Letong Han

Hi @tbykowsk, The output of `422 Unprocessable Entity` in step [3.1.1 Verify the client connection to server is OK](https://github.com/intel/intel-extension-for-transformers/blob/main/intel_extension_for_transformers/neural_chat/examples/quick_start/chatbot/README.md#311-verify-the-client-connection-to-server-is-ok) is **as expected**. **Further explanation** - `422 Unprocessable Entity` means that...

System prompt can be assigned via neuralchat backend now. The frontend feature will be completed by @WenjiaoYue later because of schedule of tasks.

@tbykowsk Since the dataprep microservice supports the knowledge base append strategy now, we will close this issue. Please let us know if there is other issues.

Merge after v0.9 release.

Merge after v0.9 release.

Hi @arun-gupta , the issue is caused by the lack of huggingface authority. Please check the docker log of `tgi-service`, and you will get the log below. You should visit...

The `deepseek-ai/deepseek-coder-6.7b-instruct` model does not have the access isssue, but seems that it's not supported by tgi. Check the [supported model](https://github.com/huggingface/text-generation-inference/blob/main/docs/source/supported_models.md) of tgi, it only support `deepseek v2`, no `deepseek-coder`....

yes, @yao531441 will help follow this issue and check these models again.

Of course. @WenjiaoYue can you help with this UI issue?

AgentQnA test by @ZePan110 : https://github.com/opea-project/GenAIExamples/actions/runs/16067420884/job/45344464090