LLM API Reference

Message explanation and generation, and the provider layer. Generated from the package docstrings.

`iso8583sim.llm`

LLM-powered features for ISO 8583 message handling.

This module provides AI-powered tools for explaining and generating ISO 8583 messages using various LLM providers.

Features:

MessageExplainer: Explain messages in plain English
MessageGenerator: Generate messages from natural language

Supported Providers:

Anthropic (Claude)
OpenAI (GPT)
Google (Gemini)
Ollama (local models)

Example: »> from iso8583sim.llm import MessageExplainer, MessageGenerator »> »> # Explain a message »> explainer = MessageExplainer() # Auto-detects provider »> print(explainer.explain(message)) »> »> # Generate a message »> generator = MessageGenerator(provider=”anthropic”) »> message = generator.generate(“$100 VISA purchase”)

Installation: # Install with all LLM providers pip install iso8583sim[llm]

# Or install specific providers
pip install iso8583sim[anthropic]
pip install iso8583sim[openai]
pip install iso8583sim[google]
pip install iso8583sim[ollama]

`iso8583sim.llm.base`

Base classes for LLM providers.

This module defines the abstract base class for LLM providers, allowing multiple backend implementations (Anthropic, OpenAI, Google, Ollama).

class `LLMResponse`

Response from an LLM provider.

LLMResponse(content: 'str', model: 'str', provider: 'str', usage: 'dict[str, int] | None' = None) -> None

class `LLMError`

Base exception for LLM-related errors.

class `ProviderNotAvailableError`

Raised when a provider’s dependencies are not installed.

ProviderNotAvailableError(provider: 'str', package: 'str')

class `ProviderConfigError`

Raised when provider configuration is invalid.

class `GenerationError`

Raised when message generation fails.

class `LLMProvider`

Abstract base class for LLM providers.

All LLM providers must implement this interface to be compatible with MessageExplainer and MessageGenerator.

Example: »> class MyProvider(LLMProvider): … def complete(self, prompt, system=None): … return “response” … @property … def name(self): … return “my-provider”

`complete(prompt: 'str', system: 'str | None' = None) -> 'str'`

Send a prompt to the LLM and return the response text.

Args: prompt: The user prompt to send system: Optional system prompt for context

Returns: The LLM’s response text

Raises: LLMError: If the API call fails

`complete_with_metadata(prompt: 'str', system: 'str | None' = None) -> 'LLMResponse'`

Send a prompt and return response with metadata.

Default implementation wraps complete(). Providers can override for more detailed metadata.

Args: prompt: The user prompt to send system: Optional system prompt for context

Returns: LLMResponse with content and metadata

`model` (property)

Return the model name being used.

`name` (property)

Return the provider name for logging/display.

`iso8583sim.llm.explainer`

Message Explainer using LLM to provide human-readable explanations.

class `MessageExplainer`

Explains ISO 8583 messages in plain English using an LLM.

This class uses an LLM provider to generate human-readable explanations of ISO 8583 messages, making them easier to understand for developers and analysts.

Example: »> explainer = MessageExplainer() # Auto-detects provider »> message = parser.parse(“0100…”) »> print(explainer.explain(message)) “This is a VISA authorization request for $100.00…”

>>> # Or explain a raw message string
>>> print(explainer.explain("0100702406C120E09000..."))

>>> # Use a specific provider
>>> explainer = MessageExplainer(provider="anthropic")

MessageExplainer(provider: 'LLMProvider | str | None' = None)

`explain(message: 'ISO8583Message | str', verbose: 'bool' = False) -> 'str'`

Explain an ISO 8583 message in plain English.

Args: message: ISO8583Message object or raw message string to explain verbose: If True, include more technical details

Returns: Human-readable explanation of the message

`explain_error(error: 'str', message: 'ISO8583Message | str') -> 'str'`

Explain a validation or parsing error in context.

Args: error: The error message to explain message: The message that caused the error

Returns: Human-readable explanation of the error and how to fix it

`explain_field(field_number: 'int', value: 'str') -> 'str'`

Explain a specific ISO 8583 field value.

Args: field_number: The field number (e.g., 2, 39, 55) value: The field value to explain

Returns: Human-readable explanation of the field and its value

`explain_response_code(code: 'str') -> 'str'`

Explain an ISO 8583 response code.

