Nlp extended examples

Actualmente, el motor de NLP de MindsDB está impulsado por Hugging Face y OpenAI. Pero planeamos expandirnos a otras opciones de NLP en el futuro, ¡así que estén atentos!

El motor de Hugging Face de MindsDB es extensible. Estamos trabajando activamente en agregar más tareas y modelos. Si tienes una tarea o modelo específico en mente, háganoslo saber en la Comunidad de MindsDB.

Ejemplos de Hugging Face

Aquí están las tareas soportadas por MindsDB y Hugging Face:

Clasificación de Texto
Clasificación Zero-Shot
Traducción
Resumen

Veamos los ejemplos.

Clasificación de Texto

Spam

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_spam
PREDICT PRED
USING
engine = 'huggingface',
task = 'text-classification',
model_name = 'mariagrandury/roberta-base-finetuned-sms-spam-detection',
input_column = 'text',
labels = ['spam', 'ham'];

Y comprobemos su estado.

DESCRIBE hf_spam;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT *
FROM mindsdb.hf_spam
WHERE text = 'I like you. I love you.';

Al ejecutar, obtenemos:

+----+--------------------------------------------------------+-----------------------+
|PRED|PRED_explain                                            |text                   |
+----+--------------------------------------------------------+-----------------------+
|spam|{"ham":0.00020051795581821352,"spam":0.9997995495796204}|I like you. I love you.|
+----+--------------------------------------------------------+-----------------------+

Sentimiento

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_sentiment
PREDICT PRED
USING
engine = 'huggingface',
task = 'text-classification',
model_name = 'cardiffnlp/twitter-roberta-base-sentiment',
input_column = 'text',
labels = ['neg', 'neu', 'pos'];

Y comprobemos su estado.

DESCRIBE hf_sentiment;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT *
FROM mindsdb.hf_sentiment
WHERE text = 'I like you. I love you.';

Al ejecutar, obtenemos:

+----+--------------------------------------------------------------------------------+-----------------------+
|PRED|PRED_explain                                                                    |text                   |
+----+--------------------------------------------------------------------------------+-----------------------+
|pos |{"neg":0.003046575468033552,"neu":0.021965451538562775,"pos":0.9749879240989685}|I like you. I love you.|
+----+--------------------------------------------------------------------------------+-----------------------+

Sentimiento (Finanzas)

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_sentiment_finance
PREDICT PRED
USING
engine = 'huggingface',
task = 'text-classification',
model_name = 'ProsusAI/finbert',
input_column = 'text';

Y comprobemos su estado.

DESCRIBE hf_sentiment_finance;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT *
FROM mindsdb.hf_sentiment_finance
WHERE text = 'Stocks rallied and the British pound gained.';

Al ejecutar, obtenemos:

+--------+-------------------------------------------------------------------------------------------+--------------------------------------------+
|PRED    |PRED_explain                                                                               |text                                        |
+--------+-------------------------------------------------------------------------------------------+--------------------------------------------+
|positive|{"negative":0.0344734713435173,"neutral":0.06716493517160416,"positive":0.8983616232872009}|Stocks rallied and the British pound gained.|
+--------+-------------------------------------------------------------------------------------------+--------------------------------------------+

Emociones (6)

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_emotions_6
PREDICT PRED
USING
engine = 'huggingface',
task = 'text-classification',
model_name = 'j-hartmann/emotion-english-distilroberta-base',
input_column = 'text';

Y comprobemos su estado.

DESCRIBE hf_emotions_6;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT *
FROM mindsdb.hf_emotions_6
WHERE text = 'Oh Happy Day';

Al ejecutar, obtenemos:

+----+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+------------+
|PRED|PRED_explain                                                                                                                                                                                                   |text        |
+----+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+------------+
|joy |{"anger":0.0028446922078728676,"disgust":0.0009613594156689942,"fear":0.0007112706662155688,"joy":0.7692911624908447,"neutral":0.037753619253635406,"sadness":0.015293814241886139,"surprise":0.17314413189888}|Oh Happy Day|
+----+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+------------+

Toxicidad

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_toxicity
PREDICT PRED
USING
engine = 'huggingface',
task = 'text-classification',
model_name = 'SkolkovoInstitute/roberta_toxicity_classifier',
input_column = 'text';

Y comprobemos su estado.

