# AIWand 🪄
> **One API to rule them all** - Unified OpenAI and Gemini interface with automatic provider switching and structured data extraction from anywhere.
[](https://pypi.org/project/aiwand/)
[](https://pypi.org/project/aiwand/)
[](https://github.com/onlyoneaman/aiwand/blob/main/LICENSE)
[](https://github.com/onlyoneaman/aiwand/actions?query=workflow%3ACI)
[](https://pepy.tech/project/aiwand)
[](https://pepy.tech/project/aiwand/month)
[](https://pepy.tech/project/aiwand/week)
## 🚀 **Stop Wrestling with AI APIs**
**Before:** Different APIs, manual JSON parsing, provider-specific code 😫
**After:** One API, automatic everything ✨
```python
import aiwand
# Works with any model - provider auto-detected
response = aiwand.call_ai(model="gpt-4o", user_prompt="Explain quantum computing?")
# returns structured json data directly
data = aiwand.extract(content="John Doe, john@example.com, (555) 123-4567")
```
## 🔧 Installation & Setup
```bash
pip install aiwand
export OPENAI_API_KEY="your-key" # Set either key (or both for fallback)
export GEMINI_API_KEY="your-key"
```
## 💡 Core Features
### **`call_ai`** - Universal AI Interface
Same code works with OpenAI and Gemini - automatic provider detection:
```python
from pydantic import BaseModel
# Basic AI calls
response = aiwand.call_ai(model="gpt-4o", user_prompt="Explain quantum computing?")
# Structured output - get Pydantic objects directly
class BlogPost(BaseModel):
title: str
content: str
tags: list[str]
blog = aiwand.call_ai(
model="gemini-2.0-flash",
user_prompt="Write a blog about AI",
response_format=BlogPost # Returns BlogPost object!
)
print(blog.title) # Direct access, no JSON parsing
# Works with any model
for model in ["gpt-4o", "gemini-2.0-flash", "o3-mini"]:
response = aiwand.call_ai(model=model, user_prompt=f"What makes {model} special?")
```
### **`extract`** - Smart Data Extraction
Extract structured data from text, web links, documents, and images:
```python
from pydantic import BaseModel
class CompanyInfo(BaseModel):
name: str
founded: int
employees: int
technologies: list[str]
# Extract from individual sources
contact = aiwand.extract(content="John Doe, john@example.com, (555) 123-4567")
webpage = aiwand.extract(links=["https://company.com/about"])
docs = aiwand.extract(document_links=["resume.pdf", "report.docx"])
images = aiwand.extract(images=["chart.png", "diagram.jpg"])
# Or mix all sources together with custom structure
company = aiwand.extract(
content="Research notes about tech companies...",
links=["https://company.com/about"], # Web pages
document_links=["annual_report.pdf"], # Documents
images=["company_chart.png"], # Images
response_format=CompanyInfo # Get typed object back
)
print(f"{company.name} founded in {company.founded}") # Direct access
```
## ⚡ Quick Examples
```python
import aiwand
# Instant AI calls
summary = aiwand.summarize("Long article...", style="bullet-points")
response = aiwand.chat("What is machine learning?")
story = aiwand.generate_text("Write a haiku about coding")
# Smart classification
grader = aiwand.create_binary_classifier(criteria="technical accuracy")
result = grader(question="What is 2+2?", answer="4", expected="4")
print(f"Accuracy: {result.score}/5")
```
## 🎨 CLI Magic
```bash
# Quick chat
aiwand "Explain quantum computing simply"
# Extract from anything
aiwand extract "Dr. Sarah Johnson, sarah@lab.com" --json
aiwand extract --links https://example.com --document-links resume.pdf --images chart.png
# Built-in functions
aiwand summarize "Long text..." --style concise
aiwand chat "Hello there!"
```
## ✨ Why Choose AIWand?
| 🔄 **Provider Agnostic** | Same code, OpenAI or Gemini |
|---|---|
| 🏗️ **Structured Output** | Pydantic objects, no JSON parsing |
| 🧠 **Smart Detection** | Automatic provider selection |
| 📄 **Universal Extraction** | Text, web links, documents, images |
| ⚡ **Zero Setup** | Just add API keys |
| 🎯 **Drop-in Ready** | Minimal code changes |
## 📚 Documentation
- **[API Reference](docs/api-reference.md)** - Complete function docs
- **[CLI Guide](docs/cli.md)** - Command line usage
- **[Installation](docs/installation.md)** - Setup details
- **[Development](docs/development.md)** - Contributing guide
## 🤝 Contributing
We welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.
## 📝 License
MIT License - see [LICENSE](LICENSE) file for details.
