorSearch`
- [x] ~Remove~ deprecate the old `langchain_community` VectorStore
references.
## Additional Callouts
- Implemented the `delete` method
- Included any missing async function implementations
- `amax_marginal_relevance_search_by_vector`
- `adelete`
- Added new Unit Tests that test for functionality of
`MongoDBVectorSearch` methods
- Removed [`del
res[self._embedding_key]`](https://github.com/langchain-ai/langchain/blob/e0c81e1cb0ede673a69aae6434e17e34868c3bcc/libs/community/langchain_community/vectorstores/mongodb_atlas.py#L218)
in `_similarity_search_with_score` function as it would make the
`maximal_marginal_relevance` function fail otherwise. The `Document`
needs to store the embedding key in metadata to work.
Checklist:
- [x] PR title: Please title your PR "package: description", where
"package" is whichever of langchain, community, core, experimental, etc.
is being modified. Use "docs: ..." for purely docs changes, "templates:
..." for template changes, "infra: ..." for CI changes.
- Example: "community: add foobar LLM"
- [x] PR message
- [x] Pass lint and test: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified to check that you're
passing lint and testing. See contribution guidelines for more
information on how to write/run tests, lint, etc:
https://python.langchain.com/docs/contributing/
- [x] Add tests and docs: If you're adding a new integration, please
include
1. Existing tests supplied in docs/docs do not change. Updated
docstrings for new functions like `delete`
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory. (This already exists)
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Steven Silvester <steven.silvester@ieee.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-29 23:09:48 +00:00
[ tool . poetry . group . test . dependencies ]
pytest = "^7.3.0"
freezegun = "^1.2.2"
pytest-mock = "^3.10.0"
syrupy = "^4.0.2"
pytest-watcher = "^0.3.4"
pytest-asyncio = "^0.21.1"
[ tool . poetry . group . codespell . dependencies ]
codespell = "^2.2.0"
2024-08-07 20:10:29 +00:00
[ tool . poetry . group . test_integration . dependencies . langchain-openai ]
path = "../openai"
develop = true
mongodb[minor]: MongoDB Partner Package -- Porting MongoDBAtlasVectorSearch (#17652)
This PR migrates the existing MongoDBAtlasVectorSearch abstraction from
the `langchain_community` section to the partners package section of the
codebase.
- [x] Run the partner package script as advised in the partner-packages
documentation.
- [x] Add Unit Tests
- [x] Migrate Integration Tests
- [x] Refactor `MongoDBAtlasVectorStore` (autogenerated) to
`MongoDBAtlasVectorSearch`
- [x] ~Remove~ deprecate the old `langchain_community` VectorStore
references.
## Additional Callouts
- Implemented the `delete` method
- Included any missing async function implementations
- `amax_marginal_relevance_search_by_vector`
- `adelete`
- Added new Unit Tests that test for functionality of
`MongoDBVectorSearch` methods
- Removed [`del
res[self._embedding_key]`](https://github.com/langchain-ai/langchain/blob/e0c81e1cb0ede673a69aae6434e17e34868c3bcc/libs/community/langchain_community/vectorstores/mongodb_atlas.py#L218)
in `_similarity_search_with_score` function as it would make the
`maximal_marginal_relevance` function fail otherwise. The `Document`
needs to store the embedding key in metadata to work.
Checklist:
- [x] PR title: Please title your PR "package: description", where
"package" is whichever of langchain, community, core, experimental, etc.
is being modified. Use "docs: ..." for purely docs changes, "templates:
..." for template changes, "infra: ..." for CI changes.
- Example: "community: add foobar LLM"
- [x] PR message
- [x] Pass lint and test: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified to check that you're
passing lint and testing. See contribution guidelines for more
information on how to write/run tests, lint, etc:
https://python.langchain.com/docs/contributing/
- [x] Add tests and docs: If you're adding a new integration, please
include
1. Existing tests supplied in docs/docs do not change. Updated
docstrings for new functions like `delete`
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory. (This already exists)
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Steven Silvester <steven.silvester@ieee.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-29 23:09:48 +00:00
[ tool . poetry . group . lint . dependencies ]
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 17:33:27 +00:00
ruff = "^0.5"
mongodb[minor]: MongoDB Partner Package -- Porting MongoDBAtlasVectorSearch (#17652)
This PR migrates the existing MongoDBAtlasVectorSearch abstraction from
the `langchain_community` section to the partners package section of the
codebase.