DESCRIBE hf_toxicity;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT *
FROM mindsdb.hf_toxicity
WHERE text = 'I like you. I love you.';

Al ejecutar, obtenemos:

+-------+-------------------------------------------------------------+-----------------------+
|PRED   |PRED_explain                                                 |text                   |
+-------+-------------------------------------------------------------+-----------------------+
|neutral|{"neutral":0.9999547004699707,"toxic":0.00004535282641882077}|I like you. I love you.|
+-------+-------------------------------------------------------------+-----------------------+

ESG (6)

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_esg_6
PREDICT PRED
USING
engine = 'huggingface',
task = 'text-classification',
model_name = 'yiyanghkust/finbert-esg',
input_column = 'text';

Y comprobemos su estado.

DESCRIBE hf_esg_6;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT * FROM  mindsdb.hf_esg_6
WHERE text = 'Rhonda has been volunteering for several years for a variety of charitable community programs.';

Al ejecutar, obtenemos:

+------+---------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------------------------------------------------------+
|PRED  |PRED_explain                                                                                                                     |text                                                                                          |
+------+---------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------------------------------------------------------+
|Social|{"Environmental":0.0034267122391611338,"Governance":0.004729956854134798,"None":0.001239194767549634,"Social":0.9906041026115417}|Rhonda has been volunteering for several years for a variety of charitable community programs.|
+------+---------------------------------------------------------------------------------------------------------------------------------+----------------------------------------------------------------------------------------------+

ESG (26)

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_esg_26
PREDICT PRED
USING
engine = 'huggingface',
task = 'text-classification',
model_name = 'yiyanghkust/finbert-esg',
input_column = 'text';

Y comprobemos su estado.

DESCRIBE hf_esg_26;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT *
FROM mindsdb.hf_esg_26
WHERE text = 'We believe it is essential to establish validated conflict-free sources of 3TG within the Democratic Republic of the Congo (the “DRC”) and adjoining countries (together, with the DRC, the “Covered Countries”), so that these minerals can be procured in a way that contributes to economic growth and development in the region. To aid in this effort, we have established a conflict minerals policy and an internal team to implement the policy.';

Al ejecutar, obtenemos:

+------+-----------------------------------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|PRED  |PRED_explain                                                                                                                 |text                                                                                                                                                                                                                                                                                                                                                                                                                                                    |
+------+-----------------------------------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|Social|{"Environmental":0.2031959593296051,"Governance":0.08251894265413284,"None":0.050893042236566544,"Social":0.6633920073509216}|We believe it is essential to establish validated conflict-free sources of 3TG within the Democratic Republic of the Congo (the “DRC”) and adjoining countries (together, with the DRC, the “Covered Countries”), so that these minerals can be procured in a way that contributes to economic growth and development in the region. To aid in this effort, we have established a conflict minerals policy and an internal team to implement the policy.|
+------+-----------------------------------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

Discurso de Odio

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_hate
PREDICT PRED
USING
engine = 'huggingface',
task = 'text-classification',
model_name = 'Hate-speech-CNERG/bert-base-uncased-hatexplain',
input_column = 'text';

Y comprobemos su estado.

DESCRIBE hf_hate;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT *
FROM mindsdb.hf_hate
WHERE text = 'I like you. I love you.';

Al ejecutar, obtenemos:

+------+-----------------------------------------------------------------------------------------------+-----------------------+
|PRED  |PRED_explain                                                                                   |text                   |
+------+-----------------------------------------------------------------------------------------------+-----------------------+
|normal|{"hate speech":0.03551718592643738,"normal":0.7747423648834229,"offensive":0.18974047899246216}|I like you. I love you.|
+------+-----------------------------------------------------------------------------------------------+-----------------------+

Señales de Compra de Criptomonedas

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_crypto
PREDICT PRED
USING
engine = 'huggingface',
task = 'text-classification',
model_name = 'ElKulako/cryptobert',
input_column = 'text';

Y comprobemos su estado.

