TeamGenKI/Inference-API

Updated system status response.

WIP adapter.py

Trying VPN IP on host.

Fixed port.

Updated run.sh and Dockerfile. small update....again...again....again...again...again...

Updated run.sh and Dockerfile. small update....again...again....again...again...

Updated run.sh and Dockerfile. small update....again...again....again...

Updated run.sh and Dockerfile. small update....again...again.

Updated run.sh and Dockerfile. small update....again.

Updated run.sh and Dockerfile. small update.

Updated run.sh and Dockerfile.

Updated run.sh again

Updated run.sh

Updated run.sh

Added run.sh

Updated Dockerfile

Fixed macos issue

debugging chunks v5

debugging chunks v4

debugging chunks v3

debugging chunks v2

debugging chunks

Fixed Streaming response being double wrapped

Fixed streaming in chat_completion

Fixed issue with the server not managing request lifecycle correctly

Fixed await issue

Changed routing prefix

Fixed v1 error

Added resoruces folder for configs

fixed base_url issue

Update main/config.yaml

fixed config issue

Fixed minor issues

Adding query expansion and reranker

changed to uvicorn setup for HF v17

changed to uvicorn setup for HF v16

changed to uvicorn setup for HF v15

changed to uvicorn setup for HF v14

changed to uvicorn setup for HF v13

changed to uvicorn setup for HF v12

changed to uvicorn setup for HF v11

changed to uvicorn setup for HF v10

changed to uvicorn setup for HF v9

changed to uvicorn setup for HF v8

changed to uvicorn setup for HF v7

changed to uvicorn setup for HF v6

changed to uvicorn setup for HF v5

changed to uvicorn setup for HF v4

changed to uvicorn setup for HF v3

changed to uvicorn setup for HF v2