Ayush Lall

KeyBERT had been working for me about 10-ish days ago, so I explored what had changed in the last 10 days. Apart from the new version (0.5.1) of KeyBERT being...

@tslmy As far as I can figure out, as there is no explicitly defined embedding model in your Settings, the Neo4jVectorStore defaults to text_ada_embedding_002 (which is of dimension 1536). However,...

@hemanth could it be that the error is not because of the model name? AFAIK llama-index passes three arguments to the genai.GenerativeModel class, model_name, generation_config, and safety_settings. ``` self._model =...

Will work on a PR for this. Probably a very simple modification to add the 'region' argument in AzureOpenAI class.

Hey, I found a workaround for this. It can be solved using LangChain in the [Python API.](https://github.com/NVIDIA/NeMo-Guardrails/blob/main/docs/user_guide/python-api.md) You can define your LLM in LangChain using the [Azure Chat OpenAI object](https://python.langchain.com/docs/modules/model_io/models/chat/integrations/azure_chat_openai)...