DESCRIBE hf_crypto;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT *
FROM mindsdb.hf_crypto
WHERE text = 'BTC is killing it right now';

Al ejecutar, obtenemos:

+-------+------------------------------------------------------------------------------------------+---------------------------+
|PRED   |PRED_explain                                                                              |text                       |
+-------+------------------------------------------------------------------------------------------+---------------------------+
|Bullish|{"Bearish":0.0002816587220877409,"Bullish":0.559426486492157,"Neutral":0.4402918517589569}|BTC is killing it right now|
+-------+------------------------------------------------------------------------------------------+---------------------------+

Partido Político de EE.UU.

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_us_party
PREDICT PRED
USING
engine = 'huggingface',
task = 'text-classification',
model_name = 'm-newhauser/distilbert-political-tweets',
input_column = 'text';

Y comprobemos su estado.

DESCRIBE hf_us_party;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT *
FROM mindsdb.hf_us_party
WHERE text = 'This pandemic has shown us clearly the vulgarity of our healthcare system. Highest costs in the world, yet not enough nurses or doctors. Many millions uninsured, while insurance company profits soar. The struggle continues. Healthcare is a human right. Medicare for all.';

Al ejecutar, obtenemos:

+--------+-------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|PRED    |PRED_explain                                                       |text                                                                                                                                                                                                                                                                          |
+--------+-------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|Democrat|{"Democrat":0.9999973773956299,"Republican":0.00000261212517216336}|This pandemic has shown us clearly the vulgarity of our healthcare system. Highest costs in the world, yet not enough nurses or doctors. Many millions uninsured, while insurance company profits soar. The struggle continues. Healthcare is a human right. Medicare for all.|
+--------+-------------------------------------------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

Detección de Preguntas

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_question
PREDICT PRED
USING
engine = 'huggingface',
task = 'text-classification',
model_name = 'shahrukhx01/bert-mini-finetune-question-detection',
input_column = 'text',
labels = ['question', 'query'];

Y comprobemos su estado.

DESCRIBE hf_question;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT *
FROM mindsdb.hf_question
WHERE text = 'Where can I buy electronics in London';

Al ejecutar, obtenemos:

+-----+--------------------------------------------------------------+-------------------------------------+
|PRED |PRED_explain                                                  |text                                 |
+-----+--------------------------------------------------------------+-------------------------------------+
|query|{"query":0.9997773766517639,"question":0.00022261829872149974}|Where can I buy electronics in London|
+-----+--------------------------------------------------------------+-------------------------------------+

Industria

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_industry
PREDICT PRED
USING
engine = 'huggingface',
task = 'text-classification',
model_name = 'sampathkethineedi/industry-classification',
input_column = 'text';

Y comprobemos su estado.

DESCRIBE hf_industry;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT *
FROM mindsdb.hf_industry
WHERE text = 'Low latency is one of our best cloud features';

Al ejecutar, obtenemos:

