langflow-base-nightly 0.5.1.dev3__py3-none-any.whl → 0.5.1.dev4__py3-none-any.whl

langflow/base/memory/memory.py

@@ -1,49 +0,0 @@
-from langflow.custom.custom_component.custom_component import CustomComponent
-from langflow.schema.data import Data
-from langflow.utils.constants import MESSAGE_SENDER_AI, MESSAGE_SENDER_USER
-
-
-class BaseMemoryComponent(CustomComponent):
-    display_name = "Chat Memory"
-    description = "Retrieves stored chat messages given a specific Session ID."
-    beta: bool = True
-    icon = "history"
-
-    def build_config(self):
-        return {
-            "sender": {
-                "options": [MESSAGE_SENDER_AI, MESSAGE_SENDER_USER, "Machine and User"],
-                "display_name": "Sender Type",
-            },
-            "sender_name": {"display_name": "Sender Name", "advanced": True},
-            "n_messages": {
-                "display_name": "Number of Messages",
-                "info": "Number of messages to retrieve.",
-            },
-            "session_id": {
-                "display_name": "Session ID",
-                "info": "Session ID of the chat history.",
-                "input_types": ["Message"],
-            },
-            "order": {
-                "options": ["Ascending", "Descending"],
-                "display_name": "Order",
-                "info": "Order of the messages.",
-                "advanced": True,
-            },
-            "data_template": {
-                "display_name": "Data Template",
-                "multiline": True,
-                "info": "Template to convert Data to Text. "
-                "If left empty, it will be dynamically set to the Data's text key.",
-                "advanced": True,
-            },
-        }
-
-    def get_messages(self, **kwargs) -> list[Data]:
-        raise NotImplementedError
-
-    def add_message(
-        self, sender: str, sender_name: str, text: str, session_id: str, metadata: dict | None = None, **kwargs
-    ) -> None:
-        raise NotImplementedError

langflow/base/memory/model.py

@@ -1,38 +0,0 @@
-from abc import abstractmethod
-
-from langchain.memory import ConversationBufferMemory
-
-from langflow.custom.custom_component.component import Component
-from langflow.field_typing import BaseChatMemory
-from langflow.field_typing.constants import Memory
-from langflow.template.field.base import Output
-
-
-class LCChatMemoryComponent(Component):
-    trace_type = "chat_memory"
-    outputs = [
-        Output(
-            display_name="Memory",
-            name="memory",
-            method="build_message_history",
-        )
-    ]
-
-    def _validate_outputs(self) -> None:
-        required_output_methods = ["build_message_history"]
-        output_names = [output.name for output in self.outputs]
-        for method_name in required_output_methods:
-            if method_name not in output_names:
-                msg = f"Output with name '{method_name}' must be defined."
-                raise ValueError(msg)
-            if not hasattr(self, method_name):
-                msg = f"Method '{method_name}' must be defined."
-                raise ValueError(msg)
-
-    def build_base_memory(self) -> BaseChatMemory:
-        """Builds the base memory."""
-        return ConversationBufferMemory(chat_memory=self.build_message_history())
-
-    @abstractmethod
-    def build_message_history(self) -> Memory:
-        """Builds the chat message history memory."""

langflow/base/models/aiml_constants.py

@@ -1,51 +0,0 @@
-import httpx
-from openai import APIConnectionError, APIError
-
-
-class AimlModels:
-    def __init__(self):
-        self.chat_models = []
-        self.image_models = []
-        self.embedding_models = []
-        self.stt_models = []
-        self.tts_models = []
-        self.language_models = []
-
-    def get_aiml_models(self):
-        try:
-            with httpx.Client() as client:
-                response = client.get("https://api.aimlapi.com/models")
-                response.raise_for_status()
-        except httpx.RequestError as e:
-            msg = "Failed to connect to the AI/ML API."
-            raise APIConnectionError(msg) from e
-        except httpx.HTTPStatusError as e:
-            msg = f"AI/ML API responded with status code: {e.response.status_code}"
-            raise APIError(
-                message=msg,
-                body=None,
-                request=e.request,
-            ) from e
-
-        try:
-            models = response.json().get("data", [])
-            self.separate_models_by_type(models)
-        except (ValueError, KeyError, TypeError) as e:
-            msg = "Failed to parse response data from AI/ML API. The format may be incorrect."
-            raise ValueError(msg) from e
-
-    def separate_models_by_type(self, models):
-        model_type_mapping = {
-            "chat-completion": self.chat_models,
-            "image": self.image_models,
-            "embedding": self.embedding_models,
-            "stt": self.stt_models,
-            "tts": self.tts_models,
-            "language-completion": self.language_models,
-        }
-
-        for model in models:
-            model_type = model.get("type")
-            model_id = model.get("id")
-            if model_type in model_type_mapping:
-                model_type_mapping[model_type].append(model_id)

