jens-f

When converting e.g. this sentence: "TTS comes with pretrained models, tools for measuring dataset quality and already used in 20+ languages for products and research projects." In that sentence the...

Proper way to share generated container accross multiple .c files

6

We are sharing a generated List across multiple .c files. The code generated for the list is making all the functions `static`. In order to call these, we are creating...

Support for remote repo on S3 and others for upload after commiting

9

I don't think it is currently possible to pull from or push to repositories that are in AWS S3 or similar storage. Is this something you guys have thought about...

Support for Accelerated Hierarchical Density Clustering?

1

I was wondering if this library includes the accelerated version of the HDBSCAN algo from 2017? The paper: https://arxiv.org/abs/1705.07321 The implementation in Python: https://github.com/scikit-learn-contrib/hdbscan

Typescript exports for 3 namespace levels uses wrong relative paths

11

Using flatc version 23.3.3 and compiling to Typescript: I'm running into an issue where using 3 levels of namespacing in the flatbuffer file (e.g. com.company.test) produces an export file named...

Direct line speech - Echo bot not using final formatted recognition result

1

## Sample information 1. Sample type: \samples\ 2. Sample language: typescript 3. Sample name: 02.echo-bot ## Describe the bug When using Direct Line Speech, the echo bot does not echo...

This PR adds the ability of using subclasses of class Collection. Without this change, providing a subclass to the index functionality will cause the assert to trigger

Support for Optimum Inference?

6

### Feature request Are you currently supporting inference of [Optimum](https://huggingface.co/docs/optimum/index) converted models, e.g. through the [ONNX Runtime](https://huggingface.co/docs/optimum/v1.2.1/en/onnxruntime/modeling_ort)? I tried a couple of pre-optimized HF models, e.g. this: https://huggingface.co/Xenova/bge-large-en-v1.5 but get...

Why is Searcher loading a second Checkpoint, i.e. the same model again?

2

When following the basic examples I noticed that the `Searcher` class when called through `RAG.search` will always load the pytorch model used in the index (e.g. `colbert-ir/colbertv2.0`) a second time,...

Quantizing from cli using config file fails

1

I'm running ``` onnxruntime quantize --onnx_model ONNX_MODEL --c ort_config.json -o ONNX_MODEL_quantized ``` and this fails with ``` Traceback (most recent call last): File "/opt/homebrew/Caskroom/miniconda/base/envs/rag/bin/optimum-cli", line 8, in sys.exit(main()) ^^^^^^ File...