Args: code: The response code (e.g., “00”, “51”, “05”)

Returns: Human-readable explanation of the response code

`provider` (property)

Return the LLM provider being used.

`iso8583sim.llm.generator`

Message Generator using LLM to create ISO 8583 messages from natural language.

class `MessageGenerator`

Generates ISO 8583 messages from natural language descriptions.

This class uses an LLM to interpret natural language descriptions and generate valid ISO 8583 messages.

Example: »> generator = MessageGenerator() »> message = generator.generate(“$100 VISA purchase at a gas station”) »> print(message.mti) # “0100” »> print(message.fields[4]) # “000000010000”

>>> # Generate without validation
>>> message = generator.generate("refund $50", validate=False)

MessageGenerator(provider: 'LLMProvider | str | None' = None)

`generate(description: 'str', validate: 'bool' = True) -> 'ISO8583Message'`

Generate an ISO 8583 message from a natural language description.

Args: description: Natural language description of the desired message (e.g., “$100 VISA purchase at a gas station in NYC”) validate: Whether to validate the generated message

Returns: Valid ISO8583Message object

Raises: GenerationError: If the message cannot be generated or validated

`provider` (property)

Return the LLM provider being used.

`suggest_fields(partial_message: 'ISO8583Message') -> 'dict[int, str]'`

Suggest missing fields for a partial message.

Args: partial_message: Partial ISO8583Message with some fields populated

Returns: Dictionary of suggested field values

`iso8583sim.llm.providers`

LLM provider factory and auto-detection.

This module provides a factory function to create LLM providers and auto-detect available providers based on installed packages and configured API keys.

Functions

`get_provider(name: 'str | None' = None, **kwargs) -> 'LLMProvider'`

Get an LLM provider instance.

If name is provided, creates that specific provider. If name is None, auto-detects the first available provider.

Args: name: Provider name (‘anthropic’, ‘openai’, ‘google’, ‘ollama’) or None for auto-detection **kwargs: Additional arguments passed to the provider constructor

Returns: An initialized LLMProvider instance

Raises: ProviderConfigError: If no provider is available or configured

Example: »> provider = get_provider() # Auto-detect »> provider = get_provider(“anthropic”) # Specific provider »> provider = get_provider(“openai”, model=”gpt-4-turbo”)

`list_available_providers() -> 'list[str]'`

List all available and configured providers.

Returns: List of provider names that are installed and configured

`list_installed_providers() -> 'list[str]'`

List all installed providers (may not be configured).

Returns: List of provider names that have their packages installed

`iso8583sim.llm.providers.anthropic`

Anthropic (Claude) LLM provider implementation.

class `AnthropicProvider`

LLM provider using Anthropic’s Claude API.

Example: »> provider = AnthropicProvider() # Uses ANTHROPIC_API_KEY env var »> response = provider.complete(“Explain ISO 8583”) »> print(response)

>>> # Or with explicit API key
>>> provider = AnthropicProvider(api_key="sk-ant-...")

AnthropicProvider(api_key: 'str | None' = None, model: 'str | None' = None, max_tokens: 'int | None' = None)

`complete(prompt: 'str', system: 'str | None' = None) -> 'str'`

Send a prompt to Claude and return the response.

Args: prompt: The user prompt to send system: Optional system prompt for context

Returns: The response text from Claude

Raises: LLMError: If the API call fails

`complete_with_metadata(prompt: 'str', system: 'str | None' = None) -> 'LLMResponse'`

Send a prompt and return response with metadata.

Args: prompt: The user prompt to send system: Optional system prompt for context

Returns: LLMResponse with content and usage metadata

`model` (property)

Return the model name being used.

`name` (property)

Return the provider name.

Functions

`is_available() -> 'bool'`

Check if Anthropic provider is available.

Returns: True if anthropic package is installed and API key is configured.

`iso8583sim.llm.providers.openai`

OpenAI (GPT) LLM provider implementation.

class `OpenAIProvider`

LLM provider using OpenAI’s GPT API.

Example: »> provider = OpenAIProvider() # Uses OPENAI_API_KEY env var »> response = provider.complete(“Explain ISO 8583”) »> print(response)

>>> # Or with explicit API key
>>> provider = OpenAIProvider(api_key="sk-...")

