PostgreSQL, Ollama, and the DBeaver AI Assistant

Ollama is an open-source project that simplifies running large language models (LLMs). It runs locally on your machine, and you can choose from multiple LLMs. Keeping all the data on your machine should provide a security bonus.   

DBeaver is a universal database tool with an AI Assistant. This assistant provides an extra layer of security by allowing you to lock down what is shared, with the default being metadata only, no data.

Webinar

I recently presented a webinar on using the DBeaver AI Assistant. Several questions were raised about using Ollama, one of the many AI Engines available. But I had not tried it.

The first step is downloading Ollama for your platform (Linux, Windows, or Mac) and installing.  Once you have Ollama installed, you will need to pick a LLM.  I chose the Gemma3 and installed it using the command line client.

Adding the Gemma3 LLM to Ollama


DBeaver Configuration

Ollama listens on port 11434. I was able to load the Gemma3 model using the 'Load Model' button.

Sample Ollama Settings for Dbeaver EE


Example 1

I started with a simple address book type schema and asked about one last name - @ai who in the address_book has a name last name of Jones?


Finding the Jones

Example 2


The nest test was more of a conversation.

Using the AI Assistant in DBeaver to converse with Ollama

And the results:



Summary


DBeaver works well with Ollama.  To me, Ollama is many times slower than the paid AI engines. Now my laptop is not a superpower GPU-laden machine.  And maybe the Gemma3 engine is not the optimum for database work.  But it does work and is a good place for starting the exploration of your data with an AI.














Comments

Post a Comment

Popular posts from this blog

Incremental Backups in PostgreSQL 17

 The old adage that a DBA or SRE is only as good as their last backup is true.  PostgreSQL 17 added the ability to combine multiple incremental backups with a full backup to provide a complete data dictionary to recover a failed system. It is very easy to use. This is a quick example of using incrementals. I recommend watching this video by Robert Haas for more details and some discussion of backup strategies. Step 1 - Enable WALL Summerization The incremental backups require Write Ahead Log Summarization. It is likely not on your instance by default. But it is easy to enable. demo=# alter system set summerize_wal = 'on'; ALTER SYSTEM demo=# select pg_reload_conf(); pg_reload_conf  ----------------  t (1 row) Step 2 - Full Backup The examples below are much simpler than you will run into in real life.  The scenario is that we make a full backup on Sunday and do incrementals the rest of the week. Wednesday through Saturday are omitted below.  stoker@ThinkPa...
Read more

Can Artificial Intelligence Created Better Tables Than You?

 Artificial Intelligence is one of those conundrums where the ability to have some tasks handled for you contrasts with a mix of ego and pride that it may be better than you at those tasks.  I recently wrote a blog using another database about an AI-generated SQL that was quite sophisticated . But what about asking an AI to create a table with a specification like a DBA/SRE/Analyst might receive? I used Grok and entered the following prompt: Write the SQL to create a table on a PostgreSQL version 17 server to record data on customers. The data will include a first name, a last name, an address, a birthdate, and a unique UUID primary key. Partition the data by the year of birth. And produce some test data of at least ten records. I am sure many of us have started large projects given less instruction.  Notice: I did not denote the format for the address (US Post Office's format, or UK, or other). Nor did I set a name length. I wanted to see what assumptions were made by t...
Read more

Saving The Output From psql

  Occasionally, you will need to capture data when working with a database. You can cut-n-paste or use a shell command like script . In typical PostgreSQL fashion, psql  has two ways to save your output. The First Way You must invoke psql with the --log-file-<filename> or -L <filename> option. The entire session will be recorded. stoker@ThinkPad:~$ psql --log-file=/tmp/psqllog demo Password for user stoker: psql (17.4 (Ubuntu 17.4-1.pgdg24.04+2)) Type "help" for help. demo=# \d ledger                    Table "public.ledger"      Column     |  Type   | Collation | Nullable | Default ----------------+---------+-----------+----------+---------  id             | integer |           |          |  tx_id          | integer |        ...
Read more