search

infiniflow / ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
https://ragflow.io
Apache License 2.0
23.58k stars 2.31k forks source link

[Bug]: the term similarity and vctor similarity giving wrong values #3330

Open tanzeel291994 opened 1 week ago

tanzeel291994 commented 1 week ago

Is there an existing issue for the same bug?

Branch name

main

Commit ID

latest

Other environment information

No response

Actual behavior

in the retrieval test why exactly few documents that aren't similar show 100 % term and vector similarity

image

Expected behavior

No response

Steps to reproduce

only 'name' is used for vector embeddings not and code_ID is used as metadata

Additional information

No response

KevinHuSh commented 1 week ago

How to reproduce that?