initial app commit

Dockerfile

@@ -11,4 +11,4 @@ RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
 
 COPY . .
 
-CMD ["panel", "serve", "/code/app.py","--address", "0.0.0.0", "--port", "7860", "--allow-websocket-origin","easysci-panel-main.hf.space"]
+CMD ["panel", "serve", "/code/app2.py","--address", "0.0.0.0", "--port","7860","--allow-websocket-origin","easysci-panel-example7.hf.space"]

README.md

@@ -1,8 +1,8 @@
 ---
-title: Panel Main
-emoji: 😻
-colorFrom: green
-colorTo: pink
+title: Panel Example7
+emoji: 🌍
+colorFrom: yellow
+colorTo: blue
 sdk: docker
 pinned: false
 ---

TLDR.py

@@ -0,0 +1,73 @@
+import panel as pn
+import pytz
+from datetime import date
+from datetime import datetime
+from dateutil.relativedelta import relativedelta, MO
+import param
+import json
+
+from functools import partial
+from src.search import Search_Papers
+
+
+def load_categories():
+    # f = open("categories_general.txt", "r")
+    # list_categories = f.read().splitlines() 
+
+    # reading the data from the file
+    with open('categories_arxiv.txt') as f:
+        data = f.read()
+    # reconstructing the data as a dictionary
+    category_dict = json.loads(data)
+    
+    return category_dict
+
+
+def run_code(category, loaded_dict, event = None):
+    timeframe_today = (datetime.combine(date.today(), datetime.min.time())).replace(tzinfo = pytz.utc)
+    timeframe_week = timeframe_today + relativedelta(weekday=MO(-1))
+    
+    timeframe_day = (datetime.combine(datetime(2023, 7, 16), datetime.min.time())).replace(tzinfo = pytz.utc)
+
+    search_mode = "Timeframe" #Accepted values: 'NumberResults' and 'Timeframe
+    sort_by = "PublishDate" #Accepted values: 'PublishDate', 'LastUpdatedDate' and 'Relevance'
+    sort_order = "Descending" #Accepted values: 'Ascending' and 'Descending' 
+
+        
+    query = list(loaded_dict.keys())[list(loaded_dict.values()).index(category)]
+    
+    search = Search_Papers(query, search_mode, timeframe_week, sort_by, sort_order)
+    result_arxiv = search.search_arxiv()
+    
+
+    return result_arxiv
+
+
+def update_mainTLDR(buttons_to_add, paper_list):
+    main_tldr = []
+
+    if buttons_to_add:
+        for i in range(len(buttons_to_add)):
+            category_content = []
+            for paper in paper_list[i]:
+
+                paper_content = pn.Column(
+                    pn.pane.LaTeX(f"{paper.title}", styles={'font-size': '18pt'}),
+                    pn.pane.LaTeX(paper.summary, styles={'font-size': '14pt'}),
+                    pn.pane.Markdown("### " + (paper.published).strftime("%d/%m/%Y %H:%M:%S")),
+                    sizing_mode='stretch_width'
+                )
+                category_content.append(paper_content)
+
+            category_column = pn.Column(
+                pn.pane.Markdown(f"# {buttons_to_add[i]}"),
+                *category_content,
+                sizing_mode='stretch_width'
+            )
+
+            main_tldr.append(category_column)
+
+    else:
+        main_tldr.append(pn.pane.Markdown("# Please select some tags!"))
+
+    return main_tldr

app.py

@@ -1,42 +1,154 @@
 import panel as pn
-import hvplot.pandas
+pn.extension('katex')
+
+import pytz
+from datetime import date
+from datetime import datetime
+from dateutil.relativedelta import relativedelta, MO
 import param
 
-# Load Data
-from bokeh.sampledata.autompg import autompg_clean as df
+import TLDR
+from src.search import Search_Papers
+
+class MainBody(param.Parameterized):
+    main_body = param.List(default=[pn.pane.LaTeX("Please select some tags!", styles={'font-size': '20pt'})])
+
+    @param.depends("main_body")
+    def update(self):
+        return pn.Column(*self.main_body)
+
+main_body_instance = MainBody()
+
+paper_list = []  # Add this line to initialize paper_list as an empty list
+
+main_body = [pn.pane.LaTeX("Please select some tags!", styles={'font-size': '20pt'})]
+
+# Create buttons for the toggleable sidebar
+# button1 = pn.widgets.Button(name="🏠 Home", button_type='default', button_style='outline', width=140)
+# button2 = pn.widgets.Button(name='📁 My papers', button_type='default', button_style='outline', width=140)
+# button3 = pn.widgets.Toggle(name='⚙️ Settings', button_type='default', button_style='outline', width=140, value=False)
+
+# Create buttons for the toggleable sidebar
+button1 = pn.widgets.Button(icon='home', name="Daily papers", icon_size='1.5em', button_type = 'primary', button_style = 'outline', width = 140)
+button2 = pn.widgets.Button(icon='calendar-filled', name="Search papers", icon_size='1.5em', button_type = 'primary', button_style = 'outline', width = 140)
+button3 = pn.widgets.Button(icon='file-analytics', name='My papers', icon_size='1.5em', button_type = 'primary', button_style = 'outline', width = 140)
+button4 = pn.widgets.Toggle(name='Accessibility',icon='settings', icon_size='1.5em', button_type='default', button_style='outline', width=140, value=False)
+
+# Custom RadioButtonGroup widget
+select = pn.widgets.RadioButtonGroup(value="Scientic", options=["General", "Scientic"], name='String', align='center', button_type='default') # , align='center'
+select2 = pn.widgets.RadioButtonGroup(value="Normal", options=["Bionic", "Normal"], name='String', align='center', button_type='default')
+
+# Define a callback to display the selected value
+def display_selected_value(event):
+    print(f"Selected value: {event.new}", flush=True)
+
+# Attach the callback to the value_change event of the RadioButtonGroup
+select.param.watch(display_selected_value, 'value')
+select2.param.watch(display_selected_value, 'value')
+
+
+# Create a column layout for the buttons inside the toggleable sidebar
+buttons = pn.Column(
+    button1, button2, button3,
+    pn.Column(
+        select,
+        select2,
+        visible=True,
+        sizing_mode='stretch_width',
+    ),
+    css_classes=['hidden']
+)
+
+# Define a callback to show/hide the select buttons when "Settings" button is toggled
+def toggle_settings(event):
+    buttons[-1].visible = event.new
 
-# create a self-contained dashboard class
-class InteractiveDashboard(param.Parameterized):
-    cylinders =  param.Integer(label='Cylinders', default=4, bounds=(4, 8))
-    mfr = param.ListSelector(
-        label='MFR',
-        default=['ford', 'chevrolet', 'honda', 'toyota', 'audi'], 
-        objects=['ford', 'chevrolet', 'honda', 'toyota', 'audi'], precedence=0.5)
-    yaxis = param.Selector(label='Y axis', objects=['hp', 'weight'])
+button3.param.watch(toggle_settings, 'value')
 
+# List to store the entered options
+loaded_dict = TLDR.load_categories()
+
+arxiv_tags = list(loaded_dict.keys())
+entered_options = list(loaded_dict.values())
+
+# Create buttons for the header
+header_buttons = pn.Row(sizing_mode='stretch_width', css_classes=['header-buttons'])
+
+# "+" button to trigger the addition to the header
+add_to_header_button = pn.widgets.Button(name="", icon='search', icon_size='1.5em', button_style = 'outline',button_type = 'light')
+
+# List to store the names of buttons to be added to the header
+buttons_to_add = []
+
+paper_list = []
+
+# Callback for adding selected options to the list
+def add_to_header(event):
+    global paper_list
     
