text-embeddings-inference

text-embeddings-inference copied to clipboard

edit logging functionality with configurable OpenTelemetry integration

3

- Implement dynamic log level setting and OpenTelemetry integration - Add configurable OpenTelemetry logging with JSON output option - Refactor logging to include OpenTelemetry and JSON formatting

kbshal

### System Info ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 ### Information - [X] Docker - [ ] The CLI directly ### Tasks - [X] An officially supported command - [ ] My own modifications ###...

gree2

Allow fetching token embeddings from a cross-encoding

1

### Feature request It would be nice to allow fetching the token embeddings from a cross-encoding, which is necessary to implement systems such as retrieval augmented named entity recognition [(RA-NER)](https://openreview.net/pdf?id=HyKNjew2Ad)....

dan-octo

ROCM build fixes

1

# What does this PR do? As per title!

mht-sharma

unknown flag: --gpus See 'docker run --help'

1

### System Info docker info docker info Containers: 0 Running: 0 Paused: 0 Stopped: 0 Images: 10 Server Version: 27.2.0 Storage Driver: overlay2 Backing Filesystem: extfs Supports d_type: true Using...

sswolf

### System Info Inference endpoints TEI version 1.5 ### Information - [ ] Docker - [ ] The CLI directly ### Tasks - [ ] An officially supported command -...

MoritzLaurer

dunzhang/stella_en_1.5B_v5 Maximum Token Limit Set to 512 Despite Model Capabilities

1

### System Info docker run --gpus all -p 8081:80 -v $HF_HOME/hub:/data ghcr.io/huggingface/text-embeddings-inference:1.5 --model-id dunzhang/stella_en_1.5B_v5 --auto-truncate ### Information - [x] Docker - [ ] The CLI directly ### Tasks - [x]...

taoari

### System Info 3090 GPU (Ampere model) ### Information - [X] Docker - [ ] The CLI directly ### Tasks - [X] An officially supported command - [ ] My...

sleepingcat4

When using `/embed` and `truncate=true` with long inputs, the input is correctly truncated at the token level, but I still get a validation error for inputs longer than 32,000 characters:...

ffalkenberg

### Feature request can support https://huggingface.co/BAAI/bge-visualized/blob/main/README.md ? ### Motivation can support https://huggingface.co/BAAI/bge-visualized/blob/main/README.md ### Your contribution testing

whybeyoung