# FSCrawler and Open AI model
**URL:** https://discuss.elastic.co/t/fscrawler-and-open-ai-model/372299
**Category:** Elastic Search
**Created:** [December 22, 2024, 6:06am UTC](https://discuss.elastic.co/t/fscrawler-and-open-ai-model/372299 "2024-12-22T06:06:54Z")
**Posts on this page:** 2
**Page:** 1
### Author:  [@samer\_saleh](https://discuss.elastic.co/u/samer_saleh)
#### Post date: [December 22, 2024, 6:06am UTC](https://discuss.elastic.co/t/fscrawler-and-open-ai-model/372299/1 "2024-12-22T06:06:54Z")
Hi Im trying to follow this [example](https://github.com/elastic/elasticsearch-labs/blob/main/notebooks/search/07-inference.ipynb) 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](https://www.elastic.co/search-labs/blog/chunking-via-ingest-pipelines) . However Im getting the following error when running the inference ingestion process on each chunk:
```auto
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
---
### Author:  [@system](https://discuss.elastic.co/u/system)
#### Post date: [January 19, 2025, 6:07am UTC](https://discuss.elastic.co/t/fscrawler-and-open-ai-model/372299/2 "2025-01-19T06:07:43Z")
This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.