Azure OpenAI Services document search for multiple items at once

Community
,
1

I am new to OpenAI and I am using it for document search after the embedding process. In the given example from the blog, I need to ask questions individually. However, in my use case, I have more than 10 questions and I would like to use a prompt to run the top 4 questions all together. Can someone help me modify the code to accommodate all my 10 questions in “res = search_docs”?

The blog I am using: Azure OpenAI Service embeddings tutorial - Azure OpenAI | Microsoft Learn

The code snippet I need help on :

# search through the reviews for a specific product
def search_docs(df, user_query, top_n=3, to_print=True):
    embedding = get_embedding(
        user_query,
        engine="text-embedding-ada-002" # engine 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?", to
2

I am not familiar with Azure but if I am going to implement this to vanilla code, here is how I will do it:

1. submit user query with X number of questions 
2. use function calling to extract all X questions from user query (1 chat api call)
3. run each questions in embeddings api ( X embeddings api call)
4. process each question embeddings vector one by one with your stored embeddings
5. gather all the results and submit to chat api for summary (1 chat api call)