lionagi 0.5.4__py3-none-any.whl → 0.6.0__py3-none-any.whl

lionagi/core/session/types.py

@@ -1,8 +0,0 @@
-# Copyright (c) 2023 - 2024, HaiyangLi <quantocean.li at gmail dot com>
-#
-# SPDX-License-Identifier: Apache-2.0
-
-from .branch import Branch
-from .session import Session
-
-__all__ = ["Session", "Branch"]

lionagi/core/typing/__init__.py

@@ -1,9 +0,0 @@
-# Copyright (c) 2023 - 2024, HaiyangLi <quantocean.li at gmail dot com>
-#
-# SPDX-License-Identifier: Apache-2.0
-
-from ..models import *
-from ._concepts import *
-from ._id import *
-from ._pydantic import *
-from ._typing import *

lionagi/core/typing/_concepts.py

@@ -1,173 +0,0 @@
-# Copyright (c) 2023 - 2024, HaiyangLi <quantocean.li at gmail dot com>
-#
-# SPDX-License-Identifier: Apache-2.0
-
-from __future__ import annotations
-
-import uuid
-from abc import ABC, abstractmethod
-from dataclasses import dataclass
-from typing import Any, Generic, TypeVar
-
-from lionagi.settings import Settings
-
-
-class IDType:
-
-    def __init__(self, _id: uuid.UUID):
-        self._id = _id
-
-    @classmethod
-    def validate(cls, value) -> IDType:
-        if isinstance(value, cls):
-            return value
-        if isinstance(value, str | int):
-            try:
-                _id = uuid.UUID(value, version=Settings.Config.UUID_VERSION)
-                return cls(_id=_id)
-            except Exception as e:
-                raise ValueError(f"Invalid IDType value: {value}") from e
-        raise ValueError(f"Invalid IDType value: {value}")
-
-    def __str__(self):
-        return str(self._id)
-
-    def __repr__(self):
-        return f"{self.__class__.__name__}({self._id})"
-
-    def __hash__(self):
-        return hash(self._id)
-
-    def __eq__(self, other):
-        if not isinstance(other, IDType):
-            return False
-        return self._id == other._id
-
-    __slots__ = ("_id",)
-
-
-class Observable(ABC):
-    """
-    Abstract base class for objects that can be uniquely identified and tracked.
-
-    All Observable objects must have a unique identifier (id) that allows them
-    to be tracked and referenced within the Lion system.
-    """
-
-    ln_id: IDType
-
-
-T = TypeVar("T", bound=Observable)
-
-
-class Container(ABC, Generic[T]):
-    """
-    Abstract base class for objects that can contain Observable items.
-
-    Generic type T must be a subclass of Observable.
-    """
-
-    pass
-
-
-class Ordering(ABC, Generic[T]):
-    """
-    Abstract base class for objects that maintain an ordered collection of items.
-
-    Generic type T must be a subclass of Observable.
-    """
-
-    pass
-
-
-class Communicatable(ABC):
-    """
-    Abstract base class for objects that can participate in communication.
-
-    Defines the interface for objects that can send and receive messages within
-    the Lion system.
-    """
-
-    pass
-
-
-class Relational(Observable):
-
-    pass
-
-
-class Event(ABC):
-
-    @abstractmethod
-    async def invoke(self, *args, **kwargs) -> Any:
-        pass
-
-
-class Condition(ABC):
-
-    @abstractmethod
-    async def apply(self, *args, **kwargs) -> bool:
-        pass
-
-
-class Structure(ABC):
-    pass
-
-
-class ItemError(Exception):
-    """Base exception for errors related to framework items."""
-
-    def __init__(
-        self,
-        message: str = "Item error.",
-        item_id: str | None = None,
-    ):
-        self.item_id = item_id
-        item_info = f" Item ID: {item_id}" if item_id else ""
-        super().__init__(f"{message}{item_info}")
-
-
-class ItemNotFoundError(ItemError):
-    """Exception raised when an item is not found."""
-
-    def __init__(
-        self,
-        message: str = "Item not found.",
-        item_id: str | None = None,
-    ):
-        super().__init__(message, item_id)
-
-
-class ItemExistsError(ItemError):
-    """Exception raised when an item already exists."""
-
-    def __init__(
-        self,
-        message: str = "Item already exists.",
-        item_id: str | None = None,
-    ):
-        super().__init__(message, item_id)
-
-
-class RelationError(Exception):
-    """Base exception for errors related to framework relations."""
-
-    def __init__(self, message: str = "Relation error."):
-        super().__init__(message)
-
-
-__all__ = [
-    "Observable",
-    "Container",
-    "Ordering",
-    "Communicatable",
-    "ItemError",
-    "ItemNotFoundError",
-    "ItemExistsError",
-    "Relational",
-    "Event",
-    "Condition",
-    "Structure",
-    "RelationError",
-    "IDType",
-]

