Merge pull request #89 from DL4DS/code_restructure

.gitignore

@@ -169,5 +169,16 @@ code/.chainlit/translations/
 storage/logs/*
 vectorstores/*
 
-*/.files/*
+**/.files/*
 code/storage/models/
+
+**/translations/en-US.json
+**/translations/zh-CN.json
+
+
+**/vectorstores/*
+
+**/private/students.json
+
+**/apps/*/storage/logs/*
+**/apps/*/private/*

Dockerfile

@@ -3,13 +3,18 @@ FROM python:3.11
 WORKDIR /code
 
 COPY ./requirements.txt /code/requirements.txt
+COPY ./setup.py /code/setup.py
 
 RUN pip install --upgrade pip
 
 RUN pip install --no-cache-dir -r /code/requirements.txt
+RUN pip install -e .
 
 COPY . /code
 
+# Copy .env file to the application directory
+COPY .env /code/apps/ai_tutor/.env
+
 # List the contents of the /code directory to verify files are copied correctly
 RUN ls -R /code
 
@@ -17,12 +22,15 @@ RUN ls -R /code
 RUN chmod -R 777 /code
 
 # Create a logs directory and set permissions
-RUN mkdir /code/logs && chmod 777 /code/logs
+RUN mkdir /code/apps/ai_tutor/logs && chmod 777 /code/apps/ai_tutor/logs
 
 # Create a cache directory within the application's working directory
 RUN mkdir /.cache && chmod -R 777 /.cache
 
-WORKDIR /code/code
+WORKDIR /code/apps/ai_tutor
+
+# Expose the port the app runs on
+EXPOSE 7860
 
 RUN --mount=type=secret,id=HUGGINGFACEHUB_API_TOKEN,mode=0444,required=true 
 RUN --mount=type=secret,id=OPENAI_API_KEY,mode=0444,required=true 
@@ -35,4 +43,4 @@ RUN --mount=type=secret,id=LITERAL_API_KEY_LOGGING,mode=0444,required=true
 RUN --mount=type=secret,id=CHAINLIT_AUTH_SECRET,mode=0444,required=true 
 
 # Default command to run the application
-CMD ["sh", "-c", "python -m modules.vectorstore.store_manager && uvicorn app:app --host 0.0.0.0 --port 7860"]
+CMD python -m modules.vectorstore.store_manager --config_file config/config.yml --project_config_file config/project_config.yml && python -m uvicorn app:app --host 0.0.0.0 --port 7860

Dockerfile.dev

@@ -3,13 +3,18 @@ FROM python:3.11
 WORKDIR /code
 
 COPY ./requirements.txt /code/requirements.txt
+COPY ./setup.py /code/setup.py
 
 RUN pip install --upgrade pip
 
 RUN pip install --no-cache-dir -r /code/requirements.txt
+RUN pip install -e .
 
 COPY . /code
 
+# Copy .env file to the application directory
+COPY .env /code/apps/ai_tutor/.env
+
 # List the contents of the /code directory to verify files are copied correctly
 RUN ls -R /code
 
@@ -17,15 +22,17 @@ RUN ls -R /code
 RUN chmod -R 777 /code
 
 # Create a logs directory and set permissions
-RUN mkdir /code/logs && chmod 777 /code/logs
+RUN mkdir /code/apps/ai_tutor/logs && chmod 777 /code/apps/ai_tutor/logs
 
 # Create a cache directory within the application's working directory
 RUN mkdir /.cache && chmod -R 777 /.cache
 
-WORKDIR /code/code
+WORKDIR /code/apps/ai_tutor
+
+RUN ls -R /code
 
 # Expose the port the app runs on
-EXPOSE 8000
+EXPOSE 7860
 
 # Default command to run the application
-CMD ["sh", "-c", "python -m modules.vectorstore.store_manager && chainlit run main.py --host 0.0.0.0 --port 8000"]
+CMD python -m modules.vectorstore.store_manager --config_file config/config.yml --project_config_file config/project_config.yml && python -m uvicorn app:app --host 0.0.0.0 --port 7860

README.md

@@ -9,6 +9,12 @@ app_port: 7860
 ---
 # DL4DS Tutor 🏃
 
+![Build Status](https://github.com/DL4DS/dl4ds_tutor/actions/workflows/push_to_hf_space.yml/badge.svg)
+![License](https://img.shields.io/github/license/DL4DS/dl4ds_tutor)
+![GitHub stars](https://img.shields.io/github/stars/DL4DS/dl4ds_tutor)
+![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)
+
+
 Check out the configuration reference at [Hugging Face Spaces Config Reference](https://huggingface.co/docs/hub/spaces-config-reference).
 
