diff --git a/example.py b/example.py index c66c5454..5e5943ed 100644 --- a/example.py +++ b/example.py @@ -12,7 +12,7 @@ api_key = os.environ.get("OPENAI_API_KEY") # Initialize the language model, this model can be swapped out with Anthropic, ETC, Huggingface Models like Mistral, ETC llm = OpenAI( # model_name="gpt-4" - openai_api_key=api_key, + # openai_api_key=api_key, temperature=0.5, # max_tokens=100, ) @@ -23,7 +23,7 @@ flow = Flow( llm=llm, max_loops=2, dashboard=True, - # tools = [search_api, slack, ] + # tools=[search_api] # stopping_condition=None, # You can define a stopping condition as needed. # loop_interval=1, # retry_attempts=3, diff --git a/swarms/models/__init__.py b/swarms/models/__init__.py index bdaea689..e946bffd 100644 --- a/swarms/models/__init__.py +++ b/swarms/models/__init__.py @@ -5,15 +5,15 @@ import sys # LLMs -from swarms.models.anthropic import Anthropic -from swarms.models.petals import Petals -from swarms.models.mistral import Mistral -from swarms.models.openai_models import OpenAIChat, AzureOpenAI, OpenAI -from swarms.models.zephyr import Zephyr -from swarms.models.biogpt import BioGPT -from swarms.models.huggingface import HuggingfaceLLM -from swarms.models.wizard_storytelling import WizardLLMStoryTeller -from swarms.models.mpt import MPT7B +from swarms.models.anthropic import Anthropic # noqa: E402 +from swarms.models.petals import Petals # noqa: E402 +from swarms.models.mistral import Mistral # noqa: E402 +from swarms.models.openai_models import OpenAI, AzureOpenAI, OpenAIChat # noqa: E402 +from swarms.models.zephyr import Zephyr # noqa: E402 +from swarms.models.biogpt import BioGPT # noqa: E402 +from swarms.models.huggingface import HuggingfaceLLM # noqa: E402 +from swarms.models.wizard_storytelling import WizardLLMStoryTeller # noqa: E402 +from swarms.models.mpt import MPT7B # noqa: E402 # MultiModal Models from swarms.models.idefics import Idefics # noqa: E402 diff --git a/swarms/models/openai_chat.py b/swarms/models/openai_chat.py deleted file mode 100644 index d53658da..00000000 --- a/swarms/models/openai_chat.py +++ /dev/null @@ -1,676 +0,0 @@ -from __future__ import annotations - -import logging -import os -import sys -from typing import ( - TYPE_CHECKING, - Any, - AsyncIterator, - Callable, - Dict, - Iterator, - List, - Mapping, - Optional, - Sequence, - Tuple, - Type, - Union, -) - -from langchain.adapters.openai import convert_dict_to_message, convert_message_to_dict -from langchain.callbacks.manager import ( - AsyncCallbackManagerForLLMRun, - CallbackManagerForLLMRun, -) -from langchain.chat_models.base import ( - BaseChatModel, -) -from langchain.llms.base import create_base_retry_decorator -from langchain.pydantic_v1 import BaseModel, Field, root_validator -from langchain.schema import ChatGeneration, ChatResult -from langchain.schema.language_model import LanguageModelInput -from langchain.schema.messages import ( - AIMessageChunk, - BaseMessage, - BaseMessageChunk, - ChatMessageChunk, - FunctionMessageChunk, - HumanMessageChunk, - SystemMessageChunk, - ToolMessageChunk, -) -from langchain.schema.output import ChatGenerationChunk -from langchain.schema.runnable import Runnable -from langchain.utils import ( - get_from_dict_or_env, - get_pydantic_field_names, -) -from langchain.utils.openai import is_openai_v1 - -if TYPE_CHECKING: - import tiktoken - - -logger = logging.getLogger(__name__) - - -def _generate_from_stream(stream: Iterator[ChatGenerationChunk]) -> ChatResult: - generation: Optional[ChatGenerationChunk] = None - for chunk in stream: - if generation is None: - generation = chunk - else: - generation += chunk - assert generation is not None - return ChatResult(generations=[generation]) - - -async def _agenerate_from_stream( - stream: AsyncIterator[ChatGenerationChunk], -) -> ChatResult: - generation: Optional[ChatGenerationChunk] = None - async for chunk in stream: - if