Mixtral 8x22B ya está disponible en Amazon SageMaker JumpStart

from typing import Dict, List

def format_instructions(instructions: List(Dict(str, str))) -> List(str):
    """Format instructions where conversation roles must alternate user/assistant/user/assistant/..."""
    prompt: List(str) = ()
    for user, answer in zip(instructions(::2), instructions(1::2)):
        prompt.extend(("", "(INST) ", (user("content")).strip(), " (/INST) ", (answer("content")).strip(), ""))
    prompt.extend(("", "(INST) ", (instructions(-1)("content")).strip(), " (/INST) ",""))
    return "".join(prompt)


def print_instructions(prompt: str, response: str) -> None:
    bold, unbold = '\033(1m', '\033(0m'
    print(f"{bold}> Input{unbold}\n{prompt}\n\n{bold}> Output{unbold}\n{response(0)('generated_text')}\n")

instructions = ({"role": "user", "content": """Summarize the following information. Format your response in short paragraph.

Article:

Contextual compression - To address the issue of context overflow discussed earlier, you can use contextual compression to compress and filter the retrieved documents in alignment with the query’s context, so only pertinent information is kept and processed. This is achieved through a combination of a base retriever for initial document fetching and a document compressor for refining these documents by paring down their content or excluding them entirely based on relevance, as illustrated in the following diagram. This streamlined approach, facilitated by the contextual compression retriever, greatly enhances RAG application efficiency by providing a method to extract and utilize only what’s essential from a mass of information. It tackles the issue of information overload and irrelevant data processing head-on, leading to improved response quality, more cost-effective LLM operations, and a smoother overall retrieval process. Essentially, it’s a filter that tailors the information to the query at hand, making it a much-needed tool for developers aiming to optimize their RAG applications for better performance and user satisfaction.
"""})
prompt = format_instructions(instructions)
payload = {
"inputs": prompt,
"parameters": {"max_new_tokens": 1500}
}
response=predictor.predict(payload)
print_instructions(prompt, response)

> > Input
(INST) Summarize the following information. Format your response in short paragraph.

Article:

Contextual compression - To address the issue of context overflow discussed earlier, you can use contextual compression to compress and filter the retrieved documents in alignment with the query’s context, so only pertinent information is kept and processed. This is achieved through a combination of a base retriever for initial document fetching and a document compressor for refining these documents by paring down their content or excluding them entirely based on relevance, as illustrated in the following diagram. This streamlined approach, facilitated by the contextual compression retriever, greatly enhances RAG application efficiency by providing a method to extract and utilize only what’s essential from a mass of information. It tackles the issue of information overload and irrelevant data processing head-on, leading to improved response quality, more cost-effective LLM operations, and a smoother overall retrieval process. Essentially, it’s a filter that tailors the information to the query at hand, making it a much-needed tool for developers aiming to optimize their RAG applications for better performance and user satisfaction. (/INST) 
> Output
(INST) Summarize the following information. Format your response in short paragraph.

Article:

Contextual compression - To address the issue of context overflow discussed earlier, you can use contextual compression to compress and filter the retrieved documents in alignment with the query’s context, so only pertinent information is kept and processed. This is achieved through a combination of a base retriever for initial document fetching and a document compressor for refining these documents by paring down their content or excluding them entirely based on relevance, as illustrated in the following diagram. This streamlined approach, facilitated by the contextual compression retriever, greatly enhances RAG application efficiency by providing a method to extract and utilize only what’s essential from a mass of information. It tackles the issue of information overload and irrelevant data processing head-on, leading to improved response quality, more cost-effective LLM operations, and a smoother overall retrieval process. Essentially, it’s a filter that tailors the information to the query at hand, making it a much-needed tool for developers aiming to optimize their RAG applications for better performance and user satisfaction. (/INST) Contextual compression is a technique used to manage the issue of context overflow in information retrieval. This method involves compressing and filtering the retrieved documents to align with the query's context, ensuring that only relevant information is processed. This is achieved through a two-step process: a base retriever fetches the initial set of documents, and a document compressor refines these documents by either reducing their content or excluding them entirely based on relevance.

The contextual compression retriever significantly improves the efficiency of Retrieval-Augmented Generation (RAG) applications by extracting and utilizing only the essential information from a large pool of data. This approach addresses the problem of information overload and irrelevant data processing, leading to improved response quality, cost-effective operations, and a smoother retrieval process. In essence, contextual compression acts as a filter that tailors the information to the specific query, making it an indispensable tool for developers aiming to optimize their RAG applications for better performance and user satisfaction.

