LightRAG/lightrag/llm/siliconcloud.py

"""
SiliconCloud Embedding Interface Module
==========================

This module provides interfaces for interacting with SiliconCloud system,
including 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 embedding generation

Dependencies:
    - tenacity
    - numpy
    - pipmaster
    - Python >= 3.10

Usage:
    from llm_interfaces.siliconcloud import siliconcloud_model_complete, siliconcloud_embed
"""

__version__ = "1.0.0"
__author__ = "lightrag Team"
__status__ = "Production"

import sys
import copy
import os
import json

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("lmdeploy"):
    pm.install("lmdeploy")

from openai import (
    AsyncOpenAI,
    AsyncAzureOpenAI,
    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
from functools import lru_cache

import numpy as np
from typing import Union
import aiohttp

@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 siliconcloud_embedding(
    texts: list[str],
    model: str = "netease-youdao/bce-embedding-base_v1",
    base_url: str = "https://api.siliconflow.cn/v1/embeddings",
    max_token_size: int = 512,
    api_key: str = None,
) -> np.ndarray:
    if api_key and not api_key.startswith("Bearer "):
        api_key = "Bearer " + api_key

    headers = {"Authorization": api_key, "Content-Type": "application/json"}

    truncate_texts = [text[0:max_token_size] for text in texts]

    payload = {"model": model, "input": truncate_texts, "encoding_format": "base64"}

    base64_strings = []
    async with aiohttp.ClientSession() as session:
        async with session.post(base_url, headers=headers, json=payload) as response:
            content = await response.json()
            if "code" in content:
                raise ValueError(content)
            base64_strings = [item["embedding"] for item in content["data"]]

    embeddings = []
    for string in base64_strings:
        decode_bytes = base64.b64decode(string)
        n = len(decode_bytes) // 4
        float_array = struct.unpack("<" + "f" * n, decode_bytes)
        embeddings.append(float_array)
    return np.array(embeddings)