Metadata-Version: 2.4
Name: verifai-llm-sdk
Version: 0.2.0
Summary: VerifAI Python SDK for LLM tracing and evaluation
Home-page: https://github.com/verifai-ai/verifai-sdk
Author: VerifAI Contributors
Author-email: VerifAI Contributors <hello@verifai.dev>
License: Apache-2.0
Project-URL: Homepage, https://github.com/verifai-ai/verifai-sdk
Project-URL: Documentation, https://docs.verifai.dev
Project-URL: Repository, https://github.com/verifai-ai/verifai-sdk
Project-URL: Issues, https://github.com/verifai-ai/verifai-sdk/issues
Keywords: ai,llm,tracing,evaluation,observability,opentelemetry
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: requests>=2.31.0
Requires-Dist: openai>=1.0.0
Requires-Dist: opentelemetry-sdk>=1.20.0
Requires-Dist: opentelemetry-api>=1.20.0
Requires-Dist: opentelemetry-instrumentation>=0.41b0
Provides-Extra: openai
Requires-Dist: opentelemetry-instrumentation-openai>=0.1.0; extra == "openai"
Provides-Extra: langchain
Requires-Dist: opentelemetry-instrumentation-langchain>=0.1.0; extra == "langchain"
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
Requires-Dist: black>=23.0.0; extra == "dev"
Requires-Dist: ruff>=0.1.0; extra == "dev"
Dynamic: author
Dynamic: home-page
Dynamic: requires-python

# VerifAI SDK

[![PyPI version](https://badge.fury.io/py/verifai-sdk.svg)](https://pypi.org/project/verifai-sdk/)
[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)

**VerifAI SDK** provides automatic tracing and evaluation for your AI/LLM applications. With one line of code, capture all LLM calls and send them to the VerifAI platform for analysis.

## Installation

```bash
pip install verifai-sdk
```

## Quick Start

```python
import verifai
from openai import OpenAI

# 1. Initialize (one line!)
verifai.auto_instrument(
    project_name="my_project",
    capture_content=True
)

# 2. Use your AI libraries as usual
client = OpenAI()
response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello!"}]
)

# Traces are automatically sent to VerifAI! ✨
```

## Configuration

Set your API key as an environment variable:

```bash
export VERIFAI_API_KEY="your_api_key_here"
export VERIFAI_API_URL="http://localhost:8000"  # Optional
```

## Supported Frameworks

- ✅ OpenAI
- ✅ Anthropic
- ✅ LangChain
- ✅ LlamaIndex
- ✅ Custom agents (via `@verifai.trace` decorator)

## Manual Tracing

For custom agent logic:

```python
@verifai.trace
def my_agent(query: str):
    # Your agent logic here
    return result
```

## License

Apache 2.0
