Chat Completions API {#chat-completions-api}

The chat completions API is the primary way to interact with HelpingAI. It generates conversational responses with built-in emotional intelligence and Chain of Recursive Thoughts capabilities.

POST/v1/chat/completions

Create a chat completion with emotional intelligence and Chain of Recursive Thoughts

Request Body {#request-body}

Required Parameters {#required-parameters}

Parameter	Type	Description
model	string	ID of the model to use. Currently supports `Dhanishtha-2.0-preview`
messages	array	A list of messages comprising the conversation so far

Optional Parameters {#optional-parameters}

Parameter	Type	Description	Default
temperature	number	Controls randomness (0-2). Higher values make output more random	0.7
max_tokens	integer	Maximum number of tokens to generate (1-4000)	150
top_p	number	Nucleus sampling parameter (0-1)	1
frequency_penalty	number	Penalize frequent tokens (-2 to 2)	0
presence_penalty	number	Penalize new tokens (-2 to 2)	0
stream	boolean	Whether to stream back partial progress	false
hideThink	boolean	Hide Chain of Recursive Thoughts in `<think>` tags	true
tools	array	List of tools the model may call	null
tool_choice	string/object	Controls which tool is called	"auto"

Message Object {#message-object}

Each message in the messages array should have:

Field	Type	Description
role	string	The role of the message author (`system`, `user`, `assistant`, or `tool`)
content	string	The contents of the message
name	string	(Optional) The name of the author of this message
tool_calls	array	(Optional) Tool calls generated by the model
tool_call_id	string	(Optional) Tool call that this message is responding to

Examples {#examples}

Basic Chat Completion {#basic-chat-completion}

Python (using requests) {#python-using-requests}

Python

import requests

url = "https://api.helpingai.co/v1/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
data = {
    "model": "Dhanishtha-2.0-preview",
    "messages": [
        {"role": "user", "content": "I'm feeling overwhelmed with my workload today."}
    ],
    "temperature": 0.7,
    "max_tokens": 200
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Python (using OpenAI SDK) {#python-using-openai-sdk}

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.helpingai.co/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="Dhanishtha-2.0-preview",
    messages=[
        {"role": "user", "content": "I'm feeling overwhelmed with my workload today."}
    ],
    temperature=0.7,
    max_tokens=200
)

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

Python (using HelpingAI SDK) {#python-using-helpingai-sdk}

Python

from helpingai import HelpingAI

client = HelpingAI(api_key="YOUR_API_KEY")

response = client.chat.completions.create(
    model="Dhanishtha-2.0-preview",
    messages=[
        {"role": "user", "content": "I'm feeling overwhelmed with my workload today."}
    ],
    temperature=0.7,
    max_tokens=200
)

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

JavaScript (using axios) {#javascript-using-axios}

JavaScript

const axios = require("axios");

(async () => {
  const response = await axios.post(
    "https://api.helpingai.co/v1/chat/completions",
    {
      model: "Dhanishtha-2.0-preview",
      messages: [
        {
          role: "user",
          content: "I'm feeling overwhelmed with my workload today.",
        },
      ],
      temperature: 0.7,
      max_tokens: 200,
    },
    {
      headers: {
        Authorization: "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
      },
    }
  );

  console.log(response.data.choices[0].message.content);
})();

JavaScript (using OpenAI package) {#javascript-using-openai-package}

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.helpingai.co/v1",
  apiKey: "YOUR_API_KEY",
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "Dhanishtha-2.0-preview",
    messages: [
      {
        role: "user",
        content: "I'm feeling overwhelmed with my workload today.",
      },
    ],
    temperature: 0.7,
    max_tokens: 200,
  });

  console.log(completion.choices[0].message.content);
}

main();

JavaScript (using HelpingAI SDK) {#javascript-using-helpingai-sdk}

JavaScript

import { HelpingAI } from "helpingai";

const client = new HelpingAI({
  apiKey: "YOUR_API_KEY",
});

async function main() {
  const completion = await client.chat.completions.create({
    model: "Dhanishtha-2.0-preview",
    messages: [
      {
        role: "user",
        content: "I'm feeling overwhelmed with my workload today.",
      },
    ],
    temperature: 0.7,
    max_tokens: 200,
  });

  console.log(completion.choices[0].message.content);
}

main();

