updated docs

python/casting.mdx

@@ -29,4 +29,4 @@ Cast the input to the specified type.
 
   The input after casting to the new type.
 
-<a id="utils"></a>
+<a id="dataset"></a>

python/chat/chatbot.mdx

@@ -90,4 +90,3 @@ Starts the chat interaction loop.
 - `show_credits` - Whether to show credit consumption. Defaults to False.
 - `show_endpoint` - Whether to show the endpoint used. Defaults to False.
 
-<a id="chat.clients.uni_llm"></a>

python/chat/clients/base.mdx

@@ -12,190 +12,6 @@ class _Client(ABC)
 
 Base Abstract class for interacting with the Unify chat completions endpoint.
 
-<a id="chat.clients.base._Client.__init__"></a>
-
----
-
-### \_\_init\_\_
-
-```python
-def __init__(*,
-             system_message: Optional[str] = None,
-             messages: Optional[Union[List[ChatCompletionMessageParam], Dict[
-                 str, List[ChatCompletionMessageParam]]]] = None,
-             frequency_penalty: Optional[float] = None,
-             logit_bias: Optional[Dict[str, int]] = None,
-             logprobs: Optional[bool] = None,
-             top_logprobs: Optional[int] = None,
-             max_completion_tokens: Optional[int] = 1024,
-             n: Optional[int] = None,
-             presence_penalty: Optional[float] = None,
-             response_format: Optional[ResponseFormat] = None,
-             seed: Optional[int] = None,
-             stop: Union[Optional[str], List[str]] = None,
-             stream: Optional[bool] = False,
-             stream_options: Optional[ChatCompletionStreamOptionsParam] = None,
-             temperature: Optional[float] = 1.0,
-             top_p: Optional[float] = None,
-             tools: Optional[Iterable[ChatCompletionToolParam]] = None,
-             tool_choice: Optional[ChatCompletionToolChoiceOptionParam] = None,
-             parallel_tool_calls: Optional[bool] = None,
-             use_custom_keys: bool = False,
-             tags: Optional[List[str]] = None,
-             drop_params: Optional[bool] = True,
-             region: Optional[str] = None,
-             log_query_body: Optional[bool] = True,
-             log_response_body: Optional[bool] = True,
-             api_key: Optional[str] = None,
-             return_full_completion: bool = False,
-             cache: bool = False,
-             extra_headers: Optional[Headers] = None,
-             extra_query: Optional[Query] = None,
-             **kwargs) -> None
-```
-
-Initialize the base Unify client.
-
-**Arguments**:
-
-- `system_message` - An optional string containing the system message. This
-  always appears at the beginning of the list of messages.
-
-- `messages` - A list of messages comprising the conversation so far, or
-  optionally a dictionary of such messages, with clients as the keys in the
-  case of multi-llm clients. This will be appended to the system_message if it
-  is not None, and any user_message will be appended if it is not None.
-
-- `frequency_penalty` - 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.
-
-- `logit_bias` - 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` - 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.
-
-- `top_logprobs` - 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.
-
-- `max_completion_tokens` - The maximum number of tokens 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. Defaults to the provider's default
-  max_completion_tokens when the value is None.
-
-- `n` - 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` - 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.
-
-- `response_format` - An object specifying the format that the model must output.
-  Setting to `{ "type": "json_schema", "json_schema": {...} }` enables
-  Structured Outputs which ensures the model will match your supplied JSON
-  schema. Learn more in the Structured Outputs guide. Setting to
-  `{ "type": "json_object" }` enables JSON mode, which ensures the message the
-  model generates is valid JSON.
-
-- `seed` - If specified, a best effort attempt is made 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` - Up to 4 sequences where the API will stop generating further tokens.
-
-- `stream` - If True, generates content as a stream. If False, generates content
-  as a single response. Defaults to False.
-
-- `stream_options` - Options for streaming response. Only set this when you set
-- `stream` - true.
-
-- `temperature` - 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.
-  It is generally recommended to alter this or top_p, but not both.
-  Defaults to the provider's default max_completion_tokens when the value is
-  None.
-
-- `top_p` - 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. Generally recommended to alter this or temperature, but not
-  both.
-
-- `tools` - 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.
-
-- `tool_choice` - Controls which (if any) tool is called by the
-  model. none means the model will not call any tool and instead generates a
-  message. auto means the model can pick between generating a message or
-  calling one or more tools. required means the model must call one or more
-  tools. Specifying a particular tool via
-  `{ "type": "function", "function": {"name": "my_function"} }`
-  forces the model to call that tool.
-  none is the default when no tools are present. auto is the default if tools
-  are present.
-
-- `parallel_tool_calls` - Whether to enable parallel function calling during tool
-  use.
-
-- `use_custom_keys` - Whether to use custom API keys or our unified API keys
-  with the backend provider.
-
-- `tags` - Arbitrary number of tags to classify this API query as needed. Helpful
-  for generally grouping queries across tasks and users, for logging purposes.
-
-- `drop_params` - Whether or not to drop unsupported OpenAI params by the
-  provider you’re using.
-
-- `region` - A string used to represent the region where the endpoint is
-  accessed. Only relevant for on-prem deployments with certain providers like
-  `vertex-ai`, `aws-bedrock` and `azure-ml`, where the endpoint is being
-  accessed through a specified region.
-
-- `log_query_body` - Whether to log the contents of the query json body.
-
-- `log_response_body` - Whether to log the contents of the response json body.
-
-- `return_full_completion` - If False, only return the message content
-  chat_completion.choices[0].message.content.strip(" ") from the OpenAI
-  return. Otherwise, the full response chat_completion is returned.
-  Defaults to False.
-
-- `cache` - If True, then the arguments will be stored in a local cache file, and
-  any future calls with identical arguments will read from the cache instead
-  of running the LLM query. This can help to save costs and also debug
-  multi-step LLM applications, while keeping early steps fixed.
-  This argument only has any effect when stream=False.
-
-- `extra_headers` - Additional "passthrough" headers for the request which are
-  provider-specific, and are not part of the OpenAI standard. They are handled
-  by the provider-specific API.
-
-- `extra_query` - Additional "passthrough" query parameters for the request which
-  are provider-specific, and are not part of the OpenAI standard. They are
-  handled by the provider-specific API.
-
-- `kwargs` - Additional "passthrough" JSON properties for the body of the
-  request, which are provider-specific, and are not part of the OpenAI
-  standard. They will be handled by the provider-specific API.
-
-
-**Raises**:
-
-- `UnifyError` - If the API key is missing.
-
 <a id="chat.clients.base._Client.system_message"></a>
 
