WIP

app.py

@@ -1,49 +1,41 @@
 import gradio as gr
 from tts import speak
-from voice_input import convert_voice_to_text, convert_voice_text_to_command
-
-
-def process(input_text: str = None,
-            file_path: str = None,
-            input_audio = None):
-    if input_text and len(input_text) > 0:
-        audio_stream = speak(input_text)
-    else:
-        audio_stream = None
-
-    if input_audio:
-        voice_text = convert_voice_to_text(input_audio)
-        command = convert_voice_text_to_command(voice_text)
-    else:
-        voice_text = ""
-        command = ""
-
-    return (gr.Audio(value=audio_stream, format="wav", autoplay=True, visible=False),
-            file_path,
-            voice_text,
-            command
+from arxiv_helper import arxiv_categories
+
+
+def process(categories: gr.Dropdown,
+            subcategories: gr.Dropdown):
+    
+    conversaion_text = "The conversation goes here"
+
+    return (gr.Audio(value=None, format="wav", autoplay=True, visible=False),
+            conversaion_text
             )
 
-options = gr.WaveformOptions(show_recording_waveform=False)
-
-demo = gr.Interface(
-    fn=process,
-    inputs=[
-        gr.Textbox(label="Input Text", lines=5),
-        gr.File(file_count='single'),
-        gr.Audio(label="Commands", sources=["microphone"], editable=False, waveform_options=options)
-    ],
-    outputs=[
-        gr.Audio(visible=False),
-        gr.Textbox(label="Echo Output", lines=2),
-        gr.Textbox(label="User Voice Input", lines=1),
-        gr.Textbox(label="Recognized Command", lines=1)
-    ],
-    title="Some title",
-    description='Some description',
-    article="Paper Whisperer",
-    analytics_enabled=False,
-    allow_flagging='never'
-)
+def update_subcategory_dropdown(selection):
+    return gr.update(choices=list(arxiv_categories[selection].values()))
+
+
+with gr.Blocks() as demo:
+    category_dropdown = gr.Dropdown(label="arXiv Category", choices=list(arxiv_categories.keys()))
+    subcategory_dropdown = gr.Dropdown(label="arXiv Subcategory", choices=[])
+    category_dropdown.change(fn=update_subcategory_dropdown, inputs=category_dropdown, outputs=subcategory_dropdown)
+
+    demo_interface = gr.Interface(
+        fn=process,
+        inputs=[
+            category_dropdown,
+            subcategory_dropdown,
+        ],
+        outputs=[
+            gr.Audio(visible=False),
+            gr.Textbox(label="Conversation", lines=20),
+        ],
+        title="Paper Whisperer",
+        description='Select arXiv papers(s) to convert into an engaging conversation!',
+        article="Paper Whisperer",
+        analytics_enabled=False,
+        allow_flagging='never'
+    )
 
 demo.launch()

app2.py

@@ -3,7 +3,7 @@ from tts import speak
 from voice_input import convert_voice_to_text, convert_voice_text_to_command
 from bs4 import BeautifulSoup
 import time
-from parser import (
+from parser2 import (
     get_paper_by_id,
     parse_pdf,
     parse_xml,

