Ollama

The UC AI Ollama package provides integration with locally-running Ollama instances, allowing you to use open-source language models within your Oracle database applications.

Features

• Support for popular open-source models (Llama, Mistral, Qwen, DeepSeek, Gemma, Phi, CodeLlama)
• Full function calling (tools) support
• Reasoning capabilities with models that support it
• Multi-modal support (text, images, PDFs) with models that support it
• No API keys required (runs locally)

Prerequisites

1. Install and run Ollama on your local machine or server
2. Download the models you want to use
3. Ensure Oracle database can access the Ollama API endpoint

You can follow the Ollama installation guide for detailed instructions on setting up Ollama. You can run it containerized or directly on your machine, or install the MacOS/Windows GUI application.

Configuration

By default, the package connects to http://localhost:11434/api/chat. If your Ollama instance is running on a different host or port, you’ll need to modify the c_api_url constant in the package body.

-- In my case the database is running in a Docker container, so I use the host's internal address
uc_ai.g_base_url := 'host.containers.internal:11434/api';

-- instead you can use any ip or hostname
uc_ai.g_base_url := 'example-ollama-server.com:11434/api';

Models

Ollama support a wide range of open-source models, you can browse them on the Ollama website. The UC AI Ollama package does not come with pre-defined model constants as you can only use models that you have downloaded and installed locally. So instead create or own constants like qwen3:8b for the 8 billion parameter Qwen 3 model.

Usage Examples

Basic Text Generation

declare
  l_result json_object_t;
begin
  uc_ai.g_base_url := 'host.containers.internal:11434/api';

  l_result := uc_ai.generate_text(
    p_user_prompt => 'What is Oracle APEX?',
    p_provider => uc_ai.c_provider_ollama,
    p_model => 'qwen3:8b'
  );

  dbms_output.put_line('AI Response: ' || l_result.get_string('final_message'));
end;
/

With System Prompt

declare
  l_result json_object_t;
begin
  l_result := uc_ai.generate_text(
    p_user_prompt => 'Write a SQL query to find all employees hired this year',
    p_system_prompt => 'You are a helpful SQL expert. Write clean, efficient queries.',
    p_provider => uc_ai.c_provider_ollama,
    p_model => 'codellama:70b'
  );

  dbms_output.put_line('SQL Query: ' || l_result.get_string('final_message'));
end;
/

Using Tools/Function Calling

Refer to the list of models that support tools to find models that can use function calling. Note that small models might support it but are not very capable to do complex tasks with it. I noticed that enabling reasoning can help the LLM to call the tools more effectively.

See the tools guide for details on how to set up and use tools.

Multi-modal Analysis

Refer to the list of models that support vision to find models that can use to analyze images.

Refer to the file analysis guide for examples on how to analyze images.

Reasoning / Thinking

Make sure that you use a model that supports reasoning, such as qwen3:8b or deepseek-r1:8b. Here is a list of models that support reasoning.

Make sure to set the uc_ai.g_enable_reasoning variable to true in the package specification.

declare
  l_result json_object_t;
begin
  uc_ai.g_base_url := 'host.containers.internal:11434/api';
  uc_ai.g_enable_reasoning := true;

  l_result := uc_ai.GENERATE_TEXT(
    p_user_prompt => 'Answer in one sentence. If there is a great filter, are we before or after it and why.',
    p_provider => uc_ai.c_provider_ollama,
    p_model => c_model_qwen_4b
  );

  dbms_output.put_line('AI Response: ' || l_result.get_string('final_message'));
end;
/