mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-31 20:19:43 +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()
```
98 lines
3.2 KiB
Python
98 lines
3.2 KiB
Python
"""Test self-hosted embeddings."""
|
|
|
|
from typing import Any
|
|
|
|
from langchain_community.embeddings import (
|
|
SelfHostedEmbeddings,
|
|
SelfHostedHuggingFaceEmbeddings,
|
|
SelfHostedHuggingFaceInstructEmbeddings,
|
|
)
|
|
|
|
|
|
def get_remote_instance() -> Any:
|
|
"""Get remote instance for testing."""
|
|
import runhouse as rh
|
|
|
|
gpu = rh.cluster(name="rh-a10x", instance_type="A100:1", use_spot=False)
|
|
gpu.install_packages(["pip:./"])
|
|
return gpu
|
|
|
|
|
|
def test_self_hosted_huggingface_embedding_documents() -> None:
|
|
"""Test self-hosted huggingface embeddings."""
|
|
documents = ["foo bar"]
|
|
gpu = get_remote_instance()
|
|
embedding = SelfHostedHuggingFaceEmbeddings(hardware=gpu)
|
|
output = embedding.embed_documents(documents)
|
|
assert len(output) == 1
|
|
assert len(output[0]) == 768
|
|
|
|
|
|
def test_self_hosted_huggingface_embedding_query() -> None:
|
|
"""Test self-hosted huggingface embeddings."""
|
|
document = "foo bar"
|
|
gpu = get_remote_instance()
|
|
embedding = SelfHostedHuggingFaceEmbeddings(hardware=gpu)
|
|
output = embedding.embed_query(document)
|
|
assert len(output) == 768
|
|
|
|
|
|
def test_self_hosted_huggingface_instructor_embedding_documents() -> None:
|
|
"""Test self-hosted huggingface instruct embeddings."""
|
|
documents = ["foo bar"]
|
|
gpu = get_remote_instance()
|
|
embedding = SelfHostedHuggingFaceInstructEmbeddings(hardware=gpu)
|
|
output = embedding.embed_documents(documents)
|
|
assert len(output) == 1
|
|
assert len(output[0]) == 768
|
|
|
|
|
|
def test_self_hosted_huggingface_instructor_embedding_query() -> None:
|
|
"""Test self-hosted huggingface instruct embeddings."""
|
|
query = "foo bar"
|
|
gpu = get_remote_instance()
|
|
embedding = SelfHostedHuggingFaceInstructEmbeddings(hardware=gpu)
|
|
output = embedding.embed_query(query)
|
|
assert len(output) == 768
|
|
|
|
|
|
def get_pipeline() -> Any:
|
|
"""Get pipeline for testing."""
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
|
|
|
|
model_id = "facebook/bart-base"
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
|
model = AutoModelForCausalLM.from_pretrained(model_id)
|
|
return pipeline("feature-extraction", model=model, tokenizer=tokenizer)
|
|
|
|
|
|
def inference_fn(pipeline: Any, prompt: str) -> Any:
|
|
"""Inference function for testing."""
|
|
# Return last hidden state of the model
|
|
if isinstance(prompt, list):
|
|
return [emb[0][-1] for emb in pipeline(prompt)]
|
|
return pipeline(prompt)[0][-1]
|
|
|
|
|
|
def test_self_hosted_embedding_documents() -> None:
|
|
"""Test self-hosted huggingface instruct embeddings."""
|
|
documents = ["foo bar"] * 2
|
|
gpu = get_remote_instance()
|
|
embedding = SelfHostedEmbeddings( # type: ignore[call-arg]
|
|
model_load_fn=get_pipeline, hardware=gpu, inference_fn=inference_fn
|
|
)
|
|
output = embedding.embed_documents(documents)
|
|
assert len(output) == 2
|
|
assert len(output[0]) == 50265
|
|
|
|
|
|
def test_self_hosted_embedding_query() -> None:
|
|
"""Test self-hosted custom embeddings."""
|
|
query = "foo bar"
|
|
gpu = get_remote_instance()
|
|
embedding = SelfHostedEmbeddings( # type: ignore[call-arg]
|
|
model_load_fn=get_pipeline, hardware=gpu, inference_fn=inference_fn
|
|
)
|
|
output = embedding.embed_query(query)
|
|
assert len(output) == 50265
|