The comprehensive guide to building with HelpingAI models - featuring the revolutionary Dhanishta 2.0 with intermediate thinking capabilities
Welcome to the HelpingAI Cookbook! This repository contains examples, guides, and best practices for using HelpingAI's powerful AI models, including the groundbreaking Dhanishta 2.0 - the world's first AI model with intermediate thinking capabilities.
- World's First Intermediate Thinking Model: See AI think, reconsider, and refine its reasoning in real-time
- Transparent Reasoning:
<think>...</think>
blocks show the AI's thought process - Self-Correction: AI can identify and fix its own logical inconsistencies
- Multi-Phase Reasoning: Complex problems solved through iterative thinking
- 39+ Languages: Multilingual reasoning with consistent quality
pip install HelpingAI
from HelpingAI import HAI
# Initialize the client
hai = HAI()
# Experience Dhanishta 2.0's thinking process
response = hai.chat.completions.create(
model="Dhanishtha-2.0-preview",
messages=[
{"role": "user", "content": "How many letter 'r' are in 'strawberry'?"}
],
hide_think=False # Show the thinking process!
)
print(response.choices[0].message.content)
- Quick Start Guide - Your first steps with HelpingAI
- Model Overview - Understanding all available models
- Intermediate Thinking - Understanding AI reasoning
- First API Call - Hello World with HelpingAI
- Chat Completions - Basic conversations
- Streaming Responses - Real-time responses
- Parameter Tuning - Controlling AI behavior
- Tool Calling - Function calling and tool integration
- Thinking Process Demo - See AI think step-by-step
- Complex Reasoning - Multi-step problem solving
- Self-Correction Examples - AI fixing its mistakes
- Multilingual Thinking - Reasoning in multiple languages
- API Reference - Complete API documentation
- Model Specifications - Detailed model information
- Best Practices - Production-ready guidelines
# Watch AI solve a logic puzzle step by step
response = hai.chat.completions.create(
model="Dhanishtha-2.0-preview",
messages=[{
"role": "user",
"content": "If it takes 5 machines 5 minutes to make 5 widgets, how long would it take 100 machines to make 100 widgets?"
}],
hide_think=False
)
# Output shows thinking process:
# <think>
# Let me think about this step by step...
# If 5 machines make 5 widgets in 5 minutes...
# That means each machine makes 1 widget in 5 minutes...
# So 100 machines would each make 1 widget in 5 minutes...
# Therefore 100 machines make 100 widgets in 5 minutes!
# </think>
Use Case | Best Model | Key Features |
---|---|---|
Complex Problem Solving | Dhanishta 2.0 | Intermediate thinking, self-correction |
Educational Content | Dhanishta 2.0 | Step-by-step reasoning, explanations |
Creative Writing | Dhanishta 2.0 | Creativity with advanced reasoning |
Multilingual Tasks | Dhanishta 2.0 | 39+ languages with consistent reasoning |
- 🆕 Dhanishta 2.0 Preview: World's first intermediate thinking AI model
- 🧠 Transparent Reasoning: See how AI thinks with
<think>
blocks - 🔄 Self-Correction: AI that can fix its own mistakes
- 🌍 Multilingual Reasoning: Consistent thinking across 39+ languages
We welcome contributions! Feel free to open issues, submit pull requests, or suggest improvements to help make this project better.
This project is licensed under the Apache 2.0 License - see the LICENSE file for details.
Built with ❤️ by the HelpingAI Team
Empowering developers to build the future of AI applications