llm config_error ai_generated true

ValueError: 嵌入维度不匹配：查询嵌入维度（384）与索引嵌入维度（768）不匹配

ValueError: Embedding dimension mismatch: query embedding dimension (384) does not match index embedding dimension (768)

ID: llm/llamaindex-embedding-model-mismatch-on-retrieval

其他格式: JSON · Markdown 中文 · English
90%修复率
89%置信度
1证据数
2024-04-12首次发现

版本兼容性

版本状态引入弃用备注
llama-index 0.10.0 active — — —
llama-index 0.10.15 active — — —
llama-index 0.10.30 active — — —
sentence-transformers 2.2.2 active — — —
sentence-transformers 3.0.0 active — — —

根因分析

LlamaIndex使用与构建向量索引时不同的输出维度的嵌入模型来检索查询，通常是由于在索引构建后更改了embed_model配置。

English

LlamaIndex retrieves a query using an embedding model with a different output dimension than the model used to build the vector index, often due to changing the embed_model config after index construction.

generic

官方文档

https://docs.llamaindex.ai/en/stable/module_guides/loading/embeddings/

解决方案

  1. 使用与查询相同的嵌入模型重建索引：

from llama_index.core import VectorStoreIndex, Settings
from llama_index.embeddings.huggingface import HuggingFaceEmbedding

embed_model = HuggingFaceEmbedding(model_name='BAAI/bge-small-en-v1.5')
Settings.embed_model = embed_model
index = VectorStoreIndex.from_documents(documents, embed_model=embed_model)
  2. 在索引元数据中持久化嵌入模型名称，并在加载时验证：

from llama_index.core import StorageContext, load_index_from_storage

storage_context = StorageContext.from_defaults(persist_dir='./index')
index = load_index_from_storage(storage_context)
if index.embed_model != current_embed_model:
    raise ValueError(f"嵌入模型不匹配：索引使用{index.embed_model}")

无效尝试

常见但无效的做法:

  1. 80% 失败

    Reshaping distorts the embedding space, producing semantically meaningless similarity scores and retrieval results.

  2. 50% 失败

    The default embedding model may still have a different dimension than the one used during indexing, unless it's the exact same model.