OpenAI vs Ollama en utilisant l’outil SQLDatabaseToolkit de LangChain

CREATE TABLE IF NOT EXISTS tick (
    symbol VARCHAR(10),
    ts     DATETIME SERIES TIMESTAMP,
    open   NUMERIC(18, 2),
    high   NUMERIC(18, 2),
    low    NUMERIC(18, 2),
    price  NUMERIC(18, 2),
    volume INT,
    KEY(ts)
);

CREATE TABLE IF NOT EXISTS portfolio (
    symbol         VARCHAR(10),
    shares_held    INT,
    purchase_date  DATE,
    purchase_price NUMERIC(18, 2)
);

CREATE TABLE IF NOT EXISTS stock_sentiment (
    headline  VARCHAR(250),
    positive  FLOAT,
    negative  FLOAT,
    neutral   FLOAT,
    url       TEXT,
    publisher VARCHAR(30),
    ts        DATETIME,
    symbol    VARCHAR(10)
);

INSERT INTO portfolio (symbol, shares_held, purchase_date, purchase_price) VALUES
('AAPL', 100, '2022-01-15',  150.25),
('MSFT',  50, '2021-12-10',  305.50),
('GOOGL', 25, '2021-11-05', 2800.75),
('AMZN',  10, '2020-07-20', 3200.00),
('TSLA',  40, '2022-02-18',  900.60),
('NFLX',  15, '2021-09-01',  550.00);

mysql -u "<username>" -p"<password>" -h "<host>" -P <port> -D <database> < stock_sentiment.sql

CREATE PIPELINE tick
AS LOAD DATA KAFKA 'public-kafka.memcompute.com:9092/stockticker'
BATCH_INTERVAL 45000
INTO TABLE tick
FIELDS TERMINATED BY ','
(symbol,ts,open,high,low,price,volume);

ALTER PIPELINE tick SET OFFSETS EARLIEST;

TEST PIPELINE tick LIMIT 1;

+--------+---------------------+--------+--------+--------+--------+--------+
| symbol | ts                  | open   | high   | low    | price  | volume |
+--------+---------------------+--------+--------+--------+--------+--------+
| MMM    | 2025-01-23 21:40:32 | 178.34 | 178.43 | 178.17 | 178.24 |  38299 |
+--------+---------------------+--------+--------+--------+--------+--------+

START PIPELINE tick;

SELECT COUNT(*)
FROM tick;

SELECT symbol, (MAX(high) - MIN(low)) AS volatility
FROM tick
GROUP BY symbol
ORDER BY volatility ASC
LIMIT 1;

"For each stock symbol, calculate the volatility as the difference\n"
"between the highest recorded price and the lowest recorded price over time.\n"
"Which stock symbol has the least volatility?"

+--------+------------+
| symbol | volatility |
+--------+------------+
| FTR    |       0.55 |
+--------+------------+

The stock symbol with the least volatility is FTR, with a volatility of 0.55.

To find the stock with the highest price, we need to compare the prices of all the given stocks and find the maximum value. However, I don't have real-time access to financial data or the ability to execute code that interacts with external APIs. Therefore, I can't directly calculate the highest price from this list.

However, if you provide me with a specific date or time range, I can help you find the stock with the highest price during that period. For example, if you want to know the stock with the highest price on a particular day in the past, I can assist you with that.

If you're looking for the current highest-priced stock, I recommend checking a financial news website or an API that provides real-time stock data, such as Yahoo Finance, Google Finance, or a service like Alpha Vantage or Finnhub.io. These platforms can give you the most up-to-date information on stock prices.`
For troubleshooting, visit: https://python.langchain.com/docs/troubleshooting/errors/OUTPUT_PARSING_FAILURE

SELECT COUNT(*)
FROM tick;

"How many rows are in the tick table?"

+----------+
| COUNT(*) |
+----------+
| 22367162 |
+----------+

There are 22,367,162 rows in the tick table.

The "tick" table has 3 rows.

-- Étape 1 : Obtenir le dernier prix pour chaque symbole
WITH latest_prices AS (
    SELECT symbol, price
    FROM tick t1
    WHERE ts = (
        SELECT MAX(ts)
        FROM tick t2
        WHERE t2.symbol = t1.symbol
    )
)

-- Étape 2 : Calculer la valeur totale du portefeuille
SELECT SUM(p.shares_held * lp.price) AS total_portfolio_value
FROM portfolio p, latest_prices lp
WHERE p.symbol = lp.symbol;

"Taking all the stock symbols from the portfolio table,\n"
"and using the latest value for each stock symbol from the tick table,\n"
"calculate the grand total value of all the shares listed in the portfolio table."

+-----------------------+
| total_portfolio_value |
+-----------------------+
|              44540.60 |
+-----------------------+

$44,540.60

I don't know. The provided SQL query does not contain any of the common mistakes listed. It uses the correct join conditions, functions, and data types. The query also properly quotes identifiers and uses the correct number of arguments for functions. Therefore, no changes are needed. However, without access to the actual database schema and table data, I cannot provide a specific answer to the question.

SELECT
    (
        SELECT ts
        FROM stock_sentiment
        WHERE symbol = 'AAPL'
        ORDER BY positive DESC
        LIMIT 1
    ) AS sentiment_date,
    (
        SELECT positive
        FROM stock_sentiment
        WHERE symbol = 'AAPL'
        ORDER BY positive DESC
        LIMIT 1
    ) AS most_positive_sentiment,
    (
        SELECT price
        FROM tick
        WHERE symbol = 'AAPL'
        ORDER BY ts DESC
        LIMIT 1
    ) AS current_best_price;

"Using the symbol AAPL, show me the date and the most\n"
"positive sentiment in the stock sentiment table and the\n"
"current best price for this symbol from the tick table."

+---------------------+-------------------------+--------------------+
| sentiment_date      | most_positive_sentiment | current_best_price |
+---------------------+-------------------------+--------------------+
| 2020-05-28 00:00:00 |                0.331509 |             116.27 |
+---------------------+-------------------------+--------------------+

On 2020-05-28, the most positive sentiment for AAPL was 0.331509, and the current best price for AAPL is 116.27.

The provided list contains decimal numbers, which appear to be the results of some kind of experiment or analysis. Without additional context, it's difficult to determine the exact nature of these results. However, we can observe that the majority of the numbers are between 116.85 and 117.27, with a few outliers at 115.99 and 117.30. The smallest number in the list is 115.99, and the largest is 117.30.`
For troubleshooting, visit: https://python.langchain.com/docs/troubleshooting/errors/OUTPUT_PARSING_FAILURE