generation is None: - generation = chunk - else: - generation += chunk - assert generation is not None - return ChatResult(generations=[generation]) - - -def _import_tiktoken() -> Any: - try: - import tiktoken - except ImportError: - raise ValueError( - "Could not import tiktoken python package. " - "This is needed in order to calculate get_token_ids. " - "Please install it with `pip install tiktoken`." - ) - return tiktoken - - -def _create_retry_decorator( - llm: OpenAIChat, - run_manager: Optional[ - Union[AsyncCallbackManagerForLLMRun, CallbackManagerForLLMRun] - ] = None, -) -> Callable[[Any], Any]: - import openai - - errors = [ - openai.Timeout, - openai.APIError, - openai.APIConnectionError, - openai.RateLimitError, - openai.ServiceUnavailableError, - ] - return create_base_retry_decorator( - error_types=errors, max_retries=llm.max_retries, run_manager=run_manager - ) - - -async def acompletion_with_retry( - llm: OpenAIChat, - run_manager: Optional[AsyncCallbackManagerForLLMRun] = None, - **kwargs: Any, -) -> Any: - """Use tenacity to retry the async completion call.""" - if is_openai_v1(): - return await llm.async_client.create(**kwargs) - - retry_decorator = _create_retry_decorator(llm, run_manager=run_manager) - - @retry_decorator - async def _completion_with_retry(**kwargs: Any) -> Any: - # Use OpenAI's async api https://github.com/openai/openai-python#async-api - return await llm.client.acreate(**kwargs) - - return await _completion_with_retry(**kwargs) - - -def _convert_delta_to_message_chunk( - _dict: Mapping[str, Any], default_class: Type[BaseMessageChunk] -) -> BaseMessageChunk: - role = _dict.get("role") - content = _dict.get("content") or "" - additional_kwargs: Dict = {} - if _dict.get("function_call"): - function_call = dict(_dict["function_call"]) - if "name" in function_call and function_call["name"] is None: - function_call["name"] = "" - additional_kwargs["function_call"] = function_call - if _dict.get("tool_calls"): - additional_kwargs["tool_calls"] = _dict["tool_calls"] - - if role == "user" or default_class == HumanMessageChunk: - return HumanMessageChunk(content=content) - elif role == "assistant" or default_class == AIMessageChunk: - return AIMessageChunk(content=content, additional_kwargs=additional_kwargs) - elif role == "system" or default_class == SystemMessageChunk: - return SystemMessageChunk(content=content) - elif role == "function" or default_class == FunctionMessageChunk: - return FunctionMessageChunk(content=content, name=_dict["name"]) - elif role == "tool" or default_class == ToolMessageChunk: - return ToolMessageChunk(content=content, tool_call_id=_dict["tool_call_id"]) - elif role or default_class == ChatMessageChunk: - return ChatMessageChunk(content=content, role=role) - else: - return default_class(content=content) - - -class OpenAIChat(BaseChatModel): - """`OpenAI` Chat large language models API. - - To use, you should have the ``openai`` python package installed, and the - environment variable ``OPENAI_API_KEY`` set with your API key. - - Any parameters that are valid to be passed to the openai.create call can be passed - in, even if not explicitly saved on this class. - - Example: - .. code-block:: python - - from swarms.models import ChatOpenAI - openai = ChatOpenAI(model_name="gpt-3.5-turbo") - """ - - @property - def lc_secrets(self) -> Dict[str, str]: - return {"openai_api_key": "OPENAI_API_KEY"} - - @property - def lc_attributes(self) -> Dict[str, Any]: - attributes: Dict[str, Any] = {} - - if self.openai_organization: - attributes["openai_organization"] = self.openai_organization - - if self.openai_api_base: - attributes["openai_api_base"] = self.openai_api_base - - if self.openai_proxy: - attributes["openai_proxy"] = self.openai_proxy - - return attributes - - @classmethod - def is_lc_serializable(cls) -> bool: - """Return whether this model can be serialized by Langchain.""" - return