membphis commented on code in PR #13307: URL: https://github.com/apache/apisix/pull/13307#discussion_r3201089261
########## t/lib/server.lua: ########## @@ -1036,6 +1036,114 @@ function _M.bedrock_converse() end +-- Mock for Bedrock /converse-stream. Reuses the same SigV4 + body shape Review Comment: Currently, all AI upstream services are simulated using this fake server method. I'm worried that the difference between the fake server and the real LLM request here is too big. Should we introduce a container specifically for LLM Fake Server? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
