lfoppiano commited on
Commit
d454fcb
1 Parent(s): 532d210

add more precise documentation

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -14,20 +14,20 @@ license: apache-2.0
14
 
15
  ## Introduction
16
 
17
- Question/Answering on scientific documents using LLMs (OpenAI, Mistral, LLama2, etc..).
18
  This application is the frontend for testing the RAG (Retrieval Augmented Generation) on scientific documents, that we are developing at NIMS.
19
  Differently to most of the project, we focus on scientific articles and we are using [Grobid](https://github.com/kermitt2/grobid) for text extraction instead of the raw PDF2Text converter (which is comparable with most of other solutions) allow to extract only full-text.
20
 
21
  **Work in progress**
22
 
23
  **Demos**:
24
- - (on HF spaces): https://lfoppiano-document-qa.hf.space/
25
- - (on streamlit.io): https://document-insights.streamlit.app/
26
 
27
  ## Getting started
28
 
29
- - Select the model+embedding combination you want ot use (for LLama2 you must acknowledge their licence both on meta.com and on huggingface. See [here](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf)).
30
- - Enter your API Key (Open AI or Huggingface).
31
  - Upload a scientific article as PDF document. You will see a spinner or loading indicator while the processing is in progress.
32
  - Once the spinner stops, you can proceed to ask your questions
33
 
 
14
 
15
  ## Introduction
16
 
17
+ Question/Answering on scientific documents using LLMs (OpenAI, Mistral, ~~LLama2,~~ etc..).
18
  This application is the frontend for testing the RAG (Retrieval Augmented Generation) on scientific documents, that we are developing at NIMS.
19
  Differently to most of the project, we focus on scientific articles and we are using [Grobid](https://github.com/kermitt2/grobid) for text extraction instead of the raw PDF2Text converter (which is comparable with most of other solutions) allow to extract only full-text.
20
 
21
  **Work in progress**
22
 
23
  **Demos**:
24
+ - (on HuggingFace spaces): https://lfoppiano-document-qa.hf.space/
25
+ - (on the Streamlit cloud): https://document-insights.streamlit.app/
26
 
27
  ## Getting started
28
 
29
+ - Select the model+embedding combination you want ot use ~~(for LLama2 you must acknowledge their licence both on meta.com and on huggingface. See [here](https://huggingface.co/meta-llama/Llama-2-70b-chat-hf))~~(Llama2 was removed due to API limitations).
30
+ - Enter your API Key ([Open AI](https://platform.openai.com/account/api-keys) or [Huggingface](https://huggingface.co/docs/hub/security-tokens)).
31
  - Upload a scientific article as PDF document. You will see a spinner or loading indicator while the processing is in progress.
32
  - Once the spinner stops, you can proceed to ask your questions
33