arxiv_helper.py

@@ -0,0 +1,162 @@
+arxiv_categories = {
+    "Physics": {
+        "astro-ph.GA": "Astrophysics of Galaxies",
+        "astro-ph.CO": "Cosmology and Nongalactic Astrophysics",
+        "astro-ph.EP": "Earth and Planetary Astrophysics",
+        "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.mtrl-sci": "Materials Science",
+        "cond-mat.mes-hall": "Mesoscale and Nanoscale Physics",
+        "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",
+        "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-ph": "Mathematical Physics",
+        "nlin.AO": "Adaptation and Self-Organizing Systems",
+        "nlin.CG": "Cellular Automata and Lattice Gases",
+        "nlin.CD": "Chaotic Dynamics",
+        "nlin.SI": "Exactly Solvable and Integrable Systems",
+        "nlin.PS": "Pattern Formation and Solitons",
+        "nucl-ex": "Nuclear Experiment",
+        "nucl-th": "Nuclear Theory",
+        "physics.acc-ph": "Accelerator Physics",
+        "physics.app-ph": "Applied Physics",
+        "physics.ao-ph": "Atmospheric and Oceanic 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.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.ed-ph": "Physics Education",
+        "physics.soc-ph": "Physics and Society",
+        "physics.plasm-ph": "Plasma Physics",
+        "physics.pop-ph": "Popular Physics",
+        "physics.space-ph": "Space Physics",
+        "quant-ph": "Quantum Physics",
+    },
+    "Mathematics": {
+        "math.AG": "Algebraic Geometry",
+        "math.AT": "Algebraic Topology",
+        "math.AP": "Analysis of PDEs",
+        "math.CT": "Category Theory",
+        "math.CA": "Classical Analysis and ODEs",
+        "math.CO": "Combinatorics",
+        "math.AC": "Commutative Algebra",
+        "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.GT": "Geometric Topology",
+        "math.GR": "Group Theory",
+        "math.HO": "History and Overview",
+        "math.IT": "Information Theory",
+        "math.KT": "K-Theory and Homology",
+        "math.LO": "Logic",
+        "math.MP": "Mathematical Physics",
+        "math.MG": "Metric Geometry",
+        "math.NT": "Number Theory",
+        "math.NA": "Numerical Analysis",
+        "math.OA": "Operator Algebras",
+        "math.OC": "Optimization and Control",
+        "math.PR": "Probability",
+        "math.QA": "Quantum Algebra",
+        "math.RT": "Representation Theory",
+        "math.RA": "Rings and Algebras",
+        "math.SP": "Spectral Theory",
+        "math.ST": "Statistics Theory",
+        "math.SG": "Symplectic Geometry",
+    },
+    "Computer Science": {
+        "cs.AI": "Artificial Intelligence",
+        "cs.CL": "Computation and Language",
+        "cs.CC": "Computational Complexity",
+        "cs.CE": "Computational Engineering, Finance, and Science",
+        "cs.CG": "Computational Geometry",
+        "cs.GT": "Computer Science and Game Theory",
+        "cs.CV": "Computer Vision and Pattern Recognition",
+        "cs.CY": "Computers and Society",
+        "cs.CR": "Cryptography and Security",
+        "cs.DS": "Data Structures and Algorithms",
+        "cs.DB": "Databases",
+        "cs.DL": "Digital Libraries",
+        "cs.DM": "Discrete Mathematics",
+        "cs.DC": "Distributed, Parallel, and Cluster Computing",
+        "cs.ET": "Emerging Technologies",
+        "cs.FL": "Formal Languages and Automata Theory",
+        "cs.GL": "General Literature",
+        "cs.GR": "Graphics",
+        "cs.AR": "Hardware Architecture",
+        "cs.HC": "Human-Computer Interaction",
+        "cs.IR": "Information Retrieval",
+        "cs.IT": "Information Theory",
+        "cs.LG": "Learning",
+        "cs.LO": "Logic in Computer Science",
+        "cs.MS": "Mathematical Software",
+        "cs.MA": "Multiagent Systems",
+        "cs.MM": "Multimedia",
+        "cs.NI": "Networking and Internet Architecture",
+        "cs.NE": "Neural and Evolutionary Computing",
+        "cs.NA": "Numerical Analysis",
+        "cs.OS": "Operating Systems",
+        "cs.OH": "Other Computer Science",
+        "cs.PF": "Performance",
+        "cs.PL": "Programming Languages",
+        "cs.RO": "Robotics",
+        "cs.SI": "Social and Information Networks",
+        "cs.SE": "Software Engineering",
+        "cs.SD": "Sound",
+        "cs.SC": "Symbolic Computation",
+        "cs.SY": "Systems and Control",
+    },
+    "Quantitative Biology": {
+        "q-bio.BM": "Biomolecules",
+        "q-bio.GN": "Genomics",
+        "q-bio.MN": "Molecular Networks",
+        "q-bio.SC": "Subcellular Processes",
+        "q-bio.CB": "Cell Behavior",
+        "q-bio.NC": "Neurons and Cognition",
+        "q-bio.TO": "Tissues and Organs",
+        "q-bio.PE": "Populations and Evolution",
+        "q-bio.QM": "Quantitative Methods",
+        "q-bio.OT": "Other",
+    },
+    "Quantitative Finance": {
+        "q-fin.PR": "Pricing of Securities",
+        "q-fin.RM": "Risk Management",
+        "q-fin.PM": "Portfolio Management",
+        "q-fin.TR": "Trading and Microstructure",
+        "q-fin.MF": "Mathematical Finance",
+        "q-fin.CP": "Computational Finance",
+        "q-fin.ST": "Statistical Finance",
+        "q-fin.GN": "General Finance",
+        "q-fin.EC": "Economics",
+    },
+    "Statistics": {
+        "stat.AP": "Applications",
+        "stat.CO": "Computation",
+        "stat.ML": "Machine Learning",
+        "stat.ME": "Methodology",
+        "stat.OT": "Other Statistics",
+        "stat.TH": "Theory",
+    }
+}

generate_qa.py

@@ -71,7 +71,7 @@ def process_qa_chain(sections_dict: OrderedDict):
 
 if __name__ == '__main__':
     from bs4 import BeautifulSoup
-    from parser import (
+    from parser2 import (
         get_paper_by_id,
         parse_pdf,
         parse_xml,