Using OpenAI for Embedding Generation in Your Project

or to direct it to use openai which i've used for my embedding generation already?

· Sorted by Oldest

Aman K.
·
Hi Yujian T. it might be helpful to understand what you’re aimining to do here! if you’re looking to log data from your langchain application, we recommend tracing here: https://docs.arize.com/arize/large-language-models/quickstart-llm#langchain If you already have embeddings generated you’re looking to log to arize for RAG application (monitoring embeddings/LLM response generation), we recommend the approach here: https://docs.arize.com/arize/large-language-models/troubleshoot-retrieval-with-vector-stores Let me know if neither of these work - I’ll note to the team we need to update langchain ArizeCallbackHandler docs

Aman K.
·
Hi Yujian T. it might be helpful to understand what you’re aimining to do here! if you’re looking to log data from your langchain application, we recommend tracing here: https://docs.arize.com/arize/large-language-models/quickstart-llm#langchain If you already have embeddings generated you’re looking to log to arize for RAG application (monitoring embeddings/LLM response generation), we recommend the approach here: https://docs.arize.com/arize/large-language-models/troubleshoot-retrieval-with-vector-stores Let me know if neither of these work - I’ll note to the team we need to update langchain ArizeCallbackHandler docs