OpenAIProvider(api_key: 'str | None' = None, model: 'str | None' = None, max_tokens: 'int | None' = None)

`complete(prompt: 'str', system: 'str | None' = None) -> 'str'`

Send a prompt to GPT and return the response.

Args: prompt: The user prompt to send system: Optional system prompt for context

Returns: The response text from GPT

Raises: LLMError: If the API call fails

`complete_with_metadata(prompt: 'str', system: 'str | None' = None) -> 'LLMResponse'`

Send a prompt and return response with metadata.

Args: prompt: The user prompt to send system: Optional system prompt for context

Returns: LLMResponse with content and usage metadata

`model` (property)

Return the model name being used.

`name` (property)

Return the provider name.

Functions

`is_available() -> 'bool'`

Check if OpenAI provider is available.

Returns: True if openai package is installed and API key is configured.

`iso8583sim.llm.providers.google`

Google (Gemini) LLM provider implementation.

class `GoogleProvider`

LLM provider using Google’s Gemini API.

Example: »> provider = GoogleProvider() # Uses GOOGLE_API_KEY env var »> response = provider.complete(“Explain ISO 8583”) »> print(response)

>>> # Or with explicit API key
>>> provider = GoogleProvider(api_key="...")

GoogleProvider(api_key: 'str | None' = None, model: 'str | None' = None)

`complete(prompt: 'str', system: 'str | None' = None) -> 'str'`

Send a prompt to Gemini and return the response.

Args: prompt: The user prompt to send system: Optional system prompt for context

Returns: The response text from Gemini

Raises: LLMError: If the API call fails

`complete_with_metadata(prompt: 'str', system: 'str | None' = None) -> 'LLMResponse'`

Send a prompt and return response with metadata.

Args: prompt: The user prompt to send system: Optional system prompt for context

Returns: LLMResponse with content and metadata

`model` (property)

Return the model name being used.

`name` (property)

Return the provider name.

Functions

`is_available() -> 'bool'`

Check if Google provider is available.

Returns: True if google-generativeai package is installed and API key is configured.

`iso8583sim.llm.providers.ollama`

Ollama (local) LLM provider implementation.

class `OllamaProvider`

LLM provider using local Ollama server.

Example: »> provider = OllamaProvider() # Uses llama3.2 on localhost »> response = provider.complete(“Explain ISO 8583”) »> print(response)

>>> # Or with custom model and host
>>> provider = OllamaProvider(model="mistral", host="http://192.168.1.100:11434")

OllamaProvider(model: 'str | None' = None, host: 'str | None' = None)

`complete(prompt: 'str', system: 'str | None' = None) -> 'str'`

Send a prompt to Ollama and return the response.

Args: prompt: The user prompt to send system: Optional system prompt for context

Returns: The response text from Ollama

Raises: LLMError: If the API call fails

`complete_with_metadata(prompt: 'str', system: 'str | None' = None) -> 'LLMResponse'`

Send a prompt and return response with metadata.

Args: prompt: The user prompt to send system: Optional system prompt for context

Returns: LLMResponse with content and metadata

`model` (property)

Return the model name being used.

`name` (property)

Return the provider name.

Functions

`is_available() -> 'bool'`

Check if Ollama provider is available.

Returns: True if ollama package is installed. Note: doesn’t check if server is running.

LLM API Reference

iso8583sim.llm

iso8583sim.llm.base

class LLMResponse

class LLMError

class ProviderNotAvailableError

class ProviderConfigError

class GenerationError

class LLMProvider

complete(prompt: 'str', system: 'str | None' = None) -> 'str'

complete_with_metadata(prompt: 'str', system: 'str | None' = None) -> 'LLMResponse'

model (property)

name (property)

iso8583sim.llm.explainer

class MessageExplainer

explain(message: 'ISO8583Message | str', verbose: 'bool' = False) -> 'str'

explain_error(error: 'str', message: 'ISO8583Message | str') -> 'str'

explain_field(field_number: 'int', value: 'str') -> 'str'

explain_response_code(code: 'str') -> 'str'

provider (property)

iso8583sim.llm.generator

class MessageGenerator

generate(description: 'str', validate: 'bool' = True) -> 'ISO8583Message'

provider (property)

suggest_fields(partial_message: 'ISO8583Message') -> 'dict[int, str]'

iso8583sim.llm.providers

Functions

get_provider(name: 'str | None' = None, **kwargs) -> 'LLMProvider'

list_available_providers() -> 'list[str]'

list_installed_providers() -> 'list[str]'

iso8583sim.llm.providers.anthropic

class AnthropicProvider

complete(prompt: 'str', system: 'str | None' = None) -> 'str'

complete_with_metadata(prompt: 'str', system: 'str | None' = None) -> 'LLMResponse'

model (property)

name (property)