-    @param.depends('cylinders', 'mfr', 'yaxis')
-    def plot(self):
-        return (
-            df[
-                (df.cyl == self.cylinders) & 
-                (df.mfr.isin(self.mfr))
-            ]
-            .groupby(['origin', 'mpg'])[self.yaxis].mean()
-            .to_frame()
-            .reset_index()
-            .sort_values(by='mpg')  
-            .reset_index(drop=True)
-            .hvplot(x='mpg', y=self.yaxis, by='origin', color=["#ff6f69", "#ffcc5c", "#88d8b0"], line_width=6, height=400)
-        )
-dashboard = InteractiveDashboard()
+    selected_options = filter_list.value
+    if selected_options:
+        for option in selected_options:
+            if option not in buttons_to_add:  # Check if option is already in header
+                buttons_to_add.append(option)  # Add to header if not already present
+
+                paper_list_itr = TLDR.run_code(option, loaded_dict)
+                paper_list.append(paper_list_itr)
+        filter_list.value = []  # Clear the selected options after adding them to the header
+        update_header()  # Update the header after adding options
 
+
+add_to_header_button.on_click(add_to_header)
+
+# Function to update the header layout with the newly created buttons
+def update_header():
+    global paper_list
+    header_buttons.clear()  # Clear the existing buttons
+
+    for button_name in buttons_to_add:
+        header_button = pn.widgets.Button(name=button_name, button_type = 'primary', button_style = 'outline')
+        header_button.on_click(remove_from_header)  # Add callback to remove the header button
+        header_buttons.append(header_button)
+    buttons_to_add
+    # Update the filter list options to exclude buttons that are already in the header
+    filter_list.options = [option for option in entered_options if option not in buttons_to_add]
+    main_body_instance.main_body = TLDR.update_mainTLDR(buttons_to_add, paper_list)
+    
+# Callback to remove the clicked header button
+def remove_from_header(event):
+    global paper_list
+    button = event.obj  # Get the clicked button
+    if button.name in buttons_to_add:
+        del paper_list[buttons_to_add.index(button.name)]
+        buttons_to_add.remove(button.name)  # Remove from the header buttons list
+        filter_list.options.append(button.name)  # Add back to the filter list options
+    update_header()  # Update the header and filter list
+    
+# MultiChoice widget to display the filter options with delete buttons
+filter_list = pn.widgets.MultiChoice(
+    name='',
+    value=[],
+    options=entered_options,
+    margin=(20, 10),
+    sizing_mode='fixed',
+    solid=False,
+    styles={'background': '#f0f0f0'},
+    placeholder="Search Topics"
+)
+   
 # Layout using Template
 template = pn.template.FastListTemplate(
-    title='Interactive DataFrame Dashboards with param .depends', 
-    sidebar=[pn.Param(dashboard.param, widgets={'mfr': pn.widgets.ToggleGroup,'yaxis': pn.widgets.RadioButtonGroup})],
-    main=[dashboard.plot],
+    title="EasySciRead",
+    header=[pn.Row(header_buttons, width=750, sizing_mode='stretch_width'), pn.Row(filter_list, width=250), pn.Row(add_to_header_button, width=55)],
+    main= main_body_instance.update,
+    sidebar=[buttons],
     accent_base_color="#88d8b0",
-    header_background="#88d8b0",
+    header_background="#FFFFFF",
+    header_color="#000000",
+    text_align='center',
+    sidebar_width=160,
+    sizing_mode = 'stretch_both'
 )
+
+# Run the app
 template.servable()

app2.py

@@ -0,0 +1,209 @@
+import panel as pn
+pn.extension('katex')
+
+import pytz
+from datetime import date
+from datetime import datetime
+from dateutil.relativedelta import relativedelta, MO
+import param
+
+import TLDR
+from src.search import Search_Papers
+
+# Create the MainBody class
+class MainBody(param.Parameterized):
+    main_body = param.List(default=[pn.pane.LaTeX("Please select some tags!", styles={'font-size': '20pt'})])
+
+    @param.depends("main_body")
+    def update(self):
+        return pn.Column(*self.main_body)
+
+# Initialize the MainBody instance
+main_body_instance = MainBody()
+
+# Store the initial content of the main panel in the MainBody instance
+main_body_instance.main_body = [pn.pane.LaTeX("Please select some tags!", styles={'font-size': '20pt'})]
+initial_main_body = main_body_instance.main_body.copy()
+
+# Function to reset the main panel content to the initial content
+def reset_main_panel(event):
+    # Clear the existing main panel content if it's not the initial content
+    if main_body_instance.main_body != initial_main_body:
+        main_body_instance.main_body.clear()
+        main_body_instance.main_body.extend(initial_main_body)
+        main_body_instance.param.trigger('main_body')  # Trigger the update manually
+
+paper_list = []  # Add this line to initialize paper_list as an empty list
+
+main_body = [pn.pane.LaTeX("Please select some tags!", styles={'font-size': '20pt'})]
+
+# Create buttons for the toggleable sidebar
+# button1 = pn.widgets.Button(name="🏠 Home", button_type='default', button_style='outline', width=140)
+# button2 = pn.widgets.Button(name='📁 My papers', button_type='default', button_style='outline', width=140)
+# button3 = pn.widgets.Toggle(name='⚙️ Settings', button_type='default', button_style='outline', width=140, value=False)
+
+# Create buttons for the toggleable sidebar
+button1 = pn.widgets.Button(icon='home', name="Daily papers", icon_size='1.5em', button_type = 'primary', button_style = 'outline', width = 140)
+button2 = pn.widgets.Button(icon='calendar-filled', name="Search papers", icon_size='1.5em', button_type = 'primary', button_style = 'outline', width = 140)
+button3 = pn.widgets.Button(icon='file-analytics', name='My papers', icon_size='1.5em', button_type = 'primary', button_style = 'outline', width = 140)
+button4 = pn.widgets.Toggle(name='Accessibility',icon='settings', icon_size='1.5em', button_type='default', button_style='outline', width=140, value=False)
+
+# Custom RadioButtonGroup widget
+select = pn.widgets.RadioButtonGroup(value="Scientic", options=["General", "Scientic"], name='String', align='center', button_type='default') # , align='center'
+select2 = pn.widgets.RadioButtonGroup(value="Normal", options=["Bionic", "Normal"], name='String', align='center', button_type='default')
+
+# Define a callback to display the selected value
+def display_selected_value(event):
+    print(f"Selected value: {event.new}", flush=True)
+
+# Attach the callback to the value_change event of the RadioButtonGroup
+select.param.watch(display_selected_value, 'value')
+select2.param.watch(display_selected_value, 'value')
+
+# Create a column layout for the buttons inside the toggleable sidebar
+buttons = pn.Column(
+    button1, button2, button3,
+    pn.Column(
+        select,
+        select2,
+        visible=True,
+        sizing_mode='stretch_width',
+    ),
+    css_classes=['hidden']
+)
+
+# Define a callback to show/hide the select buttons when "Settings" button is toggled
+def toggle_settings(event):
+    buttons[-1].visible = event.new
+
+button3.param.watch(toggle_settings, 'value')
+
+# Attach the reset_main_panel function to the on_click event of button1
+button1.on_click(reset_main_panel)
+
+# Function to update the main panel content when button3 is pressed
+def update_main_panel_button3(event):
+    main_body_instance.main_body.clear()  # Clear the existing main panel content
+    main_body_instance.main_body.append(pn.pane.Markdown("You pressed button3!"))
+    main_body_instance.param.trigger('main_body')  # Trigger the update manually
+
+# Attach the functions to the on_click event of button1 and button3
+button3.on_click(update_main_panel_button3)
+
+# Create the main panel with some initial content
+main_panel = pn.Column(pn.pane.Markdown("# Main Panel"))
+
+# Define a callback to show/hide the select buttons when "Settings" button is toggled
+def toggle_date_picker(event):
+    if event.new:
+        # Create a FloatPanel and place the DatePicker inside it
+        float_panel = pn.layout.FloatPanel(date_picker, name="Free Floating FloatPanel", contained=False, position='bottom_left')
+        float_panel.show()
+    else:
+        # Remove any existing FloatPanel if the toggle is set to False
+        try:
+            float_panel.close()
+        except NameError:
+            pass
+
+# List to store the entered options
+loaded_dict = TLDR.load_categories()
+
+arxiv_tags = list(loaded_dict.keys())
+entered_options = list(loaded_dict.values())
+
+# Create buttons for the header
+header_buttons = pn.Row(sizing_mode='stretch_width', css_classes=['header-buttons'])
+
+# "+" button to trigger the addition to the header
+add_to_header_button = pn.widgets.Button(name="", icon='search', icon_size='1.5em', button_style = 'outline',button_type = 'light')
+
+# List to store the names of buttons to be added to the header
+buttons_to_add = []
+
+paper_list = []
+
+# Callback for adding selected options to the list
+def add_to_header(event):
+    global paper_list
+    
+    selected_options = filter_list.value
+    if selected_options:
+        for option in selected_options:
+            if option not in buttons_to_add:  # Check if option is already in header
+                buttons_to_add.append(option)  # Add to header if not already present
+
+                paper_list_itr = TLDR.run_code(option, loaded_dict)
+                paper_list.append(paper_list_itr)
+        filter_list.value = []  # Clear the selected options after adding them to the header
+        
+        # Update the main panel content
+        main_body_instance.main_body = TLDR.update_mainTLDR(buttons_to_add, paper_list)
+        main_body_instance.param.trigger('main_body')  # Trigger the update manually
+
+add_to_header_button.on_click(add_to_header)
+
+# Function to update the header layout with the newly created buttons
+def update_header():
+    global paper_list
+    header_buttons.clear()  # Clear the existing buttons
+
+    for button_name in buttons_to_add:
+        header_button = pn.widgets.Button(name=button_name, button_type = 'primary', button_style = 'outline')
+        header_button.on_click(remove_from_header)  # Add callback to remove the header button
+        header_buttons.append(header_button)
+    buttons_to_add
+    # Update the filter list options to exclude buttons that are already in the header
+    filter_list.options = [option for option in entered_options if option not in buttons_to_add]
+    main_body_instance.main_body = TLDR.update_mainTLDR(buttons_to_add, paper_list)
+    
+# Callback to remove the clicked header button
+def remove_from_header(event):
+    global paper_list
+    button = event.obj  # Get the clicked button
+    if button.name in buttons_to_add:
+        del paper_list[buttons_to_add.index(button.name)]
+        buttons_to_add.remove(button.name)  # Remove from the header buttons list
+        filter_list.options.append(button.name)  # Add back to the filter list options
+    update_header()  # Update the header and filter list
+    # Update the main panel content
+    main_body_instance.main_body = TLDR.update_mainTLDR(buttons_to_add, paper_list)
+    main_body_instance.param.trigger('main_body')  # Trigger the update manually
+    
+# MultiChoice widget to display the filter options with delete buttons
+filter_list = pn.widgets.MultiChoice(
+    name='',
+    value=[],
+    options=entered_options,
+    margin=(20, 10),
+    sizing_mode='fixed',
+    solid=False,
+    styles={'background': '#f0f0f0'},
+    placeholder="Search Topics"
+)
+   
+# Layout using Template
+template = pn.template.FastListTemplate(
+    title="EasySciRead",
+    header=[
+        pn.Row(
+            header_buttons, width=750, sizing_mode='stretch_width'
+        ), 
+        pn.Row(filter_list, width=250), 
+        pn.Row(add_to_header_button, width=55)
+    ],
+    main=main_body_instance.update,
+    sidebar=[buttons],
+    accent_base_color="#88d8b0",
+    header_background="#FFFFFF",
+    header_color="#000000",
+    text_align='center',
+    sidebar_width=160,
+    sizing_mode='stretch_both'
+)
+
+# Update the header to populate the header buttons initially
+update_header()
+
+# Run the app
+template.servable()