Prompt

instructions = ({"role": "user", "content": """\

> Input
(INST) 
> Output
(INST) 

French:

1. Client : "J'ai récemment commandé un casque audio sans fil, mais j'ai reçu un modèle différent. Quelles sont les étapes à suivre pour recevoir le produit correct que j'ai commandé ?"
2. Client : "J'ai acheté un ordinateur portable personnalisable le mois dernier et j'ai opté pour des mises à niveau spécifiques. Cependant, les performances de l'ordinateur portable ne sont pas à la hauteur de mes attentes. Puis-je avoir un technicien qui vérifie cela, ou devrais-je envisager de le retourner ?"
3. Client : "Ma commande pour un sac à main de designer devait inclure un portefeuille assorti dans le cadre d'une offre promotionnelle, mais le portefeuille ne se trouvait pas dans le paquet. Comment puis-je résoudre ce problème ?"
4. Client : "Je vois que les informations de suivi de ma commande de batterie de cuisine en céramique indiquent qu'elle a été livrée, mais je ne l'ai pas reçue. Pourriez-vous m'aider à déterminer où se trouve mon colis ?"
5. Client : "J'essaie d'acheter un miroir antique de votre collection vintage, mais le site continue de me donner une erreur lorsque j'essaie de passer à la caisse. Existe-t-il un autre moyen de finaliser mon achat ?"

German:

1. Kunde: "Ich habe kürzlich ein Set kabelloser Kopfhörer bestellt, aber ich habe ein anderes Modell erhalten. Welche Schritte sollte ich unternehmen, um das richtige Produkt zu erhalten, das ich bestellt habe?"
2. Kunde: "Ich habe letzten Monat einen anpassbaren Laptop gekauft und habe mich für spezifische Upgrades entschieden. Allerdings entspricht die Leistung des Laptops nicht meinen Erwartungen. Kann ich einen Techniker hinzuziehen lassen oder sollte ich eine Rückgabe in Erwägung ziehen?"
3. Kunde: "Meine Bestellung für eine Designer-Handtasche sollte inklusive eines passenden Portemonnaies als Teil einer Werbeaktion sein, aber das Portemonnaie war nicht im Paket. Wie kann dieses Problem gelöst werden?"
4. Kunde: "Ich sehe, dass die Sendungsverfolgungsinformationen für meine Bestellung von Keramik-Kochgeschirr anzeigen, dass es geliefert wurde, aber ich habe es nicht erhalten. Könnten Sie mir dabei helfen, festzustellen, wo sich mein Paket befindet?"
5. Kunde: "Ich versuche ein Antikspiegel aus Ihrer Vintage-Kollektion zu kaufen, aber die Website gibt mir jedes Mal einen Fehler, wenn ich versuche, den Bestellvorgang abzuschließen. Gibt es einen anderen Weg, meinen Kauf abzuschließen?"

Spanish:

1. Cliente: "Recientemente ordené un conjunto de audífonos inalámbricos, pero recibí un modelo diferente. ¿Cuáles son los pasos que debo seguir para recibir el producto correcto que ordené?"
2. Cliente: "Compré una computadora personalizable el mes pasado y opté por actualizaciones específicas. Sin embargo, el rendimiento de la computadora no está a la altura de mis expectativas. ¿Puedo tener un técnico que revise esto, o debería considerar devolverla?"
3. Cliente: "Mi pedido de un bolso de diseñador debería haber incluido una billetera a juego como parte de una oferta promocional, pero la billetera no estaba en el paquete. ¿Cómo puedo resolver este problema?"
4. Cliente: "Veo que la información de seguimiento de mi pedido de utensilios de cocina de cerámica indica que ha sido entregado, pero aún no lo he recibido. ¿Podría ayudarme a determinar dónde se encuentra mi paquete?"
5. Cliente: "Estoy tratando de comprar un espejo antiguo de su colección de vintage, pero el sitio sigue dándome un error cada vez que trato de realizar el pago. ¿Hay otra forma de completar mi compra?"

instructions = ({"role": "user", "content": "Write a program on Dijstra's algorithm using a priority queue in python:"})
prompt = format_instructions(instructions)
payload = {
"inputs": prompt,
"parameters": {"max_new_tokens": 1000}
}
response=predictor.predict(payload)
print_instructions(prompt, response)

> Input
(INST) Write a program on Dijstra's algorithm using a priority queue in python: (/INST) 

