[Bug]wrong TGI endpoint for ChatQnA testing - Githubissues

opea-project / GenAIExamples

Generative AI Examples is a collection of GenAI examples such as ChatQnA, Copilot, which illustrate the pipeline capabilities of the Open Platform for Enterprise AI (OPEA) project.

https://opea.dev

Apache License 2.0

276 stars 193 forks source link

[Bug]wrong TGI endpoint for ChatQnA testing #1104

Closed louie-tsai closed 1 week ago

louie-tsai commented 1 week ago

Priority

P3-Medium

OS type

Ubuntu

Hardware type

Xeon-SPR

Installation method

[X] Pull docker images from hub.docker.com
[ ] Build docker images from source

Deploy method

[X] Docker compose
[ ] Docker
[ ] Kubernetes
[ ] Helm

Running nodes

Single Node

What's the version?

1.0

Description

The ChatQnA REAMDE TGI instruction below is not aligned with our LLM gen component. https://github.com/opea-project/GenAIExamples/tree/main/ChatQnA/docker_compose/intel/hpu/gaudi

LLM GenAI component implementation: https://github.com/opea-project/GenAIComps/blob/main/comps/llms/text-generation/tgi/llm.py#L41

Reproduce steps

just follow the README. it should still work for testing since TGI also has generate endpoint, but our microservice use v1/completion instead.

Raw log

No response

louie-tsai commented 1 week ago

fixed with commit : https://github.com/intel-ai-tce/GenAIExamples/commit/aa314f6757c503f0b10a6481b1e2eb00db13fa6e