Thoonsen Maxime comments

Results 84 comments of


                                            Thoonsen Maxime

How do I add prompts in VectorDBQAChain?

I haven't tried it

ManyToMany field is not updated correctly

Thanks @alexhayes for your message ! I'll add our use case if it can help someone else. We have a One-To-Many relation and I want to have everything in a...

[Bug] `generateChat` does not process tools like `generateText` does

Hey @vijaythecoder , do you prefer the behavior of generateText or the behavior of generateTextOrReturnFunctionCalled that gives you more control over the way the function is called?

Feature Request: support for image embeddings

@andrefrcastro I agree it would be cool. What do you use to generate the embeddings of images for now?

[Feature] - Add ChromaDB support for Vector Storage

hey @f-lombardo , For now I add this kind of specific dependencies in the "suggest" section. So we can keep it light and avoid a dependencies hell. Sounds good to...

[Feature] - Add ChromaDB support for Vector Storage

@f-lombardo yes!

How to use stream to return a message even instead of waiting until everything has been processed

hey @pslxx , there are dedicated method in the ChatInterface like `generateStreamOfText`. Does it help you?

How to use stream to return a message even instead of waiting until everything has been processed

hello @ezimuel, how are you? It seems there is a lot of questions around streaming. Can we still do streaming with [StreamInterface](https://www.php-fig.org/psr/psr-7/#34-psrhttpmessagestreaminterface) and LLPhant? What is the "clean/simple" working example?...

Added extra function to return function return value from chat

hey @samuelgjekic, thanks a lot for the PR! Can you please rebase your branch with main so I can review only the file that changed?

feat(#111): support user-defined embedding dimensions

Hey @bernard-ng , I suggest you throw an "not implemented" exception when it is not used with OpenAI. Sound good to you?