spaces init

README.md

@@ -1,3 +1,15 @@
+----
+-title: Surveyor
+-emoji: 📊
+-colorFrom: gray
+-colorTo: pink
+-sdk: streamlit
+-sdk_version: 1.9.0
+-app_file: app.py
+-pinned: false
+-license: apache-2.0
+----
+
 # Auto-Research
 ![Auto-Research][logo]
 
@@ -22,32 +34,23 @@ Kaggle Re-usable Demo : https://www.kaggle.com/sidharthpal/auto-research-generat
 (`[TIP]` click 'edit and run' to run the demo for your custom queries on a free GPU)
 
 
-#### Steps to run (pip coming soon):
+#### Installation:
+```
+sudo apt-get install build-essential poppler-utils libpoppler-cpp-dev pkg-config python-dev
+pip install git+https://github.com/sidphbot/Auto-Research.git
 ```
-apt install -y poppler-utils libpoppler-cpp-dev
-git clone https://github.com/sidphbot/Auto-Research.git
 
-cd Auto-Research/
-pip install -r requirements.txt
+#### Run Survey (cli):
+```
 python survey.py [options] <your_research_query>
 ```
 
-#### Artifacts generated (zipped):
-- Detailed survey draft paper as txt file
-- A curated list of top 25+ papers as pdfs and txts
-- Images extracted from above papers as jpegs, bmps etc
-- Heading/Section wise highlights extracted from above papers as a re-usable pure python joblib dump
-- Tables extracted from papers(optional)
-- Corpus of metadata highlights/text of top 100 papers as a re-usable pure python joblib dump
-
-## Example run #1 - python utility
-
+#### Run Survey (Streamlit web-interface - new):
 ```
-python survey.py 'multi-task representation learning'
+streamlit run app.py
 ```
 
-## Example run #2 - python class
-
+#### Run Survey (Python API):
 ```
 from survey import Surveyor
 mysurveyor = Surveyor()
@@ -264,4 +267,17 @@ optional arguments:
     > during survey generation with `surveyor_obj.survey(query="my_research_query")`
     - `max_search`: int maximium number of papers to gaze at - defaults to `100`
     - `num_papers`: int maximium number of papers to download and analyse - defaults to `25`
+
+
+
+#### Artifacts generated (zipped):
+- Detailed survey draft paper as txt file
+- A curated list of top 25+ papers as pdfs and txts
+- Images extracted from above papers as jpegs, bmps etc
+- Heading/Section wise highlights extracted from above papers as a re-usable pure python joblib dump
+- Tables extracted from papers(optional)
+- Corpus of metadata highlights/text of top 100 papers as a re-usable pure python joblib dump
+
+
+Please cite this repo if it helped you :)
     

app.py

@@ -2,7 +2,7 @@ import streamlit as st
 import pandas as pd
 import numpy as np
 
-#from src.Surveyor import Surveyor
+from src.Surveyor import Surveyor
 
 def run_survey(surveyor, research_keywords, max_search, num_papers):
     zip_file_name, survey_file_name = surveyor.survey(research_keywords, 
@@ -21,16 +21,10 @@ def run_survey(surveyor, research_keywords, max_search, num_papers):
         btn = st.download_button(
              label="Download detailed generated survey file",
              data=file,
-             file_name=str(zip_file_name)
-           )
-
-    with open(str(survey_file_name), "rb") as file:
-        btn = st.download_button(
-             label="Download detailed generated survey file",
-             data=file,
-             file_name=str(zip_file_name)
+             file_name=str(survey_file_name)
            )
-        st.write(file.readlines())
+        for line in file.readlines():
+            st.write(line)
 
 
 def survey_space():
@@ -47,9 +41,9 @@ def survey_space():
 
     if submit:
         st.write("hello")
-        #if surveyor_obj is None:
-        #    surveyor_obj = Surveyor()
-        #run_survey(surveyor_obj, research_keywords, max_search, num_papers)
+        if surveyor_obj is None:
+            surveyor_obj = Surveyor()
+        run_survey(surveyor_obj, research_keywords, max_search, num_papers)
 
 
 if __name__ == '__main__':