Pipelines models reference Innovation Release

SELECT * FROM aidb.models;

 name  |  provider  |    options
-------+------------+---------------
 bert  | bert_local | {"config={}"}
 clip  | clip_local | {"config={}"}
 t5    | t5_local   | {"config={}"}

SELECT aidb.create_model(
               name => 'my_t5'::text,
               provider => 't5_local'::character varying,
               config => '{"param1": "value1", "param2": "value2"}'::jsonb,
               credentials => '{"token": "abcd"}'::jsonb
           );

SELECT aidb.create_model('my_t5', 't5_local');

SELECT aidb.create_model(
               name => 'my_t5'::text,
               provider => 't5_local'::character varying,
               config => '{"param1": "value1", "param2": "value2"}'::jsonb,
               credentials => '{"token": "abcd"}'::jsonb,
               replace_credentials => true
           );

"tls_config": {
  "insecure_skip_verify": true,  // (optional) disables certificate validation
  "ca_path": "/etc/aidb/myCA.pem"  // (optional) path to a trusted CA certificate
}

SELECT * FROM aidb.get_model('t5');

 name | provider |    options
------+----------+---------------
 t5   | t5_local | {"config={}"}
(1 row)

SELECT aidb.delete_model('t5');

     delete_model
---------------------------------
 (t5,t5_local,"{""config={}""}")
(1 row)

SELECT * FROM  aidb.get_hcp_models();
                 name                  |                                       url                                        |               model
---------------------------------------+----------------------------------------------------------------------------------+------------------------------------
 llama-3-1-8b-instruct-1xgpu-g6        | http://llama-3-1-8b-instruct-1xgpu-g6-predictor.default.svc.cluster.local        | meta/llama-3.1-8b-instruct
 llama-3-2-nv-embedqa-1b-v2            | http://llama-3-2-nv-embedqa-1b-v2-predictor.default.svc.cluster.local            | nvidia/llama-3.2-nv-embedqa-1b-v2
 meta-nim-llama3-70b-instruct-8xgpu-g5 | http://meta-nim-llama3-70b-instruct-8xgpu-g5-predictor.default.svc.cluster.local | meta/llama3-70b-instruct
(3 rows)

-- Basic usage
SELECT aidb.decode_text('t5', 'translate to german: hello world');

-- With inference configuration
SELECT aidb.decode_text(
    'llama',
    'Explain quantum computing.',
    aidb.inference_config(
        system_prompt => 'Be concise and factual.',
        temperature => 0.7,
        max_tokens => 100
    )::json
);

-- Basic usage
SELECT * FROM aidb.decode_text_batch('t5', ARRAY[
    'translate to german: hello',
    'translate to german: goodbye'
]);

-- With inference configuration
SELECT * FROM aidb.decode_text_batch(
    't5',
    ARRAY['summarize: a very long text goes here', 'summarize: another text'],
    aidb.inference_config(
        temperature => 0.3,
        max_tokens => 50,
        seed => 42
    )::json
);

-- Basic inference configuration
SELECT aidb.decode_text(
    'llama',
    'Explain relativity.',
    aidb.inference_config(
        temperature => 0.7,
        max_tokens => 200
    )::json
);

-- Full configuration with system prompt
SELECT aidb.decode_text(
    'llama',
    'What is machine learning?',
    aidb.inference_config(
        system_prompt => 'You are a computer science professor. Explain concepts clearly.',
        temperature => 0.5,
        max_tokens => 150,
        top_p => 0.9,
        seed => 42,
        repeat_penalty => 1.1,
        repeat_last_n => 64
    )::json
);

-- With thinking tags control (for reasoning models)
SELECT aidb.decode_text(
    'reasoning_model',
    'Solve this step by step: 2x + 5 = 15',
    aidb.inference_config(
        thinking => false,  -- Hide internal reasoning
        temperature => 0.3
    )::json
);

-- With provider-specific extra arguments
SELECT aidb.decode_text(
    'openai_model',
    'List three colors.',
    aidb.inference_config(
        max_tokens => 50,
        extra_args => '{"stop": ["\n\n"], "logprobs": true}'::jsonb
    )::json
);

-- Use with summarize_text_config
SELECT aidb.summarize_text(
    'Long text to summarize...',
    aidb.summarize_text_config(
        't5',
        inference_config => aidb.inference_config(
            temperature => 0.3,
            max_tokens => 100
        )
    )::json
);

SELECT aidb.create_model(
  'my_model',
  'openai_embeddings',
  aidb.embeddings_config(model => 'text-embedding-3-small'),
  '{"api_key": "sk-..."}'::JSONB
);

-- Basic configuration
SELECT aidb.create_model(
  'my_model',
  'openai_completions',
  aidb.completions_config(model => 'gpt-4o'),
  '{"api_key": "sk-..."}'::JSONB
);

-- Configuration with default inference settings
SELECT aidb.create_model(
  'my_assistant',
  'openai_completions',
  aidb.completions_config(
    model => 'gpt-4o',
    system_prompt => 'You are a helpful assistant.',
    temperature => 0.7,
    top_p => 0.9
  ),
  '{"api_key": "sk-..."}'::JSONB
);

aidb.completions_config(
  model => 'gpt-4o',
  max_tokens => aidb.max_tokens_config(size => 1024, format => 'default')
)