initial pass at adding Heroku chat provider

litellm/__init__.py

@@ -216,6 +216,7 @@ nlp_cloud_key: Optional[str] = None
 novita_api_key: Optional[str] = None
 snowflake_key: Optional[str] = None
 nebius_key: Optional[str] = None
+heroku_key: Optional[str] = None
 common_cloud_provider_auth_params: dict = {
     "params": ["project", "region_name", "token"],
     "providers": ["vertex_ai", "bedrock", "watsonx", "azure", "vertex_ai_beta"],
@@ -1151,6 +1152,7 @@ from .llms.azure.azure import (
     AzureOpenAIAssistantsAPIConfig,
 )
 
+from .llms.heroku.chat.transformation import HerokuChatConfig
 from .llms.azure.chat.gpt_transformation import AzureOpenAIConfig
 from .llms.azure.completion.transformation import AzureOpenAITextConfig
 from .llms.hosted_vllm.chat.transformation import HostedVLLMChatConfig

litellm/constants.py

@@ -279,6 +279,7 @@ LITELLM_CHAT_PROVIDERS = [
     "dashscope",
     "moonshot",
     "v0",
+    "heroku",
 ]
 
 LITELLM_EMBEDDING_PROVIDERS_SUPPORTING_INPUT_ARRAY_OF_TOKENS = [

litellm/litellm_core_utils/get_llm_provider_logic.py

@@ -350,6 +350,8 @@ def get_llm_provider(  # noqa: PLR0915
         # bytez models
         elif model.startswith("bytez/"):
             custom_llm_provider = "bytez"
+        elif model.startswith("heroku/"):
+            custom_llm_provider = "heroku"
         if not custom_llm_provider:
             if litellm.suppress_debug_info is False:
                 print()  # noqa

litellm/llms/heroku/chat/transformation.py

@@ -0,0 +1,28 @@
+from typing import Optional, List, Union
+from litellm.llms.base_llm.chat.transformation import BaseConfig
+from litellm.types.llms.openai import AllMessageValues
+
+class HerokuChatConfig(BaseConfig):
+  def validate_environment(
+        self,
+        headers: dict,
+        model: str,
+        messages: List[AllMessageValues],
+        optional_params: dict,
+        litellm_params: dict,
+        api_key: Optional[str] = None,
+        api_base: Optional[str] = None,
+    ) -> dict:
+        headers.update({"Authorization": f"Bearer {api_key}"})
+        return headers
+  
+  def get_complete_url(
+        self,
+        api_base: Optional[str],
+        api_key: Optional[str],
+        model: str,
+        optional_params: dict,
+        litellm_params: dict,
+        stream: Optional[bool] = None,
+    ) -> str:
+        return f"{api_base}/v1/chat/completions"

litellm/main.py

@@ -151,6 +151,7 @@ from .llms.custom_llm import CustomLLM, custom_chat_llm_router
 from .llms.databricks.embed.handler import DatabricksEmbeddingHandler
 from .llms.deprecated_providers import aleph_alpha, palm
 from .llms.groq.chat.handler import GroqChatCompletion
+from .llms.heroku.chat.transformation import HerokuChatConfig
 from .llms.huggingface.embedding.handler import HuggingFaceEmbedding
 from .llms.nlp_cloud.chat.handler import completion as nlp_cloud_chat_completion
 from .llms.ollama.completion import handler as ollama
@@ -254,6 +255,7 @@ base_llm_http_handler = BaseLLMHTTPHandler()
 base_llm_aiohttp_handler = BaseLLMAIOHTTPHandler()
 sagemaker_chat_completion = SagemakerChatHandler()
 bytez_transformation = BytezChatConfig()
+heroku_transformation = HerokuChatConfig()
 ####### COMPLETION ENDPOINTS ################
 
 
@@ -1768,6 +1770,35 @@ def completion(  # type: ignore # noqa: PLR0915
                     additional_args={"headers": headers},
                 )
                 raise e
+        elif custom_llm_provider == "heroku":
+            try:
+                response = base_llm_http_handler.completion(
+                    model=model,
+                    messages=messages,
+                    headers=headers,
+                    model_response=model_response,
+                    api_key=api_key,
+                    api_base=api_base,
+                    acompletion=acompletion,
+                    logging_obj=logging,
+                    optional_params=optional_params,
+                    litellm_params=litellm_params,
+                    timeout=timeout,
+                    client=client,
+                    custom_llm_provider=custom_llm_provider,
+                    encoding=encoding,
+                    stream=stream,
+                    provider_config=provider_config,
+                )
+            except Exception as e:
+                logging.post_call(
+                    input=messages,
+                    api_key=api_key,
+                    original_response=str(e),
+                    additional_args={"headers": headers},
+                )
+                raise e
+
         elif custom_llm_provider == "xai":
             ## COMPLETION CALL
             try: