#tedt

1 messages · Page 1 of 1 (latest)

silk helm
#

Hello

I’m using a quickstart guide that includes a prompt file that lets us add top level info about 2 Snowflake tables that I send to OpeanAi via a function I created: get_system_prompt
which is used like this:
st.session_state.messages = [{"role": "system", "content": get_system_prompt()}]

In this function I’ve hardcoded a table description variable that I wrote describing the 2 tables.

Unfortunately I can’t attach a link but the name of the quickstart I’m using is " Frosty: Build an LLM Chatbot in Streamlit on your Snowflake Data"

I’m looking for some recommendations on how to make this more dynamic so I don’t have to hardcode each table name, and also how to make the table description for each table? Is it necessary to include the table description, its alot of typing for like 100 tables… Open to any/all suggestions!

sleek larkBOT
#

Hi @silk helm. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

Hmm, I don't know enough to give you a confident answer yet. The extracts provided do not contain specific information about dynamically generating table descriptions or avoiding hardcoding each table name in the context of using OpenAI with Snowflake data and Streamlit.

However, OpenAI's models like GPT-3 and GPT-4 are capable of understanding and generating text based on the prompts provided to them. In the context of your question, it might be possible to create a more dynamic system by generating prompts that include the necessary table information, but the specifics of how to do this would depend on the details of your implementation and the capabilities of the OpenAI models.

For more detailed guidance, I would recommend referring to OpenAI's documentation (https://platform.openai.com/docs) and community forum (https://community.openai.com) for additional resources and discussions related to your question.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

#

@silk helm kapa.ai is still learning and improving, please let us know how it did by reacting below

crystal gulch
#

When exactly GPTs store is going to start and where can I learn about it?