categories_arxiv.txt

@@ -0,0 +1,154 @@
+{
+    "astro-ph.CO": "Cosmology and Nongalactic Astrophysics",
+    "astro-ph.EP": "Earth and Planetary Astrophysics",
+    "astro-ph.GA": "Astrophysics of Galaxies",
+    "astro-ph.HE": "High Energy Astrophysical Phenomena",
+    "astro-ph.IM": "Instrumentation and Methods for Astrophysics",
+    "astro-ph.SR": "Solar and Stellar Astrophysics",
+    "cond-mat.dis-nn": "Disordered Systems and Neural Networks",
+    "cond-mat.mes-hall": "Mesoscale and Nanoscale Physics",
+    "cond-mat.mtrl-sci": "Materials Science",
+    "cond-mat.other": "Other Condensed Matter",
+    "cond-mat.quant-gas": "Quantum Gases",
+    "cond-mat.soft": "Soft Condensed Matter",
+    "cond-mat.stat-mech": "Statistical Mechanics",
+    "cond-mat.str-el": "Strongly Correlated Electrons",
+    "cond-mat.supr-con": "Superconductivity",
+    "cs.AI": "Artificial Intelligence",
+    "cs.AR": "Hardware Architecture",
+    "cs.CC": "Computational Complexity",
+    "cs.CE": "Computational Engineering, Finance, and Science",
+    "cs.CG": "Computational Geometry",
+    "cs.CL": "Computation and Language",
+    "cs.CR": "Cryptography and Security",
+    "cs.CV": "Computer Vision and Pattern Recognition",
+    "cs.CY": "Computers and Society",
+    "cs.DB": "Databases",
+    "cs.DC": "Distributed, Parallel, and Cluster Computing",
+    "cs.DL": "Digital Libraries",
+    "cs.DM": "Discrete Mathematics",
+    "cs.DS": "Data Structures and Algorithms",
+    "cs.ET": "Emerging Technologies",
+    "cs.FL": "Formal Languages and Automata Theory",
+    "cs.GL": "General Literature",
+    "cs.GR": "Graphics",
+    "cs.GT": "Computer Science and Game Theory",
+    "cs.HC": "Human-Computer Interaction",
+    "cs.IR": "Information Retrieval",
+    "cs.IT": "Information Theory",
+    "cs.LG": "Machine Learning",
+    "cs.LO": "Logic in Computer Science",
+    "cs.MA": "Multiagent Systems",
+    "cs.MM": "Multimedia",
+    "cs.MS": "Mathematical Software",
+    "cs.NA": "Numerical Analysis",
+    "cs.NE": "Neural and Evolutionary Computing",
+    "cs.NI": "Networking and Internet Architecture",
+    "cs.OH": "Other Computer Science",
+    "cs.OS": "Operating Systems",
+    "cs.PF": "Performance",
+    "cs.PL": "Programming Languages",
+    "cs.RO": "Robotics",
+    "cs.SC": "Symbolic Computation",
+    "cs.SD": "Sound",
+    "cs.SE": "Software Engineering",
+    "cs.SI": "Social and Information Networks",
+    "cs.SY": "Systems and Control",
+    "econ.EM": "Econometrics",
+    "eess.AS": "Audio and Speech Processing",
+    "eess.IV": "Image and Video Processing",
+    "eess.SP": "Signal Processing",
+    "gr-qc": "General Relativity and Quantum Cosmology",
+    "hep-ex": "High Energy Physics - Experiment",
+    "hep-lat": "High Energy Physics - Lattice",
+    "hep-ph": "High Energy Physics - Phenomenology",
+    "hep-th": "High Energy Physics - Theory",
+    "math.AC": "Commutative Algebra",
+    "math.AG": "Algebraic Geometry",
+    "math.AP": "Analysis of PDEs",
+    "math.AT": "Algebraic Topology",
+    "math.CA": "Classical Analysis and ODEs",
+    "math.CO": "Combinatorics",
+    "math.CT": "Category Theory",
+    "math.CV": "Complex Variables",
+    "math.DG": "Differential Geometry",
+    "math.DS": "Dynamical Systems",
+    "math.FA": "Functional Analysis",
+    "math.GM": "General Mathematics",
+    "math.GN": "General Topology",
+    "math.GR": "Group Theory",
+    "math.GT": "Geometric Topology",
+    "math.HO": "History and Overview",
+    "math.IT": "Information Theory",
+    "math.KT": "K-Theory and Homology",
+    "math.LO": "Logic",
+    "math.MG": "Metric Geometry",
+    "math.MP": "Mathematical Physics",
+    "math.NA": "Numerical Analysis",
+    "math.NT": "Number Theory",
+    "math.OA": "Operator Algebras",
+    "math.OC": "Optimization and Control",
+    "math.PR": "Probability",
+    "math.QA": "Quantum Algebra",
+    "math.RA": "Rings and Algebras",
+    "math.RT": "Representation Theory",
+    "math.SG": "Symplectic Geometry",
+    "math.SP": "Spectral Theory",
+    "math.ST": "Statistics Theory",
+    "math-ph": "Mathematical Physics",
+    "nlin.AO": "Adaptation and Self-Organizing Systems",
+    "nlin.CD": "Chaotic Dynamics",
+    "nlin.CG": "Cellular Automata and Lattice Gases",
+    "nlin.PS": "Pattern Formation and Solitons",
+    "nlin.SI": "Exactly Solvable and Integrable Systems",
+    "nucl-ex": "Nuclear Experiment",
+    "nucl-th": "Nuclear Theory",
+    "physics.acc-ph": "Accelerator Physics",
+    "physics.ao-ph": "Atmospheric and Oceanic Physics",
+    "physics.app-ph": "Applied Physics",
+    "physics.atom-ph": "Atomic Physics",
+    "physics.atm-clus": "Atomic and Molecular Clusters",
+    "physics.bio-ph": "Biological Physics",
+    "physics.chem-ph": "Chemical Physics",
+    "physics.class-ph": "Classical Physics",
+    "physics.comp-ph": "Computational Physics",
+    "physics.data-an": "Data Analysis, Statistics and Probability",
+    "physics.ed-ph": "Physics Education",
+    "physics.flu-dyn": "Fluid Dynamics",
+    "physics.gen-ph": "General Physics",
+    "physics.geo-ph": "Geophysics",
+    "physics.hist-ph": "History and Philosophy of Physics",
+    "physics.ins-det": "Instrumentation and Detectors",
+    "physics.med-ph": "Medical Physics",
+    "physics.optics": "Optics",
+    "physics.plasm-ph": "Plasma Physics",
+    "physics.pop-ph": "Popular Physics",
+    "physics.soc-ph": "Physics and Society",
+    "physics.space-ph": "Space Physics",
+    "q-bio.BM": "Biomolecules",
+    "q-bio.CB": "Cell Behavior",
+    "q-bio.GN": "Genomics",
+    "q-bio.MN": "Molecular Networks",
+    "q-bio.NC": "Neurons and Cognition",
+    "q-bio.OT": "Other Quantitative Biology",
+    "q-bio.PE": "Populations and Evolution",
+    "q-bio.QM": "Quantitative Methods",
+    "q-bio.SC": "Subcellular Processes",
+    "q-bio.TO": "Tissues and Organs",
+    "q-fin.CP": "Computational Finance",
+    "q-fin.EC": "Economics",
+    "q-fin.GN": "General Finance",
+    "q-fin.MF": "Mathematical Finance",
+    "q-fin.PM": "Portfolio Management",
+    "q-fin.PR": "Pricing of Securities",
+    "q-fin.RM": "Risk Management",
+    "q-fin.ST": "Statistical Finance",
+    "q-fin.TR": "Trading and Market Microstructure",
+    "quant-ph": "Quantum Physics",
+    "stat.AP": "Applications",
+    "stat.CO": "Computation",
+    "stat.ME": "Methodology",
+    "stat.ML": "Machine Learning",
+    "stat.OT": "Other Statistics",
+    "stat.TH": "Statistics Theory"
+}