+----------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------+
|PRED            |PRED_explain                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |text                                         |
+----------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------+
|Systems Software|{"Advertising":0.000006795735771447653,"Aerospace & Defense":0.00001537964453746099,"Apparel Retail":5.350161131900677e-7,"Apparel, Accessories & Luxury Goods":0.000002604161181807285,"Application Software":0.009111878462135792,"Asset Management & Custody Banks":0.00003155150625389069,"Auto Parts & Equipment":0.000015504940165556036,"Biotechnology":6.533917940032552e-8,"Building Products":7.348538133555849e-8,"Casinos & Gaming":0.000013775999832432717,"Commodity Chemicals":0.0000010432338513055583,"Communications Equipment":0.000019887389498762786,"Construction & Engineering":0.000001826199536480999,"Construction Machinery & Heavy Trucks":0.000009827364920056425,"Consumer Finance":0.0000018292046206624946,"Data Processing & Outsourced Services":0.0000010666744856280275,"Diversified Metals & Mining":0.000006960767223063158,"Diversified Support Services":0.000016824227714096196,"Electric Utilities":0.000003896044290740974,"Electrical Components & Equipment":0.000001626394464437908,"Electronic Equipment & Instruments":0.00003863943129545078,"Environmental & Facilities Services":0.000736175337806344,"Gold":0.00002220332135038916,"Health Care Equipment":4.6927588925882446e-8,"Health Care Facilities":7.432880124724761e-7,"Health Care Services":6.929263918209472e-7,"Health Care Supplies":2.1007431882935634e-7,"Health Care Technology":0.000003907185146090342,"Homebuilding":3.903339234057057e-7,"Hotels, Resorts & Cruise Lines":6.0527639789143e-7,"Human Resource & Employment Services":5.48697983049351e-7,"IT Consulting & Other Services":0.0000723653138265945,"Industrial Machinery":7.230253231682582e-7,"Integrated Telecommunication Services":2.8266379104024963e-7,"Interactive Media & Services":0.00003454017496551387,"Internet & Direct Marketing Retail":0.000003871373337460682,"Internet Services & Infrastructure":0.0007196652004495263,"Investment Banking & Brokerage":0.0000040634336073708255,"Leisure Products":0.000002158361439796863,"Life Sciences Tools & Services":0.000002861268058040878,"Movies & Entertainment":0.000007286199888767442,"Oil & Gas Equipment & Services":0.000004376991455501411,"Oil & Gas Exploration & Production":0.000005569149834627751,"Oil & Gas Refining & Marketing":0.000012647416951949708,"Oil & Gas Storage & Transportation":0.000005852583853993565,"Packaged Foods & Meats":0.0000011130315442642313,"Personal Products":0.00000970239307207521,"Pharmaceuticals":0.0000037546726616710657,"Property & Casualty Insurance":0.000006116194072092185,"Real Estate Operating Companies":0.00001882187461887952,"Regional Banks":0.0000011669454806906288,"Research & Consulting Services":0.000024276219846797176,"Restaurants":8.598511840318679e-7,"Semiconductors":0.0000021006283077440457,"Specialty Chemicals":0.000004160017397225602,"Specialty Stores":2.644004553076229e-7,"Steel":0.0000013566890402216814,"Systems Software":0.9889177083969116,"Technology Distributors":0.00001339179198112106,"Technology Hardware, Storage & Peripherals":0.00004790363891515881,"Thrifts & Mortgage Finance":3.924862141957419e-7,"Trading Companies & Distributors":0.0000035233156268077437}|Low latency is one of our best cloud features|
+----------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------+

Clasificación Zero-Shot

Bart

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_zs_bart
PREDICT PRED
USING
engine = 'huggingface',
task = 'zero-shot-classification',
model_name = 'facebook/bart-large-mnli',
input_column = 'text',
candidate_labels = ['Books', 'Household', 'Clothing & Accessories', 'Electronics'];

Y comprobemos su estado.

DESCRIBE hf_zs_bart;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT *
FROM mindsdb.hf_zs_bart
WHERE text = 'Paper Plane Design Framed Wall Hanging Motivational Office Decor Art Prints';

Al ejecutar, obtenemos:

+---------+------------------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------+
|PRED     |PRED_explain                                                                                                                              |text                                                                       |
+---------+------------------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------+
|Household|{"Books":0.1876104772090912,"Clothing & Accessories":0.08688066899776459,"Electronics":0.14785148203372955,"Household":0.5776574015617371}|Paper Plane Design Framed Wall Hanging Motivational Office Decor Art Prints|
+---------+------------------------------------------------------------------------------------------------------------------------------------------+---------------------------------------------------------------------------+

Traducción

Inglés a Francés (T5)

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_t5_en_fr
PREDICT PRED
USING
engine = 'huggingface',
task = 'translation',
model_name = 't5-base',
input_column = 'text',
lang_input = 'en',
lang_output = 'fr';

Y comprobemos su estado.

