69358d830d
Format entire codebase with ruff and add type hints across all modules: - Apply ruff formatting to all Python files (121 files, 17K insertions) - Add type hints to function signatures throughout lightrag core and API - Update test suite with improved type annotations and docstrings - Add pyrightconfig.json for static type checking configuration - Create prompt_optimized.py and test_extraction_prompt_ab.py test files - Update ruff.toml and .gitignore for improved linting configuration - Standardize code style across examples, reproduce scripts, and utilities
57 lines
1.6 KiB
Python
57 lines
1.6 KiB
Python
import os
|
|
|
|
pass
|
|
|
|
import pipmaster as pm # Pipmaster for dynamic library install
|
|
|
|
# install specific modules
|
|
if not pm.is_installed('openai'):
|
|
pm.install('openai')
|
|
|
|
from typing import Literal
|
|
import numpy as np
|
|
from openai import (
|
|
APIConnectionError,
|
|
APITimeoutError,
|
|
AsyncOpenAI,
|
|
RateLimitError,
|
|
)
|
|
from tenacity import (
|
|
retry,
|
|
retry_if_exception_type,
|
|
stop_after_attempt,
|
|
wait_exponential,
|
|
)
|
|
|
|
from lightrag.utils import (
|
|
wrap_embedding_func_with_attrs,
|
|
)
|
|
|
|
|
|
@wrap_embedding_func_with_attrs(embedding_dim=2048, max_token_size=8192)
|
|
@retry(
|
|
stop=stop_after_attempt(3),
|
|
wait=wait_exponential(multiplier=1, min=4, max=60),
|
|
retry=retry_if_exception_type((RateLimitError, APIConnectionError, APITimeoutError)),
|
|
)
|
|
async def nvidia_openai_embed(
|
|
texts: list[str],
|
|
model: str = 'nvidia/llama-3.2-nv-embedqa-1b-v1',
|
|
# refer to https://build.nvidia.com/nim?filters=usecase%3Ausecase_text_to_embedding
|
|
base_url: str = 'https://integrate.api.nvidia.com/v1',
|
|
api_key: str | None = None,
|
|
input_type: str = 'passage', # query for retrieval, passage for embedding
|
|
trunc: str = 'NONE', # NONE or START or END
|
|
encode: Literal['float', 'base64'] = 'float', # float or base64
|
|
) -> np.ndarray:
|
|
if api_key:
|
|
os.environ['OPENAI_API_KEY'] = api_key
|
|
|
|
openai_async_client = AsyncOpenAI() if base_url is None else AsyncOpenAI(base_url=base_url)
|
|
response = await openai_async_client.embeddings.create(
|
|
model=model,
|
|
input=texts,
|
|
encoding_format=encode,
|
|
extra_body={'input_type': input_type, 'truncate': trunc},
|
|
)
|
|
return np.array([dp.embedding for dp in response.data])
|