True - - client: Any = None #: :meta private: - async_client: Any = None #: :meta private: - model_name: str = Field(default="gpt-3.5-turbo", alias="model") - """Model name to use.""" - temperature: float = 0.7 - """What sampling temperature to use.""" - model_kwargs: Dict[str, Any] = Field(default_factory=dict) - """Holds any model parameters valid for `create` call not explicitly specified.""" - # When updating this to use a SecretStr - # Check for classes that derive from this class (as some of them - # may assume openai_api_key is a str) - # openai_api_key: Optional[str] = Field(default=None, alias="api_key") - openai_api_key: Optional[str] = Field(default=None, alias="api_key") - """Automatically inferred from env var `OPENAI_API_KEY` if not provided.""" - openai_api_base: Optional[str] = Field(default=None, alias="base_url") - """Base URL path for API requests, leave blank if not using a proxy or service - emulator.""" - openai_organization: Optional[str] = Field(default=None, alias="organization") - """Automatically inferred from env var `OPENAI_ORG_ID` if not provided.""" - # to support explicit proxy for OpenAI - openai_proxy: Optional[str] = None - request_timeout: Union[float, Tuple[float, float], Any, None] = Field( - default=None, alias="timeout" - ) - """Timeout for requests to OpenAI completion API. Can be float, httpx.Timeout or - None.""" - max_retries: int = 2 - """Maximum number of retries to make when generating.""" - streaming: bool = False - """Whether to stream the results or not.""" - n: int = 1 - """Number of chat completions to generate for each prompt.""" - max_tokens: Optional[int] = None - """Maximum number of tokens to generate.""" - tiktoken_model_name: Optional[str] = None - """The model name to pass to tiktoken when using this class. - Tiktoken is used to count the number of tokens in documents to constrain - them to be under a certain limit. By default, when set to None, this will - be the same as the embedding model name. However, there are some cases - where you may want to use this Embedding class with a model name not - supported by tiktoken. This can include when using Azure embeddings or - when using one of the many model providers that expose an OpenAI-like - API but with different models. In those cases, in order to avoid erroring - when tiktoken is called, you can specify a model name to use here.""" - default_headers: Union[Mapping[str, str], None] = None - default_query: Union[Mapping[str, object], None] = None - # Configure a custom httpx client. See the - # [httpx documentation](https://www.python-httpx.org/api/#client) for more details. - http_client: Union[Any, None] = None - """Optional httpx.Client.""" - - class Config: - """Configuration for this pydantic object.""" - - allow_population_by_field_name = True - - @root_validator(pre=True) - def build_extra(cls, values: Dict[str, Any]) -> Dict[str, Any]: - """Build extra kwargs from additional params that were passed in.""" - all_required_field_names = get_pydantic_field_names(cls) - extra = values.get("model_kwargs", {}) - for field_name in list(values): - if field_name in extra: - raise ValueError(f"Found {field_name} supplied twice.") - if field_name not in all_required_field_names: - logger.warning( - f"""WARNING! {field_name} is not default parameter. - {field_name} was transferred to model_kwargs. - Please confirm that {field_name} is what you intended.""" - ) - extra[field_name] = values.pop(field_name) - - invalid_model_kwargs = all_required_field_names.intersection(extra.keys()) - if invalid_model_kwargs: - raise ValueError( - f"Parameters {invalid_model_kwargs} should be specified explicitly. " - f"Instead they were passed in as part of `model_kwargs` parameter." - ) - - values["model_kwargs"] = extra - return values - - @root_validator() - def validate_environment(cls, values: Dict) -> Dict: - """Validate that api