[Bug] Alibaba Cloud Bailian Text Embedding Model vectorization dimension confusing, resulting in retrieval error #4074
Description
Contact Information
No response
MaxKB Version
v2.1.1 | v1.10.10-lts
Problem Description
接入阿里百炼平台的 text-embedding-v3 及 text-embedding-v4 模型后向量化文件导致返回向量维度不固定，检索报错
查看官网python sdk
import os
from openai import OpenAI
client = OpenAI(
api_key=os.getenv("DASHSCOPE_API_KEY"), # 如果您没有配置环境变量，请在此处用您的API Key进行替换
base_url="https://dashscope.aliyuncs.com/compatible-mode/v1" # 百炼服务的base_url
)
completion = client.embeddings.create(
model="text-embedding-v4",
input='衣服的质量杠杠的，很漂亮，不枉我等了这么久啊，喜欢，以后还来这里买',
dimensions=1024, # 指定向量维度（仅 text-embedding-v3及 text-embedding-v4支持该参数）
encoding_format="float"
)
print(completion.model_dump_json())Steps to Reproduce
- 接入百炼 text-embedding-v3 / text-embedding-v4 向量模型
- 知识库上传文档执行向量化
- 检索报错
The expected correct result
No response
Related log output
Additional Information
No response