mhillebrand

I recently upgraded to `paddlepaddle-gpu 2.0.1.post110`, and this is the error I receive when running `./scripts/predict_graphsum_local_multinews.sh`: ``` Traceback (most recent call last): File "./src/run.py", line 35, in run_graphsum(args) File "/home/matt/mr/algos/Research/NLP/ACL2020-GraphSum/src/networks/graphsum/run_graphsum.py",...

InvalidArgumentError: The shape of input[0] and input[1] is expected to be equal.But received input[0]'s shape = [-1, 0, 1], input[1]'s shape = [-1, 1, 1, 1].

1

I'm trying to test the [GraphSum](https://github.com/PaddlePaddle/Research/tree/master/NLP/ACL2020-GraphSum) model with the command `./scripts/predict_graphsum_local_multinews.sh` found in the documentation, but I get this error: ```---------------------- Error Message Summary: ---------------------- InvalidArgumentError: The shape of input[0]...

Logitech triple-click macro on macOS

4

Greetings. I have a Logitech G703 Lightspeed mouse whose driver has a bug on macOS. That is, it's impossible to create macros such as a double-click or triple-click. I've tried...

LLM Compatibility

1

Does this library only work with OpenAI models in the cloud, or can it also work with a local model—such as GPT-Neo, Alpaca, etc.?

AsyncInferenceClient - Unclosed client session

3

I'm using TGI with Flan-T5 to process thousands of text extraction requests at a time, on a 4 x A6000 machine. My client class, which uses `AsyncInferenceClient`, can handle 900...

Support gRPC interface of TEI

2

The gRPC interface of HuggingFace's Text Embeddings Inference (TEI) library is much, much faster than its HTTP interface. It would be fantastic to see Haystack add support for it. https://github.com/huggingface/text-embeddings-inference?tab=readme-ov-file#grpc

It would be wonderful to see support for [LanceDB](https://github.com/lancedb/lancedb)—a fast, serverless vector store that's incredibly easy to use.

Feature: Specify maximum cosine distance in the WHERE clause of `table.search()`

6

### SDK Python ### Description I'd love to be able to specify a minimum cosine similarity threshold (or maximum cosine distance) when using `table.search()`. One way to do this would...