Spaces:
Sleeping
Sleeping
File size: 3,187 Bytes
cfd3735 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
"""Test self-hosted embeddings."""
from typing import Any
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
from langchain.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."""
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(
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(
model_load_fn=get_pipeline, hardware=gpu, inference_fn=inference_fn
)
output = embedding.embed_query(query)
assert len(output) == 50265
|