Receive structured outputs

curl -X POST https://api.writer.com/v1/chat \
  --header "Content-Type: application/json" \
  --header "Authorization: Bearer $WRITER_API_KEY" \
  --data '{
    "model": "palmyra-x5",
    "messages": [
      { "role": "system", "content": "You are a helpful cooking assistant." },
      { "role": "user", "content": "Give me a recipe for a simple pasta dish." }
    ],
    "response_format": {
      "type": "json_schema",
      "json_schema": {
        "schema": {
          "type": "object",
          "properties": {
            "recipe_name": {"type": "string"},
            "ingredients": {"type": "array", "items": {"type": "string"}},
            "steps": {"type": "array", "items": {"type": "string"}},
            "preparation_time": {"type": "string"},
            "servings": {"type": "number"}
          },
          "required": ["recipe_name", "ingredients", "steps", "preparation_time", "servings"]
        }
      }
    }
  }'

import json
from writerai import Writer

# Initialize the client. If you don't pass the `api_key` parameter,
# the client looks for the `WRITER_API_KEY` environment variable.
client = Writer()

response = client.chat.chat(
  model="palmyra-x5",
  messages=[
    {"role": "system", "content": "You are a helpful cooking assistant."},
    {"role": "user", "content": "Give me a recipe for a simple pasta dish."}
  ],
  response_format={
    "type": "json_schema",
    "json_schema": {
      "schema": {
        "type": "object",
        "properties": {"recipe_name": {"type": "string"}, "ingredients": {"type": "array", "items": {"type": "string"}}, "steps": {"type": "array", "items": {"type": "string"}}, "preparation_time": {"type": "string"}, "servings": {"type": "number"}},
        "required": ["recipe_name", "ingredients", "steps", "preparation_time", "servings"]
      }
    }
  }
)

print(json.loads(response.choices[0].message.content))

import { Writer } from 'writer-sdk';

// Initialize the client. If you don't pass the `apiKey` parameter,
// the client looks for the `WRITER_API_KEY` environment variable.
const client = new Writer();

const response = await client.chat.chat({
  model: 'palmyra-x5',
  messages: [
    { role: 'system', content: 'You are a helpful cooking assistant.' },
    { role: 'user', content: 'Give me a recipe for a simple pasta dish.' }
  ],
  response_format: { 
    type: 'json_schema',
    json_schema: {
      schema: {
        type: 'object',
        properties: { recipe_name: { type: 'string' }, ingredients: { type: 'array', items: { type: 'string' } }, steps: { type: 'array', items: { type: 'string' } }, preparation_time: { type: 'string' }, servings: { type: 'number' } },
        required: ['recipe_name', 'ingredients', 'steps', 'preparation_time', 'servings']
      }
    }
  },
});

console.log(JSON.parse(response.choices[0].message.content));

{
"id": "1234",
"object": "chat.completion",
"choices": [
    {
    "index": 0,
    "finish_reason": "stop",
    "message": {
        "content": "{ \"recipe_name\": \"Spaghetti Aglio e Olio\", \"ingredients\": [\"12 oz spaghetti\", \"3-4 garlic cloves\", \"1/3 cup extra virgin olive oil\", \"4-6 dried red chili flakes (optional)\", \"Salt\", \"Freshly ground black pepper\", \"Grated Parmesan cheese (optional)\", \"Fresh parsley, chopped (optional)\"], \"steps\": [\"Bring a large pot of salted water to a boil. Cook the spaghetti according to the package instructions until al dente. Reserve 1 cup of pasta water before draining.\", \"In a large skillet, heat the olive oil over medium-low heat. Add the thinly sliced garlic and cook, stirring occasionally, until golden brown (about 4-5 minutes). Be careful not to burn the garlic.\", \"If using red chili flakes, add them to the skillet and cook for another minute.\", \"Add the reserved pasta water to the skillet and stir to combine.\", \"Add the cooked spaghetti to the skillet, tossing to coat the pasta in the garlic and oil mixture. Season with salt and black pepper to taste.\", \"Serve hot, topped with grated Parmesan cheese and chopped fresh parsley if desired.\"] }",
        "role": "assistant",
        "tool_calls": null,
        "graph_data": {
        "sources": null,
        "status": null,
        "subqueries": null
        },
        "llm_data": null,
        "image_data": null,
        "translation_data": null,
        "refusal": null
    },
    "logprobs": null
    }
],
"created": 1745948916,
"model": "palmyra-x5",
"usage": {
    "prompt_tokens": 2550,
    "total_tokens": 2797,
    "completion_tokens": 247,
    "prompt_token_details": null,
    "completion_tokens_details": null
},
"system_fingerprint": "v1",
"service_tier": null
}

from typing import List
from pydantic import Field, BaseModel
from writerai import Writer

# Initialize the client. If you don't pass the `api_key` parameter,
# the client looks for the `WRITER_API_KEY` environment variable.
client = Writer()

# Define a Pydantic model for structured output
class Recipe(BaseModel):
    recipe_name: str = Field(description="The name of the recipe")
    ingredients: List[str] = Field(description="A list of ingredients for the recipe")
    steps: List[str] = Field(description="A list of steps for the recipe")
    preparation_time: str = Field(description="The preparation time for the recipe")
    servings: int = Field(description="The number of servings for the recipe")

parsed_response = client.chat.parse(
    model="palmyra-x5",
    messages=[
        {"role": "system", "content": "You are a helpful cooking assistant."},
        {
            "role": "user",
            "content": "Give me a recipe for a simple pasta dish.",
        },
    ],
    response_format=Recipe,
)
parsed = parsed_response.choices[0].message.parsed

# Print the parsed response
print(f"Recipe name: {parsed.recipe_name}")
print(f"Ingredients:")
for item in parsed.ingredients:
    print(f"- {item}")
print(f"Steps:")
for item in parsed.steps:
    print(f"- {item}")
print(f"Preparation time: {parsed.preparation_time}")
print(f"Servings: {parsed.servings}")

import { Writer } from 'writer-sdk';
import { z } from 'zod';
import { zodResponseFormat } from 'writer-sdk/helpers/zod';

// Initialize the client. If you don't pass the `apiKey` parameter,
// the client looks for the `WRITER_API_KEY` environment variable.
const client = new Writer();

async function main() {
  // Define a schema for structured output
  const recipeSchema = z.object({
    recipeName: z.string(),
    ingredients: z.array(
      z.object({
        name: z.string(),
        amount: z.string(),
      }),
    ),
    steps: z.array(z.string()),
    preparationTime: z.string(),
    servings: z.number(),
  });

  const completion = await client.chat.parse({
    model: 'palmyra-x5',
    messages: [
      { role: 'system', content: 'You are a helpful cooking assistant.' },
      { role: 'user', content: 'Give me a recipe for a simple pasta dish.' },
    ],
    response_format: zodResponseFormat(recipeSchema, 'recipe'),
    temperature: 0.7,
  });

  // Access the parsed structured data
  const message = completion.choices[0]?.message;
  if (message?.parsed) {
    console.log('Recipe name:', message.parsed.recipeName);
    console.log('Ingredients:');
    message.parsed.ingredients.forEach((ing) => {
      console.log(`- ${ing.amount} ${ing.name}`);
    });
    console.log('\nSteps:');
    message.parsed.steps.forEach((step, index) => {
      console.log(`${index + 1}. ${step}`);
    });
    console.log(`\nPreparation time: ${message.parsed.preparationTime}`);
    console.log(`Servings: ${message.parsed.servings}`);
  } else {
    console.log('Raw content:', message?.content);
  }
}

main()