mirror of
https://github.com/HKUDS/LightRAG.git
synced 2025-07-04 15:41:03 +00:00
113 lines
3.0 KiB
Python
113 lines
3.0 KiB
Python
"""
|
|
OpenAI LLM Interface Module
|
|
==========================
|
|
|
|
This module provides interfaces for interacting with openai's language models,
|
|
including text generation and embedding capabilities.
|
|
|
|
Author: Lightrag team
|
|
Created: 2024-01-24
|
|
License: MIT License
|
|
|
|
Copyright (c) 2024 Lightrag
|
|
|
|
Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
of this software and associated documentation files (the "Software"), to deal
|
|
in the Software without restriction, including without limitation the rights
|
|
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
copies of the Software, and to permit persons to whom the Software is
|
|
furnished to do so, subject to the following conditions:
|
|
|
|
Version: 1.0.0
|
|
|
|
Change Log:
|
|
- 1.0.0 (2024-01-24): Initial release
|
|
* Added async chat completion support
|
|
* Added embedding generation
|
|
* Added stream response capability
|
|
|
|
Dependencies:
|
|
- openai
|
|
- numpy
|
|
- pipmaster
|
|
- Python >= 3.10
|
|
|
|
Usage:
|
|
from llm_interfaces.nvidia_openai import nvidia_openai_model_complete, nvidia_openai_embed
|
|
"""
|
|
|
|
__version__ = "1.0.0"
|
|
__author__ = "lightrag Team"
|
|
__status__ = "Production"
|
|
|
|
|
|
|
|
import sys
|
|
import os
|
|
|
|
if sys.version_info < (3, 9):
|
|
from typing import AsyncIterator
|
|
else:
|
|
from collections.abc import AsyncIterator
|
|
import pipmaster as pm # Pipmaster for dynamic library install
|
|
|
|
# install specific modules
|
|
if not pm.is_installed("openai"):
|
|
pm.install("openai")
|
|
|
|
from openai import (
|
|
AsyncOpenAI,
|
|
APIConnectionError,
|
|
RateLimitError,
|
|
APITimeoutError,
|
|
)
|
|
from tenacity import (
|
|
retry,
|
|
stop_after_attempt,
|
|
wait_exponential,
|
|
retry_if_exception_type,
|
|
)
|
|
|
|
from lightrag.utils import (
|
|
wrap_embedding_func_with_attrs,
|
|
locate_json_string_body_from_string,
|
|
safe_unicode_decode,
|
|
logger,
|
|
)
|
|
|
|
from lightrag.types import GPTKeywordExtractionFormat
|
|
|
|
import numpy as np
|
|
|
|
@wrap_embedding_func_with_attrs(embedding_dim=2048, max_token_size=512)
|
|
@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,
|
|
input_type: str = "passage", # query for retrieval, passage for embedding
|
|
trunc: str = "NONE", # NONE or START or END
|
|
encode: str = "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])
|