AIFARMS Springer Ingestion w Doc Group

ai_ta_backend/database/sql.py

@@ -11,7 +11,7 @@ def __init__(self):
     # Create a Supabase client
     self.supabase_client = supabase.create_client(  # type: ignore
         supabase_url=os.environ['SUPABASE_URL'], supabase_key=os.environ['SUPABASE_API_KEY'])
-
+    
   def getAllMaterialsForCourse(self, course_name: str):
     return self.supabase_client.table(
         os.environ['SUPABASE_DOCUMENTS_TABLE']).select('course_name, s3_path, readable_filename, url, base_url').eq(
@@ -134,3 +134,5 @@ def getConversation(self, course_name: str, key: str, value: str):
 
   def getDisabledDocGroups(self, course_name: str):
     return self.supabase_client.table("doc_groups").select("name").eq("course_name", course_name).eq("enabled", False).execute()
+  def getCourseDocumentByS3Path(self, course_name: str, s3_path: str):
+    return self.supabase_client.table("documents").select("id, course_name, readable_filename, url, base_url, s3_path, created_at").eq("course_name", course_name).eq("s3_path", s3_path).execute()

ai_ta_backend/main.py

@@ -40,6 +40,7 @@
 from ai_ta_backend.service.retrieval_service import RetrievalService
 from ai_ta_backend.service.sentry_service import SentryService
 from ai_ta_backend.service.workflow_service import WorkflowService
+from ai_ta_backend.utils.pub_ingest import downloadSpringerFulltext, downloadWileyFulltext
 
 app = Flask(__name__)
 CORS(app)
@@ -480,6 +481,56 @@ def run_flow(service: WorkflowService) -> Response:
       return response
 
 
+@app.route('/get-springer-fulltext', methods=['GET'])
+def get_springer_data():
+  course_name: str = request.args.get('course_name', default='', type=str)
+  issn = request.args.get('issn', default='', type=str)
+  subject = request.args.get('subject', default='', type=str)
+  journal = request.args.get('journal', default='', type=str)
+  title = request.args.get('title', default='', type=str)
+  doi = request.args.get('doi', default='', type=str)
+
+  print("In /get-springer-fulltext")
+
+  if (issn == '' and subject == '' and journal == '' and title == '' and doi == '') or course_name == '':
+    # proper web error "400 Bad request"
+    abort(
+        400,
+        description=
+        f"Missing required parameters: 'issn' or 'subject' or 'title' or 'journal' or 'doi' and 'course_name' must be provided."
+    )
+
+  fulltext = downloadSpringerFulltext(issn, subject, journal, title, doi, course_name)
+
+  response = jsonify(fulltext)
+  response.headers.add('Access-Control-Allow-Origin', '*')
+  return response
+
+@app.route('/get-wiley-fulltext', methods=['POST'])
+def get_wiley_data():
+  data = request.get_json()
+  print(data)
+
+  course_name = data['course_name']
+  issn = data['issn']
+
+  print("In /get-wiley-fulltext")
+
+  if issn == [] or course_name == '':
+    # proper web error "400 Bad request"
+    abort(
+        400,
+        description=
+        f"Missing required parameters: 'issn' or 'doi' and 'course_name' must be provided."
+    )
+
+  fulltext = downloadWileyFulltext(course_name, issn)
+
+  response = jsonify(fulltext)
+  response.headers.add('Access-Control-Allow-Origin', '*')
+  return response
+
+
 def configure(binder: Binder) -> None:
   binder.bind(RetrievalService, to=RetrievalService, scope=RequestScope)
   binder.bind(PosthogService, to=PosthogService, scope=SingletonScope)