With System Message {#with-system-message}

Python (using requests) {#python-using-requests}

Python

import requests

url = "https://api.helpingai.co/v1/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
data = {
    "model": "Dhanishtha-2.0-preview",
    "messages": [
        {"role": "system", "content": "You are a supportive career counselor who provides empathetic guidance."},
        {"role": "user", "content": "I'm thinking about changing careers but I'm scared."}
    ],
    "temperature": 0.8,
    "max_tokens": 300
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Python (using OpenAI SDK) {#python-using-openai-sdk}

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.helpingai.co/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="Dhanishtha-2.0-preview",
    messages=[
        {"role": "system", "content": "You are a supportive career counselor who provides empathetic guidance."},
        {"role": "user", "content": "I'm thinking about changing careers but I'm scared."}
    ],
    temperature=0.8,
    max_tokens=300
)

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

Python (using HelpingAI SDK) {#python-using-helpingai-sdk}

Python

from helpingai import HelpingAI

client = HelpingAI(api_key="YOUR_API_KEY")

response = client.chat.completions.create(
    model="Dhanishtha-2.0-preview",
    messages=[
        {"role": "system", "content": "You are a supportive career counselor who provides empathetic guidance."},
        {"role": "user", "content": "I'm thinking about changing careers but I'm scared."}
    ],
    temperature=0.8,
    max_tokens=300
)

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

JavaScript (using axios) {#javascript-using-axios}

JavaScript

const axios = require("axios");

(async () => {
  const response = await axios.post(
    "https://api.helpingai.co/v1/chat/completions",
    {
      model: "Dhanishtha-2.0-preview",
      messages: [
        {
          role: "system",
          content:
            "You are a supportive career counselor who provides empathetic guidance.",
        },
        {
          role: "user",
          content: "I'm thinking about changing careers but I'm scared.",
        },
      ],
      temperature: 0.8,
      max_tokens: 300,
    },
    {
      headers: {
        Authorization: "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
      },
    }
  );

  console.log(response.data.choices[0].message.content);
})();

JavaScript (using OpenAI package) {#javascript-using-openai-package}

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.helpingai.co/v1",
  apiKey: "YOUR_API_KEY",
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "Dhanishtha-2.0-preview",
    messages: [
      {
        role: "system",
        content:
          "You are a supportive career counselor who provides empathetic guidance.",
      },
      {
        role: "user",
        content: "I'm thinking about changing careers but I'm scared.",
      },
    ],
    temperature: 0.8,
    max_tokens: 300,
  });

  console.log(completion.choices[0].message.content);
}

main();

JavaScript (using HelpingAI SDK) {#javascript-using-helpingai-sdk}

JavaScript

import { HelpingAI } from "helpingai";

const client = new HelpingAI({
  apiKey: "YOUR_API_KEY",
});

async function main() {
  const completion = await client.chat.completions.create({
    model: "Dhanishtha-2.0-preview",
    messages: [
      {
        role: "system",
        content:
          "You are a supportive career counselor who provides empathetic guidance.",
      },
      {
        role: "user",
        content: "I'm thinking about changing careers but I'm scared.",
      },
    ],
    temperature: 0.8,
    max_tokens: 300,
  });

  console.log(completion.choices[0].message.content);
}

main();

With Chain of Recursive Thoughts (hideThink=false) {#with-chain-of-recursive-thoughts-hidethinkfalse}

Python (using requests) {#python-using-requests}

Python

import requests

url = "https://api.helpingai.co/v1/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
data = {
    "model": "Dhanishtha-2.0-preview",
    "messages": [
        {"role": "user", "content": "What's 15 * 24? Show your work."}
    ],
    "hideThink": False,  # Shows reasoning process
    "temperature": 0.3,
    "max_tokens": 300
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Python (using OpenAI SDK) {#python-using-openai-sdk}

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.helpingai.co/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="Dhanishtha-2.0-preview",
    messages=[
        {"role": "user", "content": "What's 15 * 24? Show your work."}
    ],
    hideThink=False,  # Shows reasoning process
    temperature=0.3,
    max_tokens=300
)

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

Python (using HelpingAI SDK) {#python-using-helpingai-sdk}

Python

from helpingai import HelpingAI

client = HelpingAI(api_key="YOUR_API_KEY")

response = client.chat.completions.create(
    model="Dhanishtha-2.0-preview",
    messages=[
        {"role": "user", "content": "What's 15 * 24? Show your work."}
    ],
    hideThink=False,  # Shows reasoning process
    temperature=0.3,
    max_tokens=300
)

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

JavaScript (using axios) {#javascript-using-axios}

JavaScript

const axios = require("axios");

