# How to Make a RASA Chatbot Learn from a PDF Without Defining Intents Manually?

**URL:** <https://forum.rasa.com/t/how-to-make-a-rasa-chatbot-learn-from-a-pdf-without-defining-intents-manually/66535>\
**Category:** Feedback on Rasa Open Source\
**Created:** [March 14, 2025, 11:06am UTC](https://forum.rasa.com/t/how-to-make-a-rasa-chatbot-learn-from-a-pdf-without-defining-intents-manually/66535 "2025-03-14T11:06:49Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![iggy](https://avatars.discourse-cdn.com/v4/letter/i/74df32/32.png) [@iggy](https://forum.rasa.com/u/iggy)\
**Post date:** [March 14, 2025, 11:06am UTC](https://forum.rasa.com/t/how-to-make-a-rasa-chatbot-learn-from-a-pdf-without-defining-intents-manually/66535/1 "2025-03-14T11:06:49Z")

</div>

Hello everyone, I want to build a chatbot using RASA that should learn from a PDF document and retrieve information based on its content.

**What I Want to Achieve:**

The chatbot should function as a customer support assistant by searching for relevant information in the PDF. However, I **do not** want to manually define intents and rules for every possible query. Instead, I want the chatbot to automatically learn from the PDF and generate responses based on its content—similar to how ChatGPT would process and answer questions from a document.

**Question:**

Is there a way to implement this in RASA? How can I make the chatbot extract information directly from the PDF and respond to user queries accordingly without manually specifying intents and rules? Any guidance or example implementations would be greatly appreciated!

---

<div class="post-metadata">

**Author:** ![m\_ashurkina](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/m_ashurkina/32/25068_2.png) [@m\_ashurkina](https://forum.rasa.com/u/m_ashurkina)\
**Post date:** [March 25, 2025, 9:01am UTC](https://forum.rasa.com/t/how-to-make-a-rasa-chatbot-learn-from-a-pdf-without-defining-intents-manually/66535/2 "2025-03-25T09:01:00Z")

</div>

Hi @iggy, it’s great that you are building with Rasa. It would be much easier to implement this functionality using Rasa Pro & CALM. CALM has EnterpriseSearchPolicy which handles all how-to questions and can extract information from provided docs. You can get free developer key [here](https://rasa.com/rasa-pro-developer-edition-license-key-request/). Read more about Enterpise Search Policy [here](https://rasa.com/docs/reference/config/policies/enterprise-search-policy/). Let me know if you have any further questions.