Clément Tamines

Hi @lz-chen, Thanks for merging my PR into your update! I reviewed the original changes and tested them with `azure-search-documents==11.4.0`, and everything seems to work just fine :) My PR...

I just realized that the `RunnablePassthrough()` in the provided code sample from the documentation is not correct, as it results in the whole input (document key + question key) being...

Here is a full example script with the new LangChain representation in action (both with basic and advanced usage, and with list output in the case of advanced usage). ```python...

> Ran it with success (yay!) on our system, but got some weird results. Our data input is a set of transcripts of presentations on subsidence. Many of the labels...

> I might be missing something here, but in the examples you showed the OpenAI Representation: seems like a good label, right? I think that in the provided examples of...

Hello, Just checking in to see if anyone else has had a chance to test the basic and advanced usage with a non-OpenAI LLM? I believe the solutions I proposed...

Hi, Thanks for taking the time to reply 😊 > That said, I'm actually a big fan of using tags like "[KEYWORDS]" and "[DOCUMENTS]" to indicate where in the prompt...

(disclaimer: I used ChatGPT to help generate this reply because I didn't have much time 😄) > I agree with the things that you mention, which kinda makes it difficult...

FYI I've updated the PR with all changes discussed above (+ documentation). I'm not too sure about the logic around the vector output with a bunch of empty labels so...