two version of R2R are here HEAD master

3 files changed, 527 insertions, 0 deletions

diff --git a/.venv/lib/python3.12/site-packages/litellm/llms/openai/completion/handler.py b/.venv/lib/python3.12/site-packages/litellm/llms/openai/completion/handler.py
new file mode 100644
index 00000000..2e60f55b
--- /dev/null
+++ b/.venv/lib/python3.12/site-packages/litellm/llms/openai/completion/handler.py
@@ -0,0 +1,319 @@
+import json
+from typing import Callable, List, Optional, Union
+
+from openai import AsyncOpenAI, OpenAI
+
+import litellm
+from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
+from litellm.litellm_core_utils.streaming_handler import CustomStreamWrapper
+from litellm.llms.base import BaseLLM
+from litellm.types.llms.openai import AllMessageValues, OpenAITextCompletionUserMessage
+from litellm.types.utils import LlmProviders, ModelResponse, TextCompletionResponse
+from litellm.utils import ProviderConfigManager
+
+from ..common_utils import OpenAIError
+from .transformation import OpenAITextCompletionConfig
+
+
+class OpenAITextCompletion(BaseLLM):
+    openai_text_completion_global_config = OpenAITextCompletionConfig()
+
+    def __init__(self) -> None:
+        super().__init__()
+
+    def validate_environment(self, api_key):
+        headers = {
+            "content-type": "application/json",
+        }
+        if api_key:
+            headers["Authorization"] = f"Bearer {api_key}"
+        return headers
+
+    def completion(
+        self,
+        model_response: ModelResponse,
+        api_key: str,
+        model: str,
+        messages: Union[List[AllMessageValues], List[OpenAITextCompletionUserMessage]],
+        timeout: float,
+        custom_llm_provider: str,
+        logging_obj: LiteLLMLoggingObj,
+        optional_params: dict,
+        print_verbose: Optional[Callable] = None,
+        api_base: Optional[str] = None,
+        acompletion: bool = False,
+        litellm_params=None,
+        logger_fn=None,
+        client=None,
+        organization: Optional[str] = None,
+        headers: Optional[dict] = None,
+    ):
+        try:
+            if headers is None:
+                headers = self.validate_environment(api_key=api_key)
+            if model is None or messages is None:
+                raise OpenAIError(status_code=422, message="Missing model or messages")
+
+            # don't send max retries to the api, if set
+
+            provider_config = ProviderConfigManager.get_provider_text_completion_config(
+                model=model,
+                provider=LlmProviders(custom_llm_provider),
+            )
+
+            data = provider_config.transform_text_completion_request(
+                model=model,
+                messages=messages,
+                optional_params=optional_params,
+                headers=headers,
+            )
+            max_retries = data.pop("max_retries", 2)
+            ## LOGGING
+            logging_obj.pre_call(
+                input=messages,
+                api_key=api_key,
+                additional_args={
+                    "headers": headers,
+                    "api_base": api_base,
+                    "complete_input_dict": data,
+                },
+            )
+            if acompletion is True:
+                if optional_params.get("stream", False):
+                    return self.async_streaming(
+                        logging_obj=logging_obj,
+                        api_base=api_base,
+                        api_key=api_key,
+                        data=data,
+                        headers=headers,
+                        model_response=model_response,
+                        model=model,
+                        timeout=timeout,
+                        max_retries=max_retries,
+                        client=client,
+                        organization=organization,
+                    )
+                else:
+                    return self.acompletion(api_base=api_base, data=data, headers=headers, model_response=model_response, api_key=api_key, logging_obj=logging_obj, model=model, timeout=timeout, max_retries=max_retries, organization=organization, client=client)  # type: ignore
+            elif optional_params.get("stream", False):
+                return self.streaming(
+                    logging_obj=logging_obj,
+                    api_base=api_base,
+                    api_key=api_key,
+                    data=data,
+                    headers=headers,
+                    model_response=model_response,
+                    model=model,
+                    timeout=timeout,
+                    max_retries=max_retries,  # type: ignore
+                    client=client,
+                    organization=organization,
+                )
+            else:
+                if client is None:
+                    openai_client = OpenAI(
+                        api_key=api_key,
+                        base_url=api_base,
+                        http_client=litellm.client_session,
+                        timeout=timeout,