Functions

is_available() -> 'bool'

iso8583sim.llm.providers.openai

class OpenAIProvider

complete(prompt: 'str', system: 'str | None' = None) -> 'str'

complete_with_metadata(prompt: 'str', system: 'str | None' = None) -> 'LLMResponse'

model (property)

name (property)

Functions

is_available() -> 'bool'

iso8583sim.llm.providers.google

class GoogleProvider

complete(prompt: 'str', system: 'str | None' = None) -> 'str'

complete_with_metadata(prompt: 'str', system: 'str | None' = None) -> 'LLMResponse'

model (property)

name (property)

Functions

is_available() -> 'bool'

iso8583sim.llm.providers.ollama

class OllamaProvider

complete(prompt: 'str', system: 'str | None' = None) -> 'str'

complete_with_metadata(prompt: 'str', system: 'str | None' = None) -> 'LLMResponse'

model (property)

name (property)

Functions

is_available() -> 'bool'

`iso8583sim.llm`

`iso8583sim.llm.base`

class `LLMResponse`

class `LLMError`

class `ProviderNotAvailableError`

class `ProviderConfigError`

class `GenerationError`

class `LLMProvider`

`complete(prompt: 'str', system: 'str | None' = None) -> 'str'`

`complete_with_metadata(prompt: 'str', system: 'str | None' = None) -> 'LLMResponse'`

`model` (property)

`name` (property)

`iso8583sim.llm.explainer`

class `MessageExplainer`

`explain(message: 'ISO8583Message | str', verbose: 'bool' = False) -> 'str'`

`explain_error(error: 'str', message: 'ISO8583Message | str') -> 'str'`

`explain_field(field_number: 'int', value: 'str') -> 'str'`

`explain_response_code(code: 'str') -> 'str'`

`provider` (property)

`iso8583sim.llm.generator`

class `MessageGenerator`

`generate(description: 'str', validate: 'bool' = True) -> 'ISO8583Message'`

`provider` (property)

`suggest_fields(partial_message: 'ISO8583Message') -> 'dict[int, str]'`

`iso8583sim.llm.providers`

`get_provider(name: 'str | None' = None, **kwargs) -> 'LLMProvider'`

`list_available_providers() -> 'list[str]'`

`list_installed_providers() -> 'list[str]'`

`iso8583sim.llm.providers.anthropic`

class `AnthropicProvider`

`complete(prompt: 'str', system: 'str | None' = None) -> 'str'`

`complete_with_metadata(prompt: 'str', system: 'str | None' = None) -> 'LLMResponse'`

`model` (property)

`name` (property)

`is_available() -> 'bool'`

`iso8583sim.llm.providers.openai`

class `OpenAIProvider`

`complete(prompt: 'str', system: 'str | None' = None) -> 'str'`

`complete_with_metadata(prompt: 'str', system: 'str | None' = None) -> 'LLMResponse'`

`model` (property)

`name` (property)

`is_available() -> 'bool'`

`iso8583sim.llm.providers.google`

class `GoogleProvider`

`complete(prompt: 'str', system: 'str | None' = None) -> 'str'`

`complete_with_metadata(prompt: 'str', system: 'str | None' = None) -> 'LLMResponse'`

`model` (property)

`name` (property)

`is_available() -> 'bool'`

`iso8583sim.llm.providers.ollama`

class `OllamaProvider`

`complete(prompt: 'str', system: 'str | None' = None) -> 'str'`

`complete_with_metadata(prompt: 'str', system: 'str | None' = None) -> 'LLMResponse'`

`model` (property)

`name` (property)

`is_available() -> 'bool'`