categories_general.txt

@@ -0,0 +1,334 @@
+Multidisciplinary
+General Agricultural and Biological Sciences
+Agricultural and Biological Sciences (miscellaneous)
+Agronomy and Crop Science
+Animal Science and Zoology
+Aquatic Science
+Ecology, Evolution, Behavior and Systematics
+Food Science
+Forestry
+Horticulture
+Insect Science
+Plant Science
+Soil Science
+General Arts and Humanities
+Arts and Humanities (miscellaneous)
+History
+Language and Linguistics
+Archeology (arts and humanities)
+Classics
+Conservation
+History and Philosophy of Science
+Literature and Literary Theory
+Museology
+Music
+Philosophy
+Religious Studies
+Visual Arts and Performing Arts
+General Biochemistry, Genetics and Molecular Biology
+Biochemistry, Genetics and Molecular Biology (miscellaneous)
+Aging
+Biochemistry
+Biophysics
+Biotechnology
+Cancer Research
+Cell Biology
+Clinical Biochemistry
+Developmental Biology
+Endocrinology
+Genetics
+Molecular Biology
+Molecular Medicine
+Physiology
+Structural Biology
+General Business, Management and Accounting
+Business, Management and Accounting (miscellaneous)
+Accounting
+Business and International Management
+Management Information Systems
+Management of Technology and Innovation
+Marketing
+Organizational Behavior and Human Resource Management
+Strategy and Management
+Tourism, Leisure and Hospitality Management
+Industrial Relations
+General Chemical Engineering
+Chemical Engineering (miscellaneous)
+Bioengineering
+Catalysis
+Chemical Health and Safety
+Colloid and Surface Chemistry
+Filtration and Separation
+Fluid Flow and Transfer Processes
+Process Chemistry and Technology
+General Chemistry
+Chemistry (miscellaneous)
+Analytical Chemistry
+Electrochemistry
+Inorganic Chemistry
+Organic Chemistry
+Physical and Theoretical Chemistry
+Spectroscopy
+General Computer Science
+Computer Science (miscellaneous)
+Artificial Intelligence
+Computational Theory and Mathematics
+Computer Graphics and Computer-Aided Design
+Computer Networks and Communications
+Computer Science Applications
+Computer Vision and Pattern Recognition
+Hardware and Architecture
+Human-Computer Interaction
+Information Systems
+Signal Processing
+Software
+General Decision Sciences
+Decision Sciences (miscellaneous)
+Information Systems and Management
+Management Science and Operations Research
+Statistics, Probability and Uncertainty
+General Earth and Planetary Sciences
+Earth and Planetary Sciences (miscellaneous)
+Atmospheric Science
+Computers in Earth Sciences
+Earth-Surface Processes
+Economic Geology
+Geochemistry and Petrology
+Geology
+Geophysics
+Geotechnical Engineering and Engineering Geology
+Oceanography
+Paleontology
+Space and Planetary Science
+Stratigraphy
+General Economics, Econometrics and Finance
+Economics, Econometrics and Finance (miscellaneous)
+Economics and Econometrics
+Finance
+General Energy
+Energy (miscellaneous)
+Energy Engineering and Power Technology
+Fuel Technology
+Nuclear Energy and Engineering
+Renewable Energy, Sustainability and the Environment
+General Engineering
+Engineering (miscellaneous)
+Aerospace Engineering
+Automotive Engineering
+Biomedical Engineering
+Civil and Structural Engineering
+Computational Mechanics
+Control and Systems Engineering
+Electrical and Electronic Engineering
+Industrial and Manufacturing Engineering
+Mechanical Engineering
+Mechanics of Materials
+Ocean Engineering
+Safety, Risk, Reliability and Quality
+Media Technology
+Building and Construction
+Architecture
+General Environmental Science
+Environmental Science (miscellaneous)
+Ecological Modeling
+Ecology
+Environmental Chemistry
+Environmental Engineering
+Global and Planetary Change
+Health, Toxicology and Mutagenesis
+Management, Monitoring, Policy and Law
+Nature and Landscape Conservation
+Pollution
+Waste Management and Disposal
+Water Science and Technology
+General Immunology and Microbiology
+Immunology and Microbiology (miscellaneous)
+Applied Microbiology and Biotechnology
+Immunology
+Microbiology
+Parasitology
+Virology
+General Materials Science
+Materials Science (miscellaneous)
+Biomaterials
+Ceramics and Composites
+Electronic, Optical and Magnetic Materials
+Materials Chemistry
+Metals and Alloys
+Polymers and Plastics
+Surfaces, Coatings and Films
+General Mathematics
+Mathematics (miscellaneous)
+Algebra and Number Theory
+Analysis
+Applied Mathematics
+Computational Mathematics
+Control and Optimization
+Discrete Mathematics and Combinatorics
+Geometry and Topology
+Logic
+Mathematical Physics
+Modeling and Simulation
+Numerical Analysis
+Statistics and Probability
+Theoretical Computer Science
+General Medicine
+Medicine (miscellaneous)
+Anatomy
+Anesthesiology and Pain Medicine
+Biochemistry (medical)
+Cardiology and Cardiovascular Medicine
+Critical Care and Intensive Care Medicine
+Complementary and Alternative Medicine
+Dermatology
+Drug Guides
+Embryology
+Emergency Medicine
+Endocrinology, Diabetes and Metabolism
+Epidemiology
+Family Practice
+Gastroenterology
+Genetics (clinical)
+Geriatrics and Gerontology
+Health Informatics
+Health Policy
+Hematology
+Hepatology
+Histology
+Immunology and Allergy
+Internal Medicine
+Infectious Diseases
+Microbiology (medical)
+Nephrology
+Neurology (clinical)
+Obstetrics and Gynecology
+Oncology
+Ophthalmology
+Orthopedics and Sports Medicine
+Otorhinolaryngology
+Pathology and Forensic Medicine
+Pediatrics, Perinatology and Child Health
+Pharmacology (medical)
+Physiology (medical)
+Psychiatry and Mental Health
+Public Health, Environmental and Occupational Health
+Pulmonary and Respiratory Medicine
+Radiology, Nuclear Medicine and Imaging
+Rehabilitation
+Reproductive Medicine
+Reviews and References (medical)
+Rheumatology
+Surgery
+Transplantation
+Urology
+General Neuroscience
+Neuroscience (miscellaneous)
+Behavioral Neuroscience
+Biological Psychiatry
+Cellular and Molecular Neuroscience
+Cognitive Neuroscience
+Developmental Neuroscience
+Endocrine and Autonomic Systems
+Neurology
+Sensory Systems
+General Nursing
+Nursing (miscellaneous)
+Advanced and Specialized Nursing
+Assessment and Diagnosis
+Care Planning
+Community and Home Care
+Critical Care Nursing
+Emergency Nursing
+Fundamentals and Skills
+Gerontology
+Issues, Ethics and Legal Aspects
