41–50 of 243 posts
Is the architecture they use in this diagram currently the best way to train LLMs in general on custom data sets? https://raw.githubusercontent.com/vanna-ai/vanna/main/img/va... That is, store your trained custom data in vector db and then use RAG to retrieve relevant content and inject that into the prompt of the LLM the user is querying with? As opposed to fine tuning or other methods?
The most success I had with AI+SQL was when I started feeding errors from the sql provider back to the LLM after each iteration. I also had a formatted error message wrapper that would strongly suggest querying system tables to discover schema information. These little tweaks made it scary good at finding queries, even ones requiring 4+ table joins. Even without any examples or fine tuning data.
Please turn this into a product. There's enormous demand for that.
I am not chasing this rabbit. Someone else will almost certainly catch it first. For now, this is a fun toy I enjoy in my free time. The moment I try to make money with it the fun begins to disappear.
Broadly speaking, I do think this is approximately the only thing that matters once you realize you can put pretty much anything in a big SQL database. What happens when 100% of the domain is in-scope of an LLM that has iteratively optimized itself against the schema?
The most success I had with AI+SQL was when I started feeding errors from the sql provider back to the LLM after each iteration. I also had a formatted error message wrapper that would strongly suggest querying system tables to discover schema information. These little tweaks made it scary good at finding queries, even ones requiring 4+ table joins. Even without any examples or fine tuning data.
Please turn this into a product. There's enormous demand for that.
The most success I had with AI+SQL was when I started feeding errors from the sql provider back to the LLM after each iteration. I also had a formatted error message wrapper that would strongly suggest querying system tables to discover schema information. These little tweaks made it scary good at finding queries, even ones requiring 4+ table joins. Even without any examples or fine tuning data.
Please turn this into a product. There's enormous demand for that.
- OpenAI: https://github.com/vanna-ai/vanna/blob/a4cdf7593ac0c584f7d74...
- Mistral: https://github.com/vanna-ai/vanna/blob/a4cdf7593ac0c584f7d74...
The most success I had with AI+SQL was when I started feeding errors from the sql provider back to the LLM after each iteration. I also had a formatted error message wrapper that would strongly suggest querying system tables to discover schema information. These little tweaks made it scary good at finding queries, even ones requiring 4+ table joins. Even without any examples or fine tuning data.
Please turn this into a product. There's enormous demand for that.
But sure, why not!
Earlier quoted context omitted.
Please turn this into a product. There's enormous demand for that.
I feel like by the time I could turn it into a product, Microsoft & friends will release something that makes it look like a joke. If there is no one on the SQL Server team working on this right now, I don't know what the hell their leadership is thinking. I am not chasing this rabbit. Someone else will almost certainly catch it first. For now, this is a fun toy I enjoy in my free time. The moment I try to make money…
What I'd really be interested in is being able to describe a problem space and have it generate a schema that models it. I'm actually not that bad at generating my own SQL queries.
I wish we had landed on a better acronym than RAG.
Sorry, maybe I'm just too tired to see it, but how much control do you have over the SQL query that is generated by the AI? Is there a risk that it could access unwanted portions or, worse, delete parts of your data? (the AI equivalent of Bobby Tables, so to speak)
Why not give it access to relevant parts of the database only? And read only access too?