qwak-core 0.1.37__py3-none-any.whl → 0.5.19__py3-none-any.whl

qwak/llmops/generation/chat/openai/types/chat/chat_completion_tool_message_param.py

@@ -0,0 +1,31 @@
+#
+#    Copyright 2024 OpenAI
+#
+#    Licensed under the Apache License, Version 2.0 (the "License");
+#    you may not use this file except in compliance with the License.
+#    You may obtain a copy of the License at
+#
+#        http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS,
+#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#    See the License for the specific language governing permissions and
+#    limitations under the License.
+
+from __future__ import annotations
+
+from typing_extensions import Literal, Required, TypedDict
+
+__all__ = ["ChatCompletionToolMessageParam"]
+
+
+class ChatCompletionToolMessageParam(TypedDict, total=False):
+    content: Required[str]
+    """The contents of the tool message."""
+
+    role: Required[Literal["tool"]]
+    """The role of the messages author, in this case `tool`."""
+
+    tool_call_id: Required[str]
+    """Tool call that this message is responding to."""

qwak/llmops/generation/chat/openai/types/chat/chat_completion_tool_param.py

@@ -0,0 +1,29 @@
+#
+#    Copyright 2024 OpenAI
+#
+#    Licensed under the Apache License, Version 2.0 (the "License");
+#    you may not use this file except in compliance with the License.
+#    You may obtain a copy of the License at
+#
+#        http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS,
+#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#    See the License for the specific language governing permissions and
+#    limitations under the License.
+
+from __future__ import annotations
+
+from typing_extensions import Literal, Required, TypedDict
+
+from ...types import shared_params
+
+__all__ = ["ChatCompletionToolParam"]
+
+
+class ChatCompletionToolParam(TypedDict, total=False):
+    function: Required[shared_params.FunctionDefinition]
+
+    type: Required[Literal["function"]]
+    """The type of the tool. Currently, only `function` is supported."""

qwak/llmops/generation/chat/openai/types/chat/chat_completion_user_message_param.py

@@ -0,0 +1,35 @@
+#
+#    Copyright 2024 OpenAI
+#
+#    Licensed under the Apache License, Version 2.0 (the "License");
+#    you may not use this file except in compliance with the License.
+#    You may obtain a copy of the License at
+#
+#        http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS,
+#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#    See the License for the specific language governing permissions and
+#    limitations under the License.
+
+from __future__ import annotations
+
+from typing_extensions import Literal, Required, TypedDict
+
+__all__ = ["ChatCompletionUserMessageParam"]
+
+
+class ChatCompletionUserMessageParam(TypedDict, total=False):
+    content: Required[str]
+    """The contents of the user message."""
+
+    role: Required[Literal["user"]]
+    """The role of the messages author, in this case `user`."""
+
+    name: str
+    """An optional name for the participant.
+
+    Provides the model information to differentiate between participants of the same
+    role.
+    """

