SDK regeneration

.fern/metadata.json

@@ -1,7 +1,7 @@
 {
   "cliVersion": "5.55.0",
   "generatorName": "fernapi/fern-python-sdk",
-  "generatorVersion": "5.29.3",
+  "generatorVersion": "5.39.3",
   "generatorConfig": {
     "tcp_keepalive": {
       "enabled": true,
@@ -100,10 +100,10 @@
       }
     ]
   },
-  "originGitCommit": "2bfdfa67e2f98426451cf784a8f798e6c9272b9b",
+  "originGitCommit": "90d3d3227088a6b843724a54b8779bab1aa6787e",
   "originGitCommitIsDirty": false,
   "invokedBy": "ci",
-  "requestedVersion": "7.2.0",
+  "requestedVersion": "7.3.0",
   "ciProvider": "github",
-  "sdkVersion": "7.2.0"
+  "sdkVersion": "7.3.0"
 }

pyproject.toml

@@ -1,10 +1,12 @@
 [project]
 name = "cohere"
 dynamic = ["version"]
+license = "MIT"
+license-files = ["LICENSE"]
 
 [tool.poetry]
 name = "cohere"
-version = "7.2.0"
+version = "7.3.0"
 description = ""
 readme = "README.md"
 authors = []
@@ -26,8 +28,7 @@ classifiers = [
     "Operating System :: POSIX :: Linux",
     "Operating System :: Microsoft :: Windows",
     "Topic :: Software Development :: Libraries :: Python Modules",
-    "Typing :: Typed",
-    "License :: OSI Approved :: MIT License"
+    "Typing :: Typed"
 ]
 packages = [
     { include = "cohere", from = "src"}

reference.md

@@ -1510,8 +1510,8 @@ client.embed(
         "hello",
         "goodbye"
     ],
-    model="embed-v4.0",
-    input_type="classification",
+    model="embed-v5.0-fast",
+    input_type="search_document",
 )
 
 ```
@@ -3025,8 +3025,8 @@ client.v2.embed(
         "hello",
         "goodbye"
     ],
-    model="embed-v4.0",
-    input_type="classification",
+    model="embed-v5.0-fast",
+    input_type="search_document",
     embedding_types=[
         "float"
     ],
@@ -3107,7 +3107,7 @@ For **Embed v4.0 and newer** models, there is no limit on the number of images p
 **output_dimension:** `typing.Optional[int]` 
 
 The number of dimensions of the output embedding. This is only available for `embed-v4` and newer models.
-Possible values are `256`, `512`, `1024`, and `1536`. The default is `1536`.
+For supported dimensions, please refer to the [Embed models](https://docs.cohere.com/docs/cohere-embed) page.
 
 </dd>
 </dl>
@@ -3193,7 +3193,7 @@ This endpoint takes in a query and a list of texts and produces an ordered array
 <dd>
 
 ```python
-from cohere import Client
+from cohere import Client, RerankRelevantSpans
 from cohere.environment import ClientEnvironment
 
 client = Client(
@@ -3202,16 +3202,21 @@ client = Client(
 )
 
