Skip to content

Commit c2c4fe5

Browse files
committed
Update README to explain prompt caching optimization via instruction placement
1 parent 6b16e5b commit c2c4fe5

1 file changed

Lines changed: 1 addition & 1 deletion

File tree

‎README.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -154,7 +154,7 @@ Install the [browser extension](https://github.com/robertpiosik/CodeWebChat/tree
154154
155155
## Prompt caching
156156

157-
CWC orders selected files by modification recency. This, combined with its simple design based on single-turn model interactions, creates a workflow that is extremely cache-friendly.
157+
CWC orders selected files by modification recency. This, combined with instructions placement at the message's very end, creates cost-efficient workflow where most of constructed messages utilize [prompt caching](https://developers.openai.com/api/docs/guides/prompt-caching).
158158

159159
Make your chatbot quota last longer, lower input token costs by up to 90%, and reduce latency by up to 80%.
160160

0 commit comments

Comments
 (0)