# SentenceSimilarityInputsCheck expected dict not list: \`\_\_root\_\_\` in \`parameters\` **URL:** \ **Category:** Beginners\ **Created:** [May 13, 2023, 1:15am UTC](https://discuss.huggingface.co/t/sentencesimilarityinputscheck-expected-dict-not-list-root-in-parameters/39715 "2023-05-13T01:15:46Z")\ **Posts on this page:** 1\ **Showing post:** 2
**Author:** ![radames](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/radames/32/28246_2.png) [@radames](https://discuss.huggingface.co/u/radames)\ **Post date:** [May 16, 2023, 12:29am UTC](https://discuss.huggingface.co/t/sentencesimilarityinputscheck-expected-dict-not-list-root-in-parameters/39715/2 "2023-05-16T00:29:54Z")
Hi @Denaldo, Our API Inference supports multiple tasks. For certain models, we provide a straightforward abstraction for embedding similarity, such as with sentences. The `tag` and/or `pipeline_tag` establishes the correct task on the API Inference backend for all compatible models on our hub. When using `sentence-similarity`, the backend establishes a sentence similarity pipeline. It expects multiple sentence inputs, which will subsequently be transformed into embeddings and compared through cosine similarity When the model is set for `feature-extraction`, it expects the input sentence and returns the corresponding embeddings vector. So if you need a model that is not supported into the `feature-extraction` pipeline, you can duplicate it and set the correct `tag` and `pipeline_tag`. You can check the [`README.md`](https://huggingface.co/questgen/all-mpnet-base-v2-feature-extraction-pipeline/blob/main/README.md) in different models for comparison --- _[View the full topic](https://discuss.huggingface.co/t/sentencesimilarityinputscheck-expected-dict-not-list-root-in-parameters/39715)._