Preston Rasmussen

Hey, thanks for the question! Unfortunately ~12 seconds per message is about the expected time assuming you are using openAI models. For some broader context: the `add_episode` method does quite...

Partitioning by user was an example, you can create a partition for any subgraph that you want, you'll just have to define a `group_id` for each partition. Does it make...

All of these changes will reduce accuracy. `add_episode` is a process that can be done asynchronously outside of an end user's control flow so efficacy takes precedence of latency for...

Yes, that dependency got added automatically when I rebuilt poetry at one point and I didn't catch it. Thanks for catching this and I will remove it.

this has now been fixed. Thank you again.

This is really amazing work, thank you for putting this together. We agree that it adds a lot of value. It's a large PR and I had some urgent stuff...

Hey, What service are you using for DeepSeek? If you are using something like Ollama to deploy it locally you should be able to deploy it to an openAI compatible...

Hey, so graphiti has a generic abstract `EmbedderClient` that is used for our actual calls. It implements `embedderClient.create` and `embedderClient.create_batch` methods. If you want to use an embedder that isn't...

Yes, we definitely need to add this to graphiti. Funnily enough we use an HF embedder in our deployment of graphiti so we can just port that over

You are correct in that the max() line of logic is incorrect. However, the tie-breaking isn't completely handled by line 107 since a node could have a community shared by...