updates

docs/my-website/docs/debugging/hosted_debugging.md

@@ -5,7 +5,7 @@ LiteLLM offers a free hosted debugger UI for your api calls (https://admin.litel
 
 **Needs litellm>=0.1.438***
 
-You can enable this setting `lite_debugger` as a callback. 
+You can enable this setting `litellm.debugger=True`.
 
 <Image img={require('../../img/dashboard.png')} alt="Dashboard" />
 

litellm/__init__.py

@@ -17,7 +17,6 @@ openrouter_key: Optional[str] = None
 huggingface_key: Optional[str] = None
 vertex_project: Optional[str] = None
 vertex_location: Optional[str] = None
-hugging_api_token: Optional[str] = None
 togetherai_api_key: Optional[str] = None
 caching = False
 caching_with_models = False # if you want the caching key to be model + prompt

litellm/main.py

@@ -166,6 +166,7 @@ def completion(
                 response = openai.ChatCompletion.create(
                     engine=model, messages=messages, **optional_params
                 )
+            
             ## LOGGING
             logging.post_call(input=messages, api_key=openai.api_key, original_response=response, additional_args={"headers": litellm.headers, "api_version": openai.api_version, "api_base": openai.api_base})
         elif (

litellm/tests/test_streaming.py

@@ -22,6 +22,32 @@ def logger_fn(model_call_object: dict):
 user_message = "Hello, how are you?"
 messages = [{"content": user_message, "role": "user"}]
 
+# test on openai completion call
+try:
+    response = completion(
+        model="gpt-3.5-turbo", messages=messages, stream=True, logger_fn=logger_fn
+    )
+    for chunk in response:
+        print(chunk["choices"][0]["delta"])
+    score += 1
+except:
+    print(f"error occurred: {traceback.format_exc()}")
+    pass
+
+
+# test on azure completion call
+try:
+    response = completion(
+        model="azure/chatgpt-test", messages=messages, stream=True, logger_fn=logger_fn
+    )
+    for chunk in response:
+        print(chunk["choices"][0]["delta"])
+    score += 1
+except:
+    print(f"error occurred: {traceback.format_exc()}")
+    pass
+
+
 # test on anthropic completion call
 try:
     response = completion(
@@ -35,19 +61,19 @@ except:
     pass
 
 
-# test on anthropic completion call
+# # test on huggingface completion call
-try:
+# try:
-    response = completion(
+#     response = completion(
-        model="meta-llama/Llama-2-7b-chat-hf",
+#         model="meta-llama/Llama-2-7b-chat-hf",
-        messages=messages,
+#         messages=messages,
-        custom_llm_provider="huggingface",
+#         custom_llm_provider="huggingface",
-        custom_api_base="https://s7c7gytn18vnu4tw.us-east-1.aws.endpoints.huggingface.cloud",
+#         custom_api_base="https://s7c7gytn18vnu4tw.us-east-1.aws.endpoints.huggingface.cloud",
-        stream=True,
+#         stream=True,
-        logger_fn=logger_fn,
+#         logger_fn=logger_fn,
-    )
+#     )
-    for chunk in response:
+#     for chunk in response:
-        print(chunk["choices"][0]["delta"])
+#         print(chunk["choices"][0]["delta"])
-    score += 1
+#     score += 1
-except:
+# except:
-    print(f"error occurred: {traceback.format_exc()}")
+#     print(f"error occurred: {traceback.format_exc()}")
-    pass
+#     pass

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.445"
+version = "0.1.446"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"