-
I am wondering is there a way to evaluate GPT (OpenAI Chat Completion API) on a set of multiple choice questions such as the mmlu tasks. I know that the chat completion api does not support log likeli…
-
After actual testing, the streaming output format of Xinference differs from that of OpenAI in the following two ways:
1. OpenAI outputs in UTF-8 format, while Xinference uses Unicode encoding.
2.…
-
**Describe the bug**
If I try to update LangChain4J beyond 0.31.0 I get a Jackson JsonEOFException, when making an API call to my Azure OpenAI endpoint. The LLM streamed response does work despit…
-
### Search before asking
- [X] I had searched in the [issues](https://github.com/eosphoros-ai/DB-GPT/issues?q=is%3Aissue) and found no similar issues.
### Operating system information
Linux
### P…
-
Hey guys,
Did anyone tried the project in VR?
For me everything works fine from the Unity editor but not on the Meta Quest build. I dit a test with the "microphone" permisions and it work well …
-
OpenAI starts to support [stream_options](https://platform.openai.com/docs/api-reference/chat/create#chat-create-stream) in the chat completion API.
We should look into how to support it in Azure O…
-
- Chat GPT 형식의 대화의 경우, 질문과 답변이 대부분 텍스트의 형태로 이루어진다.
- AI 캐릭터 대화의 경우, 배경 이미지와 질문과 답변, 그리고 해당 캐릭터의 프로필 정보를 받아와야 한다.
고로 두 대화기록을 따로 분리하여 관리하는 것이 효율적이라 생각된다.
1. AI 캐릭터 대화 기록의 경우 @mongo_router에 /chat/..…
-
I tried #26 and gguf model type didn't get picked up by llm until I registered a model with "llm llama-cpp add-model". I'm not sure if this is working as intended - I expected that gguf would appear …
-
docker run -p 8001:8001 -e APP_SECRET=abcd yeschat2api
INFO: Started server process [1]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn run…
-
### Is there an existing issue for the same bug?
- [X] I have checked the existing issues.
### Branch name
infiniflow/ragflow
### Commit ID
#flaskwrongrag0004
### Other environment information
…