 You can find a "production" implementation of the Tutor running live at [DL4DS Tutor](https://dl4ds-dl4ds-tutor.hf.space/)  from the
@@ -30,26 +36,31 @@ Please visit [setup](https://dl4ds.github.io/dl4ds_tutor/guide/setup/) for more
    git clone https://github.com/DL4DS/dl4ds_tutor
    ```
 
-2. **Put your data under the `storage/data` directory**
+2. Create your app in the apps folder. (An example is the `apps/ai_tutor` app)
+   ```
+   cd apps
+   mkdir your_app
+   ```
+
+2. **Put your data under the `apps/your_app/storage/data` directory**
    - Add URLs in the `urls.txt` file.
-   - Add other PDF files in the `storage/data` directory.
+   - Add other PDF files in the `apps/your_app/storage/data` directory.
 
 3. **To test Data Loading (Optional)**
    ```bash
-   cd code
-   python -m modules.dataloader.data_loader --links "your_pdf_link"
+   cd apps/your_app
+   python -m modules.dataloader.data_loader --links "your_pdf_link" --config_file config/config.yml --project_config_file config/project_config.yml
    ```
 
 4. **Create the Vector Database**
    ```bash
-   cd code
-   python -m modules.vectorstore.store_manager
+   cd apps/your_app
+   python -m modules.vectorstore.store_manager --config_file config/config.yml --project_config_file config/project_config.yml
    ```
-   - Note: You need to run the above command when you add new data to the `storage/data` directory, or if the `storage/data/urls.txt` file is updated.
 
 6. **Run the FastAPI App**
    ```bash
-   cd code
+   cd apps/your_app
    uvicorn app:app --port 7860 
    ```
 
@@ -64,7 +75,7 @@ The HuggingFace Space is built using the `Dockerfile` in the repository. To run
 
 ```bash
 docker build --tag dev  -f Dockerfile.dev .
-docker run -it --rm -p 8000:8000 dev
+docker run -it --rm -p 7860:7860 dev
 ```
 
 ## Contributing

{code → apps/ai_tutor}/.chainlit/config.toml

@@ -69,7 +69,7 @@ github = "https://github.com/DL4DS/dl4ds_tutor"
 
 # Specify a CSS file that can be used to customize the user interface.
 # The CSS file can be served from the public directory or via an external link.
-custom_css = "/public/test.css"
+custom_css = "/public/files/test.css"
 
 # Specify a Javascript file that can be used to customize the user interface.
 # The Javascript file can be served from the public directory.

apps/ai_tutor/README.md

@@ -0,0 +1,12 @@
+# WIP
+
+
+## Run the encrypt_students script
+
+- If you don't want the emails to be public, run this script to encrypt the emails of the students.
+- This will create a new file in the public/files/ directory.
+- Place your file with the students' emails in the private/ directory (do not commit this file to the repository).
+
+```bash
+python encrypt_students.py --students-file private/students.json --encrypted-students-file public/files/students_encrypted.json
+```

