📦 NEW: Online Store Customer Service Example With Agents#28
📦 NEW: Online Store Customer Service Example With Agents#28AIENGINE wants to merge 30 commits intoCommandCodeAI:mainfrom
Conversation
|
Reviewer has to change the environment vars before deploying |
| const body = await req.json() | ||
| const { messages, threadId } = body | ||
|
|
||
| const response = await fetch('http://localhost:8787', { |
There was a problem hiding this comment.
@AIENGINE Please use our SDK instead of directly calling the API. I see that you're also calling the localhost URL here, not sure why though.
There was a problem hiding this comment.
Sure will do. This chatbot has split implementation frontend (nextjs) and backend (cf worker)
| @@ -0,0 +1,43 @@ | |||
| import { OpenAIStream, StreamingTextResponse } from 'ai' | |||
There was a problem hiding this comment.
@AIENGINE Our SDK has its own streaming functions. No need to use this package.
| }) | ||
|
|
||
| // Create a stream from the response | ||
| const stream = OpenAIStream(response) |
There was a problem hiding this comment.
@AIENGINE I see that in the example pipe of this demo, you have disabled the streaming mode of the pipe. Not sure why are you using stream here after that. Also, in the current setting you will get a JSON string as a response, which you will need to parse and then extract the message from it. You will then return that message to the frontend.
Please let me know if you have any questions.
2 participants
📦 NEW: Online store customer service example with agents based on https://langbase.com/examples/online-store-customer-service
This chatbot consists of front end (online-cs-chatbot) and backend (cloudflare worker online-cs-chatbot-backend)
The following files were updated
The following files were added