feat(proxy_cli.py): add new 'log_config' cli param (#6352)

* feat(proxy_cli.py): add new 'log_config' cli param

Allows passing logging.conf to uvicorn on startup

* docs(cli.md): add logging conf to uvicorn cli docs

* fix(get_llm_provider_logic.py): fix default api base for litellm_proxy

Fixes https://github.com/BerriAI/litellm/issues/6332

* feat(openai_like/embedding): Add support for jina ai embeddings

Closes https://github.com/BerriAI/litellm/issues/6337

* docs(deploy.md): update entrypoint.sh filepath post-refactor

Fixes outdated docs

* feat(prometheus.py): emit time_to_first_token metric on prometheus

Closes https://github.com/BerriAI/litellm/issues/6334

* fix(prometheus.py): only emit time to first token metric if stream is True

enables more accurate ttft usage

* test: handle vertex api instability

* fix(get_llm_provider_logic.py): fix import

* fix(openai.py): fix deepinfra default api base

* fix(anthropic/transformation.py): remove anthropic beta header (#6361)

litellm/llms/openai_like/embedding/handler.py

@@ -0,0 +1,190 @@
+# What is this?
+## Handler file for OpenAI-like endpoints.
+## Allows jina ai embedding calls - which don't allow 'encoding_format' in payload.
+
+import copy
+import json
+import os
+import time
+import types
+from enum import Enum
+from functools import partial
+from typing import Any, Callable, List, Literal, Optional, Tuple, Union
+
+import httpx  # type: ignore
+import requests  # type: ignore
+
+import litellm
+from litellm.litellm_core_utils.core_helpers import map_finish_reason
+from litellm.llms.custom_httpx.http_handler import (
+    AsyncHTTPHandler,
+    HTTPHandler,
+    get_async_httpx_client,
+)
+from litellm.utils import EmbeddingResponse
+
+from ..common_utils import OpenAILikeError
+
+
+class OpenAILikeEmbeddingHandler:
+    def __init__(self, **kwargs):
+        pass
+
+    def _validate_environment(
+        self,
+        api_key: Optional[str],
+        api_base: Optional[str],
+        endpoint_type: Literal["chat_completions", "embeddings"],
+        headers: Optional[dict],
+    ) -> Tuple[str, dict]:
+        if api_key is None and headers is None:
+            raise OpenAILikeError(
+                status_code=400,
+                message="Missing API Key - A call is being made to LLM Provider but no key is set either in the environment variables ({LLM_PROVIDER}_API_KEY) or via params",
+            )
+
+        if api_base is None:
+            raise OpenAILikeError(
+                status_code=400,
+                message="Missing API Base - A call is being made to LLM Provider but no api base is set either in the environment variables ({LLM_PROVIDER}_API_KEY) or via params",
+            )
+
+        if headers is None:
+            headers = {
+                "Content-Type": "application/json",
+            }
+
+        if api_key is not None:
+            headers.update({"Authorization": "Bearer {}".format(api_key)})
+
+        if endpoint_type == "chat_completions":
+            api_base = "{}/chat/completions".format(api_base)
+        elif endpoint_type == "embeddings":
+            api_base = "{}/embeddings".format(api_base)
+        return api_base, headers
+
+    async def aembedding(
+        self,
+        input: list,
+        data: dict,
+        model_response: EmbeddingResponse,
+        timeout: float,
+        api_key: str,
+        api_base: str,
+        logging_obj,
+        headers: dict,
+        client=None,
+    ) -> EmbeddingResponse:
+        response = None
+        try:
+            if client is None or isinstance(client, AsyncHTTPHandler):
+                self.async_client = AsyncHTTPHandler(timeout=timeout)  # type: ignore
+            else:
+                self.async_client = client
+
+            try:
+                response = await self.async_client.post(
+                    api_base,
+                    headers=headers,
+                    data=json.dumps(data),
+                )  # type: ignore
+
+                response.raise_for_status()
+
+                response_json = response.json()
+            except httpx.HTTPStatusError as e:
+                raise OpenAILikeError(
+                    status_code=e.response.status_code,
+                    message=response.text if response else str(e),
+                )
+            except httpx.TimeoutException:
+                raise OpenAILikeError(
+                    status_code=408, message="Timeout error occurred."
+                )
+            except Exception as e:
+                raise OpenAILikeError(status_code=500, message=str(e))
+
+            ## LOGGING
+            logging_obj.post_call(
+                input=input,
+                api_key=api_key,
+                additional_args={"complete_input_dict": data},
+                original_response=response_json,
+            )
+            return EmbeddingResponse(**response_json)
+        except Exception as e:
+            ## LOGGING
+            logging_obj.post_call(
+                input=input,
+                api_key=api_key,
+                original_response=str(e),
+            )
+            raise e
+
+    def embedding(
+        self,
+        model: str,
+        input: list,
+        timeout: float,
+        logging_obj,
+        api_key: Optional[str],
+        api_base: Optional[str],
+        optional_params: dict,
+        model_response: Optional[litellm.utils.EmbeddingResponse] = None,
+        client=None,
+        aembedding=None,
+        headers: Optional[dict] = None,
+    ) -> EmbeddingResponse:
+        api_base, headers = self._validate_environment(
+            api_base=api_base,
+            api_key=api_key,
+            endpoint_type="embeddings",
+            headers=headers,
+        )
+        model = model
+        data = {"model": model, "input": input, **optional_params}
+
+        ## LOGGING
+        logging_obj.pre_call(
+            input=input,
+            api_key=api_key,
+            additional_args={"complete_input_dict": data, "api_base": api_base},
+        )
+
+        if aembedding is True:
+            return self.aembedding(data=data, input=input, logging_obj=logging_obj, model_response=model_response, api_base=api_base, api_key=api_key, timeout=timeout, client=client, headers=headers)  # type: ignore
+        if client is None or isinstance(client, AsyncHTTPHandler):
+            self.client = HTTPHandler(timeout=timeout)  # type: ignore
+        else:
+            self.client = client
+
+        ## EMBEDDING CALL
+        try:
+            response = self.client.post(
+                api_base,
+                headers=headers,
+                data=json.dumps(data),
+            )  # type: ignore
+
+            response.raise_for_status()  # type: ignore
+
+            response_json = response.json()  # type: ignore
+        except httpx.HTTPStatusError as e:
+            raise OpenAILikeError(
+                status_code=e.response.status_code,
+                message=e.response.text,
+            )
+        except httpx.TimeoutException:
+            raise OpenAILikeError(status_code=408, message="Timeout error occurred.")
+        except Exception as e:
+            raise OpenAILikeError(status_code=500, message=str(e))
+
+        ## LOGGING
+        logging_obj.post_call(
+            input=input,
+            api_key=api_key,
+            additional_args={"complete_input_dict": data},
+            original_response=response_json,
+        )
+
+        return litellm.EmbeddingResponse(**response_json)