---
⭐ **Star this repo if AIWand makes your AI development easier!**
**Made with ❤️ by [Aman Kumar](https://x.com/onlyoneaman)**
Raw data
{
"_id": null,
"home_page": "https://github.com/onlyoneaman/aiwand",
"name": "aiwand",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "aiwand, ai, wand, ai wand, ai toolkit, openai, gemini, llm, pydantic, provider switching, structured output, text processing, call_ai, extract, summarization, chat, generate, classification",
"author": "Aman Kumar",
"author_email": "2000.aman.sinha@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/2a/03/205e413726a7ccc49f468547d7414bd4e2548ff998a33299b24806a19622/aiwand-0.4.34.tar.gz",
"platform": null,
"description": "# AIWand \ud83e\ude84\n\n> **One API to rule them all** - Unified OpenAI and Gemini interface with automatic provider switching and structured data extraction from anywhere.\n\n[](https://pypi.org/project/aiwand/)\n[](https://pypi.org/project/aiwand/)\n[](https://github.com/onlyoneaman/aiwand/blob/main/LICENSE)\n[](https://github.com/onlyoneaman/aiwand/actions?query=workflow%3ACI)\n[](https://pepy.tech/project/aiwand)\n[](https://pepy.tech/project/aiwand/month)\n[](https://pepy.tech/project/aiwand/week)\n\n## \ud83d\ude80 **Stop Wrestling with AI APIs**\n\n**Before:** Different APIs, manual JSON parsing, provider-specific code \ud83d\ude2b \n**After:** One API, automatic everything \u2728\n\n```python\nimport aiwand\n# Works with any model - provider auto-detected\nresponse = aiwand.call_ai(model=\"gpt-4o\", user_prompt=\"Explain quantum computing?\")\n\n# returns structured json data directly\ndata = aiwand.extract(content=\"John Doe, john@example.com, (555) 123-4567\")\n```\n\n## \ud83d\udd27 Installation & Setup\n\n```bash\npip install aiwand\nexport OPENAI_API_KEY=\"your-key\" # Set either key (or both for fallback)\nexport GEMINI_API_KEY=\"your-key\" \n```\n\n## \ud83d\udca1 Core Features\n\n### **`call_ai`** - Universal AI Interface\nSame code works with OpenAI and Gemini - automatic provider detection:\n\n```python\nfrom pydantic import BaseModel\n\n# Basic AI calls\nresponse = aiwand.call_ai(model=\"gpt-4o\", user_prompt=\"Explain quantum computing?\")\n\n# Structured output - get Pydantic objects directly\nclass BlogPost(BaseModel):\n title: str\n content: str\n tags: list[str]\n\nblog = aiwand.call_ai(\n model=\"gemini-2.0-flash\",\n user_prompt=\"Write a blog about AI\",\n response_format=BlogPost # Returns BlogPost object!\n)\nprint(blog.title) # Direct access, no JSON parsing\n\n# Works with any model\nfor model in [\"gpt-4o\", \"gemini-2.0-flash\", \"o3-mini\"]:\n response = aiwand.call_ai(model=model, user_prompt=f\"What makes {model} special?\")\n```\n\n### **`extract`** - Smart Data Extraction \nExtract structured data from text, web links, documents, and images:\n\n```python\nfrom pydantic import BaseModel\n\nclass CompanyInfo(BaseModel):\n name: str\n founded: int\n employees: int\n technologies: list[str]\n\n# Extract from individual sources\ncontact = aiwand.extract(content=\"John Doe, john@example.com, (555) 123-4567\")\nwebpage = aiwand.extract(links=[\"https://company.com/about\"])\ndocs = aiwand.extract(document_links=[\"resume.pdf\", \"report.docx\"])\nimages = aiwand.extract(images=[\"chart.png\", \"diagram.jpg\"])\n\n# Or mix all sources together with custom structure\ncompany = aiwand.extract(\n content=\"Research notes about tech companies...\", \n links=[\"https://company.com/about\"], # Web pages\n document_links=[\"annual_report.pdf\"], # Documents \n images=[\"company_chart.png\"], # Images\n response_format=CompanyInfo # Get typed object back\n)\n\nprint(f\"{company.name} founded in {company.founded}\") # Direct access\n```\n\n## \u26a1 Quick Examples\n\n```python\nimport aiwand\n\n# Instant AI calls\nsummary = aiwand.summarize(\"Long article...\", style=\"bullet-points\")\nresponse = aiwand.chat(\"What is machine learning?