AI/LLM observability: trace prompts, completions, cost, and latency to your dashboard
Project description
Traceflow AI (SDK)
AI/LLM observability: capture prompts, completions, tokens, cost, and latency; send traces to your dashboard.
Install
pip install traceflow-ai[openai]
Use
import traceflow_ai
traceflow_ai.init(endpoint="http://localhost:8000")
# Use openai.chat.completions.create(...) as usual — traces appear in the dashboard
Optional: run the dashboard (or your own ingest API) so traces have somewhere to go.
PyPI
- Package: traceflow-ai
- Import:
import traceflow_ai
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
traceflow_ai-0.2.0.tar.gz
(3.8 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
File details
Details for the file traceflow_ai-0.2.0.tar.gz.
File metadata
- Download URL: traceflow_ai-0.2.0.tar.gz
- Upload date:
- Size: 3.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a65f1cf901572718447ed8c44d42748fa42349f8a8827eba90c4eb84e57a3634
|
|
| MD5 |
919359480fc1a078304c767c80a99227
|
|
| BLAKE2b-256 |
cbe5b59b0d993e4e4cc9cbf5995614d0d332ad78c058b1c0983d246b53c90363
|
File details
Details for the file traceflow_ai-0.2.0-py3-none-any.whl.
File metadata
- Download URL: traceflow_ai-0.2.0-py3-none-any.whl
- Upload date:
- Size: 4.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
142a5707032cfbe8625e943755d9bbc627f84117c9d995d13c4465a933baeb87
|
|
| MD5 |
bd9e3dd8b53ef966c3bed232cbee589d
|
|
| BLAKE2b-256 |
9eff9253a8ccbf6a7377d36206cda4f829d2b8b00c49585e675b2d0453c6448c
|