langflow/base/models/anthropic_constants.py

@@ -1,47 +0,0 @@
-from .model_metadata import create_model_metadata
-
-ANTHROPIC_MODELS_DETAILED = [
-    # Tool calling supported models
-    create_model_metadata(provider="Anthropic", name="claude-opus-4-20250514", icon="Anthropic", tool_calling=True),
-    create_model_metadata(provider="Anthropic", name="claude-sonnet-4-20250514", icon="Anthropic", tool_calling=True),
-    create_model_metadata(provider="Anthropic", name="claude-3-7-sonnet-latest", icon="Anthropic", tool_calling=True),
-    create_model_metadata(provider="Anthropic", name="claude-3-5-sonnet-latest", icon="Anthropic", tool_calling=True),
-    create_model_metadata(provider="Anthropic", name="claude-3-5-haiku-latest", icon="Anthropic", tool_calling=True),
-    create_model_metadata(provider="Anthropic", name="claude-3-opus-latest", icon="Anthropic", tool_calling=True),
-    create_model_metadata(provider="Anthropic", name="claude-3-sonnet-20240229", icon="Anthropic", tool_calling=True),
-    # Tool calling unsupported models
-    create_model_metadata(provider="Anthropic", name="claude-2.1", icon="Anthropic", tool_calling=False),
-    create_model_metadata(provider="Anthropic", name="claude-2.0", icon="Anthropic", tool_calling=False),
-    # Deprecated models
-    create_model_metadata(
-        provider="Anthropic", name="claude-3-5-sonnet-20240620", icon="Anthropic", tool_calling=True, deprecated=True
-    ),
-    create_model_metadata(
-        provider="Anthropic", name="claude-3-5-sonnet-20241022", icon="Anthropic", tool_calling=True, deprecated=True
-    ),
-    create_model_metadata(
-        provider="Anthropic", name="claude-3-5-haiku-20241022", icon="Anthropic", tool_calling=True, deprecated=True
-    ),
-    create_model_metadata(
-        provider="Anthropic", name="claude-3-haiku-20240307", icon="Anthropic", tool_calling=True, deprecated=True
-    ),
-]
-
-ANTHROPIC_MODELS = [
-    metadata["name"]
-    for metadata in ANTHROPIC_MODELS_DETAILED
-    if not metadata.get("deprecated", False) and metadata.get("tool_calling", False)
-]
-
-TOOL_CALLING_SUPPORTED_ANTHROPIC_MODELS = [
-    metadata["name"] for metadata in ANTHROPIC_MODELS_DETAILED if metadata.get("tool_calling", False)
-]
-
-TOOL_CALLING_UNSUPPORTED_ANTHROPIC_MODELS = [
-    metadata["name"] for metadata in ANTHROPIC_MODELS_DETAILED if not metadata.get("tool_calling", False)
-]
-
-DEPRECATED_MODELS = [metadata["name"] for metadata in ANTHROPIC_MODELS_DETAILED if metadata.get("deprecated", False)]
-
-
-DEFAULT_ANTHROPIC_API_URL = "https://api.anthropic.com"

