expose vertex ai and hf api base as env var

docs/my-website/docs/providers/huggingface.md

@@ -72,12 +72,13 @@ response = completion(
 print(response)
 ```
 
-### [OPTIONAL] API KEYS
-If the endpoint you're calling requires an api key to be passed, set it in your os environment. [Code for how it's sent](https://github.com/BerriAI/litellm/blob/0100ab2382a0e720c7978fbf662cc6e6920e7e03/litellm/llms/huggingface_restapi.py#L25)
+### [OPTIONAL] API KEYS + API BASE
+If required, you can set the api key + api base, set it in your os environment. [Code for how it's sent](https://github.com/BerriAI/litellm/blob/0100ab2382a0e720c7978fbf662cc6e6920e7e03/litellm/llms/huggingface_restapi.py#L25)
 
 ```python
 import os 
 os.environ["HUGGINGFACE_API_KEY"] = ""
+os.environ["HUGGINGFACE_API_BASE"] = "" 
 ```
 
 ### Models with Prompt Formatting

docs/my-website/docs/providers/vertex.md

@@ -13,9 +13,29 @@
 ## Set Vertex Project & Vertex Location
 All calls using Vertex AI require the following parameters:
 * Your Project ID
-`litellm.vertex_project = "hardy-device-38811" Your Project ID`
+```python
+import os, litellm 
+
+# set via env var
+os.environ["VERTEXAI_PROJECT"] = "hardy-device-38811" # Your Project ID`
+
+### OR ###
+
+# set directly on module 
+litellm.vertex_project = "hardy-device-38811" # Your Project ID`
+```
 * Your Project Location
-`litellm.vertex_location = "us-central1" `
+```python
+import os, litellm 
+
+# set via env var
+os.environ["VERTEXAI_LOCATION"] = "us-central1 # Your Location
+
+### OR ###
+
+# set directly on module 
+litellm.vertex_location = "us-central1 # Your Location
+```
 
 ## Sample Usage
 ```python

litellm/llms/huggingface_restapi.py

@@ -49,6 +49,8 @@ def completion(
         completion_url = api_base
     elif "HF_API_BASE" in os.environ:
         completion_url = os.getenv("HF_API_BASE", "")
+    elif "HUGGINGFACE_API_BASE" in os.environ:
+        completion_url = os.getenv("HUGGINGFACE_API_BASE", "")
     else:
         completion_url = f"https://api-inference.huggingface.co/models/{model}"
 

litellm/main.py

@@ -749,8 +749,10 @@ def completion(
                 raise Exception("vertexai import failed please run `pip install google-cloud-aiplatform`")
             from vertexai.preview.language_models import ChatModel, CodeChatModel, InputOutputTextPair
 
+            vertex_project = (litellm.vertex_project or get_secret("VERTEXAI_PROJECT"))
+            vertex_location = (litellm.vertex_location or get_secret("VERTEXAI_LOCATION"))
             vertexai.init(
-                project=litellm.vertex_project, location=litellm.vertex_location
+                project=vertex_project, location=vertex_location
             )
             # vertexai does not use an API key, it looks for credentials.json in the environment
 

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.734"
+version = "0.1.735"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"