mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-03 06:08:18 +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()
```
83 lines
2.9 KiB
Python
83 lines
2.9 KiB
Python
"""Fake Embedding class for testing purposes."""
|
|
|
|
import math
|
|
from typing import List
|
|
|
|
from langchain_core.embeddings import Embeddings
|
|
|
|
fake_texts = ["foo", "bar", "baz"]
|
|
|
|
|
|
class FakeEmbeddings(Embeddings):
|
|
"""Fake embeddings functionality for testing."""
|
|
|
|
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
|
"""Return simple embeddings.
|
|
Embeddings encode each text as its index."""
|
|
return [[float(1.0)] * 9 + [float(i)] for i in range(len(texts))]
|
|
|
|
async def aembed_documents(self, texts: List[str]) -> List[List[float]]:
|
|
return self.embed_documents(texts)
|
|
|
|
def embed_query(self, text: str) -> List[float]:
|
|
"""Return constant query embeddings.
|
|
Embeddings are identical to embed_documents(texts)[0].
|
|
Distance to each text will be that text's index,
|
|
as it was passed to embed_documents."""
|
|
return [float(1.0)] * 9 + [float(0.0)]
|
|
|
|
async def aembed_query(self, text: str) -> List[float]:
|
|
return self.embed_query(text)
|
|
|
|
|
|
class ConsistentFakeEmbeddings(FakeEmbeddings):
|
|
"""Fake embeddings which remember all the texts seen so far to return consistent
|
|
vectors for the same texts."""
|
|
|
|
def __init__(self, dimensionality: int = 10) -> None:
|
|
self.known_texts: List[str] = []
|
|
self.dimensionality = dimensionality
|
|
|
|
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
|
"""Return consistent embeddings for each text seen so far."""
|
|
out_vectors = []
|
|
for text in texts:
|
|
if text not in self.known_texts:
|
|
self.known_texts.append(text)
|
|
vector = [float(1.0)] * (self.dimensionality - 1) + [
|
|
float(self.known_texts.index(text))
|
|
]
|
|
out_vectors.append(vector)
|
|
return out_vectors
|
|
|
|
def embed_query(self, text: str) -> List[float]:
|
|
"""Return consistent embeddings for the text, if seen before, or a constant
|
|
one if the text is unknown."""
|
|
return self.embed_documents([text])[0]
|
|
|
|
|
|
class AngularTwoDimensionalEmbeddings(Embeddings):
|
|
"""
|
|
From angles (as strings in units of pi) to unit embedding vectors on a circle.
|
|
"""
|
|
|
|
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
|
"""
|
|
Make a list of texts into a list of embedding vectors.
|
|
"""
|
|
return [self.embed_query(text) for text in texts]
|
|
|
|
def embed_query(self, text: str) -> List[float]:
|
|
"""
|
|
Convert input text to a 'vector' (list of floats).
|
|
If the text is a number, use it as the angle for the
|
|
unit vector in units of pi.
|
|
Any other input text becomes the singular result [0, 0] !
|
|
"""
|
|
try:
|
|
angle = float(text)
|
|
return [math.cos(angle * math.pi), math.sin(angle * math.pi)]
|
|
except ValueError:
|
|
# Assume: just test string, no attention is paid to values.
|
|
return [0.0, 0.0]
|