{code → apps/ai_tutor}/app.py

@@ -8,24 +8,31 @@ from chainlit.utils import mount_chainlit
 import secrets
 import json
 import base64
-from modules.config.constants import (
+from config.constants import (
     OAUTH_GOOGLE_CLIENT_ID,
     OAUTH_GOOGLE_CLIENT_SECRET,
     CHAINLIT_URL,
-    GITHUB_REPO,
-    DOCS_WEBSITE,
-    ALL_TIME_TOKENS_ALLOCATED,
-    TOKENS_LEFT,
+    EMAIL_ENCRYPTION_KEY,
 )
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.staticfiles import StaticFiles
-from modules.chat_processor.helpers import (
-    get_user_details,
+from helpers import (
     get_time,
     reset_tokens_for_user,
     check_user_cooldown,
-    update_user_info,
 )
+from modules.chat_processor.helpers import get_user_details, update_user_info
+from config.config_manager import config_manager
+import hashlib
+
+# set config
+config = config_manager.get_config().dict()
+
+# set constants
+GITHUB_REPO = config["misc"]["github_repo"]
+DOCS_WEBSITE = config["misc"]["docs_website"]
+ALL_TIME_TOKENS_ALLOCATED = config["token_config"]["all_time_tokens_allocated"]
+TOKENS_LEFT = config["token_config"]["tokens_left"]
 
 GOOGLE_CLIENT_ID = OAUTH_GOOGLE_CLIENT_ID
 GOOGLE_CLIENT_SECRET = OAUTH_GOOGLE_CLIENT_SECRET
@@ -46,13 +53,8 @@ session_store = {}
 CHAINLIT_PATH = "/chainlit_tutor"
 
 # only admin is given any additional permissions for now -- no limits on tokens
-USER_ROLES = {
-    "[email protected]": ["instructor", "bu"],
-    "[email protected]": ["admin", "instructor", "bu"],
-    "[email protected]": ["instructor", "bu"],
-    "[email protected]": ["guest"],
-    # Add more users and roles as needed
-}
+with open("public/files/students_encrypted.json", "r") as file:
+    USER_ROLES = json.load(file)
 
 # Create a Google OAuth flow
 flow = Flow.from_client_config(
@@ -80,7 +82,20 @@ flow = Flow.from_client_config(
 
 
 def get_user_role(username: str):
-    return USER_ROLES.get(username, ["guest"])  # Default to "guest" role
+
+    # Function to deterministically hash emails
+    def deterministic_hash(email, salt):
+        return hashlib.pbkdf2_hmac("sha256", email.encode(), salt, 100000).hex()
+
+    # encrypt email (#FIXME: this is not the best way to do this, not really encryption, more like a hash)
+    encryption_salt = EMAIL_ENCRYPTION_KEY.encode()
+    encrypted_email = deterministic_hash(username, encryption_salt)
+    role = USER_ROLES.get(encrypted_email, ["guest"])
+
+    if "guest" in role:
+        return "unauthorized"
+
+    return role
 
 
 async def get_user_info_from_cookie(request: Request):
@@ -146,6 +161,11 @@ async def login_page(request: Request):
 #     return response
 
 
+@app.get("/unauthorized", response_class=HTMLResponse)
+async def unauthorized(request: Request):
+    return templates.TemplateResponse("unauthorized.html", {"request": request})
+
+
 @app.get("/login/google")
 async def login_google(request: Request):
     # Clear any existing session cookies to avoid conflicts with guest sessions
@@ -176,6 +196,9 @@ async def auth_google(request: Request):
         profile_image = user_info.get("picture", "")
         role = get_user_role(email)
 
+        if role == "unauthorized":
+            return RedirectResponse("/unauthorized")
+
         session_token = secrets.token_hex(16)
         session_store[session_token] = {
             "email": email,
@@ -228,7 +251,11 @@ async def cooldown(request: Request):
     else:
         user_details.metadata["in_cooldown"] = False
         await update_user_info(user_details)
-        await reset_tokens_for_user(user_details)
+        await reset_tokens_for_user(
+            user_details,
+            config["token_config"]["tokens_left"],
+            config["token_config"]["regen_time"],
+        )
         return RedirectResponse("/post-signin")
 
