Databricks DBRX is now available in Amazon SageMaker JumpStart

from sagemaker.jumpstart.model import JumpStartModel

accept_eula = True

model = JumpStartModel(model_id="huggingface-llm-dbrx-base")
predictor = model.deploy(accept_eula=accept_eula)

payload = {
    "inputs": "Hello!",
    "parameters": {
        "max_new_tokens": 10,
    },
}
predictor.predict(payload)

payload = { 
      "inputs": "Write a function to read a CSV file in Python using pandas library:", 
      "parameters": { 
          "max_new_tokens": 30, }, } 
           response = predictor.predict(payload)["generated_text"].strip() 
           print(response)

import pandas as pd 
df = pd.read_csv("file_name.csv") 
#The above code will import pandas library and then read the CSV file using read_csv

payload = {
"inputs": """
Tweet: "I am so excited for the weekend!"
Sentiment: Positive

Tweet: "Why does traffic have to be so terrible?"
Sentiment: Negative

Tweet: "Just saw a great movie, would recommend it."
Sentiment: Positive

Tweet: "According to the weather report, it will be cloudy today."
Sentiment: Neutral

Tweet: "This restaurant is absolutely terrible."
Sentiment: Negative

Tweet: "I love spending time with my family."
Sentiment:""",
"parameters": {
"max_new_tokens": 2,
},
}
response = predictor.predict(payload)["generated_text"].strip()
print(response)

Positive

# Question answering
payload = {
    "inputs": "Respond to the question: How did the development of transportation systems, such as railroads and steamships, impact global trade and cultural exchange?",
    "parameters": {
        "max_new_tokens": 225,
    },
}
response = predictor.predict(payload)["generated_text"].strip()
print(response)

The development of transportation systems, such as railroads and steamships, impacted global trade and cultural exchange in a number of ways. 
The documents provided show that the development of these systems had a profound effect on the way people and goods were able to move around the world. 
One of the most significant impacts of the development of transportation systems was the way it facilitated global trade. 
The documents show that the development of railroads and steamships made it possible for goods to be transported more quickly and efficiently than ever before. 
This allowed for a greater exchange of goods between different parts of the world, which in turn led to a greater exchange of ideas and cultures. 
Another impact of the development of transportation systems was the way it facilitated cultural exchange. The documents show that the development of railroads and steamships made it possible for people to travel more easily and quickly than ever before. 
This allowed for a greater exchange of ideas and cultures between different parts of the world. Overall, the development of transportation systems, such as railroads and steamships, had a profound impact on global trade and cultural exchange.

<|im_start|>system
{system_message} <|im_end|>
<|im_start|>user
{human_message} <|im_end|>
<|im_start|>assistantn

from typing import Dict, List

def format_instructions(instructions: List[Dict[str, str]]) -> List[str]:
    """Format instructions where conversation roles must alternate system/user/assistant/user/assistant/..."""
    prompt: List[str] = []
    for instruction in instructions:
        if instruction["role"] == "system":
            prompt.extend(["<|im_start|>systemn", (instruction["content"]).strip(), " <|im_end|>n"])
        elif instruction["role"] == "user":
            prompt.extend(["<|im_start|>usern", (instruction["content"]).strip(), " <|im_end|>n"])
        else:
            raise ValueError(f"Invalid role: {instruction['role']}. Role must be either 'user' or 'system'.")
    prompt.extend(["<|im_start|>assistantn"])
    return "".join(prompt)

def print_instructions(prompt: str, response: str) -> None:
    bold, unbold = '33[1m', '33[0m'
    print(f"{bold}> Input{unbold}n{prompt}nn{bold}> Output{unbold}n{response['generated_text'].strip()}n")

instructions = [
{"role": "system", "content": "You are an expert in suggesting diet plans optimized for different sports or fitness activities, taking into account energy requirements, and recovery requirements."},
{"role": "user", "content": "I am trying to build muscle mass and increase my strength. What kind of high-protein, calorie-dense diet plan would you recommend for me?"}
]
prompt = format_instructions(instructions)
payload = {
"inputs": prompt,
"parameters": {"max_new_tokens": 700, "temperature": 0.5, "do_sample": True}
}
response=predictor.predict(payload)
print_instructions(prompt, response)

> Input
<|im_start|>system
You are an expert in suggesting diet plans optimized for different sports or fitness activities, taking into account energy requirements, and recovery requirements. <|im_end|>
<|im_start|>user
I am trying to build muscle mass and increase my strength. What kind of high-protein, calorie-dense diet plan would you recommend for me? <|im_end|>
<|im_start|>assistant

> Output
Absolutely, I'd be happy to help you with that. Given your goal of building muscle mass and increasing strength, you'll want a diet that's high in protein and provides sufficient calories to support muscle growth and recovery. Here's a basic outline of what your diet plan could look like:

1. **Breakfast:**
   - 3 whole eggs
   - 3 egg whites
   - 1 cup of oatmeal
   - 1 scoop of whey protein
   - 1 banana

2. **Mid-Morning Snack:**
   - 1.5 ounces of almonds
   - 1 apple

3. **Lunch:**
   - 8 ounces of chicken breast
   - 1 cup of brown rice
   - 1 cup of mixed vegetables

4. **Afternoon Snack:**
   - 1.5 cups of Greek yogurt
   - 1 cup of mixed berries

5. **Dinner:**
   - 8 ounces of salmon or lean beef
   - 1 cup of quinoa
   - 1.5 cups of mixed vegetables

6. **Evening Snack:**
   - 1 scoop of casein protein
   - 1 tablespoon of almond butter

This is a high-protein, calorie-dense diet that includes a variety of nutrient-rich foods. It's important to note that everyone's nutritional needs are different, so you may need to adjust portion sizes or food choices based on your specific needs and preferences.

