We are using microsoft's QnAMaker service to build a FAQ bot. I would like to know if the api response has the answers sorted when there are multiple matches with different scores. Does the api return the answer with the top score first?
We tested it with a sample but wanted to make sure that there is no other factor playing a role here. Kindly let me know.
Thanks!
You can read about how QnA Maker processes a user query in the official docs:
The client application sends the user query to the
GenerateAnswer API.
QnA Maker preprocesses the user query with language detection, spellers, and word breakers.
This preprocessing is taken to alter the user query for the best search results.
This altered query is sent to an Azure Cognitive Search Index, which receives the top number of results. If the correct answer isn't in these results, increase the value of top slightly. Generally, a value of 10 for top works in 90% of queries.
QnA Maker uses syntactic and semantic based featurization to determine the similarity between the user query and the fetched QnA results.
The machine-learned ranker model uses the different features, from step 5, to determine the confidence scores and the new ranking order.
The new results are returned to the client application in ranked order.
Features used include but aren't limited to word-level semantics, term-level importance in a corpus, and deep learned semantic models to determine similarity and relevance between two text strings.
The Typescript SDK also specifies the following on the generateAnswer method:
Returns an array of answers sorted by score with the top scoring
answer returned first.
You should also be aware that multiple resources are involved in the QnA Maker ranking process - Azure Cognitive Search and QnA Maker.
The Cognitive Search resource is used to store the QnA pairs and provide the initial ranking (ranker #1) of the QnA pairs at runtime.
The QnA Maker resource provides access to the authoring and publishing APIs as well as the natural language processing (NLP) based second ranking layer (ranker #2) of the QnA pairs at runtime.
The second ranking applies intelligent filters that can include metadata and follow-up prompts.
Related
Is it possible to create a Kapow Robot that can search Google for the Operating hours of the Businesses from our list/database and update the timings if changes are made?
Please share if there are any other more efficient ways than the KAPOW robot that can be implemented with minimal effort and cost-effectiveness.
That's what the Google Places API is there for. While you could in theory just open Google Maps in a Load Page action, enter the query string and then parse the results, I would advise against it. Here's why:
The API will be faster, returning results in a structured manner (JSON)
Kapow has actions for calling RESTful services and parsing/modifying JSON
Google does not like robots parsing their pages, and most likely will lock you out (i.e. present you with Captchas sooner or later)
If you decide to go for the API, here's what you should do:
Get your API key first, see this page for details: https://developers.google.com/places/web-service/get-api-key. Note that the free plan allows for 1,000 requests within a 24-hours limit (https://developers.google.com/places/web-service/usage)
Maintain the place ids for all the businesses you'd like to query regularly, and update your list.
For each place, retrieve the details as described in the API documentation. The opening hours will be within the JSON response: https://developers.google.com/places/web-service/details
Update your list. I'd recommend using a definite type in Kapow for that, and using the actions Store in Database and Query Database. In case you need the data elsewhere, you may create additional robots (e.g. for Excel files, sending data per email, et cetera).
The pricing regarding CSE is a little bit vague:
For CSE users, the API provides 100 search queries per day for free. If you need more, you may sign up for billing in the API Console. Additional requests cost $5 per 1000 queries, up to 10k queries per day
Does one query equal one keyword regardless of pagination used, or one request? (in this sense XML is more efficient than JSON, as it allows 20 in num parameter, as opposed to JSONs 10)
Are the queries counted per API key, or per cx key?
It is vague and you are not the first to be puzzled. When I did my research I found this blog post helpful.
Assume you are talking about Custom Search Engine (terms you noted in your Q) and NOT Google Site Search (paid from the start). The reason I ask is that the XML function is only for Google Site Search customers. There is the JSON/Atom API and Custom Search API available for CSE.
For Q1, one Query = one request. You can use as many keywords or other parameters in your request (see comments in the blog post I referenced), but you will always be limited to 100 results.
For Q2, the billing is enabled through the API console. Once enabled (and in order to allow the 101st query) your code must include both your cx and API key. So in theory you could set up multiple search engines within your API and stay under the 100 request limit, but I have not seen a way to allow an API to support multiple cx keys.
Context
I am in the process of providing some consultancy on doing a HTTP GET using YouTube Data API V3; in order to develop a Windows based application to GET a list of results from Youtube, for say a specific CATEGORY, or a specific TAG.
We are open to using any programming language(I'm from a C++ background and am hoping You tube will support direct HTTP connections without using Google client SDK and so on) to connect to YouTube and (HTTP) GET data.(Once a month or so, so YouTube API quotas should not be problem).
The Issue
We are being told by some of my client's web developers that YouTube API v3 will only return a maximum of 500 records/results, for say a query that returns JUST the Total viewers, the Video's link, and basic meta data such as that.
S, say I wish to find 5,000 results for category "House music" or "basketball" - and I have the Developer Key etc are all set up, would that be possible?
If so, what GET fields would I need to populate(such as "max_results_per_page")?
Thank you.
The API won't provide more than ~500 search results for any arbitrary query. It's by design. Technically, it means that the nextPageToken field won't be returned once you hit ~500 results. No additional parameter can change that.
If you want more than ~500 results for a query, you have to split it into more specific sub-queries. I'd suggest using the publishedAfter and publishedBefore parameters to achieve that, but feel free to experiment with the other ones here.
This only holds for the search-Query. Other queries like "PlaylisItem:list" deliver more results. I have tested with 100.000 items to get the videos of a playlist.
I recently joined a team working on an application that maintains listings with addresses. The user searches, and includes their zipcode, and the application displays the distance to each listing. Currently we use the Google Maps API for this. Reading through questions here on StackOverflow seem to suggest that this is the best way of doing things:
php/mysql zip code proximity search
Search engine by distance
However, while reading through the API documentation, this seems to be expressly forbidden unless we also show a map for each result (and possibly also for each result we filter out, depending on how you read the following statement):
Use of the Distance Matrix API must relate to the display of information on a Google Map; for example, to determine origin-destination pairs that fall within a specific driving time from one another, before requesting and displaying those destinations on a map. Use of the service in an application that doesn't display a Google map is prohibited.
( https://developers.google.com/maps/documentation/distancematrix/ )
What's the best way to accomplish this without running afoul of any API terms?
do you consider the Geo::PostalCode module (perl)? It uses maxmind database to calculate distances between locations (and there is bind in different languages).
I'm trying to find out if there is a programmatic way to determine how far down in a search engine's search results my site shows up for given keywords. For example, my query would provide my domain name, and keywords, and the result would return a say 94 indicating that my site was the 94th result. I'm specifically interested in how to do this with google but also interested in Bing and Yahoo.
No.
There is no programmatic access to such data. People generally roll out their own version of such trackers. Get the Google search page and use regexes to find your position. But now different results are show in different geographies and results are personalize.
gl=us parameter will help you getting results from US, you can change geography accordingly to get the results.
Before creating this from scratch, you may want to save yourself some time (and money) by using a service that does exactly that [and more]: Ginzametrics.
They have a free plan (so you can test if it fits your requirements and check if it's really worth creating your own tool), an API and can even import data from Google Analytics.