meta/llama-2-13b-chat:df7690f1 – Run with an API on Replicate

meta /llama-2-13b-chat:df7690f1

Input

prompt

*string

Shift + Return to add a new line

User: 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.
Assistant:User: 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.
Assistant:

Prompt to send to Llama v2.

max_length

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: 0.75

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:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5",
  {
    input: {
      debug: false,
      top_p: 1,
      prompt: "User: 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.\nAssistant:",
      max_length: 500,
      temperature: 0.75,
      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:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5",
    input={
        "debug": False,
        "top_p": 1,
        "prompt": "User: 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.\nAssistant:",
        "max_length": 500,
        "temperature": 0.75,
        "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": "df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5",
    "input": {
      "debug": false,
      "top_p": 1,
      "prompt": "User: 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.\\nAssistant:",
      "max_length": 500,
      "temperature": 0.75,
      "repetition_penalty": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Sure! Here is a sample SQL query that should give you the total revenue by state of customer based on the tables you provided: SELECT state, SUM(orders.units_purchased * products.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 This query joins the customers, orders, and products tables on the common column of cust_id, and then groups the results by state to give you the total revenue by state.

{
  "completed_at": "2023-07-18T15:12:45.347613Z",
  "created_at": "2023-07-18T15:12:37.264097Z",
  "data_removed": false,
  "error": null,
  "id": "4p5yfkbbzfqo2gp642chqdxxdi",
  "input": {
    "top_p": 1,
    "prompt": "User: 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.\nAssistant:",
    "max_length": 500,
    "temperature": 0.75,
    "repetition_penalty": 1
  },
  "logs": null,
  "metrics": {
    "predict_time": 8.114586,
    "total_time": 8.083516
  },
  "output": [
    "Sure!",
    " Here",
    " is",
    " a",
    " sample",
    " SQL",
    " query",
    " that",
    " should",
    " give",
    " you",
    " the",
    " total",
    " revenue",
    " by",
    " state",
    " of",
    " customer",
    " based",
    " on",
    " the",
    " tables",
    " you",
    " provided:\n\nSELECT",
    " state,",
    " SUM(orders.units_purchased",
    " *",
    " products.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\nThis",
    " query",
    " joins",
    " the",
    " customers,",
    " orders,",
    " and",
    " products",
    " tables",
    " on",
    " the",
    " common",
    " column",
    " of",
    " cust_id,",
    " and",
    " then",
    " groups",
    " the",
    " results",
    " by",
    " state",
    " to",
    " give",
    " you",
    " the",
    " total",
    " revenue",
    " by",
    " state."
  ],
  "started_at": "2023-07-18T15:12:37.233027Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/4p5yfkbbzfqo2gp642chqdxxdi",
    "cancel": "https://api.replicate.com/v1/predictions/4p5yfkbbzfqo2gp642chqdxxdi/cancel"
  },
  "version": "df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5"
}

Generated in

8.1 seconds

Tweak it Report