Also, remember to stay hydrated by drinking plenty of water throughout the day. Regular exercise, particularly strength training, is crucial to achieving your goals. It's also important to get enough sleep to aid in muscle recovery and growth.

Before starting any new diet or exercise program, it's a good idea to consult with a healthcare professional or a registered dietitian. They can provide personalized advice based on your health history and current lifestyle.

instructions = [ 
{"role": "system", "content": "You are an expert in coding and programming. Your role is to provide examples, explanations, and insights related to programming languages, algorithms, data structures, and software development practices."}, 
{"role": "user", "content": "Write a Python script to read a CSV file containing stock prices and plot the closing prices over time using Matplotlib."} 
] 
prompt = format_instructions(instructions) 
payload = { "inputs": prompt, "parameters": {"max_new_tokens": 315, "temperature": 0.3, "do_sample": True} } 
response=predictor.predict(payload) 
print_instructions(prompt, response)

> Input
<|im_start|>system
You are an expert in coding and programming. Your role is to provide examples, explanations, and insights related to programming languages, algorithms, data structures, and software development practices. <|im_end|>
<|im_start|>user
Write a Python script to read a CSV file containing stock prices and plot the closing prices over time using Matplotlib. <|im_end|>
<|im_start|>assistant

> Output
Sure, I'd be happy to help you with that. Here's a simple Python script that uses the `pandas` library to read a CSV file and `matplotlib` to plot the closing prices over time.

```python
import pandas as pd
import matplotlib.pyplot as plt

# Load the data from a CSV file
df = pd.read_csv('stock_prices.csv')

# Plot the closing prices over time
plt.figure(figsize=(12,5))
plt.plot(df['Date'], df['Close'])
plt.xlabel('Date')
plt.ylabel('Price')
plt.title('Stock Prices Over Time')
plt.show()
```

In this script, replace `'stock_prices.csv'` with the path to your CSV file. The file should have columns named 'Date' and 'Close' for this script to work correctly. If your file uses different column names, you'll need to adjust the script accordingly.

The `pandas` library is a powerful tool for data manipulation and analysis. It can read data from a variety of sources, including CSV files, and represent the data in a tabular format. The `matplotlib` library is a popular choice for creating static, animated, and interactive visualizations in Python.

This script first loads the data from the CSV file into a pandas DataFrame. It then plots the 'Close' column against the 'Date' column using matplotlib's `plot()` function. The `figure()` function is used to specify the size of the plot, and `show()` is used to display the plot.

instructions = [
  {"role": "system", "content": "You are an expert in mathematics and reasoning. Your role is to provide examples, explanations, and insights related to mathematical concepts, problem-solving techniques, and logical reasoning."},
  {"role": "user", "content": "A car rental company charges $40 per day plus $0.25 per mile driven. If I rented a car for 3 days and drove 250 miles, what would be the total cost? Break down the calculation steps before giving the final answer."}
]
prompt = format_instructions(instructions)
payload = {
"inputs": prompt,
"parameters": {"max_new_tokens": 400, "temperature": 0.2, "do_sample": True}
}
response=predictor.predict(payload)
print_instructions(prompt, response)

> Input
<|im_start|>system
You are an expert in mathematics and reasoning. Your role is to provide examples, explanations, and insights related to mathematical concepts, problem-solving techniques, and logical reasoning. <|im_end|>
<|im_start|>user
A car rental company charges $40 per day plus $0.25 per mile driven. If I rented a car for 3 days and drove 250 miles, what would be the total cost? Break down the calculation steps before giving the final answer. <|im_end|>
<|im_start|>assistant

> Output
Sure, I'd be happy to help with that! The problem you've presented involves both fixed costs (the daily rate) and variable costs (the cost per mile). Let's break it down:

1. First, let's calculate the total cost of the fixed daily rate. The car rental company charges $40 per day, and you rented the car for 3 days. So, the total cost for the daily rate is $40/day * 3 days = $120.

2. Next, let's calculate the total cost of the variable rate, which is the cost per mile driven. The company charges $0.25 per mile, and you drove 250 miles. So, the total cost for the mileage is $0.25/mile * 250 miles = $62.50.

3. Finally, to find the total cost of renting the car, we add the total cost of the daily rate and the total cost of the mileage. So, the total cost is $120 + $62.50 = $182.50.

So, the total cost of renting the car for 3 days and driving 250 miles would be $182.50.

predictor.delete_model()
predictor.delete_endpoint()