Spaces:
Running
Running
Richard Fan
commited on
Commit
·
3c0c20a
1
Parent(s):
eab4e05
update readme
Browse files
README.md
CHANGED
|
@@ -3,6 +3,8 @@ This repo aims to provide a better daily digest for newly published arXiv papers
|
|
| 3 |
|
| 4 |
You can try it out at [https://huggingface.co/spaces/AutoLLM/ArxivDigest](https://huggingface.co/spaces/AutoLLM/ArxivDigest) using your own OpenAI api key.
|
| 5 |
|
|
|
|
|
|
|
| 6 |
## 📚 Contents
|
| 7 |
|
| 8 |
- [What this repo does](#🔍-what-this-repo-does)
|
|
@@ -26,8 +28,15 @@ This repository offers a method to curate a daily digest, sorted by relevance, u
|
|
| 26 |
* The code pulls all the abstracts for papers in those categories and ranks how relevant they are to your interest on a scale of 1-10 using `gpt-3.5-turbo`.
|
| 27 |
* The code then emits an HTML digest listing all the relevant papers, and optionally emails it to you using [SendGrid](https://sendgrid.com). You will need to have a SendGrid account with an API key for this functionality to work.
|
| 28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
-
### Some examples:
|
| 31 |
|
| 32 |
#### Digest Configuration:
|
| 33 |
- Subject/Topic: Computer Science
|
|
@@ -50,14 +59,6 @@ This repository offers a method to curate a daily digest, sorted by relevance, u
|
|
| 50 |
|
| 51 |
## 💡 Usage
|
| 52 |
|
| 53 |
-
### Hugging Face
|
| 54 |
-
|
| 55 |
-
The easiest way to get started is at [https://huggingface.co/spaces/AutoLLM/ArxivDigest](https://huggingface.co/spaces/AutoLLM/ArxivDigest). Simply enter your [OpenAI API key](https://platform.openai.com/account/api-keys) and then fill in the configuration on the right. Note that we do not store your key.
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
You can also send yourself an email of the digest by creating a SendGrid account and [api key](https://app.SendGrid.com/settings/api_keys).
|
| 60 |
-
|
| 61 |
### Running as a github action using SendGrid (Recommended).
|
| 62 |
|
| 63 |
The recommended way to get started using this repository is to:
|
|
|
|
| 3 |
|
| 4 |
You can try it out at [https://huggingface.co/spaces/AutoLLM/ArxivDigest](https://huggingface.co/spaces/AutoLLM/ArxivDigest) using your own OpenAI api key.
|
| 5 |
|
| 6 |
+
You can also create a daily subscription pipeline to email you the results.
|
| 7 |
+
|
| 8 |
## 📚 Contents
|
| 9 |
|
| 10 |
- [What this repo does](#🔍-what-this-repo-does)
|
|
|
|
| 28 |
* The code pulls all the abstracts for papers in those categories and ranks how relevant they are to your interest on a scale of 1-10 using `gpt-3.5-turbo`.
|
| 29 |
* The code then emits an HTML digest listing all the relevant papers, and optionally emails it to you using [SendGrid](https://sendgrid.com). You will need to have a SendGrid account with an API key for this functionality to work.
|
| 30 |
|
| 31 |
+
### Testing it out with Hugging Face:
|
| 32 |
+
|
| 33 |
+
We provide a demo at [https://huggingface.co/spaces/AutoLLM/ArxivDigest](https://huggingface.co/spaces/AutoLLM/ArxivDigest). Simply enter your [OpenAI API key](https://platform.openai.com/account/api-keys) and then fill in the configuration on the right. Note that we do not store your key.
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
You can also send yourself an email of the digest by creating a SendGrid account and [api key](https://app.SendGrid.com/settings/api_keys).
|
| 38 |
|
| 39 |
+
### Some examples of results:
|
| 40 |
|
| 41 |
#### Digest Configuration:
|
| 42 |
- Subject/Topic: Computer Science
|
|
|
|
| 59 |
|
| 60 |
## 💡 Usage
|
| 61 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
### Running as a github action using SendGrid (Recommended).
|
| 63 |
|
| 64 |
The recommended way to get started using this repository is to:
|