code cleanup

docs/index.md

@@ -7,7 +7,7 @@ a light 100 line package to simplify calling OpenAI, Azure, Cohere, Anthropic AP
 * Consistent Exceptions for all LLM APIs, we map RateLimit, Context Window, and Authentication Error exceptions across all providers to their OpenAI equivalents. [see Code](https://github.com/BerriAI/litellm/blob/ba1079ff6698ef238c5c7f771dd2b698ec76f8d9/litellm/utils.py#L250)
 
 ###### observability:
-* Logging - see exactly what the raw model request/response is `completion(.., logger_fn=your_logging_fn)`
+* Logging - see exactly what the raw model request/response is by plugging in your own function `completion(.., logger_fn=your_logging_fn)` and/or print statements from the package `litellm.set_verbose=True`
 * Callbacks - automatically send your data to Helicone, Sentry, Posthog, Slack - `litellm.success_callbacks`, `litellm.failure_callbacks` [see Callbacks](https://litellm.readthedocs.io/en/latest/advanced/)
 
 ## Quick Start

docs/output.md

@@ -0,0 +1,12 @@
+# Completion Function - completion()
+Here's the exact json output you can expect from a `litellm` completion call:
+
+```python 
+{'choices': [{'finish_reason': 'stop',
+   'index': 0,
+   'message': {'role': 'assistant',
+    'content': " I'm doing well, thank you for asking. I am Claude, an AI assistant created by Anthropic."}}],
+ 'created': 1691429984.3852863,
+ 'model': 'claude-instant-1',
+ 'usage': {'prompt_tokens': 18, 'completion_tokens': 23, 'total_tokens': 41}}
+```

litellm/main.py

@@ -229,7 +229,7 @@ def completion(
       prompt_tokens = anthropic.count_tokens(prompt)
       completion_tokens = anthropic.count_tokens(completion_response)
       ## RESPONSE OBJECT
-      print(f"model_response: {model_response}")
+      print_verbose(f"raw model_response: {model_response}")
       model_response["choices"][0]["message"]["content"] = completion_response
       model_response["created"] = time.time()
       model_response["model"] = model

mkdocs.yml

@@ -4,6 +4,7 @@ nav:
     - Installation & Quick Start: index.md
     - completion():
       - Input - Request Body: input.md
+      - Output - Response Object: output.md
       - Streaming & Async Calls: stream.md
   - 🤖 Supported LLM APIs: 
     - Supported Completion & Chat APIs: supported.md

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.351"
+version = "0.1.352"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"