Skip to main content

A helper library to interact with Arize AI APIs

Project description


Overview

A helper package to interact with Arize AI APIs.

Arize is an AI engineering platform. It helps engineers develop, evaluate, and observe AI applications and agents.

Arize has both Enterprise and OSS products to support this goal:

  • Arize AX — an enterprise AI engineering platform from development to production, with an embedded AI Copilot
  • Phoenix — a lightweight, open-source project for tracing, prompt engineering, and evaluation
  • OpenInference — an open-source instrumentation package to trace LLM applications across models and frameworks

We log over 1 trillion inferences and spans, 10 million evaluation runs, and 2 million OSS downloads every month.

Key Features

  • Tracing - Trace your LLM application's runtime using OpenTelemetry-based instrumentation.
  • Evaluation - Leverage LLMs to benchmark your application's performance using response and retrieval evals.
  • Datasets - Create versioned datasets of examples for experimentation, evaluation, and fine-tuning.
  • Experiments - Track and evaluate changes to prompts, LLMs, and retrieval.
  • Playground- Optimize prompts, compare models, adjust parameters, and replay traced LLM calls.
  • Prompt Management- Manage and test prompt changes systematically using version control, tagging, and experimentation.

Installation

Install Arize via pip or conda:

pip install arize

Install the arize-otel package for auto-instrumentation of your LLM library:

pip install arize-otel

Usage

Instrumentation

See https://pypi.org/project/arize-otel/

from arize.otel import register
from openinference.instrumentation.openai import OpenAIInstrumentor

# Setup OpenTelemetry via our convenience function
tracer_provider = register(
    space_id=SPACE_ID,
    api_key=API_KEY,
    project_name="agents-cookbook",
)

# Start instrumentation
OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)

Logging Spans, Evaluations, and Annotations

Use arize.pandas.logger to log spans, evaluations, and annotations in bulk. See https://arize-client-python.readthedocs.io/en/latest/llm-api/logger.html

from arize.pandas.logger import Client

arize_client = Client(
    space_key=os.environ["ARIZE_SPACE_KEY"],
    api_key=os.environ["ARIZE_API_KEY"],
)

arize_client.log_spans(
    dataframe=spans_df,
    project_name="your-llm-project",
)

arize_client.log_evaluations_sync(
    dataframe=evals_df,
    project_name="your-llm-project",
)

arize_client.log_annotations(
    dataframe=annotations_df,
    project_name="your-llm-project",
)

Datasets & Experiments

Use arize.experimental.datasets to create datasets and run experiments. See https://arize-client-python.readthedocs.io/en/latest/llm-api/datasets.html

from arize.experimental.datasets import ArizeDatasetsClient

datasets_client = ArizeDatasetsClient(api_key=os.environ["ARIZE_API_KEY"])

dataset_id = datasets_client.create_dataset(
    space_id=os.environ["ARIZE_SPACE_KEY"],
    dataset_name="llm-span-dataset",
    data=spans_df,
)

Tracing Integrations

Arize is built on top of OpenTelemetry and is vendor, language, and framework agnostic. For details about tracing integrations and example applications, see the OpenInference project.

Python Integrations

Integration Package Version Badge
OpenAI openinference-instrumentation-openai PyPI Version
OpenAI Agents openinference-instrumentation-openai-agents PyPI Version
LlamaIndex openinference-instrumentation-llama-index PyPI Version
DSPy openinference-instrumentation-dspy PyPI Version
AWS Bedrock openinference-instrumentation-bedrock PyPI Version
LangChain openinference-instrumentation-langchain PyPI Version
MistralAI openinference-instrumentation-mistralai PyPI Version
Google GenAI openinference-instrumentation-google-genai PyPI Version
Guardrails openinference-instrumentation-guardrails PyPI Version
VertexAI openinference-instrumentation-vertexai PyPI Version
CrewAI openinference-instrumentation-crewai PyPI Version
Haystack openinference-instrumentation-haystack PyPI Version
LiteLLM openinference-instrumentation-litellm PyPI Version
Groq openinference-instrumentation-groq PyPI Version
Instructor openinference-instrumentation-instructor PyPI Version
Anthropic openinference-instrumentation-anthropic PyPI Version
Smolagents openinference-instrumentation-smolagents PyPI Version

JavaScript Integrations

Integration Package Version Badge
OpenAI @arizeai/openinference-instrumentation-openai NPM Version
LangChain.js @arizeai/openinference-instrumentation-langchain NPM Version
Vercel AI SDK @arizeai/openinference-vercel NPM Version
BeeAI @arizeai/openinference-instrumentation-beeai NPM Version

Community

Join our community to connect with thousands of AI builders.

Copyright 2025 Arize AI, Inc. All Rights Reserved.

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

arize-7.47.0.tar.gz (186.9 kB view details)

Uploaded Source

Built Distribution

arize-7.47.0-py3-none-any.whl (235.6 kB view details)

Uploaded Python 3

File details

Details for the file arize-7.47.0.tar.gz.

File metadata

  • Download URL: arize-7.47.0.tar.gz
  • Upload date:
  • Size: 186.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for arize-7.47.0.tar.gz
Algorithm Hash digest
SHA256 ae1e6f004ba687e4484a99f52b0b69edb8f5aac0e1816b016433e16e35ed0386
MD5 e239049834469bdaddd8a6e3eb64bfc9
BLAKE2b-256 457de9a438e1ffb5cb567dc1b37b60b322ad8ac84935be9fd7164d10a0c6ce5b

See more details on using hashes here.

Provenance

The following attestation bundles were made for arize-7.47.0.tar.gz:

Publisher: release-sdks.yml on Arize-ai/arize

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file arize-7.47.0-py3-none-any.whl.

File metadata

  • Download URL: arize-7.47.0-py3-none-any.whl
  • Upload date:
  • Size: 235.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for arize-7.47.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2c6f2d9cd9afca655c082a946a6d8fe70e79d45155ed5293185941938b695def
MD5 97b3f9d355c2652840ba1a379a9d1271
BLAKE2b-256 c5787eb21132b59d4b826f63bd96bb3f6f1657a15ad4e479b66c64ebe215bea8

See more details on using hashes here.

Provenance

The following attestation bundles were made for arize-7.47.0-py3-none-any.whl:

Publisher: release-sdks.yml on Arize-ai/arize

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

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