meta/llama-2-13b-chat:6b4da803 – Run with an API on Replicate

meta /llama-2-13b-chat:6b4da803

Input

prompt

*string

Shift + Return to add a new line

My database has the following tables:
- customers, orders, and products

The customer table has the following columns:
- cust_id, name, email, home_address_state, phone

The orders table has the following columns:
- order_id, cust_id, prod_id, units_purchased, discount_percent

The products table has the following columns:
- prod_id, product name, product_description, unit_price

Write me a sql query based on the above that will show me my total revenue by state of customer.My database has the following tables:
- customers, orders, and products

The customer table has the following columns:
- cust_id, name, email, home_address_state, phone

The orders table has the following columns:
- order_id, cust_id, prod_id, units_purchased, discount_percent

The products table has the following columns:
- prod_id, product name, product_description, unit_price

Write me a sql query based on the above that will show me my total revenue by state of customer.

Prompt to send to Llama v2.

system_prompt

string

Shift + Return to add a new line

You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.

If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.

If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.

System prompt to send to Llama v2. This is prepended to the prompt and helps guide system behavior.

Default: "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information."

max_new_tokens

integer

(minimum: 1)

Maximum number of tokens to generate. A word is generally 2-3 tokens

Default: 500

temperature

number

(minimum: 0.01, maximum: 5)

Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.

Default: 0.5

top_p

number

(minimum: 0.01, maximum: 1)

When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens

Default: 1

repetition_penalty

number

(minimum: 0.01, maximum: 5)

Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.

Default: 1

debug

boolean

provide debugging output in logs

Default: false

Run this model in Node.js with one line of code:

npx create-replicate --model=meta/llama-2-13b-chat

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run meta/llama-2-13b-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "meta/llama-2-13b-chat:6b4da803a2382c08868c5af10a523892f38e2de1aafb2ee55b020d9efef2fdb8",
  {
    input: {
      debug: false,
      top_p: 1,
      prompt: "My database has the following tables:\n- customers, orders, and products\n\nThe customer table has the following columns:\n- cust_id, name, email, home_address_state, phone\n\nThe orders table has the following columns:\n- order_id, cust_id, prod_id, units_purchased, discount_percent\n\nThe products table has the following columns:\n- prod_id, product name, product_description, unit_price\n\nWrite me a sql query based on the above that will show me my total revenue by state of customer.",
      temperature: 0.75,
      system_prompt: "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.",
      max_new_tokens: 500,
      repetition_penalty: 1
    }
  }
);
console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run meta/llama-2-13b-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "meta/llama-2-13b-chat:6b4da803a2382c08868c5af10a523892f38e2de1aafb2ee55b020d9efef2fdb8",
    input={
        "debug": False,
        "top_p": 1,
        "prompt": "My database has the following tables:\n- customers, orders, and products\n\nThe customer table has the following columns:\n- cust_id, name, email, home_address_state, phone\n\nThe orders table has the following columns:\n- order_id, cust_id, prod_id, units_purchased, discount_percent\n\nThe products table has the following columns:\n- prod_id, product name, product_description, unit_price\n\nWrite me a sql query based on the above that will show me my total revenue by state of customer.",
        "temperature": 0.75,
        "system_prompt": "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.",
        "max_new_tokens": 500,
        "repetition_penalty": 1
    }
)

# The meta/llama-2-13b-chat model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/meta/llama-2-13b-chat/api#output-schema
    print(item, end="")

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run meta/llama-2-13b-chat using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "6b4da803a2382c08868c5af10a523892f38e2de1aafb2ee55b020d9efef2fdb8",
    "input": {
      "debug": false,
      "top_p": 1,
      "prompt": "My database has the following tables:\\n- customers, orders, and products\\n\\nThe customer table has the following columns:\\n- cust_id, name, email, home_address_state, phone\\n\\nThe orders table has the following columns:\\n- order_id, cust_id, prod_id, units_purchased, discount_percent\\n\\nThe products table has the following columns:\\n- prod_id, product name, product_description, unit_price\\n\\nWrite me a sql query based on the above that will show me my total revenue by state of customer.",
      "temperature": 0.75,
      "system_prompt": "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\\n\\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don\'t know the answer to a question, please don\'t share false information.",
      "max_new_tokens": 500,
      "repetition_penalty": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Sure, I'd be happy to help! Based on the information you provided, here is a SQL query that will show you the total revenue by state of customer: ``` SELECT state, SUM(units_purchased * unit_price) AS revenue FROM customers JOIN orders ON customers.cust_id = orders.cust_id JOIN products ON orders.prod_id = products.prod_id GROUP BY state ``` Let me explain the query: 1. `SELECT state, SUM(units_purchased * unit_price) AS revenue`: We select two columns: `state` and `revenue`. The `state` column is the state of the customer, and the `revenue` column is the total revenue for that state. 2. `FROM customers`: We start by joining the `customers` table. 3. `JOIN orders ON customers.cust_id = orders.cust_id`: We join the `orders` table on the `cust_id` column. 4. `JOIN products ON orders.prod_id = products.prod_id`: We join the `products` table on the `prod_id` column. 5. `GROUP BY state`: We group the results by the `state` column. The query will return a table with two columns: `state` and `revenue`. The `revenue` column will have the total revenue for each state. Note that this query assumes that the state is stored in the `home_address_state` column of the `customers` table. If the state is stored in a different column, you'll need to adjust the query accordingly. I hope this helps! Let me know if you have any questions or need further assistance.

