fix(http_handler.py): allow setting ca bundle path

Author: krrishdholakia

litellm/__init__.py

@@ -102,6 +102,7 @@
 }
 use_client: bool = False
 ssl_verify: bool = True
+ssl_certificate: Optional[str] = None
 disable_streaming_logging: bool = False
 in_memory_llm_clients_cache: dict = {}
 ### GUARDRAILS ###

litellm/llms/custom_httpx/http_handler.py

@@ -12,15 +12,16 @@ def __init__(
         timeout: Optional[Union[float, httpx.Timeout]] = None,
         concurrent_limit=1000,
     ):
-        sync_proxy_mounts = None
         async_proxy_mounts = None
         # Check if the HTTP_PROXY and HTTPS_PROXY environment variables are set and use them accordingly.
         http_proxy = os.getenv("HTTP_PROXY", None)
         https_proxy = os.getenv("HTTPS_PROXY", None)
         no_proxy = os.getenv("NO_PROXY", None)
         ssl_verify = bool(os.getenv("SSL_VERIFY", litellm.ssl_verify))
+        cert = os.getenv(
+            "SSL_CERTIFICATE", litellm.ssl_certificate
+        )  # /path/to/client.pem
 
-        sync_proxy_mounts = None
         if http_proxy is not None and https_proxy is not None:
             async_proxy_mounts = {
                 "http://": httpx.AsyncHTTPTransport(proxy=httpx.Proxy(url=http_proxy)),
@@ -46,6 +47,7 @@ def __init__(
             ),
             verify=ssl_verify,
             mounts=async_proxy_mounts,
+            cert=cert,
         )
 
     async def close(self):
@@ -108,6 +110,9 @@ def __init__(
         https_proxy = os.getenv("HTTPS_PROXY", None)
         no_proxy = os.getenv("NO_PROXY", None)
         ssl_verify = bool(os.getenv("SSL_VERIFY", litellm.ssl_verify))
+        cert = os.getenv(
+            "SSL_CERTIFICATE", litellm.ssl_certificate
+        )  # /path/to/client.pem
 
         sync_proxy_mounts = None
         if http_proxy is not None and https_proxy is not None:
@@ -132,6 +137,7 @@ def __init__(
                 ),
                 verify=ssl_verify,
                 mounts=sync_proxy_mounts,
+                cert=cert,
             )
         else:
             self.client = client

litellm/main.py

@@ -223,7 +223,7 @@ async def acompletion(
     extra_headers: Optional[dict] = None,
     # Optional liteLLM function params
     **kwargs,
-):
+) -> Union[ModelResponse, CustomStreamWrapper]:
     """
     Asynchronously executes a litellm.completion() call for any of litellm supported llms (example gpt-4, gpt-3.5-turbo, claude-2, command-nightly)
 
@@ -339,6 +339,8 @@ async def acompletion(
             if isinstance(init_response, dict) or isinstance(
                 init_response, ModelResponse
             ):  ## CACHING SCENARIO
+                if isinstance(init_response, dict):
+                    response = ModelResponse(**init_response)
                 response = init_response
             elif asyncio.iscoroutine(init_response):
                 response = await init_response