key and python package exists in environment.""" - if values["n"] < 1: - raise ValueError("n must be at least 1.") - if values["n"] > 1 and values["streaming"]: - raise ValueError("n must be 1 when streaming.") - - values["openai_api_key"] = get_from_dict_or_env( - values, "openai_api_key", "OPENAI_API_KEY" - ) - # Check OPENAI_ORGANIZATION for backwards compatibility. - values["openai_organization"] = ( - values["openai_organization"] - or os.getenv("OPENAI_ORG_ID") - or os.getenv("OPENAI_ORGANIZATION") - ) - values["openai_api_base"] = values["openai_api_base"] or os.getenv( - "OPENAI_API_BASE" - ) - values["openai_proxy"] = get_from_dict_or_env( - values, - "openai_proxy", - "OPENAI_PROXY", - default="", - ) - try: - import openai - - except ImportError: - raise ImportError( - "Could not import openai python package. " - "Please install it with `pip install openai`." - ) - - if is_openai_v1(): - client_params = { - "api_key": values["openai_api_key"], - "organization": values["openai_organization"], - "base_url": values["openai_api_base"], - "timeout": values["request_timeout"], - "max_retries": values["max_retries"], - "default_headers": values["default_headers"], - "default_query": values["default_query"], - "http_client": values["http_client"], - } - values["client"] = openai.OpenAI(**client_params).chat.completions - values["async_client"] = openai.AsyncOpenAI( - **client_params - ).chat.completions - else: - values["client"] = openai.ChatCompletion - return values - - @property - def _default_params(self) -> Dict[str, Any]: - """Get the default parameters for calling OpenAI API.""" - params = { - "model": self.model_name, - "stream": self.streaming, - "n": self.n, - "temperature": self.temperature, - **self.model_kwargs, - } - if self.max_tokens is not None: - params["max_tokens"] = self.max_tokens - if self.request_timeout is not None and not is_openai_v1(): - params["request_timeout"] = self.request_timeout - return params - - def completion_with_retry( - self, run_manager: Optional[CallbackManagerForLLMRun] = None, **kwargs: Any - ) -> Any: - """Use tenacity to retry the completion call.""" - if is_openai_v1(): - return self.client.create(**kwargs) - - retry_decorator = _create_retry_decorator(self, run_manager=run_manager) - - @retry_decorator - def _completion_with_retry(**kwargs: Any) -> Any: - return self.client.create(**kwargs) - - return _completion_with_retry(**kwargs) - - def _combine_llm_outputs(self, llm_outputs: List[Optional[dict]]) -> dict: - overall_token_usage: dict = {} - system_fingerprint = None - for output in llm_outputs: - if output is None: - # Happens in streaming - continue - token_usage = output["token_usage"] - for k, v in token_usage.items(): - if k in overall_token_usage: - overall_token_usage[k] += v - else: - overall_token_usage[k] = v - if system_fingerprint is None: - system_fingerprint = output.get("system_fingerprint") - combined = {"token_usage": overall_token_usage, "model_name": self.model_name} - if system_fingerprint: - combined["system_fingerprint"] = system_fingerprint - return combined - - def _stream( - self, - messages: List[BaseMessage], - stop: Optional[List[str]] = None, - run_manager: Optional[CallbackManagerForLLMRun] = None, - **kwargs: Any, - ) -> Iterator[ChatGenerationChunk]: - message_dicts, params = self._create_message_dicts(messages, stop) - params = {**params, **kwargs, "stream": True} - - default_chunk_class = AIMessageChunk - for chunk in self.completion_with_retry( - messages=message_dicts, run_manager=run_manager, **params - ): - if not isinstance(chunk, dict): - chunk = chunk.dict() - if len(chunk["choices"]) == 0: - continue - choice = chunk["choices"][0] - chunk = _convert_delta_to_message_chunk( - choice["delta"], default_chunk_class - ) - finish_reason = choice.get("finish_reason") - generation_info = ( - dict(finish_reason=finish_reason) if finish_reason is not None else None - ) - default_chunk_class = chunk.