-
Hi, thank you for this project, really cool idea!
I built the docker image and everything went fine up until 4000 of 40000 assets.
vecs = np.r…
-
Thank you very much for releasing the code for your paper!
Not serious, but I encounter some scalability issues at pairwise distance computation for > 10k points due to ```create_distance_matrix```…
-
# Summary
I would like to either enable moving the parameters, defined with ParameterSpace for a cpu index, to the GPU if the index is moved to the GPU or have a warning that flags that I need to …
-
**Is your feature request related to a problem? Please describe.**
Need ability to understand which fields in an index use the most space.
**Describe the solution you'd like**
An API that, given …
otisg updated
6 months ago
-
@vishwasg217
Unable to get the clarify_ai thing, can you please guide?
KeyError: 'st.secrets has no key "clarify_ai_pat". Did you forget to add it to secrets.toml or the app settings on Streaml…
-
例如：问答对源文件source_file.txt，生成的索引文件test_index。
需求：因某些原因，需要删除或新增source_file.txt文件中的某个问答对，请问在索引中怎么找得到这个问答进行删除或新增。
-
@lhoestq Hi I am thinking of adding this new google library to do the MIPS similar to **add_faiss_idex**. As the paper suggests, it is really fast when it comes to retrieving the nearest neighbors.
…
-
使用Faiss搭建问答系统的时候遇到一个问题，当文档文件种的内容过多的时候，创建索引的速度非常的慢
执行慢的代码是 para_embs = np.array(list(para_embs)) 请问有没有什么解决方案呢？
kenjs updated
2 years ago
-
I observe the usage of lmdb , sqlite , pq codec for hnsw
can you please provide some rationale on design choices here for example : rocksdb instead of lmdb , lucence vs sqlite3 for applying filters ,…