lionagi/core/typing/_id.py

@@ -1,104 +0,0 @@
-# Copyright (c) 2023 - 2024, HaiyangLi <quantocean.li at gmail dot com>
-#
-# SPDX-License-Identifier: Apache-2.0
-
-from __future__ import annotations
-
-import uuid
-
-from lionagi.settings import Settings
-
-from ._concepts import (
-    Container,
-    Generic,
-    IDType,
-    ItemError,
-    Observable,
-    Ordering,
-    T,
-)
-from ._typing import Container, Mapping, Sequence, TypeAlias
-
-
-class IDError(ItemError):
-    """Exception raised when an item does not have a Lion ID."""
-
-    def __init__(
-        self,
-        message: str = "Item must contain a Lion ID.",
-        item_id: str | None = None,
-    ):
-        super().__init__(message, item_id)
-
-
-class ID(Generic[T]):
-    """
-    A generic class that provides ID-related functionality for Observable objects.
-
-    This class handles the generation, validation, and management of unique identifiers
-    within the Lion system. It provides type aliases for various ID-related operations
-    and methods for working with IDs.
-    """
-
-    # For functions that accept either ID or item
-    Ref: TypeAlias = IDType | T  # type: ignore
-
-    # For functions requiring just the ID
-    ID: TypeAlias = IDType
-
-    # For functions requiring Observable object
-    Item = T  # type: ignore
-
-    # For collections
-    IDSeq: TypeAlias = list[IDType] | Ordering
-    ItemSeq: TypeAlias = (  # type: ignore
-        Sequence[T] | Mapping[IDType, T] | Container[IDType | T]
-    )
-    RefSeq: TypeAlias = IDSeq | ItemSeq
-
-    # For system-level interactions
-    SenderRecipient: TypeAlias = IDType | T | str  # type: ignore
-
-    @staticmethod
-    def id():
-        return IDType(
-            _id=getattr(uuid, f"uuid{Settings.Config.UUID_VERSION}")()
-        )
-
-    @staticmethod
-    def get_id(item, /) -> IDType:
-
-        if isinstance(item, Observable):
-            return item.ln_id
-        try:
-            return IDType.validate(item)
-        except ValueError as e:
-            raise IDError(
-                f"The input object of type <{type(item).__name__}> does "
-                "not contain or is not a valid Lion ID. Item must be an instance"
-                " of `Observable` or a valid `id`."
-            ) from e
-
-    @staticmethod
-    def is_id(item, /) -> bool:
-        """
-        Check if an item is or contains a valid Lion ID.
-
-        Args:
-            item: The item to check.
-            config: Configuration dictionary for ID validation.
-
-        Returns:
-            True if the item is a valid Lion ID, False otherwise.
-        """
-        try:
-            ID.get_id(item)
-            return True
-        except IDError:
-            return False
-
-
-__all__ = [
-    "ID",
-    "IDError",
-]

lionagi/core/typing/_pydantic.py

@@ -1,33 +0,0 @@
-# Copyright (c) 2023 - 2024, HaiyangLi <quantocean.li at gmail dot com>
-#
-# SPDX-License-Identifier: Apache-2.0
-
-from pydantic import (
-    BaseModel,
-    ConfigDict,
-    Field,
-    JsonValue,
-    PrivateAttr,
-    create_model,
-    field_serializer,
-    field_validator,
-    model_serializer,
-    model_validator,
-)
-from pydantic.fields import FieldInfo
-from pydantic_core import PydanticUndefined
-
-__all__ = [
-    "BaseModel",
-    "ConfigDict",
-    "Field",
-    "JsonValue",
-    "PrivateAttr",
-    "FieldInfo",
-    "PydanticUndefined",
-    "field_validator",
-    "model_validator",
-    "model_serializer",
-    "field_serializer",
-    "create_model",
-]

lionagi/core/typing/_typing.py

@@ -1,54 +0,0 @@
-# Copyright (c) 2023 - 2024, HaiyangLi <quantocean.li at gmail dot com>
-#
-# SPDX-License-Identifier: Apache-2.0
-
-from abc import ABC
-from collections.abc import (
-    Callable,
-    Container,
-    ItemsView,
-    Iterator,
-    Mapping,
-    Sequence,
-    ValuesView,
-)
-from enum import Enum
-from typing import (
-    Annotated,
-    Any,
-    ClassVar,
-    Generic,
-    Literal,
-    NoReturn,
-    Self,
-    TypeAlias,
-    TypeVar,
-)
-
-from typing_extensions import override
-
-from lionagi.libs.constants import UNDEFINED, UndefinedType
-
-__all__ = [
-    "ABC",
-    "Annotated",
-    "Any",
-    "ClassVar",
-    "Container",
-    "Enum",
-    "Generic",
-    "Literal",
-    "Mapping",
-    "NoReturn",
-    "Sequence",
-    "TypeAlias",
-    "TypeVar",
-    "UndefinedType",
-    "UNDEFINED",
-    "override",
-    "Callable",
-    "Self",
-    "Iterator",
-    "ValuesView",
-    "ItemsView",
-]

