timothycarambat
commented
3 months ago Are you connected to the internet? The native embedder model downloads on first use so that it does not bloat the app or your system if you use another embedder instead.
Looks like here all that is occurring is the embedder cannot download (firewall, connection, etc) and its blocking embedding
How are you running AnythingLLM?
Docker (local)
What happened?
Failed to vectorize documents, unable to upload text files, csv, pdf etc.
Adding new vectorized document into namespace test 2024-06-04 15:49:24 [NativeEmbedder] Initialized 2024-06-04 15:49:24 [RecursiveSplitter] Will split with { chunkSize: 1000, chunkOverlap: 20 } 2024-06-04 15:49:24 Chunks created from document: 1 2024-06-04 15:49:24 [NativeEmbedder] The native embedding model has never been run and will be downloaded right now. Subsequent runs will be faster. (~23MB) 2024-06-04 15:49:24 [NativeEmbedder] Downloading Xenova/all-MiniLM-L6-v2 from https://s3.us-west-1.amazonaws.com/public.useanything.com/support/models/ 2024-06-04 15:49:27 [NativeEmbedder] Failed to download model from primary URL. Using fallback https://s3.us-west-1.amazonaws.com/public.useanything.com/support/models/ 2024-06-04 15:49:27 [NativeEmbedder] Downloading Xenova/all-MiniLM-L6-v2 from https://s3.us-west-1.amazonaws.com/public.useanything.com/support/models/ 2024-06-04 15:49:28 addDocumentToNamespace fetch failed 2024-06-04 15:49:28 Failed to vectorize datacsv.csv
Are there known steps to reproduce?
No response