(async () => {
  const response = await axios.post(
    "https://api.helpingai.co/v1/chat/completions",
    {
      model: "Dhanishtha-2.0-preview",
      messages: [{ role: "user", content: "What's 15 * 24? Show your work." }],
      hideThink: false, // Shows reasoning process
      temperature: 0.3,
      max_tokens: 300,
    },
    {
      headers: {
        Authorization: "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
      },
    }
  );

  console.log(response.data.choices[0].message.content);
})();

JavaScript (using OpenAI package) {#javascript-using-openai-package}

JavaScript

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.helpingai.co/v1",
  apiKey: "YOUR_API_KEY",
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "Dhanishtha-2.0-preview",
    messages: [{ role: "user", content: "What's 15 * 24? Show your work." }],
    hideThink: false, // Shows reasoning process
    temperature: 0.3,
    max_tokens: 300,
  });

  console.log(completion.choices[0].message.content);
}

main();

JavaScript (using HelpingAI SDK) {#javascript-using-helpingai-sdk}

JavaScript

import { HelpingAI } from "helpingai";

const client = new HelpingAI({
  apiKey: "YOUR_API_KEY",
});

async function main() {
  const completion = await client.chat.completions.create({
    model: "Dhanishtha-2.0-preview",
    messages: [{ role: "user", content: "What's 15 * 24? Show your work." }],
    hideThink: false, // Shows reasoning process
    temperature: 0.3,
    max_tokens: 300,
  });

  console.log(completion.choices[0].message.content);
}

main();

Response Format {#response-format}

A successful response returns a JSON object with the following structure:

JSON

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "Dhanishtha-2.0-preview",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I understand you're feeling overwhelmed with your workload today. That's a really common experience, and it's completely valid to feel that way when you have a lot on your plate..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 45,
    "total_tokens": 65
  }
}

Response Fields {#response-fields}

Field	Type	Description
id	string	Unique identifier for the chat completion
object	string	Object type, always "chat.completion"
created	integer	Unix timestamp of when the completion was created
model	string	The model used for the completion
choices	array	List of completion choices
usage	object	Token usage information

Choice Object {#choice-object}

Field	Type	Description
index	integer	The index of the choice in the list
message	object	The generated message
finish_reason	string	Reason the model stopped generating tokens

Message Object (Response) {#message-object-response}

Field	Type	Description
role	string	Always "assistant" for generated responses
content	string	The generated response content
tool_calls	array	(Optional) Tool calls made by the model

Usage Object {#usage-object}

Field	Type	Description
prompt_tokens	integer	Number of tokens in the prompt
completion_tokens	integer	Number of tokens in the completion
total_tokens	integer	Total tokens used (prompt + completion)

Streaming {#streaming}

For streaming responses, set stream: true. You'll receive Server-Sent Events with partial responses:

JSON

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1677652288,"model":"Dhanishtha-2.0-preview","choices":[{"index":0,"delta":{"content":"I understand"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1677652288,"model":"Dhanishtha-2.0-preview","choices":[{"index":0,"delta":{"content":" you're"},"finish_reason":null}]}

data: [DONE]

Error Responses {#error-responses}

Error responses follow this format:

JSON

{
  "error": {
    "message": "Invalid API key provided",
    "type": "authentication_error",
    "code": "invalid_api_key"
  }
}

Common Error Codes {#common-error-codes}

Code	Description
`invalid_api_key`	The API key is invalid or missing
`insufficient_quota`	You've exceeded your usage quota
`model_not_found`	The specified model doesn't exist
`invalid_request_error`	The request format is invalid
`rate_limit_exceeded`	Too many requests in a short time

Best Practices {#best-practices}

Provide Emotional Context: Include emotional cues in your messages for better responses
Use System Messages: Set clear context and behavior expectations
Monitor Token Usage: Track usage to optimize costs
Handle Errors Gracefully: Always implement proper error handling
Use Appropriate Temperature: Lower for factual tasks, higher for creative tasks

Next Steps {#next-steps}

Streaming Guide - Learn about real-time responses
Tool Calling - Function calling capabilities
Chain of Recursive Thoughts - Understanding AI thoughts
Models API - Available models and their capabilities model: "Dhanishtha-2.0-preview", messages: [ { role: "user", content: "I'm feeling overwhelmed with my workload today.", }, ], temperature: 0.7, max_tokens: 200, });

console.log(completion.choices[0].message.content); }

main();

Docs•API Reference•Pricing