diff --git a/api/data_types/index.html b/api/data_types/index.html index 9fc8be47f..ad61a62b8 100644 --- a/api/data_types/index.html +++ b/api/data_types/index.html @@ -575,6 +575,54 @@ + + +
- Bases: BaseModel
+ Bases: BaseModel
Represents the output of a completion request to a model.
-
- Bases: BaseModel
+ Bases: BaseModel
- Bases: BaseModel
+ Bases: BaseModel
Response object for a synchronous prompt completion.
-
- Bases: BaseModel
+ Bases: BaseModel
Response object for a stream prompt completion task.
-
- Bases: BaseModel
+ Bases: BaseModel
Response object for creating a FineTune.
- +Request object for creating a FineTune.
@@ -1340,8 +1621,8 @@instance-attribute
fine_tune_id: str = Field(Ellipsis, description='ID of the created fine-tuning job.')
+¶
+
- The ID of the FineTune.
+ Identifier of base model to train from.
class-attribute
+ instance-attribute
+
+¶training_file: str = Field(
+ ...,
+ description="Path to file of training dataset. Dataset must be a csv with columns 'prompt' and 'response'.",
+)
+
Path to file of training dataset. Dataset must be a csv with columns 'prompt' and 'response'.
- Bases: BaseModel
Response object for retrieving a FineTune.
- + +class-attribute
+ instance-attribute
+
+¶
+validation_file: Optional[str] = Field(
+ default=None,
+ description="Path to file of validation dataset. Has the same format as training_file. If not provided, we will generate a split from the training dataset.",
+)
+
Path to file of validation dataset. Has the same format as training_file. If not provided, we will generate a split from the training dataset.
+class-attribute
+ instance-attribute
+
+
+¶
+hyperparameters: Optional[Dict[str, Any]] = Field(
+ default=None,
+ description="Hyperparameters to pass in to training job.",
+)
+
Hyperparameters to pass in to training job.
+class-attribute
+ instance-attribute
+
+
+¶suffix: Optional[str] = Field(
+ default=None,
+ description="Optional user-provided identifier suffix for the fine-tuned model.",
+)
+
Optional user-provided identifier suffix for the fine-tuned model.
+
+ Bases: BaseModel
Response object for creating a FineTune.
+ + + + +class-attribute
+ instance-attribute
+
+
+¶The ID of the FineTune.
+
+ Bases: BaseModel
Response object for retrieving a FineTune.
+ + + + +fine_tune_id: str = Field(Ellipsis, description='ID of the requested job.')
+
@@ -1429,7 +1887,7 @@
- status
+ status
@@ -1438,7 +1896,9 @@
¶
-status: BatchJobStatus = Field(Ellipsis, description='Status of the requested job.')
+
@@ -1463,21 +1923,20 @@
- ListFineTunesResponse
+ ListFineTunesResponse
¶
-
- Bases: BaseModel
+
+ Bases: BaseModel
Response object for listing FineTunes.
-
@@ -1493,7 +1952,7 @@
- jobs
+ jobs
@@ -1502,7 +1961,10 @@
¶
-jobs: List[GetFineTuneResponse] = Field(Ellipsis, description='List of fine-tuning jobs and their statuses.')
+jobs: List[GetFineTuneResponse] = Field(
+ ...,
+ description="List of fine-tuning jobs and their statuses.",
+)
@@ -1527,21 +1989,20 @@
- CancelFineTuneResponse
+ CancelFineTuneResponse
¶
-
- Bases: BaseModel
+
+ Bases: BaseModel
Response object for cancelling a FineTune.
-
@@ -1557,7 +2018,7 @@
- success
+ success
@@ -1566,7 +2027,9 @@ ¶
-success: bool = Field(Ellipsis, description='Whether cancellation was successful.')
+
@@ -1580,6 +2043,329 @@
+
+
+
+
+ GetLLMEndpointResponse
+
+
+¶
+
+
+
+
+ Bases: BaseModel
+
+
+ Response object for retrieving a Model.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ id
+
+
+
+ class-attribute
+ instance-attribute
+
+
+¶
+
+
+
+
+ The autogenerated ID of the Launch endpoint.
+
+
+
+
+
+
+
+
+
+ name
+
+
+
+ class-attribute
+ instance-attribute
+
+
+¶
+
+
+
+
+ The name of the Launch endpoint.
+
+
+
+
+
+
+
+
+
+ model_name
+
+
+
+ class-attribute
+ instance-attribute
+
+
+¶
+
+
+
+
+ The name of the model.
+
+
+
+
+
+
+
+
+
+ source
+
+
+
+ class-attribute
+ instance-attribute
+
+
+¶
+
+
+
+
+ The source of the model.
