-
### Describe the bug
After loading `wiki_dpr` using:
```py
ds = load_dataset(path='wiki_dpr', name='psgs_w100.multiset.compressed', split='train')
print(ds.get_index("embeddings").metric_type) # p…
-
While trying to implement #2, I discovered another snag: `Euclidean` and `Mahalanobis` cannot be fit by passing a dataframe as `X`. The errors seem to originate in the transformers, but I haven't dug …
-
### Problem Statement
CrateDB has a pretty powerful search functionality with `MATCH` and scoring, but for some applications it would be nice if it could support semantic search functionality as well…
-
I am receiving the following error when trying to query something using the ElasticGPT python app.
`IndexError: list index out of range`
This is what the app returns in the Traceback
Tracebac…
-
I have used BERT NextSentencePredictor to find similar sentences or similar news, However, It's super slow. Even on Tesla V100 which is the fastest GPU till now. It takes around 10secs for a query tit…
-
Steps to reproduce:
```
export DOCKER_DEFAULT_PLATFORM=linux/amd64
docker build -t viberary -f docker/prod/Dockerfile .
docker run -it viberary optimum-cli export onnx --model sentence-transformer…
-
### What is the bug?
When defining a field_map containing nested fields, the pipeline fails to compute embeddings.
### How can one reproduce the bug?
With the following configuration, using __non…
-
**What is the bug?**
This ss4o metric bug triggers on trying to activate registration, I tried a lot of settings:
```
allow_registering_model_via_url: true
```
As soon as I disable this paramet…
-
- [x] fix README example https://github.com/henomis/lingoose/pull/117
- [x] change logo and refactor README https://github.com/henomis/lingoose/pull/118
- [x] custom HTTP client support for Huggingf…
-
Currently, our estimators are named to follow method names introduced in R's `yaImpute` package. We likely want to conform to scikit-learn's model of being more explicit about whether estimators are …