 
@@ -262,7 +289,11 @@ async def post_signin(request: Request):
             return RedirectResponse("/cooldown")
         else:
             user_details.metadata["in_cooldown"] = False
-            await reset_tokens_for_user(user_details)
+            await reset_tokens_for_user(
+                user_details,
+                config["token_config"]["tokens_left"],
+                config["token_config"]["regen_time"],
+            )
 
     if user_info:
         username = user_info["email"]
@@ -335,7 +366,11 @@ async def get_tokens_left(request: Request):
     try:
         user_info = await get_user_info_from_cookie(request)
         user_details = await get_user_details(user_info["email"])
-        await reset_tokens_for_user(user_details)
+        await reset_tokens_for_user(
+            user_details,
+            config["token_config"]["tokens_left"],
+            config["token_config"]["regen_time"],
+        )
         tokens_left = user_details.metadata["tokens_left"]
         return {"tokens_left": tokens_left}
     except Exception as e:
@@ -343,7 +378,7 @@ async def get_tokens_left(request: Request):
         return {"tokens_left": 0}
 
 
-mount_chainlit(app=app, target="main.py", path=CHAINLIT_PATH)
+mount_chainlit(app=app, target="chainlit_app.py", path=CHAINLIT_PATH)
 
 if __name__ == "__main__":
     import uvicorn

code/main.py → apps/ai_tutor/chainlit_app.py

@@ -1,12 +1,11 @@
 import chainlit.data as cl_data
 import asyncio
-from modules.config.constants import (
+from config.constants import (
     LITERAL_API_KEY_LOGGING,
     LITERAL_API_URL,
 )
 from modules.chat_processor.literal_ai import CustomLiteralDataLayer
 import json
-import yaml
 from typing import Any, Dict, no_type_check
 import chainlit as cl
 from modules.chat.llm_tutor import LLMTutor
@@ -18,11 +17,13 @@ from modules.chat.helpers import (
 )
 from modules.chat_processor.helpers import (
     update_user_info,
-    get_time,
+    get_user_details,
+)
+from helpers import (
     check_user_cooldown,
     reset_tokens_for_user,
-    get_user_details,
 )
+from helpers import get_time
 import copy
 from typing import Optional
 from chainlit.types import ThreadDict
@@ -30,6 +31,7 @@ import time
 import base64
 from langchain_community.callbacks import get_openai_callback
 from datetime import datetime, timezone
+from config.config_manager import config_manager
 
 USER_TIMEOUT = 60_000
 SYSTEM = "System"
@@ -38,8 +40,8 @@ AGENT = "Agent"
 YOU = "User"
 ERROR = "Error"
 
-with open("modules/config/config.yml", "r") as f:
-    config = yaml.safe_load(f)
+# set config
+config = config_manager.get_config().dict()
 
 
 async def setup_data_layer():
@@ -81,13 +83,6 @@ class Chatbot:
         """
         self.config = config
 
-    async def _load_config(self):
-        """
-        Load the configuration from a YAML file.
-        """
-        with open("modules/config/config.yml", "r") as f:
-            return yaml.safe_load(f)
-
     @no_type_check
     async def setup_llm(self):
         """
@@ -271,24 +266,24 @@ class Chatbot:
             print(e)
             return [
                 cl.Starter(
-                    label="recording on CNNs?",
+                    label="recording on Transformers?",
                     message="Where can I find the recording for the lecture on Transformers?",
-                    icon="/public/adv-screen-recorder-svgrepo-com.svg",
+                    icon="/public/assets/images/starter_icons/adv-screen-recorder-svgrepo-com.svg",
                 ),
                 cl.Starter(
-                    label="where's the slides?",
+                    label="where's the schedule?",
                     message="When are the lectures? I can't find the schedule.",
-                    icon="/public/alarmy-svgrepo-com.svg",
+                    icon="/public/assets/images/starter_icons/alarmy-svgrepo-com.svg",
                 ),
                 cl.Starter(
                     label="Due Date?",
                     message="When is the final project due?",
-                    icon="/public/calendar-samsung-17-svgrepo-com.svg",
+                    icon="/public/assets/images/starter_icons/calendar-samsung-17-svgrepo-com.svg",
                 ),
                 cl.Starter(
                     label="Explain backprop.",
                     message="I didn't understand the math behind backprop, could you explain it?",
-                    icon="/public/acastusphoton-svgrepo-com.svg",
+                    icon="/public/assets/images/starter_icons/acastusphoton-svgrepo-com.svg",
                 ),
             ]
 