DESCRIBE hf_t5_en_fr;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT *
FROM mindsdb.hf_t5_en_fr
WHERE text = 'The monkey is on the branch';

Al ejecutar, obtenemos:

+---------------------------+---------------------------+
|PRED                       |text                       |
+---------------------------+---------------------------+
|Le singe est sur la branche|The monkey is on the branch|
+---------------------------+---------------------------+

Resumen

Bart

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_bart_sum_20
PREDICT PRED
USING
engine = 'huggingface',
task = 'summarization',
model_name = 'sshleifer/distilbart-cnn-12-6',
input_column = 'text',
min_output_length = 5,
max_output_length = 20;

Y comprobemos su estado.

DESCRIBE hf_bart_sum_20;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT *
FROM mindsdb.hf_bart_sum_20
WHERE text = 'The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct.';

Al ejecutar, obtenemos:

+-------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|PRED                                                   |text                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
+-------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|The tower is 324 metres (1,063 ft) tall, about the same|The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct.|
+-------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

Google Pegasus

Vamos a crear un modelo.

CREATE MODEL mindsdb.hf_peg_sum_20
PREDICT PRED
USING
engine = 'huggingface',
task = 'summarization',
model_name = 'google/pegasus-xsum',
input_column = 'text',
min_output_length = 5,
max_output_length = 20;

Y comprobemos su estado.

DESCRIBE hf_peg_sum_20;

Una vez que el estado es complete, podemos consultar para obtener predicciones.

SELECT *
FROM mindsdb.hf_peg_sum_20
WHERE text = 'The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct.';

Al ejecutar, obtenemos:

+------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|PRED                                            |text                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
+------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|The Eiffel Tower is a landmark in Paris, France.|The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct.|
+------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

Ejemplos de OpenAI

Aquí están las tareas soportadas por MindsDB y OpenAI:

Responder Preguntas sin Contexto
Responder Preguntas con Contexto
Completar Prompt

Sigue esta instrucción para configurar la integración de OpenAI en MindsDB.

Veamos los ejemplos.

Responder Preguntas sin Contexto

Vamos a crear un modelo.

CREATE MODEL project_a.openai_test_a
PREDICT answer
USING
    engine = 'openai',
    question_column = 'question';

Al ejecutar, obtenemos:

Query successfully completed

Ahora podemos consultar para obtener respuestas.

SELECT question, answer
FROM project_a.openai_test_a
WHERE question = 'Where is Stockholm located?';

Al ejecutar, obtenemos:

+---------------------------+-------------------------------+
|question                   |answer                         |
+---------------------------+-------------------------------+
|Where is Stockholm located?|Stockholm is located in Sweden.|
+---------------------------+-------------------------------+

Responder Preguntas con Contexto

Vamos a crear un modelo.

CREATE MODEL project_a.openai_test_b
PREDICT answer
USING
    engine = 'openai',
    question_column = 'question',
    context_column = 'context';

Al ejecutar, obtenemos:

Query successfully completed

Ahora podemos consultar para obtener respuestas.

SELECT context, question, answer
FROM project_a.openai_test_b
WHERE context = 'Answer with a joke'
AND question = 'How to cook soup?';

Al ejecutar, obtenemos:

+-------------------+------------------+---------------------------------------------------------+
|context            |question          |answer                                                   |
+-------------------+------------------+---------------------------------------------------------+
|Answer with a joke |How to cook soup? |How do you cook soup? You put it in a pot and heat it up!|
+-------------------+------------------+---------------------------------------------------------+

Completar Prompt

Completar Prompt con Parámetros Proporcionados en el Momento de la Creación

Vamos a crear un modelo.

CREATE MODEL project_a.openai_test_c
PREDICT answer
USING
    engine = 'openai',
    prompt_template = 'Context: {{context}}. Question: {{question}}. Answer:',
    max_tokens = 100,
    temperature = 0.3;

Veamos un ejemplo que utiliza parámetros proporcionados en el momento de la creación del modelo.