- [x] Run the partner package script as advised in the partner-packages
documentation.
- [x] Add Unit Tests
- [x] Migrate Integration Tests
- [x] Refactor `MongoDBAtlasVectorStore` (autogenerated) to
`MongoDBAtlasVectorSearch`
- [x] ~Remove~ deprecate the old `langchain_community` VectorStore
references.
## Additional Callouts
- Implemented the `delete` method
- Included any missing async function implementations
- `amax_marginal_relevance_search_by_vector`
- `adelete`
- Added new Unit Tests that test for functionality of
`MongoDBVectorSearch` methods
- Removed [`del
res[self._embedding_key]`](https://github.com/langchain-ai/langchain/blob/e0c81e1cb0ede673a69aae6434e17e34868c3bcc/libs/community/langchain_community/vectorstores/mongodb_atlas.py#L218)
in `_similarity_search_with_score` function as it would make the
`maximal_marginal_relevance` function fail otherwise. The `Document`
needs to store the embedding key in metadata to work.
Checklist:
- [x] PR title: Please title your PR "package: description", where
"package" is whichever of langchain, community, core, experimental, etc.
is being modified. Use "docs: ..." for purely docs changes, "templates:
..." for template changes, "infra: ..." for CI changes.
- Example: "community: add foobar LLM"
- [x] PR message
- [x] Pass lint and test: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified to check that you're
passing lint and testing. See contribution guidelines for more
information on how to write/run tests, lint, etc:
https://python.langchain.com/docs/contributing/
- [x] Add tests and docs: If you're adding a new integration, please
include
1. Existing tests supplied in docs/docs do not change. Updated
docstrings for new functions like `delete`
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory. (This already exists)
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Steven Silvester <steven.silvester@ieee.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-29 23:09:48 +00:00
[ tool . poetry . group . typing . dependencies ]
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 17:33:27 +00:00
mypy = "^1.10"
2024-08-23 14:41:39 +00:00
simsimd = "^5.0.0"
mongodb[minor]: MongoDB Partner Package -- Porting MongoDBAtlasVectorSearch (#17652)
This PR migrates the existing MongoDBAtlasVectorSearch abstraction from
the `langchain_community` section to the partners package section of the
codebase.
- [x] Run the partner package script as advised in the partner-packages
documentation.
- [x] Add Unit Tests
- [x] Migrate Integration Tests
- [x] Refactor `MongoDBAtlasVectorStore` (autogenerated) to
`MongoDBAtlasVectorSearch`
- [x] ~Remove~ deprecate the old `langchain_community` VectorStore
references.
## Additional Callouts
- Implemented the `delete` method
- Included any missing async function implementations
- `amax_marginal_relevance_search_by_vector`
- `adelete`
- Added new Unit Tests that test for functionality of
`MongoDBVectorSearch` methods
- Removed [`del
res[self._embedding_key]`](https://github.com/langchain-ai/langchain/blob/e0c81e1cb0ede673a69aae6434e17e34868c3bcc/libs/community/langchain_community/vectorstores/mongodb_atlas.py#L218)
in `_similarity_search_with_score` function as it would make the
`maximal_marginal_relevance` function fail otherwise. The `Document`
needs to store the embedding key in metadata to work.
Checklist:
- [x] PR title: Please title your PR "package: description", where
"package" is whichever of langchain, community, core, experimental, etc.
is being modified. Use "docs: ..." for purely docs changes, "templates:
..." for template changes, "infra: ..." for CI changes.
- Example: "community: add foobar LLM"
- [x] PR message
- [x] Pass lint and test: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified to check that you're
passing lint and testing. See contribution guidelines for more
information on how to write/run tests, lint, etc:
https://python.langchain.com/docs/contributing/
- [x] Add tests and docs: If you're adding a new integration, please
include
1. Existing tests supplied in docs/docs do not change. Updated
docstrings for new functions like `delete`
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory. (This already exists)
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Steven Silvester <steven.silvester@ieee.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-29 23:09:48 +00:00
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 17:33:27 +00:00
[ tool . poetry . group . test . dependencies . langchain ]
path = "../../langchain"
develop = true
mongodb[minor]: MongoDB Partner Package -- Porting MongoDBAtlasVectorSearch (#17652)
This PR migrates the existing MongoDBAtlasVectorSearch abstraction from
the `langchain_community` section to the partners package section of the
codebase.
