Metadata-Version: 2.4
Name: eval-agents
Version: 0.1.1
Summary: AgentLab — a modular framework for building, evaluating, and comparing LLM-powered agents.
Author-email: Your Name <your@email.com>
License: MIT License
        
        Copyright (c) 2024 AgentLab Contributors
        
        Permission is hereby granted, free of charge, to any person obtaining a copy
        of this software and associated documentation files (the "Software"), to deal
        in the Software without restriction, including without limitation the rights
        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
        copies of the Software, and to permit persons to whom the Software is
        furnished to do so, subject to the following conditions:
        
        The above copyright notice and this permission notice shall be included in all
        copies or substantial portions of the Software.
        
        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
        SOFTWARE.
        
Project-URL: Homepage, https://github.com/yourusername/agentlab
Project-URL: Bug Tracker, https://github.com/yourusername/agentlab/issues
Project-URL: Changelog, https://github.com/yourusername/agentlab/blob/main/CHANGELOG.md
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: fastapi>=0.100.0
Requires-Dist: uvicorn>=0.23.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: python-dotenv>=1.0.0
Requires-Dist: cohere>=7.0.0
Requires-Dist: sentence-transformers>=2.0.0
Requires-Dist: faiss-cpu>=1.7.0
Requires-Dist: rank-bm25>=0.2.2
Requires-Dist: numpy>=1.24.0
Provides-Extra: llm
Requires-Dist: openai>=1.0.0; extra == "llm"
Requires-Dist: anthropic>=0.20.0; extra == "llm"
Requires-Dist: google-generativeai>=0.5.0; extra == "llm"
Provides-Extra: rerank
Requires-Dist: cohere>=7.0.0; extra == "rerank"
Requires-Dist: sentence-transformers>=2.0.0; extra == "rerank"
Provides-Extra: dev
Requires-Dist: pytest; extra == "dev"
Requires-Dist: black; extra == "dev"
Requires-Dist: isort; extra == "dev"
Requires-Dist: twine; extra == "dev"
Requires-Dist: build; extra == "dev"
Dynamic: license-file

# Eval Agents (AgentLab)

A modular, composable framework for building, evaluating, and comparing LLM-powered agents. 

You write the agent logic. The framework provides the LLMs, embeddings, and vector stores, and automatically runs the combinatorial experiments to find the best stack.

## Installation

```bash
pip install eval-agents
```

*(Note: While the package is published on PyPI as `eval-agents`, you import it as `agentlab` in your code).*

## The Magic of AgentLab

The beauty of this framework is that you **only** write your agent logic. You don't need to write LLM integrations or hardcode API keys. AgentLab provides a built-in catalogue of OpenAI, Anthropic, Google, and local models.

### 1. Write your agent (`my_project.py`)

```python
from agentlab import agent

@agent(name="My Planner")
class PlannerAgent:
    def __init__(self, llm, embedding=None, vectorstore=None, reranker=None):
        # The framework will automatically inject the real implementations here!
        self.llm         = llm          
        self.embedding   = embedding    
        self.vectorstore = vectorstore  
        self.reranker    = reranker     

    def run(self, query: str) -> str:
        # Just use the injected LLM — you don't need to know if it's GPT-4o or Claude!
        return self.llm.generate(f"Plan this task: {query}")
```

### 2. Launch the UI (Coming Soon)

```bash
agentlab start --app my_project.py
```

### 3. Run Experiments!

The UI will automatically discover your `@agent` classes. 
1. Select your agent: `☑ My Planner`
2. Select LLMs to test: `☑ GPT-4o` `☑ Claude Sonnet` `☑ Gemini 2.5 Pro`
3. Enter your API keys in the secure UI settings.
4. Click **Run**!

The framework will execute every combination and show you a dashboard comparing latency, token costs, and response quality.

## Package Structure (Internal)

If you are contributing to AgentLab, the internal structure looks like this:

| Sub-package              | Responsibility                                      |
|--------------------------|-----------------------------------------------------|
| `agentlab`               | Top-level exports (only the `@agent` decorator)     |
| `agentlab.llm`           | Built-in LLM catalogue (OpenAI, Anthropic, Google)  |
| `agentlab.embedding`     | Built-in Embedding catalogue                        |
| `agentlab.vectorstore`   | Built-in Vector stores (FAISS, Pinecone, Chroma)    |
| `agentlab.reranker`      | Built-in Rerankers (Cohere API, CrossEncoder)       |
| `agentlab.agents`        | The agent registry                                  |
| `agentlab.execution`     | The combinatorial experiment engine                 |

## License

MIT
