From f0ccfecb0e2f09b14e0c03f6d418534b8154b92c Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Tue, 29 Aug 2023 16:09:44 -0700 Subject: [PATCH] update docs for openai mapping --- docs/my-website/docs/exception_mapping.md | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/docs/my-website/docs/exception_mapping.md b/docs/my-website/docs/exception_mapping.md index c7283f80f..654e31463 100644 --- a/docs/my-website/docs/exception_mapping.md +++ b/docs/my-website/docs/exception_mapping.md @@ -34,12 +34,17 @@ To see how it's implemented - [check out the code](https://github.com/BerriAI/li **Note** For OpenAI and Azure we return the original exception (since they're of the OpenAI Error type). But we add the 'llm_provider' attribute to them. [See code](https://github.com/BerriAI/litellm/blob/a42c197e5a6de56ea576c73715e6c7c6b19fa249/litellm/utils.py#L1221) +## custom mapping list + +Base case - we return the original exception. + | LLM Provider | Initial Status Code / Initial Error Message | Returned Exception | Returned Status Code | |----------------------|------------------------|-----------------|-----------------| | Anthropic | 401 | AuthenticationError | 401 | | Anthropic | Could not resolve authentication method. Expected either api_key or auth_token to be set. | AuthenticationError | 401 | | Anthropic | 400 | InvalidRequestError | 400 | | Anthropic | 429 | RateLimitError | 429 | +| OpenAI | This model's maximum context length is | ContextWindowExceededError | 400 | | Replicate | Incorrect authentication token | AuthenticationError | 401 | | Replicate | ModelError | InvalidRequestError | 400 | | Replicate | Request was throttled | RateLimitError | 429 |