+Leadership and Management
+LPN and LVN
+Maternity and Midwifery
+Medical and Surgical Nursing
+Nurse Assisting
+Nutrition and Dietetics
+Oncology (nursing)
+Pathophysiology
+Pediatrics
+Pharmacology (nursing)
+Psychiatric Mental Health
+Research and Theory
+Review and Exam Preparation
+General Pharmacology, Toxicology and Pharmaceutics
+Pharmacology, Toxicology and Pharmaceutics (miscellaneous)
+Drug Discovery
+Pharmaceutical Science
+Pharmacology
+Toxicology
+General Physics and Astronomy
+Physics and Astronomy (miscellaneous)
+Acoustics and Ultrasonics
+Astronomy and Astrophysics
+Condensed Matter Physics
+Instrumentation
+Nuclear and High Energy Physics
+Atomic and Molecular Physics, and Optics
+Radiation
+Statistical and Nonlinear Physics
+Surfaces and Interfaces
+General Psychology
+Psychology (miscellaneous)
+Applied Psychology
+Clinical Psychology
+Developmental and Educational Psychology
+Experimental and Cognitive Psychology
+Neuropsychology and Physiological Psychology
+Social Psychology
+General Social Sciences
+Social Sciences (miscellaneous)
+Archeology
+Development
+Education
+Geography, Planning and Development
+Health (social science)
+Human Factors and Ergonomics
+Law
+Library and Information Sciences
+Linguistics and Language
+Safety Research
+Sociology and Political Science
+Transportation
+Anthropology
+Communication
+Cultural Studies
+Demography
+Gender Studies
+Life-span and Life-course Studies
+Political Science and International Relations
+Public Administration
+Urban Studies
+General Veterinary
+Veterinary (miscellaneous)
+Equine
+Food Animals
+Small Animals
+General Dentistry
+Dentistry (miscellaneous)
+Dental Assisting
+Dental Hygiene
+Oral Surgery
+Orthodontics
+Periodontics
+General Health Professions
+Health Professions (miscellaneous)
+Chiropractics
+Complementary and Manual Therapy
+Emergency Medical Services
+Health Information Management
+Medical Assisting and Transcription
+Medical Laboratory Technology
+Medical Terminology
+Occupational Therapy
+Optometry
+Pharmacy
+Physical Therapy, Sports Therapy and Rehabilitation
+Podiatry
+Radiological and Ultrasound Technology
+Respiratory Care
+Speech and Hearing

requirements.txt

@@ -1,2 +1,4 @@
-hvplot
 panel
+hvplot
+arxiv
+crossrefapi

src/chains.py

@@ -0,0 +1,80 @@
+from langchain.document_loaders import PyPDFLoader, PyPDFDirectoryLoader
+from langchain.indexes import VectorstoreIndexCreator
+from langchain.llms import AzureOpenAI, OpenAI
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.chains import RetrievalQA, ConversationalRetrievalChain, RetrievalQAWithSourcesChain
+from langchain.chains.question_answering import load_qa_chain
+from langchain.memory import ConversationBufferMemory
+
+from langchain.chat_models import AzureChatOpenAI
+
+
+import os
+import openai
+os.environ['CWD'] = os.getcwd()
+
+# for testing
+import src.constants as constants
+# import constants 
+os.environ['OPENAI_API_KEY'] = constants.AZURE_OPENAI_KEY_FR
+os.environ['OPENAI_API_BASE'] = constants.AZURE_OPENAI_ENDPOINT_FR
+os.environ['OPENAI_API_VERSION'] = "2023-05-15"
+os.environ['OPENAI_API_TYPE'] = "azure"
+# openai.api_type = "azure"
+# openai.api_base = constants.AZURE_OPENAI_ENDPOINT_FR
+# openai.api_version = "2023-05-15"
+openai.api_key = constants.OPEN_AI_KEY
+
+def get_document_key(doc):
+    return doc.metadata['source'] + '_page_' + str(doc.metadata['page'])
+
+
+import os
+from typing import Optional
+
+class PDFEmbeddings():
+    def __init__(self, path: Optional[str] = None):
+        self.path = path or os.path.join(os.environ['CWD'], 'archive')
+        self.text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=200)
+        self.embeddings = OpenAIEmbeddings(deployment= constants.AZURE_ENGINE_NAME_US, chunk_size=1,
+                                           openai_api_key= constants.AZURE_OPENAI_KEY_US,
+                                           openai_api_base= constants.AZURE_OPENAI_ENDPOINT_US,
+                                           openai_api_version= "2023-05-15",
+                                           openai_api_type= "azure",)
+        self.vectorstore = Chroma(persist_directory=constants.persistent_dir, embedding_function=self.embeddings)
+        self.retriever = self.vectorstore.as_retriever(search_type = "similarity", search_kwags= {"k": 5})
+        self.memory = ConversationBufferMemory(memory_key='pdf_memory', return_messages=True)
+
+    def process_documents(self):
+        # Load the documents and process them
+        loader = PyPDFDirectoryLoader(self.path)
+        documents = loader.load()
+        chunks = self.text_splitter.split_documents(documents)
+        self.vectorstore.add_documents(chunks)
+
+    def search(self, query: str, chain_type: str = "stuff"):
+        chain = RetrievalQA.from_chain_type(llm= AzureChatOpenAI(deployment_name= constants.AZURE_ENGINE_NAME_FR, temperature=0),
+                                            retriever= self.retriever, chain_type= chain_type, return_source_documents= True)
+        result = chain({"query": query})
+        return result
+
+    def conversational_search(self, query: str, chain_type: str = "stuff"):
+        chain = ConversationalRetrievalChain.from_llm(llm= AzureChatOpenAI(deployment_name= constants.AZURE_ENGINE_NAME_FR),
+                                                      retriever= self.retriever, memory= self.memory, chain_type= chain_type)
+        result = chain({"question": query})
+        return result['answer']
+
+    def load_and_run_chain(self, query: str, chain_type: str = "stuff"):
+        chain = load_qa_chain(llm= AzureChatOpenAI(deployment_name= constants.AZURE_ENGINE_NAME_FR), chain_type= chain_type)
+        return chain.run(input_documents = self.retriever, question = query)
+
+if __name__ == '__main__':
+    pdf_embed = PDFEmbeddings()
+    # pdf_embed.process_documents() # This takes a while, so we only do it once
+    result = pdf_embed.search("Give me a list of short relevant queries to look for papers related to the topics of the papers in the source documents.")
+    print("\n\n", result['result'], "\n")
+    print("Source documents:")
+    for doc in result['source_documents']:
+        print(doc.metadata['source'])

