Skip to content

Commit 8e300b6

Browse files
gary149mishig25Mishig
authored
Update README.md (#435)
* Update README.md * add description of websearch on readme * Apply suggestions from code review Co-authored-by: Victor Muštar <[email protected]> * Update README.md --------- Co-authored-by: Mishig Davaadorj <[email protected]> Co-authored-by: Mishig <[email protected]>
1 parent e5afba2 commit 8e300b6

File tree

1 file changed

+15
-4
lines changed

1 file changed

+15
-4
lines changed

README.md

Lines changed: 15 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -12,16 +12,17 @@ app_port: 3000
1212

1313
# Chat UI
1414

15-
![Chat UI repository thumbnail](https://huggingface.co/datasets/huggingface/documentation-images/raw/f038917dd40d711a72d654ab1abfc03ae9f177e6/chat-ui-repo-thumbnail.svg)
15+
![Chat UI repository thumbnail](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chatui-websearch.png)
1616

1717
A chat interface using open source models, eg OpenAssistant or Llama. It is a SvelteKit app and it powers the [HuggingChat app on hf.co/chat](https://huggingface.co/chat).
1818

1919
0. [No Setup Deploy](#no-setup-deploy)
2020
1. [Setup](#setup)
2121
2. [Launch](#launch)
22-
3. [Extra parameters](#extra-parameters)
23-
4. [Deploying to a HF Space](#deploying-to-a-hf-space)
24-
5. [Building](#building)
22+
3. [Web Search](#web-search)
23+
4. [Extra parameters](#extra-parameters)
24+
5. [Deploying to a HF Space](#deploying-to-a-hf-space)
25+
6. [Building](#building)
2526

2627
##  No Setup Deploy
2728

@@ -70,6 +71,16 @@ npm install
7071
npm run dev
7172
```
7273

74+
## Web Search
75+
76+
Chat UI features a powerful Web Search feature. It works by:
77+
78+
1. Generating an appropriate Google query from the user prompt.
79+
2. Performing Google search and extracting content from webpages.
80+
3. Creating embeddings from texts using [transformers.js](https://huggingface.co/docs/transformers.js). Specifically, using [Xenova/e5-small-v2](https://huggingface.co/Xenova/e5-small-v2) model.
81+
4. From these embeddings, find the ones that are closest to the user query using vector similarity search. Specifically, we use `inner product` distance.
82+
5. Get the corresponding texts to those closest embeddings and perform [Retrieval-Augmented Generation](https://huggingface.co/papers/2005.11401) (i.e. expand user prompt by adding those texts so that a LLM can use this information).
83+
7384
## Extra parameters
7485

7586
### OpenID connect

0 commit comments

Comments
 (0)