-
I'm trying to install OpenOOD in a conda environment per yaml file, like so:
```yaml
name: env
channels:
- pytorch
- nvidia
- defaults
dependencies:
- python=3.12
- numpy
- matpl…
-
python hn_mine.py --model_name_or_path /data/bxhuang/model_folder/xiaobu-embedding-v2 --input_file /data/bxhuang/Reranking/train_data/text_pairs.json --output_file /data/bxhuang/Reranking/train_data/t…
-
# Summary
I am trying to run a baseline model [VQREC pq.py](https://github.com/RUCAIBox/VQ-Rec/blob/master/pq.py) I met `munmap_chunk(): invalid pointer \n segmentation fault (core dump)`, when `…
-
I'm getting this error when I try to index document with FAISS. Is there way change number or cluster?
`RuntimeError: Error in void faiss::Clustering::train_encoded(faiss::idx_t, const uint8_t*, cons…
-
# Summary
I am experiencing an issue with FAISS where batch retrieval of multiple embeddings using IndexIDMap(IndexFlatIP) behaves incorrectly. Specifically, while single-vector retrieval works fla…
-
### Checked other resources
- [X] I added a very descriptive title to this issue.
- [X] I searched the LangChain documentation with the integrated search.
- [X] I used the GitHub search to find a…
-
When we built the PDQ index, it was our first attempt, and we made a lot of strange/bad choices.
Namely:
* The hash -> id mapping is extremely convoluted and needlessly complicated
* The build a…
-
Hello,
Could you please share a pinned dependencies versions in form of a requirements.txt file.
Current setup doesn't work unfortunately as there is a mismatch between faiss-gpu and numpy versi…
-
We have two versions of `QueryEncoder` and two versions of `AutoQueryEncoder`. One set of classes is in `pyserini.search.faiss`, the other set is in `pyserini.encode`.
+ `QueryEncoder` in [`pyserin…
-
from towhee import ops, pipe, DataCollection
## create image embeddings and build index
p = (
pipe.input('file_name')
.map('file_name', 'img', ops.image_decode.cv2())
.map('img', 'vec…