lionagi/integrations/_services.py

@@ -1,17 +0,0 @@
-# Copyright (c) 2023 - 2024, HaiyangLi <quantocean.li at gmail dot com>
-#
-# SPDX-License-Identifier: Apache-2.0
-
-from .anthropic_.AnthropicService import AnthropicService
-from .groq_.GroqService import GroqService
-from .ollama_.OllamaService import OllamaService
-from .openai_.OpenAIService import OpenAIService
-from .perplexity_.PerplexityService import PerplexityService
-
-__all__ = (
-    "AnthropicService",
-    "GroqService",
-    "OllamaService",
-    "OpenAIService",
-    "PerplexityService",
-)

lionagi/integrations/anthropic_/AnthropicModel.py

@@ -1,273 +0,0 @@
-# Copyright (c) 2023 - 2024, HaiyangLi <quantocean.li at gmail dot com>
-#
-# SPDX-License-Identifier: Apache-2.0
-
-from pathlib import Path
-
-from dotenv import load_dotenv
-from pydantic import (
-    BaseModel,
-    ConfigDict,
-    Field,
-    field_serializer,
-    model_validator,
-)
-
-from lionagi.integrations.anthropic_.api_endpoints.api_request import (
-    AnthropicRequest,
-)
-from lionagi.integrations.anthropic_.api_endpoints.match_response import (
-    match_response,
-)
-from lionagi.integrations.anthropic_.api_endpoints.messages.request.request_body import (
-    AnthropicMessageRequestBody,
-)
-from lionagi.service.rate_limiter import RateLimiter, RateLimitError
-from lionagi.service.service_util import invoke_retry
-from lionagi.service.token_calculator import TiktokenCalculator
-
-load_dotenv()
-path = Path(__file__).parent
-
-price_config_file_name = path / "anthropic_price_data.yaml"
-max_output_token_file_name = path / "anthropic_max_output_token_data.yaml"
-
-
-class _ModuleImportClass:
-    from lionagi.libs.package.imports import check_import
-
-    yaml = check_import("yaml", pip_name="pyyaml")
-
-
-class AnthropicModel(BaseModel):
-    model: str = Field(description="ID of the model to use.")
-
-    request_model: AnthropicRequest = Field(description="Making requests")
-
-    rate_limiter: RateLimiter = Field(
-        description="Rate Limiter to track usage"
-    )
-
-    text_token_calculator: TiktokenCalculator = Field(
-        default=None, description="Token Calculator"
-    )
-
-    estimated_output_len: int = Field(
-        default=0, description="Expected output len before making request"
-    )
-
-    model_config = ConfigDict(extra="forbid")
-
-    @model_validator(mode="before")
-    @classmethod
-    def parse_input(cls, data: dict):
-        if not isinstance(data, dict):
-            raise ValueError("Invalid init param")
-
-        # parse request model
-        request_model_params = {
-            "api_key": data.pop("api_key", None),
-            "endpoint": data.pop("endpoint", None),
-            "method": data.pop("method", None),
-            "content_type": data.pop("content_type", None),
-            "api_version": data.pop("api_version", None),
-        }
-        data["request_model"] = AnthropicRequest(**request_model_params)
-
-        # parse rate limiter
-        if "rate_limiter" not in data:
-            rate_limiter_params = {}
-            if limit_tokens := data.pop("limit_tokens", None):
-                rate_limiter_params["limit_tokens"] = limit_tokens
-            if limit_requests := data.pop("limit_requests", None):
-                rate_limiter_params["limit_requests"] = limit_requests
-
-            data["rate_limiter"] = RateLimiter(**rate_limiter_params)
-
-        # parse token calculator
-        try:
-            # Anthropic uses cl100k_base encoding
-            text_calc = TiktokenCalculator(encoding_name="cl100k_base")
-            data["text_token_calculator"] = text_calc
-        except Exception:
-            pass
-
-        return data
-
-    @field_serializer("request_model")
-    def serialize_request_model(self, value: AnthropicRequest):
-        return value.model_dump(exclude_unset=True)
-
-    @invoke_retry(max_retries=3, base_delay=1, max_delay=60)
-    async def invoke(
-        self,
-        request_body: AnthropicMessageRequestBody,
-        estimated_output_len: int = 0,
-        output_file=None,
-        parse_response=True,
-    ):
-        if request_model := getattr(request_body, "model"):
-            if request_model != self.model:
-                raise ValueError(
-                    f"Request model does not match. Model is {self.model}, but request is made for {request_model}."
-                )
-
-        # check remaining rate limit
-        input_token_len = await self.get_input_token_len(request_body)
-
-        if getattr(request_body, "max_tokens", None):
-            estimated_output_len = request_body.max_tokens
-
-        invoke_viability_result = self.verify_invoke_viability(
-            input_tokens_len=input_token_len,
-            estimated_output_len=estimated_output_len,
-        )
-        if not invoke_viability_result:
-            raise RateLimitError("Rate limit reached for requests")
-
-        try:
-            if getattr(request_body, "stream", None):
-                return await self.stream(
-                    request_body,
-                    output_file=output_file,
-                    parse_response=parse_response,
-                )
-
-            response_body, response_headers = await self.request_model.invoke(
-                json_data=request_body,
-                output_file=output_file,
-                with_response_header=True,
-                parse_response=False,
-            )
-
-            if response_body:
-                # Update rate limit based on usage
-                if response_body.get("usage"):
-                    total_token_usage = (
-                        response_body["usage"]["input_tokens"]
-                        + response_body["usage"]["output_tokens"]
-                    )
-                    self.rate_limiter.update_rate_limit(
-                        response_headers.get("Date"), total_token_usage
-                    )
-                else:
-                    self.rate_limiter.update_rate_limit(
-                        response_headers.get("Date")
-                    )
-
-            if parse_response:
-                return match_response(self.request_model, response_body)
-            else:
-                return response_body
-
-        except Exception as e:
-            raise e
-
-    async def stream(
-        self,
-        request_body: AnthropicMessageRequestBody,
-        output_file=None,
-        parse_response=True,
-        verbose=True,
-    ):
-        response_chunks = []
-        response_headers = None
-
-        async for chunk in self.request_model.stream(
-            json_data=request_body,
-            output_file=output_file,
-            with_response_header=True,
-            verbose=verbose,
-        ):
-            if isinstance(chunk, dict):
-                if chunk.get("type") in [
-                    "content_block_delta",
-                    "message_delta",
-                    "message_stop",
-                ]:
-                    response_chunks.append(chunk)
-                elif "headers" in chunk:
-                    response_headers = chunk["headers"]
-
-        # Update rate limit if we have usage information
-        if response_chunks and response_chunks[-1].get("usage"):
-            total_token_usage = (
-                response_chunks[-1]["usage"]["input_tokens"]
-                + response_chunks[-1]["usage"]["output_tokens"]
-            )
-            if response_headers:
-                self.rate_limiter.update_rate_limit(
-                    response_headers.get("Date"), total_token_usage
-                )
-
-        if parse_response:
-            return match_response(self.request_model, response_chunks)
-        else:
-            return response_chunks
-
-    async def get_input_token_len(
-        self, request_body: AnthropicMessageRequestBody
-    ):
-        if request_model := getattr(request_body, "model"):
-            if request_model != self.model:
-                raise ValueError(
-                    f"Request model does not match. Model is {self.model}, but request is made for {request_model}."
-                )
-
-        total_tokens = 0
-        for message in request_body.messages:
-            total_tokens += self.text_token_calculator.calculate(
-                message.content
-            )
-
-        if request_body.system:
-            total_tokens += self.text_token_calculator.calculate(
-                request_body.system
-            )
-
-        return total_tokens
-
-    def verify_invoke_viability(
-        self, input_tokens_len: int = 0, estimated_output_len: int = 0
-    ):
-        self.rate_limiter.release_tokens()
-
-        estimated_output_len = (
-            estimated_output_len
-            if estimated_output_len != 0
-            else self.estimated_output_len
-        )
-        if estimated_output_len == 0:
-            with open(max_output_token_file_name) as file:
-                output_token_config = _ModuleImportClass.yaml.safe_load(file)
-                estimated_output_len = output_token_config.get(self.model, 0)
-                self.estimated_output_len = estimated_output_len
-
-        if self.rate_limiter.check_availability(
-            input_tokens_len, estimated_output_len
-        ):
-            return True
-        else:
-            return False
-
-    def estimate_text_price(
-        self,
-        input_text: str,
-        estimated_num_of_output_tokens: int = 0,
-    ):
-        if self.text_token_calculator is None:
-            raise ValueError("Token calculator not available")
-
-        num_of_input_tokens = self.text_token_calculator.calculate(input_text)
-
-        with open(price_config_file_name) as file:
-            price_config = _ModuleImportClass.yaml.safe_load(file)
-
-        model_price_info_dict = price_config["model"][self.model]
-        estimated_price = (
-            model_price_info_dict["input_tokens"] * num_of_input_tokens
-            + model_price_info_dict["output_tokens"]
-            * estimated_num_of_output_tokens
-        )
-
-        return estimated_price