max embeddings length 512

app.py

@@ -20,11 +20,11 @@ model = AutoModel.from_pretrained("neuml/pubmedbert-base-embeddings-matryoshka")
 
 # Function to embed text using mean pooling
 def embed_text(text):
-    inputs = tokenizer(text, padding=True, truncation=True, return_tensors='pt')
+    inputs = tokenizer(text, padding=True, truncation=True, max_length=512, return_tensors='pt')
     with torch.no_grad():
         output = model(**inputs)
     embeddings = meanpooling(output, inputs['attention_mask'])
-    return embeddings[:, :256].numpy()
+    return embeddings.numpy()
 
 # Initialize ChromaDB client
 client = chromadb.Client()