langflow/base/models/aws_constants.py

@@ -1,151 +0,0 @@
-from .model_metadata import create_model_metadata
-
-# Unified model metadata - single source of truth
-AWS_MODELS_DETAILED = [
-    # Amazon Titan Models
-    create_model_metadata(
-        provider="Amazon Bedrock", name="amazon.titan-text-express-v1", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="amazon.titan-text-lite-v1", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="amazon.titan-text-premier-v1:0", icon="Amazon", tool_calling=True
-    ),
-    # Anthropic Models
-    create_model_metadata(provider="Amazon Bedrock", name="anthropic.claude-v2", icon="Amazon", tool_calling=True),
-    create_model_metadata(provider="Amazon Bedrock", name="anthropic.claude-v2:1", icon="Amazon", tool_calling=True),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="anthropic.claude-3-sonnet-20240229-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="anthropic.claude-3-5-sonnet-20240620-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="anthropic.claude-3-5-sonnet-20241022-v2:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="anthropic.claude-3-haiku-20240307-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="anthropic.claude-3-5-haiku-20241022-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="anthropic.claude-3-opus-20240229-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="anthropic.claude-instant-v1", icon="Amazon", tool_calling=True
-    ),
-    # AI21 Labs Models
-    create_model_metadata(provider="Amazon Bedrock", name="ai21.jamba-instruct-v1:0", icon="Amazon", tool_calling=True),
-    create_model_metadata(provider="Amazon Bedrock", name="ai21.j2-mid-v1", icon="Amazon", tool_calling=True),
-    create_model_metadata(provider="Amazon Bedrock", name="ai21.j2-ultra-v1", icon="Amazon", tool_calling=True),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="ai21.jamba-1-5-large-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(provider="Amazon Bedrock", name="ai21.jamba-1-5-mini-v1:0", icon="Amazon", tool_calling=True),
-    # Cohere Models
-    create_model_metadata(provider="Amazon Bedrock", name="cohere.command-text-v14", icon="Amazon", tool_calling=True),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="cohere.command-light-text-v14", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(provider="Amazon Bedrock", name="cohere.command-r-v1:0", icon="Amazon", tool_calling=True),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="cohere.command-r-plus-v1:0", icon="Amazon", tool_calling=True
-    ),
-    # Meta Models
-    create_model_metadata(provider="Amazon Bedrock", name="meta.llama2-13b-chat-v1", icon="Amazon", tool_calling=True),
-    create_model_metadata(provider="Amazon Bedrock", name="meta.llama2-70b-chat-v1", icon="Amazon", tool_calling=True),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="meta.llama3-8b-instruct-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="meta.llama3-70b-instruct-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="meta.llama3-1-8b-instruct-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="meta.llama3-1-70b-instruct-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="meta.llama3-1-405b-instruct-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="meta.llama3-2-1b-instruct-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="meta.llama3-2-3b-instruct-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="meta.llama3-2-11b-instruct-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="meta.llama3-2-90b-instruct-v1:0", icon="Amazon", tool_calling=True
-    ),
-    # Mistral AI Models
-    create_model_metadata(
-        provider="Amazon Bedrock", name="mistral.mistral-7b-instruct-v0:2", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="mistral.mixtral-8x7b-instruct-v0:1", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="mistral.mistral-large-2402-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="mistral.mistral-large-2407-v1:0", icon="Amazon", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Amazon Bedrock", name="mistral.mistral-small-2402-v1:0", icon="Amazon", tool_calling=True
-    ),
-]
-
-# Generate backwards-compatible list from the metadata
-AWS_MODEL_IDs = [metadata["name"] for metadata in AWS_MODELS_DETAILED]
-
-AWS_EMBEDDING_MODEL_IDS = [
-    # Amazon Titan Embedding Models
-    "amazon.titan-embed-text-v1",
-    "amazon.titan-embed-text-v2:0",
-    # Cohere Embedding Models
-    "cohere.embed-english-v3",
-    "cohere.embed-multilingual-v3",
-]
-
-AWS_REGIONS = [
-    "us-west-2",
-    "us-west-1",
-    "us-gov-west-1",
-    "us-gov-east-1",
-    "us-east-2",
-    "us-east-1",
-    "sa-east-1",
-    "me-south-1",
-    "me-central-1",
-    "il-central-1",
-    "eu-west-3",
-    "eu-west-2",
-    "eu-west-1",
-    "eu-south-2",
-    "eu-south-1",
-    "eu-north-1",
-    "eu-central-2",
-    "eu-central-1",
-    "cn-northwest-1",
-    "cn-north-1",
-    "ca-west-1",
-    "ca-central-1",
-    "ap-southeast-5",
-    "ap-southeast-4",
-    "ap-southeast-3",
-    "ap-southeast-2",
-    "ap-southeast-1",
-    "ap-south-2",
-    "ap-south-1",
-    "ap-northeast-3",
-    "ap-northeast-2",
-    "ap-northeast-1",
-    "ap-east-1",
-    "af-south-1",
-]