+                        max_retries=max_retries,  # type: ignore
+                        organization=organization,
+                    )
+                else:
+                    openai_client = client
+
+                raw_response = openai_client.completions.with_raw_response.create(**data)  # type: ignore
+                response = raw_response.parse()
+                response_json = response.model_dump()
+
+                ## LOGGING
+                logging_obj.post_call(
+                    api_key=api_key,
+                    original_response=response_json,
+                    additional_args={
+                        "headers": headers,
+                        "api_base": api_base,
+                    },
+                )
+
+                ## RESPONSE OBJECT
+                return TextCompletionResponse(**response_json)
+        except Exception as e:
+            status_code = getattr(e, "status_code", 500)
+            error_headers = getattr(e, "headers", None)
+            error_text = getattr(e, "text", str(e))
+            error_response = getattr(e, "response", None)
+            if error_headers is None and error_response:
+                error_headers = getattr(error_response, "headers", None)
+            raise OpenAIError(
+                status_code=status_code, message=error_text, headers=error_headers
+            )
+
+    async def acompletion(
+        self,
+        logging_obj,
+        api_base: str,
+        data: dict,
+        headers: dict,
+        model_response: ModelResponse,
+        api_key: str,
+        model: str,
+        timeout: float,
+        max_retries: int,
+        organization: Optional[str] = None,
+        client=None,
+    ):
+        try:
+            if client is None:
+                openai_aclient = AsyncOpenAI(
+                    api_key=api_key,
+                    base_url=api_base,
+                    http_client=litellm.aclient_session,
+                    timeout=timeout,
+                    max_retries=max_retries,
+                    organization=organization,
+                )
+            else:
+                openai_aclient = client
+
+            raw_response = await openai_aclient.completions.with_raw_response.create(
+                **data
+            )
+            response = raw_response.parse()
+            response_json = response.model_dump()
+
+            ## LOGGING
+            logging_obj.post_call(
+                api_key=api_key,
+                original_response=response,
+                additional_args={
+                    "headers": headers,
+                    "api_base": api_base,
+                },
+            )
+            ## RESPONSE OBJECT
+            response_obj = TextCompletionResponse(**response_json)
+            response_obj._hidden_params.original_response = json.dumps(response_json)
+            return response_obj
+        except Exception as e:
+            status_code = getattr(e, "status_code", 500)
+            error_headers = getattr(e, "headers", None)
+            error_text = getattr(e, "text", str(e))
+            error_response = getattr(e, "response", None)
+            if error_headers is None and error_response:
+                error_headers = getattr(error_response, "headers", None)
+            raise OpenAIError(
+                status_code=status_code, message=error_text, headers=error_headers
+            )
+
+    def streaming(
+        self,
+        logging_obj,
+        api_key: str,
+        data: dict,
+        headers: dict,
+        model_response: ModelResponse,
+        model: str,
+        timeout: float,
+        api_base: Optional[str] = None,
+        max_retries=None,
+        client=None,
+        organization=None,
+    ):
+
+        if client is None:
+            openai_client = OpenAI(
+                api_key=api_key,
+                base_url=api_base,
+                http_client=litellm.client_session,
+                timeout=timeout,
+                max_retries=max_retries,  # type: ignore
+                organization=organization,
+            )
+        else:
+            openai_client = client
+
+        try:
+            raw_response = openai_client.completions.with_raw_response.create(**data)
+            response = raw_response.parse()
+        except Exception as e:
+            status_code = getattr(e, "status_code", 500)
+            error_headers = getattr(e, "headers", None)
+            error_text = getattr(e, "text", str(e))
+            error_response = getattr(e, "response", None)
+            if error_headers is None and error_response:
+                error_headers = getattr(error_response, "headers", None)
+            raise OpenAIError(
+                status_code=status_code, message=error_text, headers=error_headers
+            )
+        streamwrapper = CustomStreamWrapper(
+            completion_stream=response,
+            model=model,
+            custom_llm_provider="text-completion-openai",
+            logging_obj=logging_obj,
+            stream_options=data.get("stream_options", None),
