Narrator remembers characters generated

[SverreNystad]

No description provided.

[SverreNystad]

I found an issue where the reasoning for embeddings_utils where removed: openai/openai-python#676

This code will work for us to fix it:

def cosine_similarity(a, b):
    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))

def get_embedding(text, model="text-embedding-ada-002"): # model = "deployment_name"
    return client.embeddings.create(input = [text], model=model).data[0].embedding

def search_docs(df, user_query, top_n=4, to_print=True):
    embedding = get_embedding(
        user_query,
        model="text-embedding-ada-002" # model should be set to the deployment name you chose when you deployed the text-embedding-ada-002 (Version 2) model
    )
    df["similarities"] = df.ada_v2.apply(lambda x: cosine_similarity(x, embedding))

    res = (
        df.sort_values("similarities", ascending=False)
        .head(top_n)
    )
    if to_print:
        display(res)
    return res


res = search_docs(df_bills, "Can I get information on cable company tax revenue?", top_n=4)