-
### Bug Description
BM25Retriever cannot work on chinese.
### Version
main
### Steps to Reproduce
```python
from llama_index.retrievers.bm25 import BM25Retriever
from llama_index.core import Do…
-
Dear authors,
I was trying to reproduce repllama/repmistral and to understand the logic of the code.
# 1. Why use cross-entropy loss in contrastive learning?
in this file `/usa/dayu/Tab…
-
Description:
I am encountering an issue with the ElasticsearchVectorStore class when performing a similarity search. Specifically, when I execute a search with a topK value set to 2, it seems to on…
-
### Describe your feature request
Create this new modified cosine similarity and the related distance metric.
m = mean vector of the collection vectors.
c = a particular collection vector
q = th…
-
Proposal for a new feature below by @baptiste-pasquier
### Checked
- [X] I searched existing ideas and did not find a similar one
- [X] I added a very descriptive title
- [X] I've clearly desc…
-
![20180803_104442](https://user-images.githubusercontent.com/6811931/43665780-289868f2-9726-11e8-9d5f-0e77f3c3b464.jpg)
# Pipeline should work as follows:
### Process each incoming document: cre…
saggu updated
5 years ago
-
### Have you searched existing issues? 🔎
- [X] I have searched and found no existing issues
### Desribe the bug
Hi everyone, first of all I would like to thank @MaartenGr and all the contributors …
-
**Describe the bug**
As stated in [Wiki: Deletion Capabilities](https://github.com/IntelLabs/vdms/wiki/Deletion-Capabilities), the _deletion query allows a user to delete the content within VDMS t…
-
**Is your feature request related to a problem? Please describe.**
Firestore retriever does not support using a similarity threshold (instead of `k`) when retrieving documents.
**Describe the solu…
-
### Describe your problem
上传文档后,解析的结果会存成什么格式,在输入问题后,对文档切片结果呈现的优先级是什么?是按照文档进行排序的吗?