 client.v2.rerank(
-    model="rerank-v4.0-pro",
+    model="rerank-v5.0-pro",
     query="What is the capital of the United States?",
     documents=[
         "Carson City is the capital city of the American state of Nevada.",
         "The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean. Its capital is Saipan.",
         "Capitalization or capitalisation in English grammar is the use of a capital letter at the start of a word. English usage varies from capitalization in other languages.",
         "Washington, D.C. (also known as simply Washington or D.C., and officially as the District of Columbia) is the capital of the United States. It is a federal district.",
-        "Capital punishment has existed in the United States since beforethe United States was a country. As of 2017, capital punishment is legal in 30 of the 50 states."
+        "Capital gains are profits from the sale of an asset such as stocks or real estate. In the United States, long-term capital gains are taxed at lower rates than ordinary income."
     ],
     top_n=3,
+    relevant_spans=RerankRelevantSpans(
+        mode="enabled",
+        threshold=0.1,
+        max_spans=3,
+    ),
 )
 
 ```
@@ -3228,7 +3233,7 @@ client.v2.rerank(
 <dl>
 <dd>
 
-**model:** `str` — The identifier of the model to use, eg `rerank-v3.5`.
+**model:** `str` — The identifier of the model to use, eg `rerank-v5.0-pro`.
 
 </dd>
 </dl>
@@ -3275,6 +3280,14 @@ For optimal performance we recommend against sending more than 1,000 documents i
 <dl>
 <dd>
 
+**relevant_spans:** `typing.Optional[RerankRelevantSpans]` 
+
+</dd>
+</dl>
+
+<dl>
+<dd>
+
 **priority:** `typing.Optional[int]` — Controls how early the request is handled. Lower numbers indicate higher priority (default: 0, the highest). When the system is under load, higher-priority requests are processed first and are the least likely to be dropped.
 
 </dd>

src/cohere/__init__.py

@@ -196,6 +196,9 @@
         ParseTextBlock,
         ParseTextContentBlock,
         RerankDocument,
+        RerankRelevantSpanResponse,
+        RerankRelevantSpans,
+        RerankRelevantSpansMode,
         RerankRequestDocumentsItem,
         RerankResponse,
         RerankResponseResultsItem,
@@ -572,6 +575,9 @@
     "ParseTextBlock": ".types",
     "ParseTextContentBlock": ".types",
     "RerankDocument": ".types",
+    "RerankRelevantSpanResponse": ".types",
+    "RerankRelevantSpans": ".types",
+    "RerankRelevantSpansMode": ".types",
     "RerankRequestDocumentsItem": ".types",
     "RerankResponse": ".types",
     "RerankResponseResultsItem": ".types",
@@ -934,6 +940,9 @@ def __dir__():
     "ParseTextBlock",
     "ParseTextContentBlock",
     "RerankDocument",
+    "RerankRelevantSpanResponse",
+    "RerankRelevantSpans",
+    "RerankRelevantSpansMode",
     "RerankRequestDocumentsItem",
     "RerankResponse",
     "RerankResponseResultsItem",

src/cohere/base_client.py

@@ -123,7 +123,7 @@ def __init__(
         base_url: typing.Optional[str] = None,
         environment: ClientEnvironment = ClientEnvironment.PRODUCTION,
         client_name: typing.Optional[str] = None,
-        token: typing.Optional[typing.Union[str, typing.Callable[[], str]]] = os.getenv("CO_API_KEY"),
+        token: typing.Optional[typing.Union[str, typing.Callable[[], str]]] = None,
         headers: typing.Optional[typing.Dict[str, str]] = None,
         timeout: typing.Optional[float] = None,
         max_retries: typing.Optional[int] = None,
@@ -135,6 +135,7 @@ def __init__(
     ):
         _defaulted_timeout = timeout if timeout is not None else 300 if httpx_client is None else None
         _defaulted_max_retries = max_retries if max_retries is not None else 2
+        token = token if token is not None else os.getenv("CO_API_KEY")
         if token is None:
             raise ApiError(body="The client must be instantiated be either passing in token or setting CO_API_KEY")
         self._client_wrapper = SyncClientWrapper(
@@ -1147,8 +1148,8 @@ def embed(
         )
         client.embed(
             texts=["hello", "goodbye"],
-            model="embed-v4.0",
-            input_type="classification",
+            model="embed-v5.0-fast",
+            input_type="search_document",
         )
         """
         _response = self._raw_client.embed(
@@ -1691,7 +1692,7 @@ def __init__(
         base_url: typing.Optional[str] = None,
         environment: ClientEnvironment = ClientEnvironment.PRODUCTION,
         client_name: typing.Optional[str] = None,
-        token: typing.Optional[typing.Union[str, typing.Callable[[], str]]] = os.getenv("CO_API_KEY"),
+        token: typing.Optional[typing.Union[str, typing.Callable[[], str]]] = None,
         headers: typing.Optional[typing.Dict[str, str]] = None,
         async_token: typing.Optional[typing.Callable[[], typing.Awaitable[str]]] = None,
         timeout: typing.Optional[float] = None,
@@ -1704,6 +1705,7 @@ def __init__(
     ):
         _defaulted_timeout = timeout if timeout is not None else 300 if httpx_client is None else None
         _defaulted_max_retries = max_retries if max_retries is not None else 2
+        token = token if token is not None else os.getenv("CO_API_KEY")
         if token is None:
             raise ApiError(body="The client must be instantiated be either passing in token or setting CO_API_KEY")
         self._client_wrapper = AsyncClientWrapper(
@@ -2747,8 +2749,8 @@ async def embed(
         async def main() -> None:
             await client.embed(
                 texts=["hello", "goodbye"],
-                model="embed-v4.0",
-                input_type="classification",
+                model="embed-v5.0-fast",
+                input_type="search_document",
             )
 
 

src/cohere/core/client_wrapper.py

@@ -31,21 +31,22 @@ def __init__(
         self._max_stream_reconnection_attempts = max_stream_reconnection_attempts
         self._logging = logging
 
-    def get_headers(self) -> typing.Dict[str, str]:
+    def get_headers(self, *, include_token: bool = True) -> typing.Dict[str, str]:
         import platform
 
         headers: typing.Dict[str, str] = {
-            "User-Agent": "cohere/7.2.0",
+            "User-Agent": "cohere/7.3.0",
             "X-Fern-Language": "Python",
             "X-Fern-Runtime": f"python/{platform.python_version()}",
             "X-Fern-Platform": f"{platform.system().lower()}/{platform.release()}",
             "X-Fern-SDK-Name": "cohere",
-            "X-Fern-SDK-Version": "7.2.0",
+            "X-Fern-SDK-Version": "7.3.0",
             **(self.get_custom_headers() or {}),
         }
         if self._client_name is not None:
             headers["X-Client-Name"] = self._client_name
-        headers["Authorization"] = f"Bearer {self._get_token()}"
+        if include_token:
+            headers["Authorization"] = f"Bearer {self._get_token()}"
         return headers
 
     def _get_token(self) -> str:
@@ -148,7 +149,7 @@ def __init__(
         )
 
     async def async_get_headers(self) -> typing.Dict[str, str]:
-        headers = self.get_headers()
+        headers = self.get_headers(include_token=self._async_token is None)
         if self._async_token is not None:
             token = await self._async_token()
             headers["Authorization"] = f"Bearer {token}"