Skip to content

Commit

Permalink
[update] - chat topics were renamed
Browse files Browse the repository at this point in the history
  • Loading branch information
tbedford committed Sep 26, 2023
1 parent a5ea12d commit 7cff257
Show file tree
Hide file tree
Showing 2 changed files with 5 additions and 5 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,9 @@ The key ideas on this page:

The sentiment analysis service uses a prebuilt model from [Hugging Face](https://huggingface.co/){target=_blank} to analyze the sentiment of each message flowing through the service.

The sentiment analysis service subscribes to the `messages` and `drafts` topics. The messages and draft messages are generated by the web UI. Draft messages are messages while the user is typing them, before they are sent. These are used to generate sentiment while the user is typing.
The sentiment analysis service subscribes to the `chat-messages` and `drafts` topics. The messages and draft messages are generated by the web UI. Draft messages are messages while the user is typing them, before they are sent. These are used to generate sentiment while the user is typing.

After sentiment analysis performed by the Hugging Face model, sentiment values are published to the `sentiment` and `drafts_sentiment` topics. The UI subscribes to these topics, and can then display the setiment values in the UI.
After sentiment analysis performed by the Hugging Face model, sentiment values are published to the `chat-with-sentiment` and `drafts_sentiment` topics. The UI subscribes to these topics, and can then display the setiment values in the UI.

## 👩‍🔬 Lab - Examine messages

Expand Down
6 changes: 3 additions & 3 deletions docs/platform/tutorials/sentiment-analysis/ui-service.md
Original file line number Diff line number Diff line change
Expand Up @@ -39,12 +39,12 @@ The Streaming Reader is used to read the sentiment from the sentiment analysis s

The four topics involved are:

* `messages` - topic for the sent messages
* `chat-messages` - topic for the sent messages
* `drafts` - topic for draft messages
* `sentiment` - topic with sentiment for sent messages
* `chat-with-sentiment` - topic with sentiment for sent messages
* `drafts_sentiment` - topic with sentiment for draft messages

So, the web UI uses the Writer API to write to both `messages` and `drafts` and the Reader API to read from both `sentiment` and `drafts_sentiment`.
So, the web UI uses the Writer API to write to both `chat-messages` and `drafts` and the Reader API to read from both `chat-with-sentiment` and `drafts_sentiment`.

The Streaming Reader API has both an HTTP and WebSockets interface you can use to interface with a Quix topic. This web client uses the WebSockets interface. This enables data to be streamed from the Quix topic into the web client with good performance. This is a more efficient method than using the request-response method of HTTP.

Expand Down

0 comments on commit 7cff257

Please sign in to comment.