# llm-contracts
> 🛡️ **"ESLint + Pytest" for AI responses** — Catch LLM mistakes before they reach production.
> Schema validation, content linting, and professional reports for any LLM.
---
## 📦 Install
```bash
pip install llm-contracts
```
---
## ⚡ Why `llm-contracts`?
LLMs are **fluent, confident, and totally wrong** just often enough to break your app.
- **Air Canada's chatbot** promised non-existent bereavement fares → Legal action
- **CNET's AI** published financial advice with wrong interest rates → Public corrections
- **ChatGPT lawyer** submitted fake legal citations in court → Professional sanctions
`llm-contracts` validates every AI response **before** it causes problems.
---
## 🚀 Quick Start
### CLI
```bash
# Validate AI output against schema
llm-validate output.json --schema schema.yaml
# Generate professional reports
llm-validate output.json --schema schema.yaml --html-report report.html
```
### Python API
```python
from llm_contracts import contracts
# Validate output against schema
result = contracts.validate(data, "schema.yaml")
if not result.is_valid:
print("AI failed validation:")
for error in result.errors:
print(f" - {error}")
# Generate reports
contracts.generate_report(result, "report.html", "schema.yaml", format="html")
```
---
## ✅ Key Features
* **Schema Validation** — Ensure proper JSON/YAML structure and data types
* **Content Linting** — Check keywords, tone, word count, patterns, quality rules
* **Professional Reports** — Beautiful HTML and Markdown validation reports
* **Framework Agnostic** — Works with OpenAI, Anthropic, local models, any LLM
* **CLI + Python API** — Use in scripts or integrate into applications
* **Zero Vendor Lock-in** — Pure validation logic, no external API calls required
---
## 📋 Example Schema
```yaml
schema:
title:
type: str
min_length: 10
description:
type: str
min_length: 100
rules:
- keyword_must_include: ["quality", "premium"]
- keyword_must_not_include: ["cheap", "defective"]
- no_placeholder_text: "\\[YOUR_TEXT_HERE\\]"
- word_count_min: 100
- word_count_max: 500
```
**Result:** Every AI response gets validated before reaching your users. **No more silent failures.**
---
## 📚 Documentation & Links
* 📖 [Complete Documentation & Whitepaper](https://maxamed.github.io/llm-contract/)
* 🚀 [Getting Started Guide](https://maxamed.github.io/llm-contract/getting-started)
* 💡 [Real-World Examples](https://maxamed.github.io/llm-contract/examples)
* 🛠 [GitHub Source](https://github.com/Maxamed/llm-contract)
* 🐛 [Report Issues](https://github.com/Maxamed/llm-contract/issues)
---
## 🤝 Contributors
**Created by [Mohamed Jama](https://www.linkedin.com/in/mohamedjama/)** - Built for developers shipping AI features in production.
**Major Contributors:**
- **[Abdirahman Attila](https://github.com/Attili-sys)** - Frontend web interface, comprehensive documentation website, enhanced testing suite, and Jekyll/GitHub Pages setup
We welcome contributions! See [CONTRIBUTING.md](https://github.com/Maxamed/llm-contract/blob/main/CONTRIBUTING.md) for guidelines.
---
## 🏷 License
MIT © Mohamed Jama - see [LICENSE](https://github.com/Maxamed/llm-contract/blob/main/LICENSE) file for details.
---
**Stop hoping your AI gets it right. Start knowing it does.**
Raw data
{
"_id": null,
"home_page": null,
"name": "llm-contracts",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "llm, validation, linting, ai, schema, contracts",
"author": null,
"author_email": "Mohamed Jama <mohamed.jama@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/71/b7/81c694be887392b0cba0f7b1c0534a6a15cc9da380cadd4462703a9a1d81/llm_contracts-1.0.0.tar.gz",
"platform": null,
"description": "# llm-contracts\n\n\n\n\n\n\n\n> \ud83d\udee1\ufe0f **\"ESLint + Pytest\" for AI responses** \u2014 Catch LLM mistakes before they reach production. \n> Schema validation, content linting, and professional reports for any LLM.\n\n---\n\n## \ud83d\udce6 Install\n\n```bash\npip install llm-contracts\n```\n\n---\n\n## \u26a1 Why `llm-contracts`?\n\nLLMs are **fluent, confident, and totally wrong** just often enough to break your app.\n\n- **Air Canada's chatbot** promised non-existent bereavement fares \u2192 Legal action\n- **CNET's AI** published financial advice with wrong interest rates \u2192 Public corrections \n- **ChatGPT lawyer** submitted fake legal citations in court \u2192 Professional sanctions\n\n`llm-contracts` validates every AI response **before** it causes problems.