qwak/llmops/generation/chat/openai/types/chat/completion_create_params.py

@@ -0,0 +1,279 @@
+#
+#    Copyright 2024 OpenAI
+#
+#    Licensed under the Apache License, Version 2.0 (the "License");
+#    you may not use this file except in compliance with the License.
+#    You may obtain a copy of the License at
+#
+#        http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS,
+#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#    See the License for the specific language governing permissions and
+#    limitations under the License.
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Dict, Iterable, List, Optional, Union
+
+from typing_extensions import Literal, Required, TypedDict
+
+from ...types import shared_params
+from .chat_completion_function_call_option_param import (
+    ChatCompletionFunctionCallOptionParam,
+)
+from .chat_completion_message_param import ChatCompletionMessageParam
+from .chat_completion_tool_choice_option_param import (
+    ChatCompletionToolChoiceOptionParam,
+)
+from .chat_completion_tool_param import ChatCompletionToolParam
+
+__all__ = [
+    "CompletionCreateParamsBase",
+    "FunctionCall",
+    "Function",
+    "ResponseFormat",
+    "CompletionCreateParamsNonStreaming",
+    "CompletionCreateParamsStreaming",
+]
+
+
+class CompletionCreateParamsBase(TypedDict, total=False):
+    messages: Required[Iterable[ChatCompletionMessageParam]]
+    """A list of messages comprising the conversation so far.
+
+    [Example Python code](https://cookbook.openai.com/examples/how_to_format_inputs_to_chatgpt_models).
+    """
+
+    model: Required[str]
+    """ID of the model to use.
+
+    See the
+    [model endpoint compatibility](https://platform.openai.com/docs/models/model-endpoint-compatibility)
+    table for details on which models work with the Chat API.
+    """
+
+    frequency_penalty: Optional[float]
+    """Number between -2.0 and 2.0.
+
+    Positive values penalize new tokens based on their existing frequency in the
+    text so far, decreasing the model's likelihood to repeat the same line verbatim.
+
+    [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+    """
+
+    function_call: FunctionCall
+    """Deprecated in favor of `tool_choice`.
+
+    Controls which (if any) function is called by the model. `none` means the model
+    will not call a function and instead generates a message. `auto` means the model
+    can pick between generating a message or calling a function. Specifying a
+    particular function via `{"name": "my_function"}` forces the model to call that
+    function.
+
+    `none` is the default when no functions are present. `auto` is the default if
+    functions are present.
+    """
+
+    functions: Iterable[Function]
+    """Deprecated in favor of `tools`.
+
+    A list of functions the model may generate JSON inputs for.
+    """
+
+    logit_bias: Optional[Dict[str, int]]
+    """Modify the likelihood of specified tokens appearing in the completion.
+
+    Accepts a JSON object that maps tokens (specified by their token ID in the
+    tokenizer) to an associated bias value from -100 to 100. Mathematically, the
+    bias is added to the logits generated by the model prior to sampling. The exact
+    effect will vary per model, but values between -1 and 1 should decrease or
+    increase likelihood of selection; values like -100 or 100 should result in a ban
+    or exclusive selection of the relevant token.
+    """
+
+    logprobs: Optional[bool]
+    """Whether to return log probabilities of the output tokens or not.
+
+    If true, returns the log probabilities of each output token returned in the
+    `content` of `message`.
+    """
+
+    max_tokens: Optional[int]
+    """
+    The maximum number of [tokens](/tokenizer) that can be generated in the chat
+    completion.
+
+    The total length of input tokens and generated tokens is limited by the model's
+    context length.
+    [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
+    for counting tokens.
+    """
+
+    n: Optional[int]
+    """How many chat completion choices to generate for each input message.
+
+    Note that you will be charged based on the number of generated tokens across all
+    of the choices. Keep `n` as `1` to minimize costs.
+    """
+
+    presence_penalty: Optional[float]
+    """Number between -2.0 and 2.0.
+
+    Positive values penalize new tokens based on whether they appear in the text so
+    far, increasing the model's likelihood to talk about new topics.
+
+    [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+    """
+
+    response_format: ResponseFormat
+    """An object specifying the format that the model must output.
+
+    Compatible with
+    [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo) and
+    all GPT-3.5 Turbo models newer than `gpt-3.5-turbo-1106`.
+
+    Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the
+    message the model generates is valid JSON.
+
+    **Important:** when using JSON mode, you **must** also instruct the model to
