# SentenceTransformers embedding tool has a maximum context length of 256 tokens, not characters, right?

**URL:** <https://community.deeplearning.ai/t/sentencetransformers-embedding-tool-has-a-maximum-context-length-of-256-tokens-not-characters-right/535555>\
**Category:** Advanced Retrieval for AI with Chroma\
**Created:** [January 4, 2024, 6:17pm UTC](https://community.deeplearning.ai/t/sentencetransformers-embedding-tool-has-a-maximum-context-length-of-256-tokens-not-characters-right/535555 "2024-01-04T18:17:36Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![nealmcb](https://avatars.discourse-cdn.com/v4/letter/n/73ab20/32.png) [@nealmcb](https://community.deeplearning.ai/u/nealmcb)\
**Post date:** [January 4, 2024, 6:17pm UTC](https://community.deeplearning.ai/t/sentencetransformers-embedding-tool-has-a-maximum-context-length-of-256-tokens-not-characters-right/535555/1 "2024-01-04T18:17:36Z")

</div>

At 4:00 in the video for [https://learn.deeplearning.ai/advanced-retrieval-for-ai/lesson/2/overview-of-embeddings-based-retrieval](https://learn.deeplearning.ai/advanced-retrieval-for-ai/lesson/2/overview-of-embeddings-based-retrieval) you say that the maximum embedding context window length is 256 characters, but later on you clarify that it is 256 tokens, which I assume is correct. Otherwise picking a 1000-character default for splitting would make no sense.

---

<div class="post-metadata">

**Author:** ![Martin\_Pollard](https://avatars.discourse-cdn.com/v4/letter/m/aca169/32.png) [@Martin\_Pollard](https://community.deeplearning.ai/u/Martin_Pollard)\
**Post date:** [January 5, 2024, 4:19am UTC](https://community.deeplearning.ai/t/sentencetransformers-embedding-tool-has-a-maximum-context-length-of-256-tokens-not-characters-right/535555/2 "2024-01-05T04:19:28Z")

</div>

Hi nealmcb,

Pretty sure it’s tokens.