ai-agents-chroma-embedding-com-chroma-from-documents-or-similar-calls-fail-with-v-3eddb0d2

THEN Update the embedding function's __call__ method to accept exactly two arguments: self and input. Pass a single input argument (not args/kwargs) when calling the embedding function. Also adjust predict_fn in custom inference scripts to return batched vectors without indexing single element (e.g., return sentence_embeddings.tolist() instead of sentence_embeddings[0].tolist()).

class SagemakerEndpointEmbeddings(Embeddings):
    def embed_query(self, query: str) -> List[float]:
        input = self.prepare_input(query)
        return self.embedding_function(input)

    def embed_documents(self, documents: List[str]) -> List[List[float]]:
        input = self.prepare_input(documents)
        return self.embedding_function(input)