+    produce JSON yourself via a system or user message. Without this, the model may
+    generate an unending stream of whitespace until the generation reaches the token
+    limit, resulting in a long-running and seemingly "stuck" request. Also note that
+    the message content may be partially cut off if `finish_reason="length"`, which
+    indicates the generation exceeded `max_tokens` or the conversation exceeded the
+    max context length.
+    """
+
+    seed: Optional[int]
+    """
+    This feature is in Beta. If specified, our system will make a best effort to
+    sample deterministically, such that repeated requests with the same `seed` and
+    parameters should return the same result. Determinism is not guaranteed, and you
+    should refer to the `system_fingerprint` response parameter to monitor changes
+    in the backend.
+    """
+
+    stop: Union[Optional[str], List[str]]
+    """Up to 4 sequences where the API will stop generating further tokens."""
+
+    temperature: Optional[float]
+    """What sampling temperature to use, between 0 and 2.
+
+    Higher values like 0.8 will make the output more random, while lower values like
+    0.2 will make it more focused and deterministic.
+
+    We generally recommend altering this or `top_p` but not both.
+    """
+
+    tool_choice: ChatCompletionToolChoiceOptionParam
+    """
+    Controls which (if any) function is called by the model. `none` means the model
+    will not call a function and instead generates a message. `auto` means the model
+    can pick between generating a message or calling a function. Specifying a
+    particular function via
+    `{"type": "function", "function": {"name": "my_function"}}` forces the model to
+    call that function.
+
+    `none` is the default when no functions are present. `auto` is the default if
+    functions are present.
+    """
+
+    tools: Iterable[ChatCompletionToolParam]
+    """A list of tools the model may call.
+
+    Currently, only functions are supported as a tool. Use this to provide a list of
+    functions the model may generate JSON inputs for. A max of 128 functions are
+    supported.
+    """
+
+    top_logprobs: Optional[int]
+    """
+    An integer between 0 and 20 specifying the number of most likely tokens to
+    return at each token position, each with an associated log probability.
+    `logprobs` must be set to `true` if this parameter is used.
+    """
+
+    top_p: Optional[float]
+    """
+    An alternative to sampling with temperature, called nucleus sampling, where the
+    model considers the results of the tokens with top_p probability mass. So 0.1
+    means only the tokens comprising the top 10% probability mass are considered.
+
+    We generally recommend altering this or `temperature` but not both.
+    """
+
+    user: str
+    """
+    A unique identifier representing your end-user, which can help OpenAI to monitor
+    and detect abuse.
+    [Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids).
+    """
+
+
+FunctionCall = Union[Literal["none", "auto"], ChatCompletionFunctionCallOptionParam]
+
+
+class Function(TypedDict, total=False):
+    name: Required[str]
+    """The name of the function to be called.
+
+    Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length
+    of 64.
+    """
+
+    description: str
+    """
+    A description of what the function does, used by the model to choose when and
+    how to call the function.
+    """
+
+    parameters: shared_params.FunctionParameters
+    """The parameters the functions accepts, described as a JSON Schema object.
+
+    See the
+    [guide](https://platform.openai.com/docs/guides/text-generation/function-calling)
+    for examples, and the
+    [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for
+    documentation about the format.
+
+    Omitting `parameters` defines a function with an empty parameter list.
+    """
+
+
+class ResponseFormat(TypedDict, total=False):
+    type: Literal["text", "json_object"]
+    """Must be one of `text` or `json_object`."""
+
+
+@dataclass
+class CompletionCreateParamsNonStreaming(CompletionCreateParamsBase):
+    stream: Optional[Literal[False]]
+    """If set, partial message deltas will be sent, like in ChatGPT.
+
+    Tokens will be sent as data-only
+    [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
+    as they become available, with the stream terminated by a `data: [DONE]`
+    message.
+    [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
+    """
+
+
+@dataclass
+class CompletionCreateParamsStreaming(CompletionCreateParamsBase):
+    stream: Required[Literal[True]]
+    """If set, partial message deltas will be sent, like in ChatGPT.
+
+    Tokens will be sent as data-only
+    [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
+    as they become available, with the stream terminated by a `data: [DONE]`
+    message.
+    [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
+    """
+
+
+CompletionCreateParams = Union[
+    CompletionCreateParamsNonStreaming, CompletionCreateParamsStreaming
+]

