Python SDK for Fibinaci — universal AI activity data layer
Project description
fibinaci
Python SDK for Fibinaci — universal AI activity data layer.
Install
pip install fibinaci
Quick start
import fibinaci
# Auto-instrument OpenAI, Anthropic, etc.
fibinaci.instrument()
# Or use manual tracing
from fibinaci import trace, span, outcome
with trace("my-workflow"):
with span("step-1", span_kind="model_call"):
pass
outcome(success=True, score=0.95)
Configuration
Set via environment variables or pass to client:
export FIBINACI_API_KEY=fib_live_sk_...
export FIBINACI_BASE_URL=https://api.fibinaci.com # default
from fibinaci import Fibinaci
client = Fibinaci(api_key="fib_live_sk_...")
traces = client.traces.list()
Testing
from fibinaci._testing import MockFibinaci
mock = MockFibinaci()
# ... run your code ...
spans = mock.get_spans()
assert len(spans) == 3
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
fibinaci-0.1.1.tar.gz
(29.4 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
fibinaci-0.1.1-py3-none-any.whl
(42.5 kB
view details)
File details
Details for the file fibinaci-0.1.1.tar.gz.
File metadata
- Download URL: fibinaci-0.1.1.tar.gz
- Upload date:
- Size: 29.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
aaa3e078a1ddd3a09c79d74665d4c32bfe4899a0076edeea5a795a505db02106
|
|
| MD5 |
834f57e7d0773a2001189c1b440e0e98
|
|
| BLAKE2b-256 |
ad7d33b39817e280253c0a38101d88d0659636c67c64121d40aa252ebce1b64b
|
File details
Details for the file fibinaci-0.1.1-py3-none-any.whl.
File metadata
- Download URL: fibinaci-0.1.1-py3-none-any.whl
- Upload date:
- Size: 42.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
574beda8f05c2fd8c323ffb247d57a776c9a00b5fa0bf11a8e4684829dac6606
|
|
| MD5 |
611123259e35926ad4e4c923401be7b4
|
|
| BLAKE2b-256 |
ccaa7f2eb9e73d94217484a0016622347e2323ffb9352a6ab3c0a25ca0cb1930
|