🌿 Fern Regeneration -- September 19, 2024

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cohere"
-version = "5.9.3"
+version = "5.9.4"
 description = ""
 readme = "README.md"
 authors = []

reference.md

@@ -2858,17 +2858,14 @@ If you want to learn more how to use the embedding model, have a look at the [Se
 <dd>
 
 ```python
-from cohere import Client, ImageEmbedRequestV2
+from cohere import Client
 
 client = Client(
     client_name="YOUR_CLIENT_NAME",
     token="YOUR_TOKEN",
 )
 client.v2.embed(
-    request=ImageEmbedRequestV2(
-        images=["string"],
-        model="string",
-    ),
+    model="model",
 )
 
 ```
@@ -2885,7 +2882,80 @@ client.v2.embed(
 <dl>
 <dd>
 
-**request:** `EmbedRequestV2` 
+**model:** `str` 
+
+Defaults to embed-english-v2.0
+
+The identifier of the model. Smaller "light" models are faster, while larger models will perform better. [Custom models](/docs/training-custom-models) can also be supplied with their full ID.
+
+Available models and corresponding embedding dimensions:
+
+* `embed-english-v3.0`  1024
+* `embed-multilingual-v3.0`  1024
+* `embed-english-light-v3.0`  384
+* `embed-multilingual-light-v3.0`  384
+
+* `embed-english-v2.0`  4096
+* `embed-english-light-v2.0`  1024
+* `embed-multilingual-v2.0`  768
+
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**texts:** `typing.Optional[typing.Sequence[str]]` — An array of strings for the model to embed. Maximum number of texts per call is `96`. We recommend reducing the length of each text to be under `512` tokens for optimal quality.
+
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**images:** `typing.Optional[typing.Sequence[str]]` 
+
+An array of image data URIs for the model to embed. Maximum number of images per call is `1`.
+
+The image must be a valid [data URI](https://developer.mozilla.org/en-US/docs/Web/URI/Schemes/data). The image must be in either `image/jpeg` or `image/png` format and has a maximum size of 5MB.
+
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**input_type:** `typing.Optional[EmbedInputType]` 
+
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**embedding_types:** `typing.Optional[typing.Sequence[EmbeddingType]]` 
+
+Specifies the types of embeddings you want to get back. Not required and default is None, which returns the Embed Floats response type. Can be one or more of the following types.
+
+* `"float"`: Use this when you want to get back the default float embeddings. Valid for all models.
+* `"int8"`: Use this when you want to get back signed int8 embeddings. Valid for only v3 models.
+* `"uint8"`: Use this when you want to get back unsigned int8 embeddings. Valid for only v3 models.
+* `"binary"`: Use this when you want to get back signed binary embeddings. Valid for only v3 models.
+* `"ubinary"`: Use this when you want to get back unsigned binary embeddings. Valid for only v3 models.
+
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**truncate:** `typing.Optional[V2EmbedRequestTruncate]` 
+
+One of `NONE|START|END` to specify how the API will handle inputs longer than the maximum token length.
+
+Passing `START` will discard the start of the input. `END` will discard the end of the input. In both cases, input is discarded until the remaining input is exactly the maximum input token length for the model.
+
+If `NONE` is selected, when the input exceeds the maximum input token length an error will be returned.
 