+        )
+
+        try:
+            for chunk in streamwrapper:
+                yield chunk
+        except Exception as e:
+            status_code = getattr(e, "status_code", 500)
+            error_headers = getattr(e, "headers", None)
+            error_text = getattr(e, "text", str(e))
+            error_response = getattr(e, "response", None)
+            if error_headers is None and error_response:
+                error_headers = getattr(error_response, "headers", None)
+            raise OpenAIError(
+                status_code=status_code, message=error_text, headers=error_headers
+            )
+
+    async def async_streaming(
+        self,
+        logging_obj,
+        api_key: str,
+        data: dict,
+        headers: dict,
+        model_response: ModelResponse,
+        model: str,
+        timeout: float,
+        max_retries: int,
+        api_base: Optional[str] = None,
+        client=None,
+        organization=None,
+    ):
+        if client is None:
+            openai_client = AsyncOpenAI(
+                api_key=api_key,
+                base_url=api_base,
+                http_client=litellm.aclient_session,
+                timeout=timeout,
+                max_retries=max_retries,
+                organization=organization,
+            )
+        else:
+            openai_client = client
+
+        raw_response = await openai_client.completions.with_raw_response.create(**data)
+        response = raw_response.parse()
+        streamwrapper = CustomStreamWrapper(
+            completion_stream=response,
+            model=model,
+            custom_llm_provider="text-completion-openai",
+            logging_obj=logging_obj,
+            stream_options=data.get("stream_options", None),
+        )
+
+        try:
+            async for transformed_chunk in streamwrapper:
+                yield transformed_chunk
+        except Exception as e:
+            status_code = getattr(e, "status_code", 500)
+            error_headers = getattr(e, "headers", None)
+            error_text = getattr(e, "text", str(e))
+            error_response = getattr(e, "response", None)
+            if error_headers is None and error_response:
+                error_headers = getattr(error_response, "headers", None)
+            raise OpenAIError(
+                status_code=status_code, message=error_text, headers=error_headers
+            )
diff --git a/.venv/lib/python3.12/site-packages/litellm/llms/openai/completion/transformation.py b/.venv/lib/python3.12/site-packages/litellm/llms/openai/completion/transformation.py
new file mode 100644
index 00000000..1aef72d3
--- /dev/null
+++ b/.venv/lib/python3.12/site-packages/litellm/llms/openai/completion/transformation.py
@@ -0,0 +1,158 @@
+"""
+Support for gpt model family 
+"""
+
+from typing import List, Optional, Union
+
+from litellm.llms.base_llm.completion.transformation import BaseTextCompletionConfig
+from litellm.types.llms.openai import AllMessageValues, OpenAITextCompletionUserMessage
+from litellm.types.utils import Choices, Message, ModelResponse, TextCompletionResponse
+
+from ..chat.gpt_transformation import OpenAIGPTConfig
+from .utils import _transform_prompt
+
+
+class OpenAITextCompletionConfig(BaseTextCompletionConfig, OpenAIGPTConfig):
+    """
+    Reference: https://platform.openai.com/docs/api-reference/completions/create
+
+    The class `OpenAITextCompletionConfig` provides configuration for the OpenAI's text completion API interface. Below are the parameters:
+
+    - `best_of` (integer or null): This optional parameter generates server-side completions and returns the one with the highest log probability per token.
+
+    - `echo` (boolean or null): This optional parameter will echo back the prompt in addition to the completion.
+
+    - `frequency_penalty` (number or null): Defaults to 0. It is a numbers from -2.0 to 2.0, where positive values decrease the model's likelihood to repeat the same line.
+
+    - `logit_bias` (map): This optional parameter modifies the likelihood of specified tokens appearing in the completion.
+
+    - `logprobs` (integer or null): This optional parameter includes the log probabilities on the most likely tokens as well as the chosen tokens.
+
+    - `max_tokens` (integer or null): This optional parameter sets the maximum number of tokens to generate in the completion.
+
+    - `n` (integer or null): This optional parameter sets how many completions to generate for each prompt.
+
+    - `presence_penalty` (number or null): Defaults to 0 and can be between -2.0 and 2.0. Positive values increase the model's likelihood to talk about new topics.
+
+    - `stop` (string / array / null): Specifies up to 4 sequences where the API will stop generating further tokens.
+
+    - `suffix` (string or null): Defines the suffix that comes after a completion of inserted text.
+
+    - `temperature` (number or null): This optional parameter defines the sampling temperature to use.
+
+    - `top_p` (number or null): An alternative to sampling with temperature, used for nucleus sampling.
