Merge pull request #18 from tools4ds/Farid-Karimli-patch-1

apps/ai_tutor/config/project_config.yml

@@ -3,15 +3,47 @@ retriever:
     RAGatouille: "XThomasBU/Colbert_Index"
 
 metadata:
-  metadata_links: ["https://dl4ds.github.io/sp2024/lectures/", "https://dl4ds.github.io/sp2024/schedule/"]
-  slide_base_link: "https://dl4ds.github.io"
+  base_link: "https://tools4ds.github.io/fa2024/"
+  metadata_links:
+    [
+      "https://tools4ds.github.io/fa2024/lectures/",
+      "https://tools4ds.github.io/fa2024/schedule_a1/",
+    ]
+  slide_base_link: "https://tools4ds.github.io/fa2024/lectures/"
+
+  # Assignment base link is used to find the webpage where the assignment is described/posted
+  assignment_base_link: "https://tools4ds.github.io/fa2024/assignments/"
+
+  # These need to be patterns from URLs that can be used to identify the type of content uniquely
+  lectures_pattern: "/lectures/"
+  assignments_pattern: "/assignments/"
+
+  # These are fields that can be extracted from the webpages of the course content
+  lecture_metadata_fields:
+    - "title"
+    - "tldr"
+    - "date"
+    - "lecture_recording"
+    - "suggested_readings"
+
+  assignment_metadata_fields:
+    - "title"
+    - "release_date"
+    - "due_date"
+    - "source_file"
 
 token_config:
   cooldown_time: 60
   regen_time: 180
-  tokens_left: 2000
+  tokens_left: 50000
   all_time_tokens_allocated: 1000000
 
+content:
+  notebookheaders_to_split_on:
+    - ["####", "Question"]
+    - ["##", "Section"]
+    - ["#", "Title"]
+
 misc:
   github_repo: "https://github.com/edubotics-ai/edubot-core"
   docs_website: "https://dl4ds.github.io/dl4ds_tutor/"