feat - add cancel_fine_tuning_job

litellm/fine_tuning/main.py

@@ -180,3 +180,87 @@ def create_fine_tuning_job(
         return response
     except Exception as e:
         raise e
+
+
+def cancel_fine_tuning_job(
+    fine_tuning_job_id: str,
+    custom_llm_provider: Literal["openai"] = "openai",
+    extra_headers: Optional[Dict[str, str]] = None,
+    extra_body: Optional[Dict[str, str]] = None,
+    **kwargs,
+) -> Union[FineTuningJob, Coroutine[Any, Any, FineTuningJob]]:
+    """
+    Creates a fine-tuning job which begins the process of creating a new model from a given dataset.
+
+    Response includes details of the enqueued job including job status and the name of the fine-tuned models once complete
+
+    """
+    try:
+        optional_params = GenericLiteLLMParams(**kwargs)
+        if custom_llm_provider == "openai":
+
+            # for deepinfra/perplexity/anyscale/groq we check in get_llm_provider and pass in the api base from there
+            api_base = (
+                optional_params.api_base
+                or litellm.api_base
+                or os.getenv("OPENAI_API_BASE")
+                or "https://api.openai.com/v1"
+            )
+            organization = (
+                optional_params.organization
+                or litellm.organization
+                or os.getenv("OPENAI_ORGANIZATION", None)
+                or None  # default - https://github.com/openai/openai-python/blob/284c1799070c723c6a553337134148a7ab088dd8/openai/util.py#L105
+            )
+            # set API KEY
+            api_key = (
+                optional_params.api_key
+                or litellm.api_key  # for deepinfra/perplexity/anyscale we check in get_llm_provider and pass in the api key from there
+                or litellm.openai_key
+                or os.getenv("OPENAI_API_KEY")
+            )
+            ### TIMEOUT LOGIC ###
+            timeout = (
+                optional_params.timeout or kwargs.get("request_timeout", 600) or 600
+            )
+            # set timeout for 10 minutes by default
+
+            if (
+                timeout is not None
+                and isinstance(timeout, httpx.Timeout)
+                and supports_httpx_timeout(custom_llm_provider) == False
+            ):
+                read_timeout = timeout.read or 600
+                timeout = read_timeout  # default 10 min timeout
+            elif timeout is not None and not isinstance(timeout, httpx.Timeout):
+                timeout = float(timeout)  # type: ignore
+            elif timeout is None:
+                timeout = 600.0
+
+            _is_async = kwargs.pop("acreate_fine_tuning_job", False) is True
+
+            response = openai_fine_tuning_instance.cancel_fine_tuning_job(
+                api_base=api_base,
+                api_key=api_key,
+                organization=organization,
+                fine_tuning_job_id=fine_tuning_job_id,
+                timeout=timeout,
+                max_retries=optional_params.max_retries,
+                _is_async=_is_async,
+            )
+        else:
+            raise litellm.exceptions.BadRequestError(
+                message="LiteLLM doesn't support {} for 'create_batch'. Only 'openai' is supported.".format(
+                    custom_llm_provider
+                ),
+                model="n/a",
+                llm_provider=custom_llm_provider,
+                response=httpx.Response(
+                    status_code=400,
+                    content="Unsupported provider",
+                    request=httpx.Request(method="create_thread", url="https://github.com/BerriAI/litellm"),  # type: ignore
+                ),
+            )
+        return response
+    except Exception as e:
+        raise e

litellm/llms/openai_fine_tuning/openai.py

@@ -94,3 +94,53 @@ class OpenAIFineTuningAPI(BaseLLM):
         )
         response = openai_client.fine_tuning.jobs.create(**create_fine_tuning_job_data)
         return response
+
+    async def acancel_fine_tuning_job(
+        self,
+        fine_tuning_job_id: str,
+        openai_client: AsyncOpenAI,
+    ) -> FineTuningJob:
+        response = await openai_client.fine_tuning.jobs.cancel(
+            fine_tuning_job_id=fine_tuning_job_id
+        )
+        return response
+
+    def cancel_fine_tuning_job(
+        self,
+        _is_async: bool,
+        fine_tuning_job_id: str,
+        api_key: Optional[str],
+        api_base: Optional[str],
+        timeout: Union[float, httpx.Timeout],
+        max_retries: Optional[int],
+        organization: Optional[str],
+        client: Optional[Union[OpenAI, AsyncOpenAI]] = None,
+    ):
+        openai_client: Optional[Union[OpenAI, AsyncOpenAI]] = self.get_openai_client(
+            api_key=api_key,
+            api_base=api_base,
+            timeout=timeout,
+            max_retries=max_retries,
+            organization=organization,
+            client=client,
+            _is_async=_is_async,
+        )
+        if openai_client is None:
+            raise ValueError(
+                "OpenAI client is not initialized. Make sure api_key is passed or OPENAI_API_KEY is set in the environment."
+            )
+
+        if _is_async is True:
+            if not isinstance(openai_client, AsyncOpenAI):
+                raise ValueError(
+                    "OpenAI client is not an instance of AsyncOpenAI. Make sure you passed an AsyncOpenAI client."
+                )
+            return self.acancel_fine_tuning_job(  # type: ignore
+                fine_tuning_job_id=fine_tuning_job_id,
+                openai_client=openai_client,
+            )
+        verbose_logger.debug("canceling fine tuning job, args= %s", fine_tuning_job_id)
+        response = openai_client.fine_tuning.jobs.cancel(
+            fine_tuning_job_id=fine_tuning_job_id
+        )
+        return response