 </dd>
 </dl>

src/cohere/__init__.py

@@ -80,7 +80,6 @@
     CitationStartEventDelta,
     CitationStartEventDeltaMessage,
     CitationStartStreamedChatResponseV2,
-    ClassificationEmbedRequestV2,
     ClassifyDataMetrics,
     ClassifyExample,
     ClassifyRequestTruncate,
@@ -89,7 +88,6 @@
     ClassifyResponseClassificationsItemClassificationType,
     ClassifyResponseClassificationsItemLabelsValue,
     ClientClosedRequestErrorBody,
-    ClusteringEmbedRequestV2,
     CompatibleEndpoint,
     Connector,
     ConnectorAuthStatus,
@@ -120,7 +118,6 @@
     EmbedJobStatus,
     EmbedJobTruncate,
     EmbedRequestTruncate,
-    EmbedRequestV2,
     EmbedResponse,
     EmbeddingType,
     EmbeddingsByTypeEmbedResponse,
@@ -141,8 +138,6 @@
     Generation,
     GetConnectorResponse,
     GetModelResponse,
-    ImageEmbedRequestV2,
-    Images,
     JsonObjectResponseFormat,
     JsonObjectResponseFormatV2,
     JsonResponseFormat,
@@ -169,9 +164,7 @@
     RerankerDataMetrics,
     ResponseFormat,
     ResponseFormatV2,
-    SearchDocumentEmbedRequestV2,
     SearchQueriesGenerationStreamedChatResponse,
-    SearchQueryEmbedRequestV2,
     SearchResultsStreamedChatResponse,
     SingleGeneration,
     SingleGenerationInStream,
@@ -200,8 +193,6 @@
     TextResponseFormatV2,
     TextSystemMessageContentItem,
     TextToolContent,
-    Texts,
-    TextsTruncate,
     TokenizeResponse,
     TooManyRequestsErrorBody,
     Tool,
@@ -267,6 +258,7 @@
     V2ChatRequestSafetyMode,
     V2ChatStreamRequestDocumentsItem,
     V2ChatStreamRequestSafetyMode,
+    V2EmbedRequestTruncate,
     V2RerankRequestDocumentsItem,
     V2RerankResponse,
     V2RerankResponseResultsItem,
@@ -359,7 +351,6 @@
     "CitationStartEventDelta",
     "CitationStartEventDeltaMessage",
     "CitationStartStreamedChatResponseV2",
-    "ClassificationEmbedRequestV2",
     "ClassifyDataMetrics",
     "ClassifyExample",
     "ClassifyRequestTruncate",
@@ -372,7 +363,6 @@
     "ClientClosedRequestErrorBody",
     "ClientEnvironment",
     "ClientV2",
-    "ClusteringEmbedRequestV2",
     "CompatibleEndpoint",
     "Connector",
     "ConnectorAuthStatus",
@@ -409,7 +399,6 @@
     "EmbedJobStatus",
     "EmbedJobTruncate",
     "EmbedRequestTruncate",
-    "EmbedRequestV2",
     "EmbedResponse",
     "EmbeddingType",
     "EmbeddingsByTypeEmbedResponse",
@@ -432,8 +421,6 @@
     "Generation",
     "GetConnectorResponse",
     "GetModelResponse",
-    "ImageEmbedRequestV2",
-    "Images",
     "InternalServerError",
     "JsonObjectResponseFormat",
     "JsonObjectResponseFormatV2",
@@ -464,9 +451,7 @@
     "ResponseFormat",
     "ResponseFormatV2",
     "SagemakerClient",
-    "SearchDocumentEmbedRequestV2",
     "SearchQueriesGenerationStreamedChatResponse",
-    "SearchQueryEmbedRequestV2",
     "SearchResultsStreamedChatResponse",
     "ServiceUnavailableError",
     "SingleGeneration",
@@ -496,8 +481,6 @@
     "TextResponseFormatV2",
     "TextSystemMessageContentItem",
     "TextToolContent",
-    "Texts",
-    "TextsTruncate",
     "TokenizeResponse",
     "TooManyRequestsError",
     "TooManyRequestsErrorBody",
@@ -536,6 +519,7 @@
     "V2ChatRequestSafetyMode",
     "V2ChatStreamRequestDocumentsItem",
     "V2ChatStreamRequestSafetyMode",
+    "V2EmbedRequestTruncate",
     "V2RerankRequestDocumentsItem",
     "V2RerankResponse",
     "V2RerankResponseResultsItem",