__class__ - chunk = ChatGenerationChunk(message=chunk, generation_info=generation_info) - yield chunk - if run_manager: - run_manager.on_llm_new_token(chunk.text, chunk=chunk) - - def _generate( - self, - messages: List[BaseMessage], - stop: Optional[List[str]] = None, - run_manager: Optional[CallbackManagerForLLMRun] = None, - stream: Optional[bool] = None, - **kwargs: Any, - ) -> ChatResult: - should_stream = stream if stream is not None else self.streaming - if should_stream: - stream_iter = self._stream( - messages, stop=stop, run_manager=run_manager, **kwargs - ) - return _generate_from_stream(stream_iter) - message_dicts, params = self._create_message_dicts(messages, stop) - params = {**params, **kwargs} - response = self.completion_with_retry( - messages=message_dicts, run_manager=run_manager, **params - ) - return self._create_chat_result(response) - - def _create_message_dicts( - self, messages: List[BaseMessage], stop: Optional[List[str]] - ) -> Tuple[List[Dict[str, Any]], Dict[str, Any]]: - params = self._client_params - if stop is not None: - if "stop" in params: - raise ValueError("`stop` found in both the input and default params.") - params["stop"] = stop - message_dicts = [convert_message_to_dict(m) for m in messages] - return message_dicts, params - - def _create_chat_result(self, response: Union[dict, BaseModel]) -> ChatResult: - generations = [] - if not isinstance(response, dict): - response = response.dict() - for res in response["choices"]: - message = convert_dict_to_message(res["message"]) - gen = ChatGeneration( - message=message, - generation_info=dict(finish_reason=res.get("finish_reason")), - ) - generations.append(gen) - token_usage = response.get("usage", {}) - llm_output = { - "token_usage": token_usage, - "model_name": self.model_name, - "system_fingerprint": response.get("system_fingerprint", ""), - } - return ChatResult(generations=generations, llm_output=llm_output) - - async def _astream( - self, - messages: List[BaseMessage], - stop: Optional[List[str]] = None, - run_manager: Optional[AsyncCallbackManagerForLLMRun] = None, - **kwargs: Any, - ) -> AsyncIterator[ChatGenerationChunk]: - message_dicts, params = self._create_message_dicts(messages, stop) - params = {**params, **kwargs, "stream": True} - - default_chunk_class = AIMessageChunk - async for chunk in await acompletion_with_retry( - self, messages=message_dicts, run_manager=run_manager, **params - ): - if not isinstance(chunk, dict): - chunk = chunk.dict() - if len(chunk["choices"]) == 0: - continue - choice = chunk["choices"][0] - chunk = _convert_delta_to_message_chunk( - choice["delta"], default_chunk_class - ) - finish_reason = choice.get("finish_reason") - generation_info = ( - dict(finish_reason=finish_reason) if finish_reason is not None else None - ) - default_chunk_class = chunk.__class__ - chunk = ChatGenerationChunk(message=chunk, generation_info=generation_info) - yield chunk - if run_manager: - await run_manager.on_llm_new_token(token=chunk.text, chunk=chunk) - - async def _agenerate( - self, - messages: List[BaseMessage], - stop: Optional[List[str]] = None, - run_manager: Optional[AsyncCallbackManagerForLLMRun] = None, - stream: Optional[bool] = None, - **kwargs: Any, - ) -> ChatResult: - should_stream = stream if stream is not None else self.streaming - if should_stream: - stream_iter = self._astream( - messages, stop=stop, run_manager=run_manager, **kwargs - ) - return await _agenerate_from_stream(stream_iter) - - message_dicts, params = self._create_message_dicts(messages, stop) - params = {**params, **kwargs} - response = await acompletion_with_retry( - self, messages=message_dicts, run_manager=run_manager, **params - ) - return self._create_chat_result(response) - - @property - def _identifying_params(self) -> Dict[str, Any]: - """Get the identifying parameters.""" - return {**{"model_name": self.model_name}, **self._default_params} - - @property - def _client_params(self) -> Dict[str, Any]: - """Get the parameters used for the openai client.""" - openai_creds: Dict[str, Any] = { - "model": self.model_name, - } - if not is_openai_v1(): - openai_creds.update( - { - "api_key": self.openai_api_key, - "api_base": self.openai_api_base, - "organization": self.openai_organization, - } - ) - if self.openai_proxy: - import openai - - raise Exception("The 'openai.proxy' option isn't read in the client API. You will need to pass it when you instantiate the client, e.g. 'OpenAI(proxy={"http": self.openai_proxy, "https": self.openai_proxy})'") # type: ignore[assignment] # noqa: E501 - return {**self._default_params, **openai_creds} - - def _get_invocation_params( - self, stop: Optional[List[str]] = None, **kwargs: Any - ) -> Dict[str, Any]: - """Get the parameters used to invoke the model.""" - return { - "model": self.model_name, - **super()._get_invocation_params(stop=stop), - **self._default_params, - **kwargs, - } - - @property - def _llm_type(self) -> str: - """Return type of chat model.""" - return "openai-chat" - - def _get_encoding_model(self) -> Tuple[str, tiktoken.Encoding]: - tiktoken_ = _import_tiktoken() - if self.tiktoken_model_name is not None: - model = self.tiktoken_model_name - else: - model = self.model_name - if model == "gpt-3.5-turbo": - # gpt-3.5-turbo may change over time. - # Returning num tokens assuming gpt-3.5-turbo-0301. - model = "gpt-3.5-turbo-0301" - elif model == "gpt-4": - # gpt-4 may change over time. - # Returning num tokens assuming gpt-4-0314. - model = "gpt-4-0314" - # Returns the number of tokens used by a list of messages. - try: - encoding = tiktoken_.encoding_for_model(model) - except KeyError: - logger.warning("Warning: model not found. Using cl100k_base encoding.") - model = "cl100k_base" - encoding = tiktoken_.get_encoding(model) - return model, encoding - - def get_token_ids(self, text: str) -> List[int]: - """Get the tokens present in the text with tiktoken package.""" - # tiktoken NOT supported for Python 3.7 or below - if sys.version_info[1] <= 7: - return super().get_token_ids(text) - _, encoding_model = self._get_encoding_model() - return encoding_model.encode(text) - - def get_num_tokens_from_messages(self, messages: List[BaseMessage]) -> int: - """Calculate num tokens for gpt-3.5-turbo and gpt-4 with tiktoken package. - - Official documentation: https://github.com/openai/openai-cookbook/blob/ - main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb""" - if sys.version_info[1] <= 7: - return super().get_num_tokens_from_messages(messages) - model, encoding = self._get_encoding_model() - if model.startswith("gpt-3.5-turbo-0301"): - # every message follows {role/name}\n{content}\n - tokens_per_message = 4 - # if there's a name, the role is omitted - tokens_per_name = -1 - elif model.startswith("gpt-3.5-turbo") or model.startswith("gpt-4"): - tokens_per_message = 3 - tokens_per_name = 1 - else: - raise NotImplementedError( - f"get_num_tokens_from_messages() is not presently implemented " - f"for model {model}." - "See https://github.com/openai/openai-python/blob/main/chatml.md for " - "information on how messages are converted to tokens." - ) - num_tokens = 0 - messages_dict = [convert_message_to_dict(m) for m in messages] - for message in messages_dict: - num_tokens += tokens_per_message - for key, value in message.items(): - # Cast str(value) in case the message value is not a string - # This occurs with function messages - num_tokens += len(encoding.encode(str(value))) - if key == "name": - num_tokens += tokens_per_name - # every reply is primed with assistant - num_tokens += 3 - return num_tokens - - def bind_functions( - self, - functions: Sequence[Union[Dict[str, Any], Type[BaseModel], Callable]], - function_call: Optional[str] = None, - **kwargs: Any, - ) -> Runnable[LanguageModelInput, BaseMessage]: - """Bind functions (and other objects) to this chat model. - - Args: - functions: A list of function definitions to bind to this chat model. - Can be a dictionary, pydantic model, or callable. Pydantic - models and callables will be automatically converted to - their schema dictionary representation. - function_call: Which function to require the model to call. - Must be the name of the single provided function or - "auto" to automatically determine which function to call - (if any). - kwargs: Any additional parameters to pass to the - :class:`~swarms.runnable.Runnable` constructor. - """ - from langchain.chains.openai_functions.base import convert_to_openai_function - - formatted_functions = [convert_to_openai_function(fn) for fn in functions] - if function_call is not None: - if len(formatted_functions) != 1: - raise ValueError( - "When specifying `function_call`, you must provide exactly one " - "function." - ) - if formatted_functions[0]["name"] != function_call: - raise ValueError( - f"Function call {function_call} was specified, but the only " - f"provided function was {formatted_functions[0]['name']}." - ) - function_call_ = {"name": function_call} - kwargs = {**kwargs, "function_call": function_call_} - return super().bind( - functions=formatted_functions, - **kwargs, - ) diff --git a/swarms/models/openai_models.py b/swarms/models/openai_models.py index 615bfb0e..7a868655 100644 --- a/swarms/models/openai_models.py +++ b/swarms/models/openai_models.py @@ -33,9 +33,19 @@ from langchain.utils import get_from_dict_or_env, get_pydantic_field_names from langchain.utils.openai import is_openai_v1 from langchain.utils.utils import build_extra_kwargs + +from importlib.metadata import version + +from packaging.version import parse + logger = logging.getLogger(__name__) +def is_openai_v1() -> bool: + _version = parse(version("openai")) + return _version.major >= 1 + + def update_token_usage( keys: Set[str], response: Dict[str, Any], token_usage: Dict[str, Any] ) -> None: @@ -93,7 +103,11 @@ def _create_retry_decorator( import openai errors = [ +<<<<<<< HEAD openai.Timeout, +======= + openai.error.Timeout, +>>>>>>> master openai.error.APIError, openai.error.APIConnectionError, openai.error.RateLimitError, @@ -110,11 +124,16 @@ def completion_with_retry( **kwargs: Any, ) -> Any: """Use tenacity to retry the completion call.""" +<<<<<<< HEAD if is_openai_v1(): return llm.client.create(**kwargs) retry_decorator = _create_retry_decorator(llm, run_manager=run_manager) +======= + retry_decorator = _create_retry_decorator(llm, run_manager=run_manager) + +>>>>>>> master @retry_decorator def _completion_with_retry(**kwargs: Any) -> Any: return llm.client.create(**kwargs) @@ -128,11 +147,16 @@ async def acompletion_with_retry( **kwargs: Any, ) -> Any: """Use tenacity to retry the async completion call.""" +<<<<<<< HEAD if is_openai_v1(): return await llm.async_client.create(**kwargs) retry_decorator = _create_retry_decorator(llm, run_manager=run_manager) +======= + retry_decorator = _create_retry_decorator(llm, run_manager=run_manager) + +>>>>>>> master @retry_decorator async def _completion_with_retry(**kwargs: Any) -> Any: # Use OpenAI's async api https://github.com/openai/openai-python#async-api @@ -594,8 +618,12 @@ class BaseOpenAI(BaseLLM): if self.openai_proxy: import openai +<<<<<<< HEAD # TODO: The 'openai.proxy' option isn't read in the client API. You will need to pass it when you instantiate the client, e.g. 'OpenAI(proxy={"http": self.openai_proxy, "https": self.openai_proxy})' # openai.proxy = {"http": self.openai_proxy, "https": self.openai_proxy} # type: ignore[assignment] # noqa: E501 +======= + openai.proxy = {"http": self.openai_proxy, "https": self.openai_proxy} # type: ignore[assignment] # noqa: E501 +>>>>>>> master return {**openai_creds, **self._default_params} @property