Add docs for universal sentence encoder embedding function

docs/embeddings.md

@@ -21,6 +21,8 @@ Chroma provides lightweight wrappers around popular embedding providers, making
 | [Hugging Face Embedding Server](/embeddings/hugging-face-embedding-server) | ✅  | ✅ |
 | [Jina AI](/embeddings/jinaai) | ✅  | ✅ |
 | [Roboflow](/embeddings/roboflow-api) | ✅  | ➖ |
+| [Universal Sentence Encoder](/embeddings/universal-sentence-encoder) | ✅ | ➖ |
+
 
 We welcome pull requests to add new Embedding Functions to the community.
 

docs/embeddings/universal-sentence-encoder.md

@@ -0,0 +1,44 @@
+---
+---
+
+# Universal Sentence Encoder
+
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+<div class="select-language">Select a language</div>
+
+<Tabs queryString groupId="lang">
+<TabItem value="py" label="Python"></TabItem>
+<TabItem value="js" label="JavaScript"></TabItem>
+</Tabs>
+
+
+<Tabs queryString groupId="lang" className="hideTabSwitcher">
+<TabItem value="py" label="Python">
+
+Chroma also provides a convenient wrapper around [Universal Sentence Encoder](https://research.google.com/pubs/archive/46808.pdf)
+
+This embedding function uses models hosted on [Tensorflow Hub](https://tfhub.dev/). 
+
+This embedding function relies on the `tensforflow_hub` python package, which you can install with `pip install tensforflow_hub`.
+
+```python
+import chromadb.utils.embedding_functions as embedding_functions
+huggingface_ef = embedding_functions.UniversalSentenceEncoderEmbeddingFunction()
+
+huggingface_ef([
+    "The quick brown fox jumps over the lazy dog.",
+    "I am a sentence for which I would like to get its embedding"])
+
+```
+
+
+You can pass in an optional `model_name` argument, which lets you choose which model to use. By default, Chroma uses [Universal Sentence Encoder 4](https://tfhub.dev/google/universal-sentence-encoder/4) provided by Tensorflow Hub
+</TabItem>
+<TabItem value="js" label="JavaScript">
+
+  Support for [Universal Sentence Encoder](https://research.google.com/pubs/archive/46808.pdf) embedding function is not implemented yet. Feel free to contribute by following the doc: [Custom Embedding Functions](https://docs.trychroma.com/embeddings?lang=js)
+
+</TabItem>
+</Tabs>

sidebars.js

@@ -93,8 +93,8 @@ const sidebars = {
         'embeddings/hugging-face-embedding-server',
         'embeddings/instructor',
         'embeddings/roboflow-api',
-        'embeddings/hugging-face-embedding-server',
         'embeddings/jinaai',
+        'embeddings/universal-sentence-encoder',
       ],
     },
   ],