merge 'main' into serena-branch

.github/workflows/github-actions-demo.yml

@@ -0,0 +1,18 @@
+name: GitHub Actions Demo
+run-name: ${{ github.actor }} is testing out GitHub Actions 🚀
+on: [push]
+jobs:
+  Explore-GitHub-Actions:
+    runs-on: ubuntu-latest
+    steps:
+      - run: echo "🎉 The job was automatically triggered by a ${{ github.event_name }} event."
+      - run: echo "🐧 This job is now running on a ${{ runner.os }} server hosted by GitHub!"
+      - run: echo "🔎 The name of your branch is ${{ github.ref }} and your repository is ${{ github.repository }}."
+      - name: Check out repository code
+        uses: actions/checkout@v4
+      - run: echo "💡 The ${{ github.repository }} repository has been cloned to the runner."
+      - run: echo "🖥️ The workflow is now ready to test your code on the runner."
+      - name: List files in the repository
+        run: |
+          ls ${{ github.workspace }}
+      - run: echo "🍏 This job's status is ${{ job.status }}."

backend/app.py

@@ -0,0 +1,100 @@
+from flask import Flask, request, jsonify
+import os
+from dotenv import load_dotenv
+from lib import chat_completion_request, create_embedding
+import json
+
+from pymongo.mongo_client import MongoClient
+
+uri = "mongodb+srv://bluebookairoot:<password>@bluebookcluster.0hf4pzi.mongodb.net/?retryWrites=true&w=majority&appName=BluebookCluster"
+
+# connect to the MongoDB cluster
+client = MongoClient(uri)
+db = client['bluebookai']
+collection = db['course-info']
+
+try:
+    client.admin.command('ping')
+    print("Pinged your deployment. You successfully connected to MongoDB!")
+except Exception as e:
+    print(e)
+
+app = Flask(__name__)
+
+load_dotenv()
+
+@app.route('/chat', methods=['POST'])
+def chat():
+    data = request.get_json()
+    if 'message' not in data:
+        return jsonify({"error": "Missing 'messages' in request body"}), 400
+
+    user_messages = data['message']
+    response = chat_completion_request(messages=user_messages)
+    message = response.choices[0].message
+    print(message)
+    # if message.tool_calls is None:
+    #     return 'success'
+    #     args = json.loads(message.tool_calls[0].function.arguments)
+    #     query_vector = create_embedding(user_messages[-1]['content'])
+    #     database_response = collection.aggregate([
+    #         {
+    #         '$vectorSearch': {
+    #             'index': 'course-rating-index',
+    #             'path': 'embedding',
+    #             'filter': {
+    #                 'rating': {
+    #                     args['operator']: args['rating']
+    #                 }
+    #             },
+    #             'queryVector': query_vector,
+    #             'numCandidates': 5,
+    #             'limit': 5
+    #         }
+    #         }
+    #     ])
+    #     # print(database_response)
+
+    #     top_class = list(database_response)[0]
+    #     json_response = {
+    #         'title': top_class['title'],
+    #         'rating': top_class['rating'],
+    #     }
+    #     return jsonify(json_response)
+
+    # "{\"operator\":\"$gt\",\"rating\":4}"
+
+    # ChatCompletionMessage(content=None, role='assistant', function_call=None, tool_calls=[ChatCompletionMessageToolCall(id='call_Ub07GeA6kaC2OZ8b8KlVmtZz', function=Function(arguments='{\n  "subject_code": "CPSC",\n  "rating": 3.5,\n  "comparison_operator_rating": "$gte",\n  "workload": 1,\n  "comparison_operator_workload": "$lte"\n}', name='CourseFilter'), type='function')])
+
+    query_vector = create_embedding(user_messages[-1]['content'])
+
+    print(user_messages[-1])
+    database_response = collection.aggregate([
+            {
+            '$vectorSearch': {
+                'index': 'course-rating-index',
+                'path': 'embedding',
+                'queryVector': query_vector,
+                'numCandidates': 5,
+                'limit': 5
+            }
+            }
+        ])
+
+    classes = list(database_response)
+    # top_class = classes[0]
+    print([c['title'] for c in classes])
+    top_class = classes[0]
+    json_response = {
+        # 'message': [{
+        #     'role': response.choices[0].message.role,
+        #     'content': response.choices[0].message.content,
+        # }]
+        'title': top_class['title'],
+        # 'rating': top_class['rating'],
+    }
+
+    return jsonify(json_response)
+
+if __name__ == '__main__':
+    app.run(debug=True)

