Mishig
commited on
Commit
•
afbf680
1
Parent(s):
e943a05
Update README.md (#455)
Browse files
README.md
CHANGED
|
@@ -77,7 +77,7 @@ 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/
|
| 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 |
|
|
|
|
| 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/gte-small](https://huggingface.co/Xenova/gte-small) 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 |
|