# Is it possible to access the tracker of a conversation through a NLU custom component?

**URL:** <https://forum.rasa.com/t/is-it-possible-to-access-the-tracker-of-a-conversation-through-a-nlu-custom-component/27298>\
**Category:** Rasa Open Source\
**Created:** [April 9, 2020, 9:48pm UTC](https://forum.rasa.com/t/is-it-possible-to-access-the-tracker-of-a-conversation-through-a-nlu-custom-component/27298 "2020-04-09T21:48:20Z")\
**Posts on this page:** 1\
**Showing post:** 6

<div class="post-metadata">

**Author:** ![tomgun132](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/tomgun132/32/7462_2.png) [@tomgun132](https://forum.rasa.com/u/tomgun132)\
**Post date:** [March 15, 2021, 12:27am UTC](https://forum.rasa.com/t/is-it-possible-to-access-the-tracker-of-a-conversation-through-a-nlu-custom-component/27298/6 "2021-03-15T00:27:12Z")

</div>

Hi, I haven’t really worked on that because 1. The training data will be different from standard Rasa NLU format and more similar to Rasa stories instead, 2. Since the sentence that requires context for chatbot might be quite rare, I think for now it’s better to use the [end-to-end story instead](https://blog.rasa.com/were-a-step-closer-to-getting-rid-of-intents/).

If you still want to do this, as I said, I think you can create custom `NaturalLanguageInterpreter` and `Interpreter` class. I think you can pass the tracker [here](https://github.com/RasaHQ/rasa/blob/main/rasa/core/interpreter.py#L145), put the metadata [here](https://github.com/RasaHQ/rasa/blob/main/rasa/nlu/model.py#L448), and you need to replace `agent.interpreter` as well.

---

_[View the full topic](https://forum.rasa.com/t/is-it-possible-to-access-the-tracker-of-a-conversation-through-a-nlu-custom-component/27298)._