backend/course_subjects.json

@@ -0,0 +1,202 @@
+{
+    "ACCT": "Accounting",
+    "USAF": "Aerospace Studies",
+    "AFAM": "African American Studies",
+    "AFST": "African Studies",
+    "AKKD": "Akkadian",
+    "ASL": "American Sign Language",
+    "AMST": "American Studies",
+    "GREK": "Ancient Greek",
+    "ANTH": "Anthropology",
+    "AMTH": "Applied Mathematics",
+    "APHY": "Applied Physics",
+    "ARBC": "Arabic",
+    "ARCG": "Archaeological Studies",
+    "ARCH": "Architecture",
+    "ARMN": "Armenian",
+    "ART": "Art",
+    "ASTR": "Astronomy",
+    "BNGL": "Bengali",
+    "B&BS": "Biological & Biomedical Sci",
+    "BIOL": "Biology",
+    "BENG": "Biomedical Engineering",
+    "BIS": "Biostatistics",
+    "BRST": "British Studies",
+    "BURM": "Burmese",
+    "C&MP": "Cell & Molecular Physiology",
+    "CBIO": "Cell Biology",
+    "CENG": "Chemical Engineering",
+    "CHEM": "Chemistry",
+    "CHER": "Cherokee",
+    "CHLD": "Child Study",
+    "CHNS": "Chinese",
+    "CDE": "Chronic Disease Epidemiology",
+    "CLCV": "Classical Civilization",
+    "CLSS": "Classics",
+    "MEDR": "Clinical Clerkships",
+    "CGSC": "Cognitive Science",
+    "CSYC": "Coll Sem: Yale Coll",
+    "CSBF": "Coll Sem:Ben Franklin Coll",
+    "CSBK": "Coll Sem:Berkeley Coll",
+    "CSBR": "Coll Sem:Branford Coll",
+    "CSDC": "Coll Sem:Davenport Coll",
+    "CSES": "Coll Sem:Ezra Stiles Coll",
+    "CSGH": "Coll Sem:Grace Hopper Coll",
+    "CSJE": "Coll Sem:Jonathan Edwards Coll",
+    "CSMC": "Coll Sem:Morse Coll",
+    "CSMY": "Coll Sem:Pauli Murray Coll",
+    "CSPC": "Coll Sem:Pierson Coll",
+    "CSSY": "Coll Sem:Saybrook Coll",
+    "CSSM": "Coll Sem:Silliman Coll",
+    "CSTD": "Coll Sem:Timothy Dwight Coll",
+    "CSTC": "Coll Sem:Trumbull Coll",
+    "CB&B": "Comp Biol & Bioinfomatics",
+    "CPLT": "Comparative Literature",
+    "CPSC": "Computer Science",
+    "CSEC": "Computer Science and Economics",
+    "CPAR": "Computing and the Arts",
+    "MEDC": "Courses in School of Medicine",
+    "CZEC": "Czech",
+    "DEVN": "DeVane Lecture Course",
+    "DRST": "Directed Studies",
+    "DIR": "Directing",
+    "DISR": "Diss Research - in Residence",
+    "DRAM": "Drama",
+    "DRMA": "Drama Summer",
+    "DUTC": "Dutch",
+    "EMST": "Early Modern Studies",
+    "EPS": "Earth and Planetary Sciences",
+    "EALL": "East Asian Lang and Lit",
+    "EAST": "East Asian Studies",
+    "E&EB": "Ecology & Evolutionary Biology",
+    "ECON": "Economics",
+    "EDST": "Education Studies",
+    "EGYP": "Egyptology",
+    "EENG": "Electrical Engineering",
+    "ENRG": "Energy Studies",
+    "ENAS": "Engineering & Applied Science",
+    "ENGL": "English",
+    "ELP": "English Language Program",
+    "ENV": "Environment",
+    "ENVE": "Environmental Engineering",
+    "EHS": "Environmental Health Sciences",
+    "EVST": "Environmental Studies",
+    "EPH": "Epidemiology & Public Health",
+    "EMD": "Epidemiology Microbial Disease",
+    "EP&E": "Ethics, Politics, & Economics",
+    "ER&M": "Ethnicity, Race, & Migration",
+    "E&RS": "European & Russian Studies",
+    "EXCH": "Exchange Scholar Experience",
+    "EXPA": "Experimental Pathology",
+    "FILM": "Film & Media Studies",
+    "FNSH": "Finnish",
+    "F&ES": "Forestry & Environment Studies",
+    "FREN": "French",
+    "GENE": "Genetics",
