68f663f2f4
主要变更: - 移除Hermes智能体及相关回调服务 - 新增知识库RAG、同步、调度、规范化和索引任务服务 - 重构orchestrator服务，增强运行时聊天功能 - 更新前端聊天、政策制度、设置等页面样式和逻辑 - 更新expense_claims和document_intelligence服务 - 删除llm_wiki相关服务和测试文件 - 更新docker-compose配置和启动脚本
70 lines
1.8 KiB
Python
70 lines
1.8 KiB
Python
import sys
|
|
|
|
if sys.version_info < (3, 9):
|
|
pass
|
|
else:
|
|
pass
|
|
import pipmaster as pm # Pipmaster for dynamic library install
|
|
|
|
# install specific modules
|
|
if not pm.is_installed("lmdeploy"):
|
|
pm.install("lmdeploy")
|
|
|
|
from openai import (
|
|
APIConnectionError,
|
|
RateLimitError,
|
|
APITimeoutError,
|
|
)
|
|
from tenacity import (
|
|
retry,
|
|
stop_after_attempt,
|
|
wait_exponential,
|
|
retry_if_exception_type,
|
|
)
|
|
|
|
|
|
import numpy as np
|
|
import aiohttp
|
|
import base64
|
|
import struct
|
|
|
|
|
|
@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 = 8192,
|
|
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)
|