# Adding special symbols in the chunks and Does it affect the retrieval to pick up the right chunks?

**URL:** <https://forum.weaviate.io/t/adding-special-symbols-in-the-chunks-and-does-it-affect-the-retrieval-to-pick-up-the-right-chunks/21360>\
**Category:** General\
**Tags:** technical\
**Created:** [June 12, 2025, 1:26pm UTC](https://forum.weaviate.io/t/adding-special-symbols-in-the-chunks-and-does-it-affect-the-retrieval-to-pick-up-the-right-chunks/21360 "2025-06-12T13:26:21Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Sudhakar](https://avatars.discourse-cdn.com/v4/letter/s/f05b48/32.png) [@Sudhakar](https://forum.weaviate.io/u/Sudhakar)\
**Post date:** [June 12, 2025, 1:26pm UTC](https://forum.weaviate.io/t/adding-special-symbols-in-the-chunks-and-does-it-affect-the-retrieval-to-pick-up-the-right-chunks/21360/1 "2025-06-12T13:26:21Z")

</div>

I have a markdown file and chunk it using LangchainNodeparser - Recursive splitter with markdown language. It returns the chunk with markdown symbols. Since LLM can natively speak the markdown format, I write directly without post processing them in weaviate. Does this special symbol influence the retrieval score in a negative way?

---

<div class="post-metadata">

**Author:** ![Shahin](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/shahin/32/7944_2.png) [@Shahin](https://forum.weaviate.io/u/Shahin)\
**Post date:** [June 13, 2025, 7:04am UTC](https://forum.weaviate.io/t/adding-special-symbols-in-the-chunks-and-does-it-affect-the-retrieval-to-pick-up-the-right-chunks/21360/2 "2025-06-13T07:04:09Z")

</div>

Hi @Sudhakar, Happy Friday 🥳

Welcome to our community — it’s great to have you here! 🤗

From a Weaviate perspective, here’s helpful docs regarding symbols & tokenization and search:

> **[Tokenization and searches | Weaviate](https://weaviate.io/developers/academy/py/tokenization/searches#variable_name-vs-variable-name---symbols)**
>
> You saw how tokenization affects filters. They impact keyword searches in a similar, but not identical, way. In this section, we'll see how different tokenization methods impact search results.

Best regards,

**Mohamed Shahin**  
Weaviate Support Engineer  
(Ireland, GMT/UTC timezone)