src/constants.py

@@ -0,0 +1,167 @@
+AZURE_OPENAI_KEY_FR = "d296db50d1ad471caf944d1b148ae6c7"
+AZURE_OPENAI_ENDPOINT_FR = "https://openai-resource-team-11-france.openai.azure.com/"
+AZURE_ENGINE_NAME_FR = "gpt35-team-11"
+
+AZURE_OPENAI_KEY_US = "af7e76186d2c46458bcb6d1ecef91d68"
+AZURE_OPENAI_ENDPOINT_US = "https://openai-resource-team-11-east-us.openai.azure.com/"
+AZURE_ENGINE_NAME_US = "ada002-team-11"
+
+OPEN_AI_KEY = "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"
+
+persistent_dir = "db"
+
+# Taxonomy dictionary arxiv
+arxiv_taxonomy = {
+    "astro-ph.CO": "Cosmology and Nongalactic Astrophysics",
+    "astro-ph.EP": "Earth and Planetary Astrophysics",
+    "astro-ph.GA": "Astrophysics of Galaxies",
+    "astro-ph.HE": "High Energy Astrophysical Phenomena",
+    "astro-ph.IM": "Instrumentation and Methods for Astrophysics",
+    "astro-ph.SR": "Solar and Stellar Astrophysics",
+    "cond-mat.dis-nn": "Disordered Systems and Neural Networks",
+    "cond-mat.mes-hall": "Mesoscale and Nanoscale Physics",
+    "cond-mat.mtrl-sci": "Materials Science",
+    "cond-mat.other": "Other Condensed Matter",
+    "cond-mat.quant-gas": "Quantum Gases",
+    "cond-mat.soft": "Soft Condensed Matter",
+    "cond-mat.stat-mech": "Statistical Mechanics",
+    "cond-mat.str-el": "Strongly Correlated Electrons",
+    "cond-mat.supr-con": "Superconductivity",
+    "cs.AI": "Artificial Intelligence",
+    "cs.AR": "Hardware Architecture",
+    "cs.CC": "Computational Complexity",
+    "cs.CE": "Computational Engineering, Finance, and Science",
+    "cs.CG": "Computational Geometry",
+    "cs.CL": "Computation and Language",
+    "cs.CR": "Cryptography and Security",
+    "cs.CV": "Computer Vision and Pattern Recognition",
+    "cs.CY": "Computers and Society",
+    "cs.DB": "Databases",
+    "cs.DC": "Distributed, Parallel, and Cluster Computing",
+    "cs.DL": "Digital Libraries",
+    "cs.DM": "Discrete Mathematics",
+    "cs.DS": "Data Structures and Algorithms",
+    "cs.ET": "Emerging Technologies",
+    "cs.FL": "Formal Languages and Automata Theory",
+    "cs.GL": "General Literature",
+    "cs.GR": "Graphics",
+    "cs.GT": "Computer Science and Game Theory",
+    "cs.HC": "Human-Computer Interaction",
+    "cs.IR": "Information Retrieval",
+    "cs.IT": "Information Theory",
+    "cs.LG": "Machine Learning",
+    "cs.LO": "Logic in Computer Science",
+    "cs.MA": "Multiagent Systems",
+    "cs.MM": "Multimedia",
+    "cs.MS": "Mathematical Software",
+    "cs.NA": "Numerical Analysis",
+    "cs.NE": "Neural and Evolutionary Computing",
+    "cs.NI": "Networking and Internet Architecture",
+    "cs.OH": "Other Computer Science",
+    "cs.OS": "Operating Systems",
+    "cs.PF": "Performance",
+    "cs.PL": "Programming Languages",
+    "cs.RO": "Robotics",
+    "cs.SC": "Symbolic Computation",
+    "cs.SD": "Sound",
+    "cs.SE": "Software Engineering",
+    "cs.SI": "Social and Information Networks",
+    "cs.SY": "Systems and Control",
+    "econ.EM": "Econometrics",
+    "eess.AS": "Audio and Speech Processing",
+    "eess.IV": "Image and Video Processing",
+    "eess.SP": "Signal Processing",
+    "gr-qc": "General Relativity and Quantum Cosmology",
+    "hep-ex": "High Energy Physics - Experiment",
+    "hep-lat": "High Energy Physics - Lattice",
+    "hep-ph": "High Energy Physics - Phenomenology",
+    "hep-th": "High Energy Physics - Theory",
+    "math.AC": "Commutative Algebra",
+    "math.AG": "Algebraic Geometry",
+    "math.AP": "Analysis of PDEs",
+    "math.AT": "Algebraic Topology",
+    "math.CA": "Classical Analysis and ODEs",
+    "math.CO": "Combinatorics",
+    "math.CT": "Category Theory",
+    "math.CV": "Complex Variables",
+    "math.DG": "Differential Geometry",
+    "math.DS": "Dynamical Systems",
+    "math.FA": "Functional Analysis",
+    "math.GM": "General Mathematics",
+    "math.GN": "General Topology",
+    "math.GR": "Group Theory",
+    "math.GT": "Geometric Topology",
+    "math.HO": "History and Overview",
+    "math.IT": "Information Theory",
+    "math.KT": "K-Theory and Homology",
+    "math.LO": "Logic",
+    "math.MG": "Metric Geometry",
+    "math.MP": "Mathematical Physics",
+    "math.NA": "Numerical Analysis",
+    "math.NT": "Number Theory",
+    "math.OA": "Operator Algebras",
+    "math.OC": "Optimization and Control",
+    "math.PR": "Probability",
+    "math.QA": "Quantum Algebra",
+    "math.RA": "Rings and Algebras",
+    "math.RT": "Representation Theory",
+    "math.SG": "Symplectic Geometry",
+    "math.SP": "Spectral Theory",
+    "math.ST": "Statistics Theory",
+    "math-ph": "Mathematical Physics",
+    "nlin.AO": "Adaptation and Self-Organizing Systems",
+    "nlin.CD": "Chaotic Dynamics",
+    "nlin.CG": "Cellular Automata and Lattice Gases",
+    "nlin.PS": "Pattern Formation and Solitons",
+    "nlin.SI": "Exactly Solvable and Integrable Systems",
+    "nucl-ex": "Nuclear Experiment",
+    "nucl-th": "Nuclear Theory",
+    "physics.acc-ph": "Accelerator Physics",
+    "physics.ao-ph": "Atmospheric and Oceanic Physics",
+    "physics.app-ph": "Applied Physics",
+    "physics.atom-ph": "Atomic Physics",
+    "physics.atm-clus": "Atomic and Molecular Clusters",
+    "physics.bio-ph": "Biological Physics",
+    "physics.chem-ph": "Chemical Physics",
+    "physics.class-ph": "Classical Physics",
+    "physics.comp-ph": "Computational Physics",
+    "physics.data-an": "Data Analysis, Statistics and Probability",
+    "physics.ed-ph": "Physics Education",
+    "physics.flu-dyn": "Fluid Dynamics",
+    "physics.gen-ph": "General Physics",
+    "physics.geo-ph": "Geophysics",
+    "physics.hist-ph": "History and Philosophy of Physics",
+    "physics.ins-det": "Instrumentation and Detectors",
+    "physics.med-ph": "Medical Physics",
+    "physics.optics": "Optics",
+    "physics.plasm-ph": "Plasma Physics",
+    "physics.pop-ph": "Popular Physics",
+    "physics.soc-ph": "Physics and Society",
+    "physics.space-ph": "Space Physics",
+    "q-bio.BM": "Biomolecules",
+    "q-bio.CB": "Cell Behavior",
+    "q-bio.GN": "Genomics",
+    "q-bio.MN": "Molecular Networks",
+    "q-bio.NC": "Neurons and Cognition",
+    "q-bio.OT": "Other Quantitative Biology",
+    "q-bio.PE": "Populations and Evolution",
+    "q-bio.QM": "Quantitative Methods",
+    "q-bio.SC": "Subcellular Processes",
+    "q-bio.TO": "Tissues and Organs",
+    "q-fin.CP": "Computational Finance",
+    "q-fin.EC": "Economics",
+    "q-fin.GN": "General Finance",
+    "q-fin.MF": "Mathematical Finance",
+    "q-fin.PM": "Portfolio Management",
+    "q-fin.PR": "Pricing of Securities",
+    "q-fin.RM": "Risk Management",
+    "q-fin.ST": "Statistical Finance",
+    "q-fin.TR": "Trading and Market Microstructure",
+    "quant-ph": "Quantum Physics",
+    "stat.AP": "Applications",
+    "stat.CO": "Computation",
+    "stat.ME": "Methodology",
+    "stat.ML": "Machine Learning",
+    "stat.OT": "Other Statistics",
+    "stat.TH": "Statistics Theory"
+}

