From d7fe4f6c901facb9855aea8e6828dc764196ce0b Mon Sep 17 00:00:00 2001
From: Krrish Dholakia <krrishdholakia@gmail.com>
Date: Tue, 29 Aug 2023 15:40:16 -0700
Subject: [PATCH] adding new exception mapping details to documentation

---
 docs/my-website/docs/exception_mapping.md | 25 +++++++++++++++++++----
 litellm/utils.py                          |  8 ++------
 2 files changed, 23 insertions(+), 10 deletions(-)

diff --git a/docs/my-website/docs/exception_mapping.md b/docs/my-website/docs/exception_mapping.md
index 7710c933a7..c7283f80f3 100644
--- a/docs/my-website/docs/exception_mapping.md
+++ b/docs/my-website/docs/exception_mapping.md
@@ -1,13 +1,14 @@
 # Exception Mapping
 
-LiteLLM maps the 3 most common exceptions across all providers. 
+LiteLLM maps the 4 most common exceptions across all providers. 
 - Rate Limit Errors
 - Context Window Errors
-- InvalidAuth errors (key rotation stuff)
+- Invalid Request Errors
+- InvalidAuth Errors (incorrect key, etc.)
 
 Base case - we return the original exception.
 
-For all 3 cases, the exception returned inherits from the original OpenAI Exception but contains 3 additional attributes: 
+For all 4 cases, the exception returned inherits from the original OpenAI Exception but contains 3 additional attributes: 
 * status_code - the http status code of the exception
 * message - the error message
 * llm_provider - the provider raising the exception
@@ -44,9 +45,25 @@ To see how it's implemented - [check out the code](https://github.com/BerriAI/li
 | Replicate | Request was throttled | RateLimitError | 429 |
 | Replicate | ReplicateError | ServiceUnavailableError | 500 |
 | Cohere | invalid api token | AuthenticationError | 401 |
-| Cohere | too many tokens | InvalidRequestError | 400 |
+| Cohere | too many tokens | ContextWindowExceededError | 400 |
 | Cohere | CohereConnectionError | RateLimitError | 429 |
 | Huggingface | 401 | AuthenticationError | 401 |
 | Huggingface | 400 | InvalidRequestError | 400 | 
 | Huggingface | 429 | RateLimitError | 429 | 
+| Openrouter | 413 | ContextWindowExceededError | 400 | 
+| Openrouter | 401 | AuthenticationError | 401 | 
+| Openrouter | 429 | RateLimitError | 429 | 
+| AI21 | Prompt has too many tokens | ContextWindowExceededError | 400 | 
+| AI21 | 422 | InvalidRequestError | 400 | 
+| AI21 | 401 | AuthenticationError | 401 | 
+| AI21 | 429 | RateLimitError | 429 | 
+| TogetherAI | inputs` tokens + `max_new_tokens` must be <= | ContextWindowExceededError | 400 | 
+| TogetherAI | INVALID_ARGUMENT | InvalidRequestError | 400 | 
+| TogetherAI | "error_type": "validation" | InvalidRequestError | 400 | 
+| TogetherAI | invalid private key | AuthenticationError | 401 | 
+| TogetherAI | 429 | RateLimitError | 429 | 
+
+
+The `ContextWindowExceededError` is a sub-class of `InvalidRequestError`. It was introduced to provide more granularity for exception-handling scenarios. Please refer to [this issue to learn more](https://github.com/BerriAI/litellm/issues/228).
+
 
diff --git a/litellm/utils.py b/litellm/utils.py
index 7633950abe..ac0ca8d4a0 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -1332,8 +1332,6 @@ def exception_type(model, original_exception, custom_llm_provider):
             # Handle the OpenAIError
             exception_mapping_worked = True
             if model in litellm.openrouter_models:
-                print(f"e: {original_exception}")
-                print(f"original_exception.http_status: {original_exception.http_status}")
                 if original_exception.http_status == 413:
                     raise ContextWindowExceededError(
                         message=str(original_exception),
@@ -1422,7 +1420,7 @@ def exception_type(model, original_exception, custom_llm_provider):
                     )
                 elif "too many tokens" in error_str:
                     exception_mapping_worked = True
-                    raise InvalidRequestError(
+                    raise ContextWindowExceededError(
                         message=f"CohereException - {original_exception.message}",
                         model=model,
                         llm_provider="cohere",
@@ -1474,7 +1472,7 @@ def exception_type(model, original_exception, custom_llm_provider):
                             message=f"AI21Exception - {original_exception.message}",
                             llm_provider="ai21",
                         )
-                    if original_exception.status_code == 422 or "Prompt has too many tokens" in original_exception.message:
+                    if original_exception.status_code == 422:
                         exception_mapping_worked = True
                         raise InvalidRequestError(
                             message=f"AI21Exception - {original_exception.message}",
@@ -1522,8 +1520,6 @@ def exception_type(model, original_exception, custom_llm_provider):
                             message=f"TogetherAIException - {original_exception.message}",
                             llm_provider="together_ai",
                         )
-                print(f"error: {error_response}")
-                print(f"e: {original_exception}")
             raise original_exception  # base case - return the original exception
         else:
             raise original_exception