SELECT context, question, answer
FROM project_a.openai_test_c
WHERE context = 'Answer accurately'
AND question = 'How many planets exist in the solar system?';

Al ejecutar, obtenemos:

+-------------------+-------------------------------------------+----------------------------------------------+
|context            |question                                   |answer                                        |
+-------------------+-------------------------------------------+----------------------------------------------+
|Answer accurately  |How many planets exist in the solar system?| There are eight planets in the solar system. |
+-------------------+-------------------------------------------+----------------------------------------------+

Completar Prompt con Parámetros Proporcionados en el Momento de la Predicción

Vamos a crear un modelo.

CREATE MODEL project_a.openai_test_c
PREDICT answer
USING
    engine = 'openai',
    prompt_template = 'Context: {{context}}. Question: {{question}}. Answer:',
    max_tokens = 100,
    temperature = 0.3;

Veamos un ejemplo que anula los parámetros en el momento de la predicción.

SELECT instruction, answer
FROM project_a.openai_test_c
WHERE instruction = 'Speculate extensively'
USING
    prompt_template = '{{instruction}}. What does Tom Hanks like?',
    max_tokens = 100,
    temperature = 0.5;

Al ejecutar, obtenemos:

+----------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|instruction           |answer                                                                                                                                                                                                                         |
+----------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|Speculate extensively |Some people speculate that Tom Hanks likes to play golf, while others believe that he enjoys acting and directing. It is also speculated that he likes to spend time with his family and friends, and that he enjoys traveling.|
+----------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

Clasificación de Sentimiento

Vamos a crear un modelo.

CREATE MODEL mindsdb.sentiment_classifier                           
PREDICT sentiment
USING
  engine = 'openai',              
  prompt_template = 'predict the sentiment of the text:{{review}} exactly as either positive or negative or neutral';

Ahora podemos consultar para obtener predicciones.

SELECT output.sentiment, input.review
FROM example_db.demo_data.amazon_reviews AS input
JOIN mindsdb.sentiment_classifier AS output
LIMIT 3;

Al ejecutar, obtenemos:

+----------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| sentiment                              | review                                                                                                                                                                                                                                                                                                                                                                            |
+----------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| positive                               | Late gift for my grandson. He is very happy with it. Easy for him (9yo ).                                                                                                                                                                                                                                                                                                         |
| The sentiment of the text is positive. | I'm not super thrilled with the proprietary OS on this unit, but it does work okay and does what I need it to do. Appearance is very nice, price is very good and I can't complain too much - just wish it were easier (or at least more obvious) to port new apps onto it. For now, it helps me see things that are too small on my phone while I'm traveling. I'm a happy buyer.|
| positive                               | I purchased this Kindle Fire HD 8 was purchased for use by 5 and 8 yer old grandchildren. They basically use it to play Amazon games that you download.                                                                                                                                                                                                                           |
+----------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

¿Qué sigue?

¡Diviértete mientras lo pruebas tú mismo!

Marca como favorito el repositorio de MindsDB en GitHub.
Regístrese para obtener una cuenta gratuita de MindsDB.
Interactúe con la comunidad de MindsDB en Slack o GitHub para hacer preguntas y compartir sus ideas y pensamientos.

Si este tutorial fue útil, por favor denos una estrella en GitHub aquí.

​Ejemplos de Hugging Face

​Clasificación de Texto

​Clasificación Zero-Shot

​Traducción

​Resumen

​Ejemplos de OpenAI

​Responder Preguntas sin Contexto

​Responder Preguntas con Contexto

​Completar Prompt

​¿Qué sigue?

Ejemplos de Hugging Face

Clasificación de Texto

Clasificación Zero-Shot

Traducción

Resumen

Ejemplos de OpenAI

Responder Preguntas sin Contexto

Responder Preguntas con Contexto

Completar Prompt

¿Qué sigue?