# Implementing TFIDF as a custom component? **URL:** \ **Category:** Rasa Open Source\ **Created:** [March 13, 2020, 9:55am UTC](https://forum.rasa.com/t/implementing-tfidf-as-a-custom-component/26032 "2020-03-13T09:55:16Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![ActuallyAcey](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/actuallyacey/32/6644_2.png) [@ActuallyAcey](https://forum.rasa.com/u/ActuallyAcey)\ **Post date:** [March 13, 2020, 9:55am UTC](https://forum.rasa.com/t/implementing-tfidf-as-a-custom-component/26032/1 "2020-03-13T09:55:16Z")
Hi. As part of a project at work, I’m building a bot that can answer a predefined set of FAQs. Given the large volume of questions we have, writing training data for them all (including implementation with RasaX) will take a lot of time. I’ve found that some simple tf-idf vectorization produces really good results for answering FAQs that are similar but have entirely unique answers. Eg. `What is an escrow account?` `What is an escrow cushion?` Yields a very accurate result in TFIDF (given how it’s designed to focus on unique words, of course) but requires a substantial amount of training data to make Rasa differentiate between the two acceptably. I’ve read the tutorial on designing custom components, but there doesn’t seem to be a way to really approach this particular problem. How should I approach this? ---
**Author:** ![ActuallyAcey](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/actuallyacey/32/6644_2.png) [@ActuallyAcey](https://forum.rasa.com/u/ActuallyAcey)\ **Post date:** [March 23, 2020, 9:43am UTC](https://forum.rasa.com/t/implementing-tfidf-as-a-custom-component/26032/2 "2020-03-23T09:43:15Z")
Anything on this, guys? ---
**Author:** ![NoahDrisort](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/noahdrisort/32/9951_2.png) [@NoahDrisort](https://forum.rasa.com/u/NoahDrisort)\ **Post date:** [July 2, 2020, 10:06am UTC](https://forum.rasa.com/t/implementing-tfidf-as-a-custom-component/26032/3 "2020-07-02T10:06:45Z")
I also think TF-IDF is suitable in this case, Have you solve this problem I am going to use sklearn library but don’t know how to apply it in sparse\_featurize folder ---
**Author:** ![ActuallyAcey](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/actuallyacey/32/6644_2.png) [@ActuallyAcey](https://forum.rasa.com/u/ActuallyAcey)\ **Post date:** [July 2, 2020, 11:29am UTC](https://forum.rasa.com/t/implementing-tfidf-as-a-custom-component/26032/5 "2020-07-02T11:29:20Z")
I wasn’t able to find a “clean” solution for this, so what I did was generalize all my FAQ data into one intent (or several, if you have sections). I then used a custom action to route the user’s message to a separate Python module that runs a normal TF-IDF search and responds with the results. ---
**Author:** ![NoahDrisort](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/noahdrisort/32/9951_2.png) [@NoahDrisort](https://forum.rasa.com/u/NoahDrisort)\ **Post date:** [July 6, 2020, 3:51am UTC](https://forum.rasa.com/t/implementing-tfidf-as-a-custom-component/26032/6 "2020-07-06T03:51:25Z")
Are your both action in parallel like RASA, I mean the classifier and the action selector in TF-IDF ? I don’t know how to seperate which featurizer for each: - Countvector ngram -\> DIET classifier - TF-IDF -\> Default Reponse selector of RASA is it available parallel in RASA I am going to share the custom tf-idf when i finish it ---
**Author:** ![ActuallyAcey](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/actuallyacey/32/6644_2.png) [@ActuallyAcey](https://forum.rasa.com/u/ActuallyAcey)\ **Post date:** [July 6, 2020, 6:57am UTC](https://forum.rasa.com/t/implementing-tfidf-as-a-custom-component/26032/7 "2020-07-06T06:57:31Z")
No, they’re sequential. Its really just one custom action, but it sends the message to a different app entirely to do the TF-IDF processing and which sends back a response.