 ---
@@ -1437,3 +1253,4 @@ Get the remaining credits left on your account.
 - `BadRequestError` - If there was an HTTP error.
 - `ValueError` - If there was an error parsing the JSON response.
 
+<a id="chat.clients.multi_llm"></a>

python/chat/clients/uni_llm.mdx

@@ -324,4 +324,4 @@ class AsyncUnify(_UniLLMClient)
 Class for interacting with the Unify chat completions endpoint in a synchronous
 manner.
 
-<a id="chat.clients.multi_llm"></a>
+<a id="chat.chatbot"></a>

python/evaluator.mdx

@@ -40,4 +40,4 @@ Evaluate the given response for this input prompt, with optional extra data.
   An Evaluation instance, containing the prompt, response, agent, score and
   optional extra data used during the evaluation.
 
-<a id="casting"></a>
+<a id="evaluation"></a>

python/logging.mdx

@@ -41,4 +41,4 @@ Wrap a local model callable with logging of the queries.
 
 - `requests.HTTPError` - If the API request fails.
 
-<a id="evaluation"></a>
+<a id="casting"></a>

python/types.mdx

@@ -124,4 +124,4 @@ Create Score instance.
 
   The pydantic Score instance, with associated value and class description
 
-<a id="evaluator"></a>
+<a id="__init__"></a>

python/utils/credits.mdx

@@ -28,4 +28,4 @@ Returns the credits remaining in the user account, in USD.
 
 - `ValueError` - If there was an HTTP error.
 
-<a id="utils.efficiency_benchmarks"></a>
+<a id="utils.datasets"></a>

python/utils/custom_api_keys.mdx

@@ -143,4 +143,4 @@ Get a list of custom API keys associated with the user's account.
   A list of dictionaries containing custom API key information.
   Each dictionary has 'name' and 'value' keys.
 
-<a id="utils.evaluators"></a>
+<a id="utils.default_prompts"></a>

python/utils/custom_endpoints.mdx

@@ -129,4 +129,4 @@ Get a list of custom endpoints for the authenticated user.
 
 - `requests.exceptions.RequestException` - If the API request fails.
 
-<a id="utils.supported_endpoints"></a>
+<a id="utils.helpers"></a>

python/utils/evaluations.mdx

@@ -99,4 +99,4 @@ Delete evaluations for a specific dataset, optionally filtered by endpoint and e
 
 - `requests.exceptions.RequestException` - If the API request fails.
 
-<a id="utils.helpers"></a>
+<a id="utils.custom_api_keys"></a>

python/utils/logging.mdx

@@ -124,4 +124,4 @@ Get query metrics for specified parameters.
 
   A dictionary containing the query metrics.
 
-<a id="utils.custom_api_keys"></a>
+<a id="utils.router_deployment"></a>

python/utils/supported_endpoints.mdx

@@ -94,4 +94,4 @@ provider.
 - `BadRequestError` - If there was an HTTP error.
 - `ValueError` - If there was an error parsing the JSON response.
 
-<a id="utils.router_deployment"></a>
+<a id="utils.custom_endpoints"></a>