Hi Im trying to follow this example to utilize open AI models (text-embedding-ada-002, text-embedding-3-large") on files that are scraped via the FSCrawler. The mapping , chunking and ingesting pipeline is taken from this blog . However Im getting the following error when running the inference ingestion process on each chunk:
pipeline 'my_openai_embedding_model' failed with message '[inference_id] is configured for the _inference API and does not accept documents as input
am I doing something wrong or is it some open AI limitation? The same processed worked fine using locally deployed model "sentence-transformers__all-minilm-l12-v2".
I appreciate your help.
Thanks