Discussions

We're evaluating using voyage to generate embeddings for later use in semantic search, but it appears that at least some unicode characters are not supported and cause the embedding API call to return 400 errors: {"detail":"There was an error parsing the body"}, for example Pyrex Spring Blossom Light Green Beaded Edge Nested Mixing Bowl 402 1 ½ Qt fails but Pyrex Spring Blossom Light Green Beaded Edge Nested Mixing Bowl 402 1 Qt succeeds. The same code framework succeeds for both inputs using gemini's text embedding API, so the basic handling of HTTP requests, content types and encodings is correct (the input is JSON encoded in utf-8, which is the assumed encoding for type application/json, and declaring it explicitly in the content-type does not change the behaviour).

Hi there

Hi, does voyage-multilingual-2support traditional Chinese? Is there performance metric available for reference?

We're trying to create a vectorstore using VoyageAI embeddings for French text. I saw one blog post vaguely mention that the rerank-1 model supports multilingual performance. Where can we find more detailed information on the multilingual performance of different models? Is there a Voyage AI embeddings model instead of a reranker that has good performance on French text?

table.embedding <=> embeddings(voyage-large-2-instruct)

I would like to get costs info (API calls, accumulated cost, etc) via API in order to be included in my Grafana panels

Thank you!

Perhaps it's on Hugging face? I'm looking for a way of experimenting with different rolling windows and retrieval query schemes, comparing performance, etc.

which languages voyage-law-2 ? does it support russian language ?

I would love to see an offering of a compressor model like microsoft/llmlingua-2, that we could use both for prompts and RAG results