src/cohere/core/client_wrapper.py

@@ -24,7 +24,7 @@ def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "cohere",
-            "X-Fern-SDK-Version": "5.9.3",
+            "X-Fern-SDK-Version": "5.9.4",
         }
         if self._client_name is not None:
             headers["X-Client-Name"] = self._client_name

src/cohere/finetuning/__init__.py

@@ -13,6 +13,7 @@
     ListEventsResponse,
     ListFinetunedModelsResponse,
     ListTrainingStepMetricsResponse,
+    LoraTargetModules,
     Settings,
     Status,
     Strategy,
@@ -33,6 +34,7 @@
     "ListEventsResponse",
     "ListFinetunedModelsResponse",
     "ListTrainingStepMetricsResponse",
+    "LoraTargetModules",
     "Settings",
     "Status",
     "Strategy",

src/cohere/finetuning/finetuning/__init__.py

@@ -12,6 +12,7 @@
     ListEventsResponse,
     ListFinetunedModelsResponse,
     ListTrainingStepMetricsResponse,
+    LoraTargetModules,
     Settings,
     Status,
     Strategy,
@@ -32,6 +33,7 @@
     "ListEventsResponse",
     "ListFinetunedModelsResponse",
     "ListTrainingStepMetricsResponse",
+    "LoraTargetModules",
     "Settings",
     "Status",
     "Strategy",

src/cohere/finetuning/finetuning/types/__init__.py

@@ -11,6 +11,7 @@
 from .list_events_response import ListEventsResponse
 from .list_finetuned_models_response import ListFinetunedModelsResponse
 from .list_training_step_metrics_response import ListTrainingStepMetricsResponse
+from .lora_target_modules import LoraTargetModules
 from .settings import Settings
 from .status import Status
 from .strategy import Strategy
@@ -30,6 +31,7 @@
     "ListEventsResponse",
     "ListFinetunedModelsResponse",
     "ListTrainingStepMetricsResponse",
+    "LoraTargetModules",
     "Settings",
     "Status",
     "Strategy",

src/cohere/finetuning/finetuning/types/base_model.py

@@ -30,7 +30,7 @@ class BaseModel(UncheckedBaseModel):
 
     strategy: typing.Optional[Strategy] = pydantic.Field(default=None)
     """
-    The fine-tuning strategy.
+    Deprecated: The fine-tuning strategy.
     """
 
     if IS_PYDANTIC_V2:

src/cohere/finetuning/finetuning/types/hyperparameters.py

@@ -3,6 +3,7 @@
 from ....core.unchecked_base_model import UncheckedBaseModel
 import typing
 import pydantic
+from .lora_target_modules import LoraTargetModules
 from ....core.pydantic_utilities import IS_PYDANTIC_V2
 
 
@@ -38,6 +39,23 @@ class Hyperparameters(UncheckedBaseModel):
     The learning rate to be used during training.
     """
 
+    lora_alpha: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Controls the scaling factor for LoRA updates. Higher values make the
+    updates more impactful.
+    """
+
+    lora_rank: typing.Optional[int] = pydantic.Field(default=None)
+    """
+    Specifies the rank for low-rank matrices. Lower ranks reduce parameters
+    but may limit model flexibility.
+    """
+
+    lora_target_modules: typing.Optional[LoraTargetModules] = pydantic.Field(default=None)
+    """
+    The combination of LoRA modules to target.
+    """
+
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
     else:

src/cohere/finetuning/finetuning/types/lora_target_modules.py

@@ -0,0 +1,13 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+LoraTargetModules = typing.Union[
+    typing.Literal[
+        "LORA_TARGET_MODULES_UNSPECIFIED",
+        "LORA_TARGET_MODULES_QV",
+        "LORA_TARGET_MODULES_QKVO",
+        "LORA_TARGET_MODULES_QKVO_FFN",
+    ],
+    typing.Any,
+]