Anush
Anush
Hey @fronx. Since Qdrant is agnostic to embeddings, it provides a client-side way to generate them easily, which is the integration with FastEmbed. The Qdrant-Dspy integration uses the FastEmbed methods...
@satyaloka93, to use the DSpy Qdrant integration for search, you'll have to add the docs to Qdrant using the `add()` method as shown here. https://github.com/qdrant/qdrant-client?tab=readme-ov-file#fast-embeddings--simpler-api
I think such an infinite loop would lead to such results and won't continue running endlessly due to some eventual state build-up. Though I am no expert in performance details.
Got it. Maybe @decahedron1 could have suggestions.
Hey @orgroman. Can we get some code snippets of Qdrant's instantiation or calls that you're performing, which could help reproduce this issue?
Hi @KevinHuSh, could you reopen the PR so that I can add changes to the same? Instead of opening a new one.
Hey. The Rust based tokenizers library uses https://github.com/napi-rs/napi-rs for Node bindings. From the error, it appears like Webpack is having issues with bundling it. Could you try using fastembed in...
Thanks for the insight @sorokinvj
Hi @elkay. I'm working on a prototype that you might find interesting. Can you try ```javascript import { TextEmbedding, EmbeddingModel } from 'fasterembed' const model = new TextEmbedding(EmbeddingModel.AllMiniLML6V2); let documents...
After installing using ```bash npm install fasterembed ```