langflow/base/models/chat_result.py

@@ -1,76 +0,0 @@
-import warnings
-
-from langchain_core.messages import BaseMessage, HumanMessage, SystemMessage
-
-from langflow.field_typing.constants import LanguageModel
-from langflow.schema.message import Message
-
-
-def build_messages_and_runnable(
-    input_value: str | Message, system_message: str | None, original_runnable: LanguageModel
-) -> tuple[list[BaseMessage], LanguageModel]:
-    messages: list[BaseMessage] = []
-    system_message_added = False
-    runnable = original_runnable
-
-    if input_value:
-        if isinstance(input_value, Message):
-            with warnings.catch_warnings():
-                warnings.simplefilter("ignore")
-                if "prompt" in input_value:
-                    prompt = input_value.load_lc_prompt()
-                    if system_message:
-                        prompt.messages = [
-                            SystemMessage(content=system_message),
-                            *prompt.messages,  # type: ignore[has-type]
-                        ]
-                        system_message_added = True
-                    runnable = prompt | runnable
-                else:
-                    messages.append(input_value.to_lc_message())
-        else:
-            messages.append(HumanMessage(content=input_value))
-
-    if system_message and not system_message_added:
-        messages.insert(0, SystemMessage(content=system_message))
-
-    return messages, runnable
-
-
-def get_chat_result(
-    runnable: LanguageModel,
-    input_value: str | Message,
-    system_message: str | None = None,
-    config: dict | None = None,
-    *,
-    stream: bool = False,
-):
-    if not input_value and not system_message:
-        msg = "The message you want to send to the model is empty."
-        raise ValueError(msg)
-
-    messages, runnable = build_messages_and_runnable(
-        input_value=input_value, system_message=system_message, original_runnable=runnable
-    )
-
-    inputs: list | dict = messages or {}
-    try:
-        if config and config.get("output_parser") is not None:
-            runnable |= config["output_parser"]
-
-        if config:
-            runnable = runnable.with_config(
-                {
-                    "run_name": config.get("display_name", ""),
-                    "project_name": config.get("get_project_name", lambda: "")(),
-                    "callbacks": config.get("get_langchain_callbacks", list)(),
-                }
-            )
-        if stream:
-            return runnable.stream(inputs)
-        message = runnable.invoke(inputs)
-        return message.content if hasattr(message, "content") else message
-    except Exception as e:
-        if config and config.get("_get_exception_message") and (message := config["_get_exception_message"](e)):
-            raise ValueError(message) from e
-        raise