{
  "completed_at": "2023-07-22T00:47:47.112130Z",
  "created_at": "2023-07-22T00:47:28.317378Z",
  "data_removed": false,
  "error": null,
  "id": "3q5z6dbbp7kcfh2dhdzglwmkqu",
  "input": {
    "top_p": 1,
    "prompt": "My database has the following tables:\n- customers, orders, and products\n\nThe customer table has the following columns:\n- cust_id, name, email, home_address_state, phone\n\nThe orders table has the following columns:\n- order_id, cust_id, prod_id, units_purchased, discount_percent\n\nThe products table has the following columns:\n- prod_id, product name, product_description, unit_price\n\nWrite me a sql query based on the above that will show me my total revenue by state of customer.",
    "temperature": 0.75,
    "system_prompt": "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.",
    "max_new_tokens": 500,
    "repetition_penalty": 1
  },
  "logs": "Formatted input prompt:\n[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\n<</SYS>>\nMy database has the following tables:\n- customers, orders, and products\nThe customer table has the following columns:\n- cust_id, name, email, home_address_state, phone\nThe orders table has the following columns:\n- order_id, cust_id, prod_id, units_purchased, discount_percent\nThe products table has the following columns:\n- prod_id, product name, product_description, unit_price\nWrite me a sql query based on the above that will show me my total revenue by state of customer. [/INST]",
  "metrics": {
    "predict_time": 18.863329,
    "total_time": 18.794752
  },
  "output": [
    " Sure,",
    " I'd",
    " be",
    " happy",
    " to",
    " help!",
    " Based",
    " on",
    " the",
    " information",
    " you",
    " provided,",
    " here",
    " is",
    " a",
    " SQL",
    " query",
    " that",
    " will",
    " show",
    " you",
    " the",
    " total",
    " revenue",
    " by",
    " state",
    " of",
    " customer:\n```\nSELECT",
    " state,",
    " SUM(units_purchased",
    " *",
    " unit_price)",
    " AS",
    " revenue\nFROM",
    " customers\nJOIN",
    " orders",
    " ON",
    " customers.cust_id",
    " =",
    " orders.cust_id\nJOIN",
    " products",
    " ON",
    " orders.prod_id",
    " =",
    " products.prod_id\nGROUP",
    " BY",
    " state\n```\n\nLet",
    " me",
    " explain",
    " the",
    " query:\n\n1.",
    " `SELECT",
    " state,",
    " SUM(units_purchased",
    " *",
    " unit_price)",
    " AS",
    " revenue`:",
    " We",
    " select",
    " two",
    " columns:",
    " `state`",
    " and",
    " `revenue`.",
    " The",
    " `state`",
    " column",
    " is",
    " the",
    " state",
    " of",
    " the",
    " customer,",
    " and",
    " the",
    " `revenue`",
    " column",
    " is",
    " the",
    " total",
    " revenue",
    " for",
    " that",
    " state.\n2.",
    " `FROM",
    " customers`:",
    " We",
    " start",
    " by",
    " joining",
    " the",
    " `customers`",
    " table.\n3.",
    " `JOIN",
    " orders",
    " ON",
    " customers.cust_id",
    " =",
    " orders.cust_id`:",
    " We",
    " join",
    " the",
    " `orders`",
    " table",
    " on",
    " the",
    " `cust_id`",
    " column.\n4.",
    " `JOIN",
    " products",
    " ON",
    " orders.prod_id",
    " =",
    " products.prod_id`:",
    " We",
    " join",
    " the",
    " `products`",
    " table",
    " on",
    " the",
    " `prod_id`",
    " column.\n5.",
    " `GROUP",
    " BY",
    " state`:",
    " We",
    " group",
    " the",
    " results",
    " by",
    " the",
    " `state`",
    " column.\n\nThe",
    " query",
    " will",
    " return",
    " a",
    " table",
    " with",
    " two",
    " columns:",
    " `state`",
    " and",
    " `revenue`.",
    " The",
    " `revenue`",
    " column",
    " will",
    " have",
    " the",
    " total",
    " revenue",
    " for",
    " each",
    " state.\n\nNote",
    " that",
    " this",
    " query",
    " assumes",
    " that",
    " the",
    " state",
    " is",
    " stored",
    " in",
    " the",
    " `home_address_state`",
    " column",
    " of",
    " the",
    " `customers`",
    " table.",
    " If",
    " the",
    " state",
    " is",
    " stored",
    " in",
    " a",
    " different",
    " column,",
    " you'll",
    " need",
    " to",
    " adjust",
    " the",
    " query",
    " accordingly.\n\nI",
    " hope",
    " this",
    " helps!",
    " Let",
    " me",
    " know",
    " if",
    " you",
    " have",
    " any",
    " questions",
    " or",
    " need",
    " further",
    " assistance."
  ],
  "started_at": "2023-07-22T00:47:28.248801Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/3q5z6dbbp7kcfh2dhdzglwmkqu",
    "cancel": "https://api.replicate.com/v1/predictions/3q5z6dbbp7kcfh2dhdzglwmkqu/cancel"
  },
  "version": "6b4da803a2382c08868c5af10a523892f38e2de1aafb2ee55b020d9efef2fdb8"
}

Generated in

18.9 seconds

Tweak it Report