How to Add Images to QnA Maker?
I would like to put picture in qna maker (knowledge base).
Any help please.
[Michael Szul's Twitter] (https://img.thedailybeast.com/image/upload/c_crop,d_placeholder_euli9k,h_1440,w_2560,x_0,y_0/dpr_1.5/c_limit,w_1044/fl_lossy,q_auto/v1505327080/170911-cox-bots-politics-tease_hflhdh)
As per the QnAMaker documentation:
The knowledge base supports Markdown. However, the auto-extraction from URLs has limited HTML-to-Markdown conversion capability. If you want to use full-fledged Markdown, you can modify your content directly in the table, or upload a knowledge base with the rich content. Multimedia, such as images and videos, is not supported at this time."
Using Markdowns : you can add images to a QnAMaker answer by adding the URl via markdowns.
This will result in
What you have pasted above will render as a link.
If you want to add links via markdown, then the format is
[bing](http://bing.com)
which will result in
Hope this helps.
Related
Is it possible to get a list of all comments made by a given user's account with Youtube Data API, or even another API?
If this isn't a direct feature, would there be a convoluted way of doing this by seeing all the videos watched by a user and parsing the comments out of those specific videos?
The goal of my project is to create a 'Spotify Wrapped' style website but for youtube (showing a user their most liked comments, the channels they watch the most, etc) but I'm having trouble finding the correct search criteria in the Youtube Data API documentation.
I am using HMTL, CSS, and JavaScript currently, and any help would be greatly appreciated!
Thanks,
Tom.
I am trying to parse text from a PDF file using Computer Vision 2.0. I am following the example and have changed the MediaTypeHeaderValue to "application/pdf". I get an error that the content type is not supported. I change it to "multipart/form-data" and get an error in processing. How do I use Computer-Vision to process PDF files?
Kevin,
You are using the legacy "OCR" API that does not support PDF input. Please use the new OCR technology available as the "Read" API - see overview for processing PDF documents. The version 3.0 is in GA since May. Read supports large images and multi-page and mixed languages documents up to 2000 pages long.
Please see the Read REST API QuickStart in C#.
Note that Form Recognizer is great if you want to extract not just text, but layout insights such as tables, check-boxes, and key value pairs from forms, use pre-built models, and build custom models to process your documents. It's now in GA.
Take a look at the Form Recognizer service for extracting data from the PDF.
https://azure.microsoft.com/en-us/services/cognitive-services/form-recognizer/
I am trying to create a similar rich response to what google provides for the flight status and was wondering what kind of rich response they use to display this fancy formatting? Is that just a dynamically generated image? Thanks.
screen shot
I think The card/response in the above image are custom cards built by google, Maybe there is no option to replicate those once unless you work with Google, But as of now the only responses/cards you can build are here.
I have images with important file metadata (e.g. provenance and processing history) stored locally or in Azure blob storage.
I would like to import (POST) these to the Azure Custom Vision environment (via the API or GUI) (see e.g. https://southcentralus.dev.cognitive.microsoft.com/docs/services/Custom_Vision_Training_3.0) for training while (i) retaining those image metadata and (ii) being able to retrieve them via (a) the Custom Vision API and (b) the Custom Vision GUI.
An example use case would be to purge images of a certain provenance from the Custom Vision store because of a GDPR-related customer request [Aside: I appreciate that Azure Cognitive Services can anyway use the data for improving their models etc.].
As far as I can tell the only way to reference an image POSTed to Custom Vision is via its UUID. Is there any other way to reference metadata stored with that image or:
Would that constitute a feature request?
Could the image metadata be stored inside the image (e.g. JPEG EXIF) (assuming it is possible to retrieve the image itself from the Custom Vision "environment", which it may not be)?
Otherwise, is the only solution to store the returned Custom Vision image UUID in a database elsewhere alongside the required metadata?
NB In the above, by metadata I do not mean tags/labels in the image model-side sense, but rather data-side file metadata.
[Note that Azure Cognitive Services is using stackoverflow for Q&A, so this question is I believe appropriate for stackoverflow.]
Thanks as ever!
I am not part of Microsoft, so it is only my opinion based on my usage of Custom Vision.
I understand your use-case, especially regarding GDPR as you mentioned, but currently adding metadata is not a feature, whether through the API or the GUI.
To answer your questions:
Would that constitute a feature request?
Definitely. You can create an item on UserVoice for this feature (but 1st check if there is not another related existing item): https://cognitive.uservoice.com/forums/598141-custom-vision-service
Could the image metadata be stored inside the image (e.g. JPEG EXIF)
(assuming it is possible to retrieve the image itself from the Custom
Vision "environment", which it may not be)?
You can get the images your previously posted using GetImagesByIds method from the API for example (or GetTaggedImages / GetUntaggedImages). Remember that the images you post are treated: thumbnail images, resized images are generated based on what you posted. These methods provides the links to the images.
I made a quick try by:
- Uploading an image to CustomVision and adding a tag
- Getting its id
- Getting the image through the API
Good news: on the image downloaded with the "originalImageUri" link, I still have some EXIF available (just needed to rename the file as ".jpg" after download):
Otherwise, is the only solution to store the returned Custom Vision
image UUID in a database elsewhere alongside the required metadata?
Right now it is clearly the best solution in my opinion
I'm looking for a solution, where users of my site can use an image search engine (e.g. Google), instead of uploading an image, they can search and pick one of the results.
My problem is:
Google image search API is deprecated!
Google custom search requires me to add "sites to search" when creating a custom search API key. However, I do not want to search my own site, I want to search the internet!
Which Google API is ment to search images on the internet?
Would it be plausible to include normal image search in an iframe, and somehow capture an image selection (i.e. when clicked)?
Google made it really difficult:
http://groups.google.com/group/google-ajax-search-api/browse_thread/thread/9885ea5ab20b8f01?pli=1
http://support.google.com/customsearch/bin/answer.py?hl=en&answer=1210656
TL;DR: You have to use Google custom search, add a random site when creating the API key, afterwards you can tweak the settings to search the entire web instead.
Have you checked out LTU technology?
I found this url which JSON - seems to be the top results when searching google images:
https://ajax.googleapis.com/ajax/services/search/images?v=1.0&q=car