Spacy Relation Component Unable to predict

[shahidkhan021]

i have trained a transformer model with relation component added to pipe line by cloning
python -m spacy project clone tutorials/rel_component
then i was able to train the model successfully then i used following code for prediction

import typer
from pathlib import Path
import spacy 
from spacy.tokens import DocBin, Doc
from spacy.training.example import Example 
from scripts.rel_pipe import make_relation_extractor, score_relations
from scripts.rel_model import create_relation_model, create_classification_layer, create_instances, create_tensors

nlp2 = spacy.load("training/model-best")
doc = nlp2(Text[0])
for name, proc in nlp2.pipeline:
  doc = proc(doc)
  for value, rel_dict in doc._.rel.items():
    for sent in doc.sents:
      for e in sent.ents:
        for b in sent.ents:
          if e.start == value[0] and b.start == value[1]:
            if rel_dict['EXPERIENCE_IN'] >=0.9 :
              print(f" entities: {e.text, b.text} --> predicted relation: {rel_dict}")

but when i execute above code i am getting this message
Could not determine any instances in doc - returning doc as is. can anybody help on this

[svlandeg]

Hi! This typically means that no relevant entities were found to create REL candidate instances with. Does your pipeline have an ner component?

[shahidkhan021]

when i train i am getting this message
ℹ Pipeline: ['transformer', 'relation_extractor']
so i believe there is no ner pipeline sorry for this dumb question and can help me to add ner pipeline to this

[svlandeg]

Have a look at a related discussion thread here: #8499 ;-)