langflow/base/models/google_generative_ai_constants.py

@@ -1,70 +0,0 @@
-from .model_metadata import create_model_metadata
-
-# Unified model metadata - single source of truth
-GOOGLE_GENERATIVE_AI_MODELS_DETAILED = [
-    # GEMINI 1.5
-    create_model_metadata(
-        provider="Google Generative AI", name="gemini-1.5-pro", icon="GoogleGenerativeAI", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Google Generative AI", name="gemini-1.5-flash", icon="GoogleGenerativeAI", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Google Generative AI", name="gemini-1.5-flash-8b", icon="GoogleGenerativeAI", tool_calling=True
-    ),
-    # GEMINI 2.5
-    create_model_metadata(
-        provider="Google Generative AI", name="gemini-2.5-pro", icon="GoogleGenerativeAI", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Google Generative AI", name="gemini-2.5-flash", icon="GoogleGenerativeAI", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Google Generative AI", name="gemini-2.5-flash-lite", icon="GoogleGenerativeAI", tool_calling=True
-    ),
-    # GEMINI 2.0
-    create_model_metadata(
-        provider="Google Generative AI", name="gemini-2.0-flash-lite", icon="GoogleGenerativeAI", tool_calling=True
-    ),
-    # PREVIEW
-    create_model_metadata(
-        provider="Google Generative AI",
-        name="gemini-2.0-flash",
-        icon="GoogleGenerativeAI",
-        tool_calling=True,
-        preview=True,
-    ),
-    create_model_metadata(
-        provider="Google Generative AI",
-        name="gemini-exp-1206",
-        icon="GoogleGenerativeAI",
-        tool_calling=True,
-        preview=True,
-    ),
-    create_model_metadata(
-        provider="Google Generative AI",
-        name="gemini-2.0-flash-thinking-exp-01-21",
-        icon="GoogleGenerativeAI",
-        tool_calling=True,
-        preview=True,
-    ),
-    create_model_metadata(
-        provider="Google Generative AI",
-        name="learnlm-1.5-pro-experimental",
-        icon="GoogleGenerativeAI",
-        tool_calling=True,
-        preview=True,
-    ),
-    # GEMMA
-    create_model_metadata(
-        provider="Google Generative AI", name="gemma-2-2b", icon="GoogleGenerativeAI", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Google Generative AI", name="gemma-2-9b", icon="GoogleGenerativeAI", tool_calling=True
-    ),
-    create_model_metadata(
-        provider="Google Generative AI", name="gemma-2-27b", icon="GoogleGenerativeAI", tool_calling=True
-    ),
-]
-
-GOOGLE_GENERATIVE_AI_MODELS = [metadata["name"] for metadata in GOOGLE_GENERATIVE_AI_MODELS_DETAILED]

