I am new to Dialog flow and trying to build product search. So for that i have many text responses. While doing this my number of text response reached to 30.
As you can see in screenshot it reached till 30 and i didn't find any option to write another text response. So clicked on Add Message Content and added new text response. But now when i query something it gives me multiple response.
So my question is:
1) Is there any way to increase number of text response(30) size. Or it is limitation.
2) If there in no way to resolve above issue. How can i get only single response as it is giving me two response from both text response
Text responses are available in all platforms.
Limitation-1: Your agent can send up to 10 sequential text messages in response to a user input (assuming no other message types are defined in the intent).
Limitation-2: You can add 30 variations to each text message response.
So, the answer to your question, there's no way, you can exceed this limit either in Standard or Enterprise edition. Secondly, what you're doing is adding a number of text messages when you reached a limit (30) while adding variations. You can resolve this issue either by deleting number of text messages or by creating different intents for different responses.
When you add variations, api.ai will randomly choose any one of those 30 responses written by you & show it to a user. You have multiple such text messages & so api.ai randomly chooses one response from each text message & so you're getting multiple responses. Hope this helps.
You shouldn't try everything in one single intent. Break into multiple to avoid complex scenarios.
Related
An email arrives into a mail-in database. I look at it and see that it has a single Body item, which is Rich Text.
In an agent run after new mail arrives, I want to update the arriving memo, and append some text to that Body item and then save it. I use getfirstitem to get a handle on it, and then use AddNewLine and Appendtext in successive lines of code, adding a bit of text to it, before saving it.
After this is done, I look at the backend document again and where there used to be a single Body item there are now two. Each has a portion of what I expected a single item to have. Between the two, nothing is missing.
Note: The incoming email also has attachments...but it did originally before I updated it and again, there was only one Body item.
Note2: Sending the email from Outlook. How that could be related I don't know.
What could be causing this or what might I do to work around this. Open to all suggestions/ideas.
Thank you
Matt Smith
If you call Compact on the Body after you've finished adding to it (and before saving if you do an explicit save), that might reduce it to a single item, but it's not guaranteed.
There are cases where Body is forced to be 2 or more items. E.g.:
If an email comes in as MIME (which is common for emails from outside your network), each MIME part is always a separate Body item, and there are normally 2 or more MIME parts for a single email.
I think each rich-text item has a strict 64 kB size limit for the raw data, so content exceeding 64 kB will always be 2 or more items, but I'm not sure of this.
As others have said in comments, it's normal to have more than 1 item for rich-text content. You should never have to care about this. If you use GetFirstItem to get a rich-text item and add text to the end of it, it will act like one item from an end-user perspective.
I decided on another way to accomplish what i needed, not appending text, so this question is no longer in need of help, other than to sate my own curiosity. Thanks guys.
For an intent that I have, I ask the user to enter the error message they see on the screen. Based on the message they enter, I want to show them a response. I have added these responses in the intent (all separate responses). I have annotated the training phrases (exact copy of the error messages) to an entity that captures these messages. When I enter the error message however, I get all the responses instead of just the relevant one.
How should I solve this? I would like to control which response gets selected based on the error message the users enter. I appreciate your thoughts.
I was able to get this right. If I have different responses in an intent, all of them will be displayed. I have added the different responses I had as variants within the same response and I was able to get it working!
I'm consuming the Outlook API, attempting to access all messages from an inbox which contains ~45,000 messages (and other folders such as Sent Items).
The main request I'm making is to https://outlook.office.com/api/v2.0/me/messages. If I add ?$count=true, the "#odata.count" value is returned as -1.
I can add $top=500 to the request which gives me 500 messages returned and an "#odata.nextLink", but if I pass $top=5000, there's no "#odata.nextLink" which I'd expect to see.
A few particular questions here if anyone can help:
Is this the best way to try and get all the messages out of all folders?
Is there a reason count would be returning -1, and is there a way to get an accurate figure of the number of messages returned?
Is there a maximum $top size I need to pass to get a valid request back?
Yes, but understand it includes Drafts, Deleted Items, and Sent Items in addition to all of the other mail folders.
This is a known issue with /me/messages. Basically the way that /me/messages gives all messages across all folders is by using a search folder, which dynamically updates. The API doesn't report accurate counts for search folders (usually just returns -1).
The highest $top should be 1000.
I have two questions:
1) Is chatbase support utf8 text messages? When I am sending herbrew message ,the message under the messages appears with no text (only ellipse).
2) Can I see the history beyond 30 days?
Thanks
Elad
1) Chatbase does support utf8 text, so the messages should appear in the messages table. If you email our alias, chatbase-feedback#google.com, with your API key, I can take a look at what could be happening.
2) Right now our reports are fixed at a maximum of 30 days, however we are planning on adding the ability to view date using your own time ranges within the next few months.
I am searching this forum(and others) and I can't find how exactly the eventhandler of the SMSTools works. How does it know when it's receiving or sending in order to take an action? Think is better to explain what I want.
I want to use the eventhandler in this scenario:
I am using a IDS which is sending information by SMS via smstools. Everything is ok by now, I am receiving what I need.
The problem is that when the smstools is receiving an SMS, I want to check if it's from the correct phone number (mine for example or a list of numbers would be better).
If it's the correct number, I want to see the text (the text will pe simple, like: yes or no) and take an action depending on it.
I will really appreciate any answer.