qwak/llmops/generation/chat/openai/types/completion_choice.py

@@ -0,0 +1,47 @@
+#
+#    Copyright 2024 OpenAI
+#
+#    Licensed under the Apache License, Version 2.0 (the "License");
+#    you may not use this file except in compliance with the License.
+#    You may obtain a copy of the License at
+#
+#        http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS,
+#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#    See the License for the specific language governing permissions and
+#    limitations under the License.
+
+from dataclasses import dataclass
+from typing import Dict, List, Optional
+
+from typing_extensions import Literal
+
+__all__ = ["CompletionChoice", "Logprobs"]
+
+
+@dataclass
+class Logprobs:
+    text_offset: Optional[List[int]] = None
+
+    token_logprobs: Optional[List[float]] = None
+
+    tokens: Optional[List[str]] = None
+
+    top_logprobs: Optional[List[Dict[str, float]]] = None
+
+
+@dataclass
+class CompletionChoice:
+    finish_reason: Literal["stop", "length", "content_filter"]
+    """The reason the model stopped generating tokens.
+
+    This will be `stop` if the model hit a natural stop point or a provided stop
+    sequence, `length` if the maximum number of tokens specified in the request was
+    reached, or `content_filter` if content was omitted due to a flag from our
+    content filters.
+    """
+    index: int
+    text: str
+    logprobs: Optional[Logprobs] = None

