Find answers from the community

Updated 3 months ago

Error

from llama_index.core.ingestion import IngestionPipeline
from llama_index.core.node_parser import TokenTextSplitter
from elasticsearch import Elasticsearch, NotFoundError
from llama_index.extractors.entity import EntityExtractor

def run_pipeline(self, docs):
try:
text_splitter = TokenTextSplitter(
separator=" ", chunk_size=512, chunk_overlap=128
)
entity_extractor = EntityExtractor(prediction_threshold=0.5, label_entities=False, # include the entity label in the metadata (can be erroneous)
device="cpu", # set to "cuda" if you have a GPU
)
pipeline = IngestionPipeline(
transformations=[text_splitter, entity_extractor]
)
return pipeline.run(
documents=docs,
in_place=True,
show_progress=True,
)
except Exception as e:
logging.error(f"Error running pipeline: {e}")
return None
when i run this pipeline, I get this error - ERROR:root:Error running pipeline: too many values to unpack (expected 2).
when the code goes to extracting entities part, i get this error.
L
n
3 comments
Weird, I wonder if span marker updated their package. Whats the full error?
@Logan M Have pasted the detailed error above.
Thats pretty weird... If I'm reading this correctly, its an error inside nltk? Maybe try updating it?
Add a reply
Sign up and join the conversation on Discord