Frequently Asked Questions

Find answers to common questions about HelpingAI, our API, and how to get the most out of emotionally intelligent AI.

General Questions

What is HelpingAI?

HelpingAI is an emotionally intelligent AI platform built on the revolutionary Dhanishtha-2.0-preview architecture. Unlike traditional AI models, HelpingAI understands not just what you say, but how you feel, providing more natural, empathetic, and effective interactions.

How is HelpingAI different from other AI services?

HelpingAI offers several unique advantages:

Emotional Intelligence: Built-in understanding of human emotions with a 98 EQ score
Chain of Recursive Thoughts: Thinks during response generation, not just before
Token Efficiency: 5x fewer tokens than GPT-4 for similar quality responses
OpenAI Compatibility: Drop-in replacement for existing applications
Transparent Reasoning: Optional visibility into AI's thought process with hideThink

What is the Dhanishtha-2.0-preview model?

Dhanishtha-2.0-preview is our flagship model featuring:

Advanced emotional intelligence capabilities
Chain of Recursive Thoughts engine
32,768 token context length
Support for tool calling and streaming
Optimized performance and cost efficiency

API Questions

Is HelpingAI compatible with OpenAI's API?

Yes! HelpingAI is fully compatible with OpenAI's API format. You can use existing OpenAI libraries by simply changing the base URL and API key:

Python

from openai import OpenAI

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

What is the [object Object] parameter?

The hideThink parameter is unique to HelpingAI and controls whether you see the AI's reasoning process:

hideThink: true (default): Shows only the final response
hideThink: false: Shows reasoning in <think>...</think> tags

This transparency helps you understand how the AI arrives at its responses.

How do I get an API key?

Sign up at helpingai.co
Go to your dashboard
Generate a new API key
Keep your key secure and never expose it in client-side code

What are the rate limits?

Rate limits vary by subscription tier:

Tier	Requests/minute	Tokens/minute
Free	60	10,000
Pro	3,000	500,000
Enterprise	Custom	Custom

Can I use HelpingAI for commercial applications?

Yes! HelpingAI is designed for both personal and commercial use. Check our pricing page for details on commercial plans.

Technical Questions

What programming languages are supported?

HelpingAI provides official SDKs for:

Python: pip install helpingai
JavaScript/Node.js: npm install helpingai

You can also use any HTTP client or OpenAI-compatible library in any language.

Does HelpingAI support streaming?

Yes! Set stream: true in your request to receive responses in real-time as they're generated:

Python

stream = client.chat.completions.create(
    model="Dhanishtha-2.0-preview",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Can HelpingAI call functions/tools?

Yes! HelpingAI supports advanced tool calling. Define functions and the AI will intelligently decide when and how to use them:

Python

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get current weather",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string"}
            }
        }
    }
}]

What's the maximum context length?

Dhanishtha-2.0-preview supports up to 32,768 tokens of context, allowing for long conversations and complex tasks.

How do I handle errors?

Use try-catch blocks to handle API errors gracefully:

Python

try:
    response = client.chat.completions.create(...)
except Exception as e:
    if "authentication" in str(e).lower():
        print("Invalid API key")
    elif "rate limit" in str(e).lower():
        print("Rate limit exceeded")
    else:
        print(f"API error: {e}")

Emotional Intelligence Questions

How does emotional intelligence work?

HelpingAI automatically detects emotional cues in text and responds appropriately. It considers:

Word choice and tone
Context and situation
Emotional patterns in conversation
Appropriate empathetic responses

Can I control the emotional response style?

Yes! Use system messages to guide emotional behavior:

Python

messages = [
    {
        "role": "system", 
        "content": "You are a supportive counselor who validates emotions and provides gentle guidance."
    },
    {"role": "user", "content": "I'm feeling overwhelmed"}
]

What emotions can HelpingAI detect?

HelpingAI can detect and respond to a wide range of emotions including:

Joy, excitement, happiness
Sadness, grief, disappointment
Anger, frustration, irritation
Anxiety, worry, fear
Confusion, uncertainty
Hope, optimism
And many more nuanced emotional states

Use Case Questions

What applications is HelpingAI best for?

HelpingAI excels in scenarios requiring emotional understanding:

Mental Health & Wellness: Supportive chatbots and therapy assistants
Customer Support: Empathetic customer service interactions
Education: Adaptive tutoring that responds to student emotions
Creative Writing: AI that understands tone and emotional context
Personal Assistants: More natural, human-like interactions

Can HelpingAI replace human therapists?

No. While HelpingAI can provide emotional support and guidance, it's not a replacement for professional mental health care. It's designed to complement human services and provide accessible emotional support.

Is HelpingAI suitable for children?

HelpingAI can be used in educational applications for children, but we recommend:

Adult supervision for younger users
Appropriate content filtering
Clear boundaries about AI vs. human interaction
Following your organization's child safety policies

Pricing and Billing Questions

How is usage calculated?

Usage is calculated based on tokens processed:

Input tokens: Tokens in your prompt/messages
Output tokens: Tokens in the AI's response
Both input and output tokens count toward your usage

What happens if I exceed my rate limit?

If you exceed your rate limit, you'll receive a 429 error. You can:

Wait for the rate limit to reset
Upgrade to a higher tier
Implement request queuing in your application

Can I get a refund?

Refund policies vary by plan. Contact our support team at support@helpingai.co for specific refund requests.

Security and Privacy Questions

How is my data protected?

HelpingAI takes data security seriously:

All API communications use HTTPS encryption
We don't store conversation data longer than necessary
API keys are encrypted and securely stored
We follow industry-standard security practices

Do you train on my data?

We may use API interactions to improve our models, but:

Personal information is removed or anonymized
You can opt out of data usage for training
Enterprise customers can request data isolation

Where are your servers located?

Our primary servers are located in secure data centers in the United States, with additional regions planned for global expansion.

Troubleshooting

My API key isn't working

Check that:

Your API key is correct and hasn't been regenerated
You're using the correct base URL: https://api.helpingai.co/v1
Your account is in good standing
You haven't exceeded your usage limits

Responses seem slow

Response time can be affected by:

Request complexity and length
Current API load
Network connectivity
Whether you're using streaming (which feels faster)

I'm getting unexpected responses

Try:

Adjusting the temperature parameter
Using more specific system messages
Checking if hideThink=false reveals reasoning issues
Reviewing your prompt for clarity

Getting Help

How can I get support?

Documentation: helpingai.co/docs
Discord Community: discord.gg/helpingai
Email Support: support@helpingai.co
GitHub Issues: For SDK-specific problems

What information should I include in support requests?

Please include:

Your API key (last 4 characters only)
Request/response examples
Error messages
Programming language and SDK version
Steps to reproduce the issue

Do you offer enterprise support?

Yes! Enterprise customers receive:

Priority support
Dedicated account management
Custom rate limits
Advanced security features
SLA guarantees

Still have questions? Join our Discord community or email us at support@helpingai.co.

Docs•API Reference•Pricing