src/constants_general.txt

@@ -0,0 +1,334 @@
+Multidisciplinary
+General Agricultural and Biological Sciences
+Agricultural and Biological Sciences (miscellaneous)
+Agronomy and Crop Science
+Animal Science and Zoology
+Aquatic Science
+Ecology, Evolution, Behavior and Systematics
+Food Science
+Forestry
+Horticulture
+Insect Science
+Plant Science
+Soil Science
+General Arts and Humanities
+Arts and Humanities (miscellaneous)
+History
+Language and Linguistics
+Archeology (arts and humanities)
+Classics
+Conservation
+History and Philosophy of Science
+Literature and Literary Theory
+Museology
+Music
+Philosophy
+Religious Studies
+Visual Arts and Performing Arts
+General Biochemistry, Genetics and Molecular Biology
+Biochemistry, Genetics and Molecular Biology (miscellaneous)
+Aging
+Biochemistry
+Biophysics
+Biotechnology
+Cancer Research
+Cell Biology
+Clinical Biochemistry
+Developmental Biology
+Endocrinology
+Genetics
+Molecular Biology
+Molecular Medicine
+Physiology
+Structural Biology
+General Business, Management and Accounting
+Business, Management and Accounting (miscellaneous)
+Accounting
+Business and International Management
+Management Information Systems
+Management of Technology and Innovation
+Marketing
+Organizational Behavior and Human Resource Management
+Strategy and Management
+Tourism, Leisure and Hospitality Management
+Industrial Relations
+General Chemical Engineering
+Chemical Engineering (miscellaneous)
+Bioengineering
+Catalysis
+Chemical Health and Safety
+Colloid and Surface Chemistry
+Filtration and Separation
+Fluid Flow and Transfer Processes
+Process Chemistry and Technology
+General Chemistry
+Chemistry (miscellaneous)
+Analytical Chemistry
+Electrochemistry
+Inorganic Chemistry
+Organic Chemistry
+Physical and Theoretical Chemistry
+Spectroscopy
+General Computer Science
+Computer Science (miscellaneous)
+Artificial Intelligence
+Computational Theory and Mathematics
+Computer Graphics and Computer-Aided Design
+Computer Networks and Communications
+Computer Science Applications
+Computer Vision and Pattern Recognition
+Hardware and Architecture
+Human-Computer Interaction
+Information Systems
+Signal Processing
+Software
+General Decision Sciences
+Decision Sciences (miscellaneous)
+Information Systems and Management
+Management Science and Operations Research
+Statistics, Probability and Uncertainty
+General Earth and Planetary Sciences
+Earth and Planetary Sciences (miscellaneous)
+Atmospheric Science
+Computers in Earth Sciences
+Earth-Surface Processes
+Economic Geology
+Geochemistry and Petrology
+Geology
+Geophysics
+Geotechnical Engineering and Engineering Geology
+Oceanography
+Paleontology
+Space and Planetary Science
+Stratigraphy
+General Economics, Econometrics and Finance
+Economics, Econometrics and Finance (miscellaneous)
+Economics and Econometrics
+Finance
+General Energy
+Energy (miscellaneous)
+Energy Engineering and Power Technology
+Fuel Technology
+Nuclear Energy and Engineering
+Renewable Energy, Sustainability and the Environment
+General Engineering
+Engineering (miscellaneous)
+Aerospace Engineering
+Automotive Engineering
+Biomedical Engineering
+Civil and Structural Engineering
+Computational Mechanics
+Control and Systems Engineering
+Electrical and Electronic Engineering
+Industrial and Manufacturing Engineering
+Mechanical Engineering
+Mechanics of Materials
+Ocean Engineering
+Safety, Risk, Reliability and Quality
+Media Technology
+Building and Construction
+Architecture
+General Environmental Science
+Environmental Science (miscellaneous)
+Ecological Modeling
+Ecology
+Environmental Chemistry
+Environmental Engineering
+Global and Planetary Change
+Health, Toxicology and Mutagenesis
+Management, Monitoring, Policy and Law
+Nature and Landscape Conservation
+Pollution
+Waste Management and Disposal
+Water Science and Technology
+General Immunology and Microbiology
+Immunology and Microbiology (miscellaneous)
+Applied Microbiology and Biotechnology
+Immunology
+Microbiology
+Parasitology
+Virology
+General Materials Science
+Materials Science (miscellaneous)
+Biomaterials
+Ceramics and Composites
+Electronic, Optical and Magnetic Materials
+Materials Chemistry
+Metals and Alloys
+Polymers and Plastics
+Surfaces, Coatings and Films
+General Mathematics
+Mathematics (miscellaneous)
+Algebra and Number Theory
+Analysis
+Applied Mathematics
+Computational Mathematics
+Control and Optimization
+Discrete Mathematics and Combinatorics
+Geometry and Topology
+Logic
+Mathematical Physics
+Modeling and Simulation
+Numerical Analysis
+Statistics and Probability
+Theoretical Computer Science
+General Medicine
+Medicine (miscellaneous)
+Anatomy
+Anesthesiology and Pain Medicine
+Biochemistry (medical)
+Cardiology and Cardiovascular Medicine
+Critical Care and Intensive Care Medicine
+Complementary and Alternative Medicine
+Dermatology
+Drug Guides
+Embryology
+Emergency Medicine
+Endocrinology, Diabetes and Metabolism
+Epidemiology
+Family Practice
+Gastroenterology
+Genetics (clinical)
+Geriatrics and Gerontology
+Health Informatics
+Health Policy
+Hematology
+Hepatology
+Histology
+Immunology and Allergy
+Internal Medicine
+Infectious Diseases
+Microbiology (medical)
+Nephrology
+Neurology (clinical)
+Obstetrics and Gynecology
+Oncology
+Ophthalmology
+Orthopedics and Sports Medicine
+Otorhinolaryngology
+Pathology and Forensic Medicine
+Pediatrics, Perinatology and Child Health
+Pharmacology (medical)
+Physiology (medical)
+Psychiatry and Mental Health
+Public Health, Environmental and Occupational Health
+Pulmonary and Respiratory Medicine
+Radiology, Nuclear Medicine and Imaging
+Rehabilitation
+Reproductive Medicine
+Reviews and References (medical)
+Rheumatology
+Surgery
+Transplantation
+Urology
+General Neuroscience
+Neuroscience (miscellaneous)
+Behavioral Neuroscience
+Biological Psychiatry
+Cellular and Molecular Neuroscience
+Cognitive Neuroscience
+Developmental Neuroscience
+Endocrine and Autonomic Systems
+Neurology
+Sensory Systems
+General Nursing
+Nursing (miscellaneous)
+Advanced and Specialized Nursing
+Assessment and Diagnosis
+Care Planning
+Community and Home Care
+Critical Care Nursing
+Emergency Nursing
+Fundamentals and Skills
+Gerontology
+Issues, Ethics and Legal Aspects
+Leadership and Management
+LPN and LVN
+Maternity and Midwifery
+Medical and Surgical Nursing
+Nurse Assisting
+Nutrition and Dietetics
+Oncology (nursing)
+Pathophysiology
+Pediatrics
+Pharmacology (nursing)
+Psychiatric Mental Health
+Research and Theory
+Review and Exam Preparation
+General Pharmacology, Toxicology and Pharmaceutics
+Pharmacology, Toxicology and Pharmaceutics (miscellaneous)
+Drug Discovery
+Pharmaceutical Science
+Pharmacology
+Toxicology
+General Physics and Astronomy
+Physics and Astronomy (miscellaneous)
+Acoustics and Ultrasonics
+Astronomy and Astrophysics
+Condensed Matter Physics
+Instrumentation
+Nuclear and High Energy Physics
+Atomic and Molecular Physics, and Optics
+Radiation
+Statistical and Nonlinear Physics
+Surfaces and Interfaces
+General Psychology
+Psychology (miscellaneous)
+Applied Psychology
+Clinical Psychology
+Developmental and Educational Psychology
+Experimental and Cognitive Psychology
+Neuropsychology and Physiological Psychology
+Social Psychology
+General Social Sciences
+Social Sciences (miscellaneous)
+Archeology
+Development
+Education
+Geography, Planning and Development
+Health (social science)
+Human Factors and Ergonomics
+Law
+Library and Information Sciences
+Linguistics and Language
+Safety Research
+Sociology and Political Science
+Transportation
+Anthropology
+Communication
+Cultural Studies
+Demography
+Gender Studies
+Life-span and Life-course Studies
+Political Science and International Relations
+Public Administration
+Urban Studies
+General Veterinary
+Veterinary (miscellaneous)
+Equine
+Food Animals
+Small Animals
+General Dentistry
+Dentistry (miscellaneous)
+Dental Assisting
+Dental Hygiene
+Oral Surgery
+Orthodontics
+Periodontics
+General Health Professions
+Health Professions (miscellaneous)
+Chiropractics
+Complementary and Manual Therapy
+Emergency Medical Services
+Health Information Management
+Medical Assisting and Transcription
+Medical Laboratory Technology
+Medical Terminology
+Occupational Therapy
+Optometry
+Pharmacy
+Physical Therapy, Sports Therapy and Rehabilitation
+Podiatry
+Radiological and Ultrasound Technology
+Respiratory Care
+Speech and Hearing

