Metadata-Version: 2.4
Name: yeco-lens
Version: 1.0.0
Summary: X-ray vision for your LLM. Stream real logprobs to the Yeco-Lens dashboard.
Author-email: YecoAI <hello@yeco.ai>
License: MIT
Project-URL: Homepage, https://github.com/YecoAI/yeco-lens
Project-URL: Repository, https://github.com/YecoAI/yeco-lens
Project-URL: Issues, https://github.com/YecoAI/yeco-lens/issues
Keywords: llm,logprobs,entropy,debugger,ollama,openai,observability,devtools
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
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 :: Debuggers
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Provides-Extra: openai
Requires-Dist: openai>=1.40.0; extra == "openai"
Provides-Extra: test
Requires-Dist: pytest>=8.0.0; extra == "test"
Requires-Dist: pytest-asyncio>=0.24.0; extra == "test"

# Yeco-Lens Python SDK

Instrumentation SDK that streams **real** LLM logprobs to the Yeco-Lens dashboard.

```python
from yeco_lens import YecoLens

yeco = YecoLens()  # connects to ws://127.0.0.1:7531 (or YECO_LENS_ENDPOINT)

with yeco.trace(model="gpt-4o", system_prompt="Be concise."):
    for chunk in yeco.openai_chat(client, model="gpt-4o", messages=..., top_logprobs=10):
        print(chunk.token, end="")  # streams to your app AND the dashboard
```

See the main repo README for the full guide.
