Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

AgentNeo

To install the package

pip install agentneo -U

Authentication

Creates an authenticated session with AgentNeo

from agentneo import AgentNeo

To authenticate

agent_session = AgentNeo(
    access_key=ACCESS_KEY,
    secret_key=SECRET_KEY,
    base_url=BASE_URL
)

Project Management

Allows listing and creating projects

from agentneo import Project

# To list the available projects
Project.list_projects(session=agent_session)

# To create a new project
project = Project(session=agent_session, 
                  project_name="project_name", 
                  description="Project Description").create()

Trace Management

Enables tracing of agents, methods, and LangGraph graphs

from agentneo import Trace

# Create a tracer object
tracer = Tracer(session=agent_session)

# Decorator to trace agents & methods
@tracer.trace_node

# Decorator to trace Langgraph graphs
@tracer.trace_graph

# To add callbacks to LLMs
openai_llm = ChatOpenAI(other_parameters, 
                        ... , 
                        callbacks=[tracer.get_callback_handler()])
                        
# To upload the recorded traces
trace_id = tracer.upload_trace()

Dataset Management

Allows creation and management of datasets

from agentneo import Dataset

# To list the available Datasets
Dataset.list_datasets(session=agent_session)

# To define a new dataset
dataset = Dataset(
    session=agent_session,
    project_id=project_id, 
    dataset_name="test_dataset1", 
    description="A test dataset"
)

# Create dataset from recorded trace
dataset_traced = dataset.from_trace(trace_id=tracer.id, trace_filter=None)

# Create dataset from json dataset
dataset_json = dataset.from_json(json_filepath=filepath, 
                                 schema={"key": "value"})

Experiment Management

Allows creation, execution, and analysis of experiments

from agentneo import Experiment

# To list the available experiments
Experiment.list_experiments(session=agent_session)

# Create a new experiment 
experiment_object = Experiment(
        session=agent_session,
        experiment_name="ExperimentName",
        description="Sample Description",
        dataset_id=dataset_traced['id'],
        project_id=project_id
    )

experiment_created = experiment_object.create()

# To run a metric
exp = experiment.execute(metrics=[
    {
            "name": "goal_fulfillment_rate", 
            "config": {
                    "model": "gpt-4o-mini", 
                    "OPENAI_API_KEY": os.environ.get("OPENAI_API_KEY")
            }
    }
])

# To run multiple metrics together
exp = experiment.execute(metrics=[
    {
            "name": "summarise", 
            "config": {}
    },
    {
            "name": "tool_correctness", 
            "config": {
                    "model": "gpt-4o-mini", 
                    "OPENAI_API_KEY": os.environ.get("OPENAI_API_KEY")
            }
    },
    {
            "name": "tool_call_success_rate", 
            "config": {
                    "model": "gpt-4o-mini", 
                    "OPENAI_API_KEY": os.environ.get("OPENAI_API_KEY")
            }
    },
    {
            "name": "goal_fulfillment_rate", 
            "config": {
                    "model": "gpt-4o-mini", 
                    "OPENAI_API_KEY": os.environ.get("OPENAI_API_KEY")
            }
    }
])

# To get the results of the experiments run
experiment.get_results(exp.id)

Metadata

Release files for agentneo 0.1.3b1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for agentneo 0.1.3b1
File Size Uploaded Provenance Actions
agentneo-0.1.3b1.tar.gz 16.8 kB Without provenance Details for agentneo-0.1.3b1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for agentneo 0.1.3b1
File Interpreter ABI Platform Actions
agentneo-0.1.3b1-py3-none-any.whl Python 3 none any Details for agentneo-0.1.3b1-py3-none-any.whl

Total release size: 34.1 kB

Release files / agentneo-0.1.3b1.tar.gz

Download URL agentneo-0.1.3b1.tar.gz
Size 16.8 kB
Tags Source
SHA-256 checksum
How to use checksums
24046ba3666f54564811152b293725d12b8bac42fd7cae57dd71ea08392347cc
BLAKE2b-256 checksum
How to use checksums
7e96e44d703c4f1ff18a26afc03f115aa7d983dba6daefe40ca74af00d09ae4b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.1 CPython/3.12.4

Release files / agentneo-0.1.3b1-py3-none-any.whl

Download URL agentneo-0.1.3b1-py3-none-any.whl
Size 17.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
02279c7f77d083505919ef4ab0fd40eae866e111e593faf97121f7985ee3881a
BLAKE2b-256 checksum
How to use checksums
bd7933d5d45c5edb1bddbb58db460811b16ae807d44eb4359d15e45c3102e987
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.1 CPython/3.12.4

Security for agentneo 0.1.3b1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page