Why pipeline transformations not executing in order

ooedemis

why this dont work? transformations = []
transformations.append(TitleExtractor(nodes=5))
transformations.append(QuestionsAnsweredExtractor(questions=3))
transformations.append(Settings.embed_model)
transformations.append(splitter)
transformations.append(node_parser)

transformations = []

pipeline = IngestionPipeline(
transformations=transformations,
vector_store=vector_store,
)
nodes = pipeline.run(documents=docs), it should first parse then split then do the titleextraction etc. it dont split the doc

4 comments

LLogan M

It runs the transformations in order

LLogan M

If you want to split first, and the splitter/node parser first

LLogan M

Normally the order would be splitter -> extractors -> embeddings

ooedemis

i have a special node-parse i run it first then split then try the extractors, but the splitter dont start

Add a reply

Find answers from the community

Why pipeline transformations not executing in order