Asset listing

This guide will walk you through the process of searching for various aiXplain assets, including agents, models, pipelines, metrics, data, benchmark, corpora and files.

To explore all available assets, visit Discover in aiXplain Studio. There, you can browse, filter, sort, and compare assets side by side to find the best models, and agent tools for your needs.

Models

Models

aiXplain's collection of models are searchable using queries, filters and directly accessible using thier IDs (unique identifiers).

Models are searchable on the SDK using the following search parameters:

Python

• function: Defines the AI function the model performs (e.g., translation, summarization). Can be an enum or None.
• source_languages (Input language): Specifies the default input language(s) supported by the model. Accepts a list or None.
• target_languages (Output language): Specifies the default output language(s) produced by the model. Accepts a list or None.
• ownership (Owner): Indicates the Team/User that owns the model asset. Accepts a tuple containing ownership types.
• is_finetunable (FineTune compatible): Boolean indicating whether the model supports fine-tuning.
• suppliers: Identifies the provider hosting the model. Accepts a list or None.
• model_ids: A list of specific model IDs to filter results. Can be None.

Swift

• query (Search bar in UI): The name of the model.
• functions: The AI function performed by the model.

Python

Let's use query, function, source_languages, target_languages and suppliers to search for translation models from English to Canadian French.

from aixplain.factories import ModelFactory
from aixplain.enums import Function, Language, Supplier

model_list = ModelFactory.list(
    function=Function.TRANSLATION,
    source_languages=Language.English,
    target_languages=Language.French,
    suppliers=[Supplier.AWS, Supplier.GOOGLE, Supplier.MICROSOFT],
    )["results"]

for model in model_list:
    print(model.__dict__)

Show output

tip

Use the _member_names_ attribute to see the list of available function types, languages and suppliers.

Function._member_names_

Show output

Language._member_names_

Show output

Supplier._member_names_

Show output

Swift

Let's use query and function to search for translation models from English to Canadian French.

let provider = ModelProvider()
Task {
    let query = ModelQuery(query: "English to French Canada", functions: ["translation"])
    let result = try? await provider.list(query)

    result?.forEach { model in
        dump(model)
    }
}

Show output

tip

The best way to view a list of all available functions is to check Discover. We will add a programmatic way to get this information to Swift in future. We will also soon display all models (and functions) in the Docs. 👍

Direct Access

Once you know a model's ID, you can access the model directly (without searching for it).

EXAMPLE OpenAI's GPT-4 model has ID 6414bd3cd09663e9225130e8.

Instantiate a model object

Python

from aixplain.factories import ModelFactory
model = ModelFactory.get('6414bd3cd09663e9225130e8')
model.__dict__

Show output

Swift

import AiXplainKit
let model = ModelProvider().get("6414bd3cd09663e9225130e8")
dump(model)

Show output

Once you have identified a suitable model, you can use it for inference, benchmarking, finetuning, or integrating it into custom AI pipelines.

Pipelines

Pipelines

You can find your pipelines through the SDK. Pipelines are searchable using queries, filters, and are directly accessible using their IDs (unique identifiers).

info

Search is not yet implemented on the Swift SDK. Instead find your pipeline ID on Studio.

Pipelines are searchable on the SDK using the following search parameters:

Python

• query (Search bar in UI): The name of a pipeline.
• functions: The AI function performed by a model in the pipeline.
• suppliers (Owner): The Team/User that owns the pipeline asset - always you as currently all pipelines are private.
• input_data_types (Input modality): The pipeline's main input modalities. (Text, Audio, Image, Video.)
• output_data_types (Output modality): The pipeline's main output modalities. (Text, Audio, Image, Video.)
• models: The models that the pipeline contains.

All parameters except query can be passed as single items or lists.

Let's use models to search for pipelines containing GPT-4 (hosted by OpenAI).

Python

from aixplain.factories import ModelFactory
from aixplain.enums import Function, Language

model_list = ModelFactory.list("gpt 4")["results"]
for model in model_list:
    print(model.__dict__)

Show output

gpt4 = ModelFactory.get('6414bd3cd09663e9225130e8')

from aixplain.factories import PipelineFactory

pipeline_list = PipelineFactory.list(
    models=[model],
    )["results"]

for pipeline in pipeline_list:
    print(pipeline.__dict__)

Show output

tip

Use the _member_names_ attribute to see a list of available function types and data types.

Function._member_names_

Show output

DataType._member_names_

Show output

Direct Access

Once you know a pipeline's unique ID, you can access the pipeline directly (without searching for it).

info

To access a pipeline, you must first create one. (The pipeline below is Private, so running the code would result in an error.) Read our How to build a pipeline guide for the SDK or watch our Design Overview video to learn how to build your first pipeline (Translation & Speech Synthesis) on Studio.

EXAMPLE
The AnalyticsLLM pipeline has ID 65a5a7039ab6f53e04e45abe.

Instantiate a pipeline object

Python

from aixplain.factories import PipelineFactory
pipeline = PipelineFactory.get('65a5a7039ab6f53e04e45abe')
pipeline.__dict__

Show output

Swift

import AiXplainKit
let pipeline = PipelineProvider().get('65a5a7039ab6f53e04e45abe')

Replace the ID above with an ID for your own Pipeline. Using the AnalyticsLLM ID will give you an error. 👇

note

Private pipelines can only be accessed using an API Key for the Team that owns them. To share a pipeline with other Teams, you can save it as a JSON file that they can upload to their Teams on the Platform.

Once you have found your pipeline, you can use it for inference.

Agents

Agents

You can find your Agents through the SDK and access them directly using their IDs (unique identifiers).

Python

from aixplain.factories import AgentFactory

agent_list = AgentFactory.list()["results"]
for agent in agent_list:
    print(agent.__dict__)

Show output

Direct Access

Once you know an agent's unique ID, you can access the agent directly (without searching for it).

EXAMPLE
Our Text Aalysis Agent has ID 66a93909eb87c404212a0f2b.

Instantiate an Agent object

Python

from aixplain.factories import AgentFactory

agent = AgentFactory.get("66a93909eb87c404212a0f2b")
agent.__dict__

Show output

Replace the ID above with an ID for your own agent. Using the Text Analyser Agent ID will give you an error. 👇

note

Private agents can only be accessed using an API Key for the Team that owns them.

Once you have found your agent, you can use it for inference.

Metrics

Metrics

Metrics are searchable on the SDK using the following search parameters:

• hypothesis (Hypothesis): The metric's hypothesis modality. (Text, Audio, Image, Video, Label, Number.)
• is_source_required (Source required): Should the metric use source. Defaults to None.
• is_reference_required (Reference required):Should the metric use reference. Defaults to None.
• model_id: ID of model for which metric is to be used. Defaults to None.

All parameters except query can be passed as single items or lists.

info

View all available metrics by specifying no filters.

Python

from aixplain.factories import MetricFactory

metric_list = MetricFactory.list(page_size=50)["results"]

for metric in metric_list:
    print(metric.__dict__)

Show output

Let's search for all metrics compatible with GPT-4 that require a reference input.

Python

metric_list = MetricFactory.list(
model_id=model.id,
is_reference_required=True,
)["results"]

for metric in metric_list:
    print(metric.__dict__)

Show output

Direct Access

Once you know a metric's ID, you can access the metric directly (without searching for it).

EXAMPLE
BLEU has ID 639874ab506c987b1ae1acc6.

Instantiate a metric object

Python

from aixplain.factories import MetricFactory
bleu = MetricFactory.get('639874ab506c987b1ae1acc6')
bleu.__dict__

Show output

Once you have found your metric, you can use it for inference, finetuning and benchmarking.

Data

Data

Data assets are searchable using queries and filters and directly accessible using their IDs (unique identifiers).

note

You cannot download the contents of a Dataset or Corpus.

Corpora

Python

from aixplain.factories import CorpusFactory

corpus_list = CorpusFactory.list(
  # query="",
  # function=Function.TRANSLATION,
  # language=[Language.English],
  # data_type=DataType.TEXT,
  # page_size=5
)["results"]

for corpus in corpus_list:
  print(corpus.__dict__)

corpus = CorpusFactory.get("<CORPUS_ID>")

Datasets

Python

from aixplain.factories import DatasetFactory

dataset_list = DatasetFactory.list(
  # query="",
  # function=Function.TRANSLATION,
  # source_languages=[Language.English],
  # target_languages=[Language.Spanish],
  # data_type=DataType.TEXT,
  # page_size=5
)["results"]

for dataset in dataset_list:
  print(dataset.__dict__)

dataset = DatasetFactory.get("<DATASET_ID>")

Next, create or integrate these assets into AI agents to enhance your applications.