fm1320 commited on
Commit
6b493a7
·
verified ·
1 Parent(s): a9e2051

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +44 -0
README.md CHANGED
@@ -11,3 +11,47 @@ short_description: Superlinked powered AI research paper agent
11
  ---
12
 
13
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
14
+
15
+ # Research AI Agent
16
+
17
+ A Gradio application that provides an AI-powered research assistant for academic papers.
18
+
19
+ ## Features
20
+
21
+ - **Paper Retrieval**: Find relevant research papers based on your query
22
+ - **Paper Summarization**: Generate concise summaries of selected papers
23
+ - **Question Answering**: Ask questions about research topics and get AI-generated answers
24
+
25
+ ## Setup Instructions
26
+
27
+ This application uses OpenAI's API. You need to provide an API key as a secret in your Hugging Face Space:
28
+
29
+ 1. Go to your Space settings
30
+ 2. Add a secret with the key `OPENAI_API_KEY` and your OpenAI API key as the value
31
+
32
+ ## How to Use
33
+
34
+ ### General Query
35
+ Enter any research-related query, and the agent will classify it as retrieval, summarization, or question answering automatically.
36
+
37
+ ### Paper Retrieval
38
+ Search for papers on specific topics by entering a search query. Results include publication dates and summaries.
39
+
40
+ ### Paper Summarization
41
+ 1. Enter comma-separated paper IDs
42
+ 2. Click "View Available Papers" to see a list of paper IDs in the dataset
43
+ 3. Click "Summarize" to generate a summary of the selected papers
44
+
45
+ ### Question Answering
46
+ Ask specific questions about research topics, and the agent will provide answers based on the paper database.
47
+
48
+ ## Technology
49
+
50
+ - **Superlinked**: For vector-based similarity search and time-aware paper discovery
51
+ - **Sentence Transformers**: For text embedding
52
+ - **OpenAI**: For LLM-based summarization and question answering
53
+ - **Gradio**: For the user interface
54
+
55
+ ## Dataset
56
+
57
+ The application uses a dataset of AI research papers from arXiv.