langflow/base/models/groq_constants.py

@@ -1,134 +0,0 @@
-from .model_metadata import create_model_metadata
-
-# Unified model metadata - single source of truth
-GROQ_MODELS_DETAILED = [
-    # Production Models - Stable and reliable for production use
-    create_model_metadata(  # Google
-        provider="Groq", name="gemma2-9b-it", icon="Groq", tool_calling=True
-    ),
-    create_model_metadata(  # Meta
-        provider="Groq", name="llama-3.3-70b-versatile", icon="Groq", tool_calling=True
-    ),
-    create_model_metadata(  # Meta
-        provider="Groq", name="llama-3.1-8b-instant", icon="Groq"
-    ),
-    create_model_metadata(  # Meta
-        provider="Groq", name="llama-guard-3-8b", icon="Groq"
-    ),
-    create_model_metadata(  # Meta
-        provider="Groq", name="llama3-70b-8192", icon="Groq"
-    ),
-    create_model_metadata(  # Meta
-        provider="Groq", name="llama3-8b-8192", icon="Groq"
-    ),
-    # Preview Models - For evaluation purposes only
-    create_model_metadata(  # Meta
-        provider="Groq", name="meta-llama/llama-4-scout-17b-16e-instruct", icon="Groq", tool_calling=True, preview=True
-    ),
-    create_model_metadata(  # Meta
-        provider="Groq",
-        name="meta-llama/llama-4-maverick-17b-128e-instruct",
-        icon="Groq",
-        tool_calling=True,
-        preview=True,
-    ),
-    create_model_metadata(  # Alibaba Cloud
-        provider="Groq", name="qwen-qwq-32b", icon="Groq", tool_calling=True, preview=True
-    ),
-    create_model_metadata(  # Alibaba Cloud
-        provider="Groq", name="qwen-2.5-coder-32b", icon="Groq", tool_calling=True, preview=True
-    ),
-    create_model_metadata(  # Alibaba Cloud
-        provider="Groq", name="qwen-2.5-32b", icon="Groq", tool_calling=True, preview=True
-    ),
-    create_model_metadata(  # DeepSeek
-        provider="Groq", name="deepseek-r1-distill-qwen-32b", icon="Groq", tool_calling=True, preview=True
-    ),
-    create_model_metadata(  # DeepSeek
-        provider="Groq", name="deepseek-r1-distill-llama-70b", icon="Groq", preview=True
-    ),
-    create_model_metadata(  # Meta
-        provider="Groq", name="llama-3.3-70b-specdec", icon="Groq", tool_calling=True, preview=True
-    ),
-    create_model_metadata(  # Meta
-        provider="Groq", name="llama-3.2-1b-preview", icon="Groq", tool_calling=True, preview=True
-    ),
-    create_model_metadata(  # Meta
-        provider="Groq", name="llama-3.2-3b-preview", icon="Groq", tool_calling=True, preview=True
-    ),
-    create_model_metadata(  # Meta
-        provider="Groq", name="llama-3.2-11b-vision-preview", icon="Groq", preview=True
-    ),
-    create_model_metadata(  # Meta
-        provider="Groq", name="llama-3.2-90b-vision-preview", icon="Groq", tool_calling=True, preview=True
-    ),
-    create_model_metadata(  # Saudi Data and AI Authority (SDAIA)
-        provider="Groq", name="allam-2-7b", icon="Groq", preview=True
-    ),
-    # Deprecated Models - Previously available but now removed
-    create_model_metadata(  # Google
-        provider="Groq", name="gemma-7b-it", icon="Groq", tool_calling=True, deprecated=True
-    ),
-    create_model_metadata(  # Groq
-        provider="Groq", name="llama3-groq-70b-8192-tool-use-preview", icon="Groq", tool_calling=True, deprecated=True
-    ),
-    create_model_metadata(  # Groq
-        provider="Groq", name="llama3-groq-8b-8192-tool-use-preview", icon="Groq", tool_calling=True, deprecated=True
-    ),
-    create_model_metadata(  # Meta
-        provider="Groq", name="llama-3.1-70b-versatile", icon="Groq", tool_calling=True, deprecated=True
-    ),
-    create_model_metadata(  # Mistral
-        provider="Groq", name="mixtral-8x7b-32768", icon="Groq", tool_calling=True, deprecated=True
-    ),
-    # Unsupported Models
-    create_model_metadata(  # Mistral
-        provider="Groq", name="mistral-saba-24b", icon="Groq", not_supported=True
-    ),
-    create_model_metadata(  # Playht, Inc
-        provider="Groq", name="playai-tts", icon="Groq", not_supported=True
-    ),
-    create_model_metadata(  # Playht, Inc
-        provider="Groq", name="playai-tts-arabic", icon="Groq", not_supported=True
-    ),
-    create_model_metadata(  # OpenAI
-        provider="Groq", name="whisper-large-v3", icon="Groq", not_supported=True
-    ),
-    create_model_metadata(  # OpenAI
-        provider="Groq", name="whisper-large-v3-turbo", icon="Groq", not_supported=True
-    ),
-    create_model_metadata(  # Hugging Face
-        provider="Groq", name="distil-whisper-large-v3-en", icon="Groq", not_supported=True
-    ),
-]
-
-# Generate backwards-compatible lists from the metadata
-GROQ_PRODUCTION_MODELS = [
-    metadata["name"]
-    for metadata in GROQ_MODELS_DETAILED
-    if not metadata.get("preview", False)
-    and not metadata.get("deprecated", False)
-    and not metadata.get("not_supported", False)
-]
-
-GROQ_PREVIEW_MODELS = [metadata["name"] for metadata in GROQ_MODELS_DETAILED if metadata.get("preview", False)]
-
-DEPRECATED_GROQ_MODELS = [metadata["name"] for metadata in GROQ_MODELS_DETAILED if metadata.get("deprecated", False)]
-
-UNSUPPORTED_GROQ_MODELS = [
-    metadata["name"] for metadata in GROQ_MODELS_DETAILED if metadata.get("not_supported", False)
-]
-
-TOOL_CALLING_UNSUPPORTED_GROQ_MODELS = [
-    metadata["name"]
-    for metadata in GROQ_MODELS_DETAILED
-    if not metadata.get("tool_calling", False)
-    and not metadata.get("not_supported", False)
-    and not metadata.get("deprecated", False)
-]
-
-# Combined list of all current models for backward compatibility
-GROQ_MODELS = GROQ_PRODUCTION_MODELS + GROQ_PREVIEW_MODELS
-
-# For reverse compatibility
-MODEL_NAMES = GROQ_MODELS