qwak/llmops/generation/chat/openai/types/completion_create_params.py

@@ -0,0 +1,209 @@
+#
+#    Copyright 2024 OpenAI
+#
+#    Licensed under the Apache License, Version 2.0 (the "License");
+#    you may not use this file except in compliance with the License.
+#    You may obtain a copy of the License at
+#
+#        http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS,
+#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#    See the License for the specific language governing permissions and
+#    limitations under the License.
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Dict, Iterable, List, Optional, Union
+
+from typing_extensions import Literal, Required, TypedDict
+
+__all__ = [
+    "CompletionCreateParamsBase",
+    "CompletionCreateParamsNonStreaming",
+    "CompletionCreateParamsStreaming",
+]
+
+
+class CompletionCreateParamsBase(TypedDict, total=False):
+    model: Required[
+        Union[str, Literal["gpt-3.5-turbo-instruct", "davinci-002", "babbage-002"]]
+    ]
+    """ID of the model to use.
+
+    You can use the
+    [List models](https://platform.openai.com/docs/api-reference/models/list) API to
+    see all of your available models, or see our
+    [Model overview](https://platform.openai.com/docs/models/overview) for
+    descriptions of them.
+    """
+
+    prompt: Required[
+        Union[str, List[str], Iterable[int], Iterable[Iterable[int]], None]
+    ]
+    """
+    The prompt(s) to generate completions for, encoded as a string, array of
+    strings, array of tokens, or array of token arrays.
+
+    Note that <|endoftext|> is the document separator that the model sees during
+    training, so if a prompt is not specified the model will generate as if from the
+    beginning of a new document.
+    """
+
+    best_of: Optional[int]
+    """
+    Generates `best_of` completions server-side and returns the "best" (the one with
+    the highest log probability per token). Results cannot be streamed.
+
+    When used with `n`, `best_of` controls the number of candidate completions and
+    `n` specifies how many to return – `best_of` must be greater than `n`.
+
+    **Note:** Because this parameter generates many completions, it can quickly
+    consume your token quota. Use carefully and ensure that you have reasonable
+    settings for `max_tokens` and `stop`.
+    """
+
+    echo: Optional[bool]
+    """Echo back the prompt in addition to the completion"""
+
+    frequency_penalty: Optional[float]
+    """Number between -2.0 and 2.0.
+
+    Positive values penalize new tokens based on their existing frequency in the
+    text so far, decreasing the model's likelihood to repeat the same line verbatim.
+
+    [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+    """
+
+    logit_bias: Optional[Dict[str, int]]
+    """Modify the likelihood of specified tokens appearing in the completion.
+
+    Accepts a JSON object that maps tokens (specified by their token ID in the GPT
+    tokenizer) to an associated bias value from -100 to 100. You can use this
+    [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs.
+    Mathematically, the bias is added to the logits generated by the model prior to
+    sampling. The exact effect will vary per model, but values between -1 and 1
+    should decrease or increase likelihood of selection; values like -100 or 100
+    should result in a ban or exclusive selection of the relevant token.
+
+    As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token
+    from being generated.
+    """
+
+    logprobs: Optional[int]
+    """
+    Include the log probabilities on the `logprobs` most likely output tokens, as
+    well the chosen tokens. For example, if `logprobs` is 5, the API will return a
+    list of the 5 most likely tokens. The API will always return the `logprob` of
+    the sampled token, so there may be up to `logprobs+1` elements in the response.
+
+    The maximum value for `logprobs` is 5.
+    """
+
+    max_tokens: Optional[int]
+    """
+    The maximum number of [tokens](/tokenizer) that can be generated in the
+    completion.
+
+    The token count of your prompt plus `max_tokens` cannot exceed the model's
+    context length.
+    [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken)
+    for counting tokens.
+    """
+
+    n: Optional[int]
+    """How many completions to generate for each prompt.
+
+    **Note:** Because this parameter generates many completions, it can quickly
+    consume your token quota. Use carefully and ensure that you have reasonable
+    settings for `max_tokens` and `stop`.
+    """
+
+    presence_penalty: Optional[float]
+    """Number between -2.0 and 2.0.
+
+    Positive values penalize new tokens based on whether they appear in the text so
+    far, increasing the model's likelihood to talk about new topics.
+
+    [See more information about frequency and presence penalties.](https://platform.openai.com/docs/guides/text-generation/parameter-details)
+    """
+
+    seed: Optional[int]
+    """
+    If specified, our system will make a best effort to sample deterministically,
+    such that repeated requests with the same `seed` and parameters should return
+    the same result.
+
+    Determinism is not guaranteed, and you should refer to the `system_fingerprint`
+    response parameter to monitor changes in the backend.
+    """
+
+    stop: Union[Optional[str], List[str], None]
+    """Up to 4 sequences where the API will stop generating further tokens.
+
+    The returned text will not contain the stop sequence.
+    """
+
+    suffix: Optional[str]
+    """The suffix that comes after a completion of inserted text.
+
+    This parameter is only supported for `gpt-3.5-turbo-instruct`.
+    """
+
+    temperature: Optional[float]
+    """What sampling temperature to use, between 0 and 2.
+
+    Higher values like 0.8 will make the output more random, while lower values like
+    0.2 will make it more focused and deterministic.
+
+    We generally recommend altering this or `top_p` but not both.
+    """
+
+    top_p: Optional[float]
+    """
+    An alternative to sampling with temperature, called nucleus sampling, where the
+    model considers the results of the tokens with top_p probability mass. So 0.1
+    means only the tokens comprising the top 10% probability mass are considered.
+
+    We generally recommend altering this or `temperature` but not both.
+    """
+
+    user: str
+    """
+    A unique identifier representing your end-user, which can help OpenAI to monitor
+    and detect abuse.
+    [Learn more](https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids).
+    """
+
+
+@dataclass
+class CompletionCreateParamsNonStreaming(CompletionCreateParamsBase):
+    stream: Optional[Literal[False]]
+    """Whether to stream back partial progress.
+
+    If set, tokens will be sent as data-only
+    [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
+    as they become available, with the stream terminated by a `data: [DONE]`
+    message.
+    [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
+    """
+
+
+@dataclass
+class CompletionCreateParamsStreaming(CompletionCreateParamsBase):
+    stream: Required[Literal[True]]
+    """Whether to stream back partial progress.
+
+    If set, tokens will be sent as data-only
+    [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
+    as they become available, with the stream terminated by a `data: [DONE]`
+    message.
+    [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions).
+    """
+
+
+CompletionCreateParams = Union[
+    CompletionCreateParamsNonStreaming, CompletionCreateParamsStreaming
+]

qwak/llmops/generation/chat/openai/types/completion_usage.py

@@ -0,0 +1,30 @@
+#
+#    Copyright 2024 OpenAI
+#
+#    Licensed under the Apache License, Version 2.0 (the "License");
+#    you may not use this file except in compliance with the License.
+#    You may obtain a copy of the License at
+#
+#        http://www.apache.org/licenses/LICENSE-2.0
+#
+#    Unless required by applicable law or agreed to in writing, software
+#    distributed under the License is distributed on an "AS IS" BASIS,
+#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#    See the License for the specific language governing permissions and
+#    limitations under the License.
+
+__all__ = ["CompletionUsage"]
+
+from dataclasses import dataclass
+
+
+@dataclass
+class CompletionUsage:
+    completion_tokens: int
+    """Number of tokens in the generated completion."""
+
+    prompt_tokens: int
+    """Number of tokens in the prompt."""
+
+    total_tokens: int
+    """Total number of tokens used in the request (prompt + completion)."""