+
+
+
+
+
+
+
+
+
+ inference_framework
+
+
+
+ class-attribute
+ instance-attribute
+
+
+¶
+inference_framework: LLMInferenceFramework = Field(
+ description="The inference framework used by the endpoint."
+)
+
+
+
+
+ The inference framework used by the endpoint.
+
+
+
+
+
+
+
+
+
+ num_shards
+
+
+
+ class-attribute
+ instance-attribute
+
+
+¶
+
+
+
+
+ The number of shards.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ ListLLMEndpointsResponse
+
+
+¶
+
+
+
+
+ Bases: BaseModel
+
+
+ Response object for listing Models.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ model_endpoints
+
+
+
+ class-attribute
+ instance-attribute
+
+
+¶
+model_endpoints: List[GetLLMEndpointResponse] = Field(
+ ..., description="The list of LLM endpoints."
+)
+
+
+
+
+ A list of Models, represented as GetLLMEndpointResponse
s.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ DeleteLLMEndpointResponse
+
+
+¶
+
+
+
+
+ Bases: BaseModel
+
+
+ Response object for deleting a Model.
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ deleted
+
+
+
+ class-attribute
+ instance-attribute
+
+
+¶
+
+
+
+
+ Whether the deletion succeeded.
+
+
+
+
+
+
+
+
diff --git a/api/error_handling/index.html b/api/error_handling/index.html
index 11175dffc..c8caaf612 100644
--- a/api/error_handling/index.html
+++ b/api/error_handling/index.html
@@ -614,7 +614,7 @@ Error handling
- BadRequestError
+ BadRequestError
¶
@@ -622,15 +622,14 @@
-
- Bases: Exception
+
+ Bases: Exception
Corresponds to HTTP 400. Indicates that the request had inputs that were invalid. The user should not
attempt to retry the request without changing the inputs.
-
@@ -656,7 +655,7 @@
- UnauthorizedError
+ UnauthorizedError
¶
@@ -664,14 +663,13 @@
-
- Bases: Exception
+
+ Bases: Exception
Corresponds to HTTP 401. This means that no valid API key was provided.
-
@@ -697,7 +695,7 @@
- NotFoundError
+ NotFoundError
¶
@@ -705,8 +703,8 @@
-
- Bases: Exception
+
+ Bases: Exception
Corresponds to HTTP 404. This means that the resource (e.g. a Model, FineTune, etc.) could not be found.
@@ -715,7 +713,6 @@
the user does not have access to.
-
@@ -741,7 +738,7 @@
- RateLimitExceededError
+ RateLimitExceededError
¶
@@ -749,14 +746,13 @@
-
- Bases: Exception
+
+ Bases: Exception
Corresponds to HTTP 429. Too many requests hit the API too quickly. We recommend an exponential backoff for retries.
-
@@ -782,7 +778,7 @@
- ServerError
+ ServerError
¶
@@ -790,14 +786,13 @@
-
- Bases: Exception
+
+ Bases: Exception
Corresponds to HTTP 5xx errors on the server.
-
diff --git a/api/python_client/index.html b/api/python_client/index.html
index 3832ac7ea..37de9dc08 100644
--- a/api/python_client/index.html
+++ b/api/python_client/index.html
@@ -491,15 +491,15 @@
-
- list()
+
+ get()
-
- retrieve()
+
+ list()
@@ -514,6 +514,40 @@
+
+
+
+
+ Model
+
+
+
+
@@ -628,15 +662,15 @@
-
- list()
+
+ get()
-
- retrieve()
+
+ list()
@@ -651,6 +685,40 @@
+
+
+
+
+ Model
+
+
+
+
@@ -676,15 +744,15 @@ 🐍 Python Client API Reference
- Completion
+ Completion
¶
-
- Bases: APIEngine
+
+ Bases: APIEngine
Completion API. This API is used to generate text completions.
@@ -697,7 +765,6 @@
stream token responses or not.
-
@@ -710,12 +777,13 @@
+
- create
+ create
@@ -723,13 +791,25 @@
¶
-create(model: str, prompt: str, max_new_tokens: int = 20, temperature: float = 0.2, timeout: int = 10, stream: bool = False) -> Union[CompletionSyncV1Response, Iterator[CompletionStreamV1Response]]
+create(
+ model: str,
+ prompt: str,
+ max_new_tokens: int = 20,
+ temperature: float = 0.2,
+ timeout: int = 10,
+ stream: bool = False,
+) -> Union[
+ CompletionSyncV1Response,
+ Iterator[CompletionStreamV1Response],
+]
Creates a completion for the provided prompt and parameters synchronously.
+
+
Parameters:
@@ -833,6 +913,8 @@
+
+
Returns: