Spaces:
Sleeping
Sleeping
Vinh Nguyen
commited on
Commit
•
87c1f2e
1
Parent(s):
9caad80
Update README.md
Browse files
README.md
CHANGED
@@ -20,8 +20,8 @@
|
|
20 |
|
21 |
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
|
22 |
|
23 |
-
![GitHub User's stars](https://img.shields.io/github/stars/vinhnx)
|
24 |
-
![HackerNews User Karma](https://img.shields.io/hackernews/user-karma/vinhnx)
|
25 |
[![X (formerly Twitter) Follow](https://img.shields.io/twitter/follow/vinhnx)](https://x.com/vinhnx)
|
26 |
|
27 |
`InkChatGPT` is a `Streamlit` application that allows users to upload PDF documents and engage in a conversational Q&A with a language model (`LLM`) based on the content of those documents.
|
@@ -30,10 +30,9 @@
|
|
30 |
|
31 |
- Upload any PDF documents and start asking key information about it, currently supports: PDF, TXT, DOCX, EPUB
|
32 |
- Limit 200MB per file
|
33 |
-
- Conversational Q&A with LLM (powered by `OpenAI`'s
|
34 |
-
-
|
35 |
-
-
|
36 |
-
- Responsive UI with loading indicators and chat interface
|
37 |
|
38 |
## Prerequisites
|
39 |
|
|
|
20 |
|
21 |
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
|
22 |
|
23 |
+
[![GitHub User's stars](https://img.shields.io/github/stars/vinhnx)](https://github.com/vinhnx)
|
24 |
+
[![HackerNews User Karma](https://img.shields.io/hackernews/user-karma/vinhnx)](https://news.ycombinator.com/user?id=vinhnx)
|
25 |
[![X (formerly Twitter) Follow](https://img.shields.io/twitter/follow/vinhnx)](https://x.com/vinhnx)
|
26 |
|
27 |
`InkChatGPT` is a `Streamlit` application that allows users to upload PDF documents and engage in a conversational Q&A with a language model (`LLM`) based on the content of those documents.
|
|
|
30 |
|
31 |
- Upload any PDF documents and start asking key information about it, currently supports: PDF, TXT, DOCX, EPUB
|
32 |
- Limit 200MB per file
|
33 |
+
- Conversational Q&A with LLM (powered by `OpenAI`'s `gpt-3.5-turbo` model)
|
34 |
+
- `HuggingFace` embeddings to generate embeddings for the document chunks with `all-MiniLM-L6-v2` model.
|
35 |
+
- `VectorDB` for document vector retrieval storage
|
|
|
36 |
|
37 |
## Prerequisites
|
38 |
|