@@ -305,7 +300,7 @@ class Chatbot:
         rename_dict = {"Chatbot": LLM}
         return rename_dict.get(orig_author, orig_author)
 
-    async def start(self, config=None):
+    async def start(self):
         """
         Start the chatbot, initialize settings widgets,
         and display and load previous conversation if chat logging is enabled.
@@ -313,10 +308,6 @@ class Chatbot:
 
         start_time = time.time()
 
-        self.config = (
-            await self._load_config() if config is None else config
-        )  # Reload the configuration on chat resume
-
         await self.make_llm_settings_widgets(self.config)  # Reload the settings widgets
 
         user = cl.user_session.get("user")
@@ -386,7 +377,11 @@ class Chatbot:
 
         # update user info with last message time
         user = cl.user_session.get("user")
-        await reset_tokens_for_user(user)
+        await reset_tokens_for_user(
+            user,
+            self.config["token_config"]["tokens_left"],
+            self.config["token_config"]["regen_time"],
+        )
         updated_user = await get_user_details(user.identifier)
         user.metadata = updated_user.metadata
         cl.user_session.set("user", user)
@@ -530,7 +525,6 @@ class Chatbot:
             elements=source_elements,
             author=LLM,
             actions=actions,
-            metadata=self.config,
         ).send()
 
     async def on_chat_resume(self, thread: ThreadDict):

{code/modules → apps/ai_tutor}/config/config.yml

@@ -1,15 +1,15 @@
-log_dir: '../storage/logs' # str
-log_chunk_dir: '../storage/logs/chunks' # str
+log_dir: 'storage/logs' # str
+log_chunk_dir: 'storage/logs/chunks' # str
 device: 'cpu' # str [cuda, cpu]
 
 vectorstore:
   load_from_HF: True # bool
   reparse_files: True # bool
-  data_path: '../storage/data' # str
-  url_file_path: '../storage/data/urls.txt' # str
+  data_path: 'storage/data' # str
+  url_file_path: 'storage/data/urls.txt' # str
   expand_urls: True # bool
   db_option : 'RAGatouille' # str [FAISS, Chroma, RAGatouille, RAPTOR]
-  db_path : '../vectorstores' # str
+  db_path : 'vectorstores' # str
   model : 'sentence-transformers/all-MiniLM-L6-v2' # str [sentence-transformers/all-MiniLM-L6-v2, text-embedding-ada-002']
   search_top_k : 3 # int
   score_threshold : 0.2 # float

