How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

Currently

• The /v1/openai/embeddings endpoint requires the "inputs" key, and it needs to be a list
• this is not compatible with the OpenAI Embedding REST API Specs, which requires the "input" key
• in consequence, the AnythingLLM embeddings REST API cannot be used with the openai sdk. Using the openai sdk, AnythingLLM returns HTTP 500

Expected

• make the /v1/openai/embeddings endpoint compatible to OpenAI's

Are there known steps to reproduce?

1. Download & install AnythingLLM Desktop
2. Add an API Key
3. Use the OpenAI Python SDK

client = OpenAI(api_key=api_key, base_url='http://localhost:3001/api/v1/openai')
embeddings = client.embeddings.create(
            model=None,
            input=[ "some text" ],
            encoding_format="float"
        ) 

Environment

• OS: Linux
• AnythingLLM Version: v1.7.4