src/search.py

@@ -0,0 +1,146 @@
+import arxiv
+from crossref.restful import Works
+import pytz
+from datetime import date
+from datetime import datetime
+
+
+class Search_Papers():
+    def __init__(self, query, search_by, search_by_query, sort_by, sort_order):
+
+        self.query = query
+        self.search_mode = search_by
+        self.search_mode_query = search_by_query
+
+        self.sort_by = sort_by
+
+        self.sort_order = sort_order
+
+        self.time_search = datetime.now(pytz.utc).replace(microsecond=0)
+
+        return
+
+    
+    def search_arxiv_NResults(self, query, max_results, sort_by, sort_order):
+        search_results = arxiv.Search(
+        query = query,
+        max_results = max_results,
+        sort_by = sort_by,
+        sort_order = sort_order
+        )
+
+        return search_results.results()
+
+
+
+    def search_arxiv_Timeframe(self, query, timeframe, sort_by, sort_order):
+
+        collection = []
+        exit_flag = 0
+        n_iter = 0
+        max_results = 10
+
+        while True:
+            search_list = arxiv.Search(
+                query = query,
+                max_results = (n_iter+1)*max_results,
+                sort_by = sort_by,
+                sort_order = sort_order
+                )
+
+
+            results = list(search_list.results())
+
+            for i in range(n_iter*max_results, len(results)):
+                #print(timeframe, results[i].published, results[i].published < timeframe)
+
+                if results[i].published > timeframe:
+                    collection.append(results[i])
+                else:
+                    exit_flag = 1
+                    break
+          
+            if exit_flag:
+                break
+            else:
+                n_iter += 1
+          
+
+        return collection
+
+    
+    
+    def search_arxiv(self):
+
+        if self.sort_by == "PublishDate":
+            sort_by = arxiv.SortCriterion.SubmittedDate
+        elif self.sort_by == "LastUpdatedDate":
+            sort_by = arxiv.SortCriterion.LastUpdatedDate
+        else:
+            sort_by = arxiv.SortCriterion.Relevance
+
+
+        if self.sort_order == "Ascending":
+            sort_order = arxiv.SortOrder.Ascending
+        else:
+            sort_order = arxiv.SortOrder.Descending
+
+
+
+        if self.search_mode == "NumberResults":
+            search_results = self.search_arxiv_NResults(self.query, self.search_mode_query, sort_by, sort_order)
+        else:
+            search_results = self.search_arxiv_Timeframe(self.query, self.search_mode_query, sort_by, sort_order)
+
+        return search_results
+    
+    
+    def search_general_NResults(self, query, max_results, sort_by, sort_order):
+        works = Works()
+        # search_results = works.filter(category_name = query).sort(sort_by).order(sort_order).sample(max_results)
+        search_results = works.query(bibliographic = query).sort(sort_by).order(sort_order).sample(max_results)
+        return search_results
+
+
+    def search_general_Timeframe(self, query, timeframe, sort_by, sort_order):
+        works = Works()
+        today = (datetime.combine(date.today(), datetime.min.time())).strftime("%Y-%m-%d")
+      
+        # search_results = works.filter(category_name = query, from_created_date=timeframe, until_created_date = today).sort(sort_by).order(sort_order)
+        search_results = works.query(bibliographic = query).filter(from_created_date=timeframe, until_created_date = today).sort(sort_by).order(sort_order)
+         
+        return search_results
+
+    #'Magnetic Field Conditions Upstream of Ganymede'
+
+    def search_general(self):
+
+        if self.search_mode == 'Timeframe':
+            timeframe = self.search_mode_query.strftime("%Y-%m-%d")
+            
+
+
+
+        if self.sort_by == "PublishDate":
+            sort_by = 'created'
+        elif self.sort_by == "LastUpdatedDate":
+            sort_by = 'updated'
+        else:
+            sort_by = 'relevance'
+
+
+        if self.sort_order == "Ascending":
+            sort_order = "asc"
+        else:
+            sort_order = "desc"
+
+
+
+        if self.search_mode == "NumberResults":
+            search_results = self.search_general_NResults(self.query, self.search_mode_query, sort_by, sort_order)
+        else:
+            search_results = self.search_general_Timeframe(self.query, timeframe, sort_by, sort_order)
+
+        return search_results
+    
+