\")\nstory = aiwand.generate_text(\"Write a haiku about coding\")\n\n# Smart classification \ngrader = aiwand.create_binary_classifier(criteria=\"technical accuracy\")\nresult = grader(question=\"What is 2+2?\", answer=\"4\", expected=\"4\")\nprint(f\"Accuracy: {result.score}/5\")\n```\n\n## \ud83c\udfa8 CLI Magic\n\n```bash\n# Quick chat\naiwand \"Explain quantum computing simply\"\n\n# Extract from anything\naiwand extract \"Dr. Sarah Johnson, sarah@lab.com\" --json\naiwand extract --links https://example.com --document-links resume.pdf --images chart.png\n\n# Built-in functions\naiwand summarize \"Long text...\" --style concise\naiwand chat \"Hello there!\"\n```\n\n## \u2728 Why Choose AIWand?\n\n| \ud83d\udd04 **Provider Agnostic** | Same code, OpenAI or Gemini |\n|---|---|\n| \ud83c\udfd7\ufe0f **Structured Output** | Pydantic objects, no JSON parsing |\n| \ud83e\udde0 **Smart Detection** | Automatic provider selection |\n| \ud83d\udcc4 **Universal Extraction** | Text, web links, documents, images |\n| \u26a1 **Zero Setup** | Just add API keys |\n| \ud83c\udfaf **Drop-in Ready** | Minimal code changes |\n\n## \ud83d\udcda Documentation\n\n- **[API Reference](docs/api-reference.md)** - Complete function docs\n- **[CLI Guide](docs/cli.md)** - Command line usage \n- **[Installation](docs/installation.md)** - Setup details\n- **[Development](docs/development.md)** - Contributing guide\n\n## \ud83e\udd1d Contributing\n\nWe welcome contributions! See [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.\n\n## \ud83d\udcdd License\n\nMIT License - see [LICENSE](LICENSE) file for details.\n\n---\n\n\u2b50 **Star this repo if AIWand makes your AI development easier!**\n\n**Made with \u2764\ufe0f by [Aman Kumar](https://x.com/onlyoneaman)** \n",
"bugtrack_url": null,
"license": null,
"summary": "A simple AI toolkit for text processing using OpenAI and Gemini APIs",
"version": "0.4.34",
"project_urls": {
"Homepage": "https://github.com/onlyoneaman/aiwand"
},
"split_keywords": [
"aiwand",
" ai",
" wand",
" ai wand",
" ai toolkit",
" openai",
" gemini",
" llm",
" pydantic",
" provider switching",
" structured output",
" text processing",
" call_ai",
" extract",
" summarization",
" chat",
" generate",
" classification"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "603129038489efbbbcd734ab31b29802957bb7fbe253a95847a8d0fe4d99e883",
"md5": "a707493c810c9f402c3ab458142822d6",
"sha256": "1d4556f427389916f5a48f1e036e33c2f61c8069dad74c1ee4fd7b8a9575d558"
},
"downloads": -1,
"filename": "aiwand-0.4.34-py3-none-any.whl",
"has_sig": false,
"md5_digest": "a707493c810c9f402c3ab458142822d6",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 40558,
"upload_time": "2025-08-24T22:14:10",
"upload_time_iso_8601": "2025-08-24T22:14:10.209298Z",
"url": "https://files.pythonhosted.org/packages/60/31/29038489efbbbcd734ab31b29802957bb7fbe253a95847a8d0fe4d99e883/aiwand-0.4.34-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "2a03205e413726a7ccc49f468547d7414bd4e2548ff998a33299b24806a19622",
"md5": "dd72a3d7c1ace67ce6615533044f7318",
"sha256": "dc1f3df5916c8853bb0055173bccb2e80e9757f9c6c35d5d5e5a0ecdb5870f8f"
},
"downloads": -1,
"filename": "aiwand-0.4.34.tar.gz",
"has_sig": false,
"md5_digest": "dd72a3d7c1ace67ce6615533044f7318",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 76121,
"upload_time": "2025-08-24T22:14:11",
"upload_time_iso_8601": "2025-08-24T22:14:11.934579Z",
"url": "https://files.pythonhosted.org/packages/2a/03/205e413726a7ccc49f468547d7414bd4e2548ff998a33299b24806a19622/aiwand-0.4.34.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-24 22:14:11",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "onlyoneaman",
"github_project": "aiwand",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "google-genai",
"specs": [
[
">=",
"1.20.0"
]
]
},
{
"name": "openai",
"specs": [
[
">=",
"1.0.0"
]
]
},
{
"name": "python-dotenv",
"specs": [
[
">=",
"0.19.0"
]
]
},
{
"name": "beautifulsoup4",
"specs": [
[
">=",
"4.0"
]
]
}
],
"lcname": "aiwand"
}
JSON