- [x] Run the partner package script as advised in the partner-packages
documentation.
- [x] Add Unit Tests
- [x] Migrate Integration Tests
- [x] Refactor `MongoDBAtlasVectorStore` (autogenerated) to
`MongoDBAtlasVectorSearch`
- [x] ~Remove~ deprecate the old `langchain_community` VectorStore
references.
## Additional Callouts
- Implemented the `delete` method
- Included any missing async function implementations
- `amax_marginal_relevance_search_by_vector`
- `adelete`
- Added new Unit Tests that test for functionality of
`MongoDBVectorSearch` methods
- Removed [`del
res[self._embedding_key]`](https://github.com/langchain-ai/langchain/blob/e0c81e1cb0ede673a69aae6434e17e34868c3bcc/libs/community/langchain_community/vectorstores/mongodb_atlas.py#L218)
in `_similarity_search_with_score` function as it would make the
`maximal_marginal_relevance` function fail otherwise. The `Document`
needs to store the embedding key in metadata to work.
Checklist:
- [x] PR title: Please title your PR "package: description", where
"package" is whichever of langchain, community, core, experimental, etc.
is being modified. Use "docs: ..." for purely docs changes, "templates:
..." for template changes, "infra: ..." for CI changes.
- Example: "community: add foobar LLM"
- [x] PR message
- [x] Pass lint and test: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified to check that you're
passing lint and testing. See contribution guidelines for more
information on how to write/run tests, lint, etc:
https://python.langchain.com/docs/contributing/
- [x] Add tests and docs: If you're adding a new integration, please
include
1. Existing tests supplied in docs/docs do not change. Updated
docstrings for new functions like `delete`
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory. (This already exists)
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Steven Silvester <steven.silvester@ieee.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-29 23:09:48 +00:00
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 17:33:27 +00:00
[ tool . poetry . group . test . dependencies . langchain-core ]
path = "../../core"
develop = true
mongodb[minor]: MongoDB Partner Package -- Porting MongoDBAtlasVectorSearch (#17652)
This PR migrates the existing MongoDBAtlasVectorSearch abstraction from
the `langchain_community` section to the partners package section of the
codebase.
- [x] Run the partner package script as advised in the partner-packages
documentation.
- [x] Add Unit Tests
- [x] Migrate Integration Tests
- [x] Refactor `MongoDBAtlasVectorStore` (autogenerated) to
`MongoDBAtlasVectorSearch`
- [x] ~Remove~ deprecate the old `langchain_community` VectorStore
references.
## Additional Callouts
- Implemented the `delete` method
- Included any missing async function implementations
- `amax_marginal_relevance_search_by_vector`
- `adelete`
- Added new Unit Tests that test for functionality of
`MongoDBVectorSearch` methods
- Removed [`del
res[self._embedding_key]`](https://github.com/langchain-ai/langchain/blob/e0c81e1cb0ede673a69aae6434e17e34868c3bcc/libs/community/langchain_community/vectorstores/mongodb_atlas.py#L218)
in `_similarity_search_with_score` function as it would make the
`maximal_marginal_relevance` function fail otherwise. The `Document`
needs to store the embedding key in metadata to work.
Checklist:
- [x] PR title: Please title your PR "package: description", where
"package" is whichever of langchain, community, core, experimental, etc.
is being modified. Use "docs: ..." for purely docs changes, "templates:
..." for template changes, "infra: ..." for CI changes.
- Example: "community: add foobar LLM"
- [x] PR message
- [x] Pass lint and test: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified to check that you're
passing lint and testing. See contribution guidelines for more
information on how to write/run tests, lint, etc:
https://python.langchain.com/docs/contributing/
- [x] Add tests and docs: If you're adding a new integration, please
include
1. Existing tests supplied in docs/docs do not change. Updated
docstrings for new functions like `delete`
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory. (This already exists)
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Steven Silvester <steven.silvester@ieee.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-29 23:09:48 +00:00
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 17:33:27 +00:00
[ tool . poetry . group . test . dependencies . langchain-text-splitters ]
path = "../../text-splitters"
develop = true
mongodb[minor]: MongoDB Partner Package -- Porting MongoDBAtlasVectorSearch (#17652)
This PR migrates the existing MongoDBAtlasVectorSearch abstraction from
the `langchain_community` section to the partners package section of the
codebase.
