embedding_function_interfaceTier 1 · 70% confidence

ai-agents-embedding-function-i-valueerror-expected-embeddingfunction-call-to-have-12889d96

agent: ai_agents

When does this happen?

IF ValueError: Expected EmbeddingFunction.__call__ to have signature odict_keys(['self', 'input']) but got odict_keys(['self', 'args', 'kwargs']) after Chroma update on Nov 7, 2023.

How others solved it

THEN Update your embedding function's __call__ method to accept a single 'input' argument instead of *args and **kwargs. Modify the embed_query and embed_documents methods to call the embedding function with a prepared input argument rather than passing splatted arguments.

class MyEmbeddingFunction:
    def __call__(self, input):
        # Process the single input
        return model.encode(input)

# Usage
embeddings = MyEmbeddingFunction()
Chroma.from_documents(documents=document, embedding=embeddings)

Related patterns

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics