Skip to main content

SDK to get all the available LLM models per Provider

Project description

Fixed Data SDK Documentation

Overview

This update adds comprehensive Pydantic schemas and API methods for all fixed data endpoints identified in the provided URL patterns. The implementation:

  1. Creates Pydantic v2 schemas for all fixed data models
  2. Maintains backward compatibility with the original fixed data models
  3. Implements API methods for all fixed data endpoints
  4. Uses proper type annotations and validation

Files Updated

  • fixed_schemas_sdk.py: Added schemas for all fixed data models
  • updated_ai_models_sdk.py: Added methods for all fixed data endpoints

Fixed Data Endpoints

The SDK now supports the following fixed data endpoints:

User Status

  • get_user_statuses(): Get a list of all user statuses
  • get_user_status(status_id): Get details for a specific user status

Assistant Types

  • get_assistant_types(): Get a list of all assistant types
  • get_assistant_type(type_id): Get details for a specific assistant type

Assistant Scopes

  • get_assistant_scopes(): Get a list of all assistant scopes
  • get_assistant_scope(scope_id): Get details for a specific assistant scope

Service Types

  • get_service_types(): Get a list of all service types
  • get_service_type(type_id): Get details for a specific service type

Services

  • get_services(): Get a list of all services
  • get_service(service_id): Get details for a specific service

Data Source Types

  • get_data_source_types(): Get a list of all data source types
  • get_data_source_type(type_id): Get details for a specific data source type

Data Sources

  • get_data_sources(): Get a list of all data sources
  • get_data_source(source_id): Get details for a specific data source

Channels

  • get_channels(): Get a list of all channels
  • get_channel(channel_id): Get details for a specific channel

Assistant Types Service Types

  • get_assistant_types_service_types(): Get a list of all assistant types service types
  • get_assistant_types_service_type(id): Get details for a specific assistant types service type

Session Types

  • get_session_types(): Get a list of all session types
  • get_session_type(type_id): Get details for a specific session type

Connection Types

  • get_connection_types(): Get a list of all connection types
  • get_connection_type(type_id): Get details for a specific connection type

Connection Providers

  • get_connection_providers(): Get a list of all connection providers
  • get_connection_provider(provider_id): Get details for a specific connection provider

Vector Distance Strategies

  • get_vector_distance_strategies(): Get a list of all vector distance strategies
  • get_vector_distance_strategy(strategy_id): Get details for a specific vector distance strategy

Connection Providers Vector Distance Strategies

  • get_connection_providers_vector_distance_strategies(): Get a list of all connection providers vector distance strategies
  • get_connection_providers_vector_distance_strategy(id): Get details for a specific connection providers vector distance strategy

Retriever Types

  • get_retriever_types(): Get a list of all retriever types
  • get_retriever_type(type_id): Get details for a specific retriever type

Retriever Strategies

  • get_retriever_strategies(): Get a list of all retriever strategies
  • get_retriever_strategy(strategy_id): Get details for a specific retriever strategy

Vector Channel Strategies

  • get_vector_channel_strategies(): Get a list of all vector channel strategies
  • get_vector_channel_strategy(strategy_id): Get details for a specific vector channel strategy

Run Statuses

  • get_run_statuses(): Get a list of all run statuses
  • get_run_status(status_id): Get details for a specific run status

Avatars

  • get_avatars(): Get a list of all avatars
  • get_avatar(avatar_id): Get details for a specific avatar

Guardrail Types

  • get_guardrail_types(): Get a list of all guardrail types
  • get_guardrail_type(type_id): Get details for a specific guardrail type

Usage Example

from kosmoy_data_sdk import kosmoy_data

# Get all user statuses
user_statuses = kosmoy_data.fixed.get_user_statuses()
print(f"Found {len(user_statuses)} user statuses")

# Get a specific assistant type
assistant_type = kosmoy_data.fixed.get_assistant_type(1)
print(f"Assistant type: {assistant_type.name}")

# Get all guardrail types
guardrail_types = kosmoy_data.fixed.get_guardrail_types()
for gt in guardrail_types:
    print(f"Guardrail type: {gt.name}, Built-in: {gt.is_built_in}")

Models SDK

How to Use Kosmoy Data SDK

This guide explains how to use the kosmoy_data SDK after importing it in your Python project.

Basic Usage

After importing the SDK, you can access its functionality through the main kosmoy_data object and its fixed property.

# The SDK should already be imported in your environment
# from kosmoy_data_sdk import kosmoy_data

Working with Models

Get Available Models

# Get all available models for a specific stage
models = kosmoy_data.get_available_models(stage_name="production")

# Filter models by various parameters
verified_models = kosmoy_data.get_available_models(
    stage_name="production",
    is_verified=True,
    model_type_name="chat"
)

# Get a specific model by ID
model = kosmoy_data.get_available_model(available_model_id=123)

Providers & Creators

# Get all providers
providers = kosmoy_data.get_providers(stage_name="production")

# Get providers filtered by model type
chat_providers = kosmoy_data.get_providers(
    stage_name="production", 
    model_type_name="chat"
)

# Get all model creators
creators = kosmoy_data.get_model_creators(stage_name="production")

# Get a specific creator by ID
creator = kosmoy_data.get_model_creator(creator_id=456)

Error Handling

The SDK uses the requests library internally and will raise exceptions for HTTP errors. Always handle potential exceptions:

try:
    models = kosmoy_data.get_available_models(stage_name="production")
except requests.exceptions.HTTPError as e:
    print(f"HTTP error occurred: {e}")
except Exception as e:
    print(f"An error occurred: {e}")

Response Types

All methods return validated Pydantic models, which means you can access fields using attribute notation:

model = kosmoy_data.get_available_model(available_model_id=123)
print(model.name)
print(model.provider.name)

Project details


Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

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

kosmoy_data_sdk-0.4.2-py3-none-any.whl (6.7 kB view details)

Uploaded Python 3

File details

Details for the file kosmoy_data_sdk-0.4.2-py3-none-any.whl.

File metadata

File hashes

Hashes for kosmoy_data_sdk-0.4.2-py3-none-any.whl
Algorithm Hash digest
SHA256 990a948d48ce00cb7e12ed9ef8d281fe61882548e14efeefed2dcfdba748302c
MD5 aae35fa62ddd01bf365b302c11cc9faf
BLAKE2b-256 80541582db0cc7f7cd1ddfbad6ddf10e82a87bad4e56ab7617355db60146b811

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