As a question-answering plugin service, Ask A Question requires what we call "chat managers" - platforms that help you build end-user chat flows and integrate with channels like WhatsApp.
To make this integration process easier, we published a Turn.io Playbook. Playbooks are reusable, pre-built chat flows that can be shared with and remixed by other teams in the chat-for-impact community.
We refactored our two question-answering endpoints into a single one called /search for clarity and ease of use.
In the last month or so, we've had support from Google fellows to pinch hit on a few items. Ahn Mac, a UI/UX designer at Google, helped design a new dashboard that we are very excited about. The first page, "Overview", is now ready for you to check out.
Filtering contents has been made easier with tags.
By integrating Langfuse, a popular LLM observability tool with a generous free tier, you can now track all LLM calls made via AAQ.
Getting insights from your app has been made easy with the introduction of a questions dashboard page.
You may wish to handle urgent messages differently. For example, when deploying a question answering service in a health context, you may wish to refer the user to their nearest health center, or escalate it immediately to a human operator.
We introduce a new endpoint and new page in the Admin App to enable this.
There are now two new endpoints for feedback:
POST /response-feedback - Allows you to capture feedback for the overall response returned by either of the
Question-Answering APIs.POST /content-feedback - Allows you to capture feedback for a specific piece of content.These can be used in chat managers to collect feedback after answers are shown.
Admin app now has a new Playground page where you can test out the FAQ matching and LLM response endpoints!
Instead of being handled directly in our code, our model calls are now routed through a LiteLLM Proxy server. This lets us change models on the fly and have retries, fallbacks, budget tracking, and more.