+    "G&G": "Geology and Geophysics",
+    "GMAN": "German",
+    "GLBL": "Global Affairs",
+    "HPM": "Health Policy and Management",
+    "HLTH": "Health Studies",
+    "HEBR": "Hebrew",
+    "HNDI": "Hindi",
+    "HSHM": "Hist of Science, Hist of Med",
+    "HIST": "History",
+    "HSAR": "History of Art",
+    "HMRT": "Human Rights",
+    "HUMS": "Humanities",
+    "HGRN": "Hungarian",
+    "IBIO": "Immunobiology",
+    "IDRS": "Ind Res in Sciences",
+    "INDN": "Indonesian",
+    "INP": "Interdpt Neuroscience Pgm",
+    "IMED": "Investigative Medicine",
+    "ITAL": "Italian Studies",
+    "JAPN": "Japanese",
+    "JDST": "Jewish Studies",
+    "KHMR": "Khmer",
+    "SWAH": "Kiswahili",
+    "KREN": "Korean",
+    "LATN": "Latin",
+    "LAST": "Latin American Studies",
+    "LAW": "Law",
+    "LING": "Linguistics",
+    "LITR": "Literature",
+    "MGT": "Management",
+    "MGMT": "Management, PhD",
+    "MRES": "Master's Thesis Research",
+    "MHHR": "Material Hist of Human Record",
+    "MATH": "Mathematics",
+    "MENG": "Mechanical Engineering",
+    "MDVL": "Medieval Studies",
+    "MESO": "Mesopotamia",
+    "MBIO": "Microbiology",
+    "MGRK": "Modern Greek",
+    "MMES": "Modern Middle East Studies",
+    "MTBT": "Modern Tibetan",
+    "MB&B": "Molecular Biophysics & Biochem",
+    "MCDB": "Molecular, Cellular & Dev Biol",
+    "MUSI": "Music Department",
+    "NAVY": "Naval Science",
+    "NELC": "Near Eastern Langs & Civs",
+    "NPLI": "Nepali",
+    "NSCI": "Neuroscience",
+    "NURS": "Nursing",
+    "OTTM": "Ottoman",
+    "PATH": "Pathology",
+    "PERS": "Persian",
+    "PHAR": "Pharmacology",
+    "PHIL": "Philosophy",
+    "OLPA": "Physician Assistant Online Pgm",
+    "PA": "Physician Associate Program",
+    "PHYS": "Physics",
+    "PLSH": "Polish",
+    "PLSC": "Political Science",
+    "PORT": "Portuguese",
+    "PRAC": "Practicum Analysis",
+    "CAND": "Prep for Adv to Candidacy",
+    "QUAL": "Preparing for Qualifying Exams",
+    "PSYC": "Psychology",
+    "PHUM": "Public Humanities",
+    "PNJB": "Punjabi",
+    "REL": "Religion",
+    "RLST": "Religious Studies",
+    "RNST": "Renaissance Studies",
+    "ROMN": "Romanian",
+    "RUSS": "Russian",
+    "RSEE": "Russian & East Europe Studies",
+    "SKRT": "Sanskrit",
+    "MD": "School of Medicine",
+    "MUS": "School of Music",
+    "SCIE": "Science",
+    "SMTC": "Semitic",
+    "SBCR": "Serbian & Croatian",
+    "SNHL": "Sinhala",
+    "SLAV": "Slavic",
+    "SBS": "Social and Behavioral Sciences",
+    "SOCY": "Sociology",
+    "SAST": "South Asian Studies",
+    "SPAN": "Spanish",
+    "SPEC": "Special Divisional Major",
+    "STRT": "Start Program - Medical School",
+    "S&DS": "Statistics and Data Sciences",
+    "STEV": "Studies in the Environment",
+    "STCY": "Study of the City",
+    "SUMR": "Summer Term",
+    "SWED": "Swedish",
+    "TAML": "Tamil",
+    "THST": "Theater and Performance Studies",
+    "TBTN": "Tibetan",
+    "PTB": "Translational Biomedicine",
+    "TKSH": "Turkish",
+    "TWI": "Twi",
+    "UKRN": "Ukrainian",
+    "URBN": "Urban Studies",
+    "VIET": "Vietnamese",
+    "VAIR": "Visiting Assistant in Research",
+    "WLOF": "Wolof",
+    "WGSS": "Women's, Gender & Sexuality Studies",
+    "YDSH": "Yiddish",
+    "YORU": "Yoruba",
+    "ZULU": "Zulu"
+}