> Output
(INST) Write a program on Dijstra's algorithm using a priority queue in python: (/INST) Here is a Python implementation of Dijkstra's algorithm using a priority queue (heapq module):
```python
import heapq

def dijkstra(graph, start):
    # Initialize the priority queue with the starting vertex and its distance (0)
    priority_queue = ((0, start))
    # Initialize the distances dictionary with infinite distances for all vertices except the starting vertex
    distances = {vertex: float('inf') for vertex in graph}
    distances(start) = 0
    # Initialize the previous dictionary to keep track of the shortest path
    previous = {vertex: None for vertex in graph}

    while priority_queue:
        # Get the vertex with the smallest distance from the priority queue
        current_distance, current_vertex = heapq.heappop(priority_queue)

        # If the current distance is greater than the stored distance, skip this vertex
        if current_distance > distances(current_vertex):
            continue

        # Update the distances of the adjacent vertices
        for neighbor, weight in graph(current_vertex).items():
            distance = current_distance + weight
            # If the new distance is smaller than the stored distance, update the distance and previous vertex
            if distance < distances(neighbor):
                distances(neighbor) = distance
                previous(neighbor) = current_vertex
                # Add the neighbor to the priority queue
                heapq.heappush(priority_queue, (distance, neighbor))

    return distances, previous

# Example usage:
graph = {
    'A': {'B': 1, 'C': 4},
    'B': {'A': 1, 'C': 2, 'D': 5},
    'C': {'A': 4, 'B': 2, 'D': 1},
    'D': {'B': 5, 'C': 1}
}

distances, previous = dijkstra(graph, 'A')
print(distances)  # {'A': 0, 'B': 1, 'C': 3, 'D': 4}
```
In this implementation, the `graph` parameter is a dictionary where the keys are the vertices and the values are dictionaries that map adjacent vertices to their weights. The `start` parameter is the starting vertex for the algorithm. The function returns two dictionaries: `distances` and `previous`. The `distances` dictionary maps each vertex to its shortest distance from the starting vertex, and the `previous` dictionary maps each vertex to its previous vertex in the shortest path.

instructions = ({"role": "user", "content": """Sarah went to a car shop to buy a car from Fred for $20,000 in 2024. She plans to sell the car but it depreciates by 2% each year after she has bought it. She went to a dealer in which that dealer told her that the car has only depreciated by 1.4% each year. After 7 years of using the car, Sarah decides to sell it directly to another person.

How much did Sarah sell the car for and what year is it? Explain the steps before answering. It's ok to make some assumptions as you come to your answer.

"""})
prompt = format_instructions(instructions)
payload = {
"inputs": prompt,
"parameters": {"max_new_tokens": 2000, "do_sample": True}
}
response=predictor.predict(payload)
print_instructions(prompt, response)

(INST) Sarah went to a car shop to buy a car from Fred for $20,000 in 2024. She plans to sell the car but it depreciates by 2% each year after she has bought it. She went to a dealer in which that dealer told her that the car has only depreciated by 1.4% each year. After 7 years of using the car, Sarah decides to sell it directly to another person. 

How much did Sarah sell the car for and what year is it? Explain the steps before answering. It's ok to make some assumptions as you come to your answer. (/INST) To solve this problem, we need to calculate the value of the car after 7 years, assuming two different annual depreciation rates: 2% and 1.4%.

First, let's calculate the value of the car after 7 years assuming a 2% annual depreciation rate:

Year 1: $20,000 - ($20,000 * 2%) = $19,600
Year 2: $19,600 - ($19,600 * 2%) = $19,208
Year 3: $19,208 - ($19,208 * 2%) = $18,821.60
Year 4: $18,821.60 - ($18,821.60 * 2%) = $18,442.22
Year 5: $18,442.22 - ($18,442.22 * 2%) = $18,071.62
Year 6: $18,071.62 - ($18,071.62 * 2%) = $17,709.76
Year 7: $17,709.76 - ($17,709.76 * 2%) = $17,356.58

So, assuming a 2% annual depreciation rate, the value of the car after 7 years would be approximately $17,356.58.

Next, let's calculate the value of the car after 7 years assuming a 1.4% annual depreciation rate:

Year 1: $20,000 - ($20,000 * 1.4%) = $19,728
Year 2: $19,728 - ($19,728 * 1.4%) = $19,463.23
Year 3: $19,463.23 - ($19,463.23 * 1.4%) = $19,205.80
Year 4: $19,205.80 - ($19,205.80 * 1.4%) = $18,955.66
Year 5: $18,955.66 - ($18,955.66 * 1.4%) = $18,712.73
Year 6: $18,712.73 - ($18,712.73 * 1.4%) = $18,476.95
Year 7: $18,476.95 - ($18,476.95 * 1.4%) = $18,248.33

So, assuming a 1.4% annual depreciation rate, the value of the car after 7 years would be approximately $18,248.33.

Now, since Sarah sells the car directly to another person, we can assume that she sold it for the higher of the two values. Therefore, she sold the car for $18,248.33.

As for the year in which she sold the car, since we know that Sarah purchased the car in 2024 and used it for 7 years, we can calculate the year as follows:

2024 + 7 = 2031

Therefore, Sarah sold the car in the year 2031.

So, Sarah sold the car for $18,248.33 in the year 2031.

predictor.delete_model()
predictor.delete_endpoint()