\n\n---\n\n## \ud83d\ude80 Quick Start\n\n### CLI\n```bash\n# Validate AI output against schema\nllm-validate output.json --schema schema.yaml\n\n# Generate professional reports\nllm-validate output.json --schema schema.yaml --html-report report.html\n```\n\n### Python API\n```python\nfrom llm_contracts import contracts\n\n# Validate output against schema\nresult = contracts.validate(data, \"schema.yaml\")\n\nif not result.is_valid:\n print(\"AI failed validation:\")\n for error in result.errors:\n print(f\" - {error}\")\n\n# Generate reports\ncontracts.generate_report(result, \"report.html\", \"schema.yaml\", format=\"html\")\n```\n\n---\n\n## \u2705 Key Features\n\n* **Schema Validation** \u2014 Ensure proper JSON/YAML structure and data types\n* **Content Linting** \u2014 Check keywords, tone, word count, patterns, quality rules \n* **Professional Reports** \u2014 Beautiful HTML and Markdown validation reports\n* **Framework Agnostic** \u2014 Works with OpenAI, Anthropic, local models, any LLM\n* **CLI + Python API** \u2014 Use in scripts or integrate into applications\n* **Zero Vendor Lock-in** \u2014 Pure validation logic, no external API calls required\n\n---\n\n## \ud83d\udccb Example Schema\n\n```yaml\nschema:\n title:\n type: str\n min_length: 10\n description:\n type: str\n min_length: 100\n\nrules:\n - keyword_must_include: [\"quality\", \"premium\"]\n - keyword_must_not_include: [\"cheap\", \"defective\"]\n - no_placeholder_text: \"\\\\[YOUR_TEXT_HERE\\\\]\"\n - word_count_min: 100\n - word_count_max: 500\n```\n\n**Result:** Every AI response gets validated before reaching your users. **No more silent failures.**\n\n---\n\n## \ud83d\udcda Documentation & Links\n\n* \ud83d\udcd6 [Complete Documentation & Whitepaper](https://maxamed.github.io/llm-contract/)\n* \ud83d\ude80 [Getting Started Guide](https://maxamed.github.io/llm-contract/getting-started)\n* \ud83d\udca1 [Real-World Examples](https://maxamed.github.io/llm-contract/examples)\n* \ud83d\udee0 [GitHub Source](https://github.com/Maxamed/llm-contract)\n* \ud83d\udc1b [Report Issues](https://github.com/Maxamed/llm-contract/issues)\n\n---\n\n## \ud83e\udd1d Contributors\n\n**Created by [Mohamed Jama](https://www.linkedin.com/in/mohamedjama/)** - Built for developers shipping AI features in production.\n\n**Major Contributors:**\n- **[Abdirahman Attila](https://github.com/Attili-sys)** - Frontend web interface, comprehensive documentation website, enhanced testing suite, and Jekyll/GitHub Pages setup\n\nWe welcome contributions! See [CONTRIBUTING.md](https://github.com/Maxamed/llm-contract/blob/main/CONTRIBUTING.md) for guidelines.\n\n---\n\n## \ud83c\udff7 License\n\nMIT \u00a9 Mohamed Jama - see [LICENSE](https://github.com/Maxamed/llm-contract/blob/main/LICENSE) file for details.\n\n---\n\n**Stop hoping your AI gets it right. Start knowing it does.** \n",
"bugtrack_url": null,
"license": "MIT",
"summary": "LLM Output Validation, Linting, and Assertion Layer",
"version": "1.0.0",
"project_urls": {
"Bug Tracker": "https://github.com/Maxamed/llm-contract/issues",
"Documentation": "https://github.com/Maxamed/llm-contract#readme",
"Homepage": "https://github.com/Maxamed/llm-contract",
"Repository": "https://github.com/Maxamed/llm-contract"
},
"split_keywords": [
"llm",
" validation",
" linting",
" ai",
" schema",
" contracts"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "5f43e43013078e936f4b94aa1f31716a08695617347471c7af255166baf98a2f",
"md5": "b98e60a3288fb372e5dc87012bce79cf",
"sha256": "1041f6cb3d8f71154eefabc711559bb3940958662f67bda2e32fee9d484415ea"
},
"downloads": -1,
"filename": "llm_contracts-1.0.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "b98e60a3288fb372e5dc87012bce79cf",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 20400,
"upload_time": "2025-07-26T12:08:25",
"upload_time_iso_8601": "2025-07-26T12:08:25.208481Z",
"url": "https://files.pythonhosted.org/packages/5f/43/e43013078e936f4b94aa1f31716a08695617347471c7af255166baf98a2f/llm_contracts-1.0.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "71b781c694be887392b0cba0f7b1c0534a6a15cc9da380cadd4462703a9a1d81",
"md5": "ca6797ec72e6e9f35aff462b59894d54",
"sha256": "867e7b6c559619554e20400deadf09bb8ff046b23b876f44f4a2a0403eca5cc5"
},
"downloads": -1,
"filename": "llm_contracts-1.0.0.tar.gz",
"has_sig": false,
"md5_digest": "ca6797ec72e6e9f35aff462b59894d54",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 36573,
"upload_time": "2025-07-26T12:08:26",
"upload_time_iso_8601": "2025-07-26T12:08:26.821296Z",
"url": "https://files.pythonhosted.org/packages/71/b7/81c694be887392b0cba0f7b1c0534a6a15cc9da380cadd4462703a9a1d81/llm_contracts-1.0.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-26 12:08:26",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "Maxamed",
"github_project": "llm-contract",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "llm-contracts"
}
JSON
