-
### Bug Description
In the DensexRetriver pack, I added a code to use milvus vector db, (I tried with elastic search too, it works fine with the existing dense-x code). However, upon querying, I get …
-
首先感谢BGE提供的这么强大的模型, 我们在之前的RAG应用中, 对企业的文档通过BGE将资料转成向量存储到milvus中, 用户查询时通过dense retrieve 从milvus召回文档,我们使用的是langchain作为框架. 请问如果用BGE配合使用做 dense+sparse retrieve 有没有例子可以参考. 目前是在不知道如何进行. 万分感谢.
-
This might be closable as "Not a Problem", but figgered I'd post it here anyway.
**WARNING**: These benchmarks are still relatively shallow. More work would be necessary to draw meaningful conclusi…
-
Submitting Author: Sara Miskovich (@pluflou)
All current maintainers: (@pluflou, @bmeyers)
Package Name: Solar Data Tools
One-Line Description of Package: Library of tools for analyzing photovoltai…
-
### Data Owner Name
NASA
### Data Owner Country/Region
United States
### Data Owner Industry
Environment
### Website
https://gedi.umd.edu/data/products/
### Social Media Handle
https://twitte…
-
Hi,
I found a weird thing that if using the multilingual-bert e.g: bert-base-multilingual-uncased, it seems like the grad_cache doesn't work. I know it sounds weird, changing different bert models…
-
Submitting Author: Katy Brown (@KatyBrown)
All current maintainers: Katy Brown (@KatyBrown)
Package Name: plot_phylo
One-Line Description of Package: A Python package to plot a phylogenetic tree on…
-
Conduct thorough testing of the FastAPI integration to ensure seamless communication between the chatbot and the deployed FastAPI application. Verify that user input is correctly captured, API request…
j-94 updated
8 months ago
-
Reader em: 43.321, f1: 65.053.The em is lower nearly 30 percentage and the f1 is lower nearly 20 percentage than the paper's result.That's why?I have only changed the batch and n_para_train.
I displ…
-
it seems like bi encoders are using the same encoder for the training. Is there any implementation in this repo where encoder 1 and encoder 2 can be different?