+    """
+
+    best_of: Optional[int] = None
+    echo: Optional[bool] = None
+    frequency_penalty: Optional[int] = None
+    logit_bias: Optional[dict] = None
+    logprobs: Optional[int] = None
+    max_tokens: Optional[int] = None
+    n: Optional[int] = None
+    presence_penalty: Optional[int] = None
+    stop: Optional[Union[str, list]] = None
+    suffix: Optional[str] = None
+
+    def __init__(
+        self,
+        best_of: Optional[int] = None,
+        echo: Optional[bool] = None,
+        frequency_penalty: Optional[int] = None,
+        logit_bias: Optional[dict] = None,
+        logprobs: Optional[int] = None,
+        max_tokens: Optional[int] = None,
+        n: Optional[int] = None,
+        presence_penalty: Optional[int] = None,
+        stop: Optional[Union[str, list]] = None,
+        suffix: Optional[str] = None,
+        temperature: Optional[float] = None,
+        top_p: Optional[float] = None,
+    ) -> None:
+        locals_ = locals().copy()
+        for key, value in locals_.items():
+            if key != "self" and value is not None:
+                setattr(self.__class__, key, value)
+
+    @classmethod
+    def get_config(cls):
+        return super().get_config()
+
+    def convert_to_chat_model_response_object(
+        self,
+        response_object: Optional[TextCompletionResponse] = None,
+        model_response_object: Optional[ModelResponse] = None,
+    ):
+        try:
+            ## RESPONSE OBJECT
+            if response_object is None or model_response_object is None:
+                raise ValueError("Error in response object format")
+            choice_list = []
+            for idx, choice in enumerate(response_object["choices"]):
+                message = Message(
+                    content=choice["text"],
+                    role="assistant",
+                )
+                choice = Choices(
+                    finish_reason=choice["finish_reason"],
+                    index=idx,
+                    message=message,
+                    logprobs=choice.get("logprobs", None),
+                )
+                choice_list.append(choice)
+            model_response_object.choices = choice_list
+
+            if "usage" in response_object:
+                setattr(model_response_object, "usage", response_object["usage"])
+
+            if "id" in response_object:
+                model_response_object.id = response_object["id"]
+
+            if "model" in response_object:
+                model_response_object.model = response_object["model"]
+
+            model_response_object._hidden_params["original_response"] = (
+                response_object  # track original response, if users make a litellm.text_completion() request, we can return the original response
+            )
+            return model_response_object
+        except Exception as e:
+            raise e
+
+    def get_supported_openai_params(self, model: str) -> List:
+        return [
+            "functions",
+            "function_call",
+            "temperature",
+            "top_p",
+            "n",
+            "stream",
+            "stream_options",
+            "stop",
+            "max_tokens",
+            "presence_penalty",
+            "frequency_penalty",
+            "logit_bias",
+            "user",
+            "response_format",
+            "seed",
+            "tools",
+            "tool_choice",
+            "max_retries",
+            "logprobs",
+            "top_logprobs",
+            "extra_headers",
+        ]
+
+    def transform_text_completion_request(
+        self,
+        model: str,
+        messages: Union[List[AllMessageValues], List[OpenAITextCompletionUserMessage]],
+        optional_params: dict,
+        headers: dict,
+    ) -> dict:
+        prompt = _transform_prompt(messages)
+        return {
+            "model": model,
+            "prompt": prompt,
+            **optional_params,
+        }
diff --git a/.venv/lib/python3.12/site-packages/litellm/llms/openai/completion/utils.py b/.venv/lib/python3.12/site-packages/litellm/llms/openai/completion/utils.py
new file mode 100644
index 00000000..8b3efb4c
--- /dev/null
+++ b/.venv/lib/python3.12/site-packages/litellm/llms/openai/completion/utils.py
@@ -0,0 +1,50 @@
+from typing import List, Union, cast
+
+from litellm.litellm_core_utils.prompt_templates.common_utils import (
+    convert_content_list_to_str,
+)
+from litellm.types.llms.openai import (
+    AllMessageValues,
+    AllPromptValues,
+    OpenAITextCompletionUserMessage,
+)
+
+
+def is_tokens_or_list_of_tokens(value: List):
+    # Check if it's a list of integers (tokens)
+    if isinstance(value, list) and all(isinstance(item, int) for item in value):
+        return True
+    # Check if it's a list of lists of integers (list of tokens)
+    if isinstance(value, list) and all(
+        isinstance(item, list) and all(isinstance(i, int) for i in item)
+        for item in value
+    ):
+        return True
+    return False
+
+
+def _transform_prompt(
+    messages: Union[List[AllMessageValues], List[OpenAITextCompletionUserMessage]],
+) -> AllPromptValues:
+    if len(messages) == 1:  # base case
+        message_content = messages[0].get("content")
+        if (
+            message_content
+            and isinstance(message_content, list)
+            and is_tokens_or_list_of_tokens(message_content)
+        ):
+            openai_prompt: AllPromptValues = cast(AllPromptValues, message_content)
+        else:
+            openai_prompt = ""
+            content = convert_content_list_to_str(cast(AllMessageValues, messages[0]))
+            openai_prompt += content
+    else:
+        prompt_str_list: List[str] = []
+        for m in messages:
+            try:  # expect list of int/list of list of int to be a 1 message array only.
+                content = convert_content_list_to_str(cast(AllMessageValues, m))
+                prompt_str_list.append(content)
+            except Exception as e:
+                raise e
+        openai_prompt = prompt_str_list
+    return openai_prompt