- [x] Run the partner package script as advised in the partner-packages
documentation.
- [x] Add Unit Tests
- [x] Migrate Integration Tests
- [x] Refactor `MongoDBAtlasVectorStore` (autogenerated) to
`MongoDBAtlasVectorSearch`
- [x] ~Remove~ deprecate the old `langchain_community` VectorStore
references.
## Additional Callouts
- Implemented the `delete` method
- Included any missing async function implementations
- `amax_marginal_relevance_search_by_vector`
- `adelete`
- Added new Unit Tests that test for functionality of
`MongoDBVectorSearch` methods
- Removed [`del
res[self._embedding_key]`](https://github.com/langchain-ai/langchain/blob/e0c81e1cb0ede673a69aae6434e17e34868c3bcc/libs/community/langchain_community/vectorstores/mongodb_atlas.py#L218)
in `_similarity_search_with_score` function as it would make the
`maximal_marginal_relevance` function fail otherwise. The `Document`
needs to store the embedding key in metadata to work.
Checklist:
- [x] PR title: Please title your PR "package: description", where
"package" is whichever of langchain, community, core, experimental, etc.
is being modified. Use "docs: ..." for purely docs changes, "templates:
..." for template changes, "infra: ..." for CI changes.
- Example: "community: add foobar LLM"
- [x] PR message
- [x] Pass lint and test: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified to check that you're
passing lint and testing. See contribution guidelines for more
information on how to write/run tests, lint, etc:
https://python.langchain.com/docs/contributing/
- [x] Add tests and docs: If you're adding a new integration, please
include
1. Existing tests supplied in docs/docs do not change. Updated
docstrings for new functions like `delete`
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory. (This already exists)
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Steven Silvester <steven.silvester@ieee.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-29 23:09:48 +00:00
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 17:33:27 +00:00
[ tool . poetry . group . dev . dependencies . langchain-core ]
path = "../../core"
develop = true
mongodb[minor]: MongoDB Partner Package -- Porting MongoDBAtlasVectorSearch (#17652)
This PR migrates the existing MongoDBAtlasVectorSearch abstraction from
the `langchain_community` section to the partners package section of the
codebase.
- [x] Run the partner package script as advised in the partner-packages
documentation.
- [x] Add Unit Tests
- [x] Migrate Integration Tests
- [x] Refactor `MongoDBAtlasVectorStore` (autogenerated) to
`MongoDBAtlasVectorSearch`
- [x] ~Remove~ deprecate the old `langchain_community` VectorStore
references.
## Additional Callouts
- Implemented the `delete` method
- Included any missing async function implementations
- `amax_marginal_relevance_search_by_vector`
- `adelete`
- Added new Unit Tests that test for functionality of
`MongoDBVectorSearch` methods
- Removed [`del
res[self._embedding_key]`](https://github.com/langchain-ai/langchain/blob/e0c81e1cb0ede673a69aae6434e17e34868c3bcc/libs/community/langchain_community/vectorstores/mongodb_atlas.py#L218)
in `_similarity_search_with_score` function as it would make the
`maximal_marginal_relevance` function fail otherwise. The `Document`
needs to store the embedding key in metadata to work.
Checklist:
- [x] PR title: Please title your PR "package: description", where
"package" is whichever of langchain, community, core, experimental, etc.
is being modified. Use "docs: ..." for purely docs changes, "templates:
..." for template changes, "infra: ..." for CI changes.
- Example: "community: add foobar LLM"
- [x] PR message
- [x] Pass lint and test: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified to check that you're
passing lint and testing. See contribution guidelines for more
information on how to write/run tests, lint, etc:
https://python.langchain.com/docs/contributing/
- [x] Add tests and docs: If you're adding a new integration, please
include
1. Existing tests supplied in docs/docs do not change. Updated
docstrings for new functions like `delete`
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory. (This already exists)
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Steven Silvester <steven.silvester@ieee.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-02-29 23:09:48 +00:00
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 17:33:27 +00:00
[ tool . poetry . group . typing . dependencies . langchain-core ]
path = "../../core"
develop = true
