Chroma similarity search by image not working

### Checked other resources - [x] This is a bug, not a usage question. - [x] I added a clear and descriptive title that summarizes this issue. - [x] I used the GitHub search to find a similar question and didn't find it. - [x] I am sure that this is a bug in LangChain rather than my code. - [x] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package). - [x] This is not related to the langchain-community package. - [x] I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example). - [x] I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS. ### Example Code ``` from langchain_chroma import Chroma from langchain_experimental.open_clip import OpenCLIPEmbeddings vs = Chroma(embedding_function=OpenCLIPEmbeddings()) vs.similarity_search_by_image(uri="my_local_file.jpg") --> ValueError: Expected embeddings to be a list of floats or ints, a list of lists, a numpy array, or a list of numpy arrays, got [[[0.0287, ... ]]] ``` ### Error Message and Stack Trace (if applicable) _No response_ ### Description Chroma similarity search by image does not seem to be working. It looks like this is caused by the following code: https://github.com/langchain-ai/langchain/blob/9a09ed065996df402872b7e85cd42fb18b290832/libs/partners/chroma/langchain_chroma/vectorstores.py#L892 ``` image_embedding = self._embedding_function.embed_image(uris=[uri]) (--> image_embedding is a list containing 1 list of floats) return self.similarity_search_by_vector(embedding=image_embedding, ...) --> results = self.__query_collection(query_embeddings=[embedding]) (--> [embedding] is now a list of list of list of floats) ``` We probably need this instead: `image_embedding = self._embedding_function.embed_image(uris=[uri])[0]` Can you confirm? ### System Info > Python Version: 3.11.11 (main, Dec 4 2024, 08:55:07) [GCC 11.4.0] Package Information ----------…