landhu comments

Results 8 comments of


                                            landhu

Report doesn't display all scenarios when running tests with pytest-xdist

Any update here?NO fix??

将其封装为http服务后调用，无法获取组件信息

@lxf920125 能分享一下你的服务及exe吗？正好也有这样的需求

Test execution is not stopping automatically in report portal [v5.2.2]. need to stop forcefully after every execution to analyse

Any one can help to INVESTIGATE?

Test execution is not stopping automatically in report portal [v5.2.2]. need to stop forcefully after every execution to analyse

I had same issue. But I found if not add autoMerge=true option. It can be fixed. you can try it.

Integrating third-party LLMs for Evaluating Chinese-native RAGs

@hurenjun I think you can check https://docs.ragas.io/en/stable/howtos/customisations/bring-your-own-llm-or-embs.html Also, aliyun API compatible with Openai. you could replace base_url.

[Question] How to change custom mode name

Thanks Very much. If I just want evaluate like simple demo: ` from datasets import Dataset import os from ragas import evaluate from ragas.metrics import faithfulness, answer_correctness os.environ["OPENAI_API_KEY"] = "your-openai-key"...

can customize CORRECTNESS_INSTRUCTIONS and CORRECTNESS_PROMPT when evaluate answer_correctnes

@dosu What does the complete code example look like?

For use with Azure OpenAI services

I can answer this question. Yes, can be use azure openai `from langchain_openai.chat_models import AzureChatOpenAI azure = AzureChatOpenAI( openai_api_version=xxxx, azure_endpoint=xxxx, azure_deployment=xxxx, model=xxxx, validate_base_url=False, api_key="your key" ) agent1 = Agent( task=task,...