time

microsoft · Sep 30, 2023 · e68228b · e68228b
1 parent bc8ef5d
commit e68228b
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/autogen/oai/completion.py b/autogen/oai/completion.py
@@ -746,7 +746,7 @@ def yes_or_no_filter(context, config, response):
             **config: Configuration for the openai API call. This is used as parameters for calling openai API.
                 The "prompt" or "messages" parameter can contain a template (str or Callable) which will be instantiated with the context.
                 Besides the parameters for the openai API call, it can also contain:
-                - `max_retry_period` (int): the total timeout (in seconds) allowed for retrying failed requests.
+                - `max_retry_period` (int): the total time (in seconds) allowed for retrying failed requests.
                 - `retry_wait_time` (int): the time interval to wait (in seconds) before retrying a failed request.
                 - `seed` (int) for the cache. This is useful when implementing "controlled randomness" for the completion.
 

diff --git a/website/docs/Use-Cases/enhanced_inference.md b/website/docs/Use-Cases/enhanced_inference.md
@@ -126,7 +126,7 @@ API call results are cached locally and reused when the same request is issued.
 It is easy to hit error when calling OpenAI APIs, due to connection, rate limit, or timeout. Some of the errors are transient. `autogen.Completion.create` deals with the transient errors and retries automatically. Request timeout, max retry period and retry wait time can be configured via `request_timeout`, `max_retry_period` and `retry_wait_time`.
 
 - `request_timeout` (int): the timeout (in seconds) sent with a single request.
-- `max_retry_period` (int): the total timeout (in seconds) allowed for retrying failed requests.
+- `max_retry_period` (int): the total time (in seconds) allowed for retrying failed requests.
 - `retry_wait_time` (int): the time interval to wait (in seconds) before retrying a failed request.
 
 Moreover, one can pass a list of configurations of different models/endpoints to mitigate the rate limits. For example,