Skip to main content

LangSmith tracer backend for genblaze

Project description

genblaze-langsmith

LangSmith tracer backend for genblaze — AI-pipeline observability for generative media, with every run, step, and asset traced alongside its SHA-256 provenance manifest.

genblaze-langsmith plugs a LangSmithTracer into genblaze's observability stack, forwarding pipeline spans, provider calls, and manifest events to a LangSmith project. Combine it with genblaze's existing OTelTracer, LoggingTracer, or CompositeTracer for multi-destination tracing across your generative AI workflows.

Why genblaze-langsmith

  • End-to-end AI pipeline traces — every provider call (Sora, Veo, Runway, Flux, ElevenLabs, …) appears as a LangSmith span with prompt, model, params, cost, and manifest hash.
  • Drop-in tracer — attach to Pipeline(tracer=…); no code changes to providers or steps.
  • Composable — wrap with CompositeTracer to send to LangSmith + OTel + logs simultaneously.
  • Project-aware — traces land in the LangSmith project of your choice via standard LANGSMITH_* env vars.
  • Works offline — tracer no-ops if LangSmith isn't configured; no production risk.

Install

pip install genblaze-langsmith

Quickstart

pip install genblaze-core genblaze-langsmith
export LANGSMITH_API_KEY="..."
export LANGSMITH_PROJECT="genblaze-prod"
from genblaze_core import Modality, Pipeline
from genblaze_core.testing import MockVideoProvider
from genblaze_langsmith import LangSmithTracer

tracer = LangSmithTracer()   # reads LANGSMITH_* env vars

run, manifest = (
    Pipeline("traced-demo", tracer=tracer)
    .step(MockVideoProvider(), model="mock-v1",
          prompt="a drone shot over a city at dusk",
          modality=Modality.VIDEO)
    .run()
)

# Span with prompt, model, manifest hash, duration now appears in LangSmith
print(manifest.canonical_hash)

Compose with other tracers:

from genblaze_core import CompositeTracer, LoggingTracer, OTelTracer
from genblaze_langsmith import LangSmithTracer

tracer = CompositeTracer([LangSmithTracer(), OTelTracer(), LoggingTracer()])
# Pipeline("…", tracer=tracer)…

Credentials

Env var Notes
LANGSMITH_API_KEY LangSmith API key
LANGSMITH_PROJECT Target project (optional; defaults to LangSmith default)
LANGSMITH_ENDPOINT Override the LangSmith endpoint (optional)

Documentation

Related packages

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

genblaze_langsmith-0.2.1.tar.gz (5.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

genblaze_langsmith-0.2.1-py3-none-any.whl (4.8 kB view details)

Uploaded Python 3

File details

Details for the file genblaze_langsmith-0.2.1.tar.gz.

File metadata

  • Download URL: genblaze_langsmith-0.2.1.tar.gz
  • Upload date:
  • Size: 5.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for genblaze_langsmith-0.2.1.tar.gz
Algorithm Hash digest
SHA256 e90a153341de96893b2f831fd771e0538a650a94bf5e48cf9f51b4df12f62b56
MD5 21fb299e90fed765c2d531d767b66032
BLAKE2b-256 55027289ade6c772648a4596274305c5e6d9a1a5e97c9238ccde543337283718

See more details on using hashes here.

File details

Details for the file genblaze_langsmith-0.2.1-py3-none-any.whl.

File metadata

File hashes

Hashes for genblaze_langsmith-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 c735f0dc1f9b997a7abf4e4e1b636eea25669255e046864fd536ce86c41825ae
MD5 6fd67813a390006bc4cc7ef74fe936f2
BLAKE2b-256 7d1e67285a80328296b172fbb4272807573c89a26a26f05ff1946e7f948851c0

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page