apps/ai_tutor/config/config_manager.py

@@ -0,0 +1,188 @@
+from pydantic import BaseModel, conint, confloat, HttpUrl
+from typing import Optional, List
+import yaml
+
+
+class FaissParams(BaseModel):
+    index_path: str = "vectorstores/faiss.index"
+    index_type: str = "Flat"  # Options: [Flat, HNSW, IVF]
+    index_dimension: conint(gt=0) = 384
+    index_nlist: conint(gt=0) = 100
+    index_nprobe: conint(gt=0) = 10
+
+
+class ColbertParams(BaseModel):
+    index_name: str = "new_idx"
+
+
+class VectorStoreConfig(BaseModel):
+    load_from_HF: bool = True
+    reparse_files: bool = True
+    data_path: str = "storage/data"
+    url_file_path: str = "storage/data/urls.txt"
+    expand_urls: bool = True
+    db_option: str = "RAGatouille"  # Options: [FAISS, Chroma, RAGatouille, RAPTOR]
+    db_path: str = "vectorstores"
+    model: str = (
+        "sentence-transformers/all-MiniLM-L6-v2"  # Options: [sentence-transformers/all-MiniLM-L6-v2, text-embedding-ada-002]
+    )
+    search_top_k: conint(gt=0) = 3
+    score_threshold: confloat(ge=0.0, le=1.0) = 0.2
+
+    faiss_params: Optional[FaissParams] = None
+    colbert_params: Optional[ColbertParams] = None
+
+
+class OpenAIParams(BaseModel):
+    temperature: confloat(ge=0.0, le=1.0) = 0.7
+
+
+class LocalLLMParams(BaseModel):
+    temperature: confloat(ge=0.0, le=1.0) = 0.7
+    repo_id: str = "TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF"  # HuggingFace repo id
+    filename: str = (
+        "tinyllama-1.1b-chat-v1.0.Q5_0.gguf"  # Specific name of gguf file in the repo
+    )
+    model_path: str = (
+        "storage/models/tinyllama-1.1b-chat-v1.0.Q5_0.gguf"  # Path to the model file
+    )
+
+
+class LLMParams(BaseModel):
+    llm_arch: str = "langchain"  # Options: [langchain]
+    use_history: bool = True
+    generate_follow_up: bool = False
+    memory_window: conint(ge=1) = 3
+    llm_style: str = "Normal"  # Options: [Normal, ELI5]
+    llm_loader: str = (
+        "gpt-4o-mini"  # Options: [local_llm, gpt-3.5-turbo-1106, gpt-4, gpt-4o-mini]
+    )
+    openai_params: Optional[OpenAIParams] = None
+    local_llm_params: Optional[LocalLLMParams] = None
+    stream: bool = False
+    pdf_reader: str = "gpt"  # Options: [llama, pymupdf, gpt]
+
+
+class ChatLoggingConfig(BaseModel):
+    log_chat: bool = True
+    platform: str = "literalai"
+    callbacks: bool = True
+
+
+class SplitterOptions(BaseModel):
+    use_splitter: bool = True
+    split_by_token: bool = True
+    remove_leftover_delimiters: bool = True
+    remove_chunks: bool = False
+    chunking_mode: str = "semantic"  # Options: [fixed, semantic]
+    chunk_size: conint(gt=0) = 300
+    chunk_overlap: conint(ge=0) = 30
+    chunk_separators: List[str] = ["\n\n", "\n", " ", ""]
+    front_chunks_to_remove: Optional[conint(ge=0)] = None
+    last_chunks_to_remove: Optional[conint(ge=0)] = None
+    delimiters_to_remove: List[str] = ["\t", "\n", "   ", "  "]
+
+
+class RetrieverConfig(BaseModel):
+    retriever_hf_paths: dict[str, str] = {"RAGatouille": "XThomasBU/Colbert_Index"}
+
+
+class MetadataConfig(BaseModel):
+    metadata_links: List[HttpUrl] = [
+        "https://dl4ds.github.io/sp2024/lectures/",
+        "https://dl4ds.github.io/sp2024/schedule/",
+    ]
+    slide_base_link: HttpUrl = "https://dl4ds.github.io"
+
+
+class TokenConfig(BaseModel):
+    cooldown_time: conint(gt=0) = 60
+    regen_time: conint(gt=0) = 180
+    tokens_left: conint(gt=0) = 2000
+    all_time_tokens_allocated: conint(gt=0) = 1000000
+
+
+class MiscConfig(BaseModel):
+    github_repo: HttpUrl = "https://github.com/DL4DS/dl4ds_tutor"
+    docs_website: HttpUrl = "https://dl4ds.github.io/dl4ds_tutor/"
+
+
+class APIConfig(BaseModel):
+    timeout: conint(gt=0) = 60
+
+
+class Config(BaseModel):
+    log_dir: str = "storage/logs"
+    log_chunk_dir: str = "storage/logs/chunks"
+    device: str = "cpu"  # Options: ['cuda', 'cpu']
+
+    vectorstore: VectorStoreConfig
+    llm_params: LLMParams
+    chat_logging: ChatLoggingConfig
+    splitter_options: SplitterOptions
+    retriever: RetrieverConfig
+    metadata: MetadataConfig
+    token_config: TokenConfig
+    misc: MiscConfig
+    api_config: APIConfig
+
+
+class ConfigManager:
+    def __init__(self, config_path: str, project_config_path: str):
+        self.config_path = config_path
+        self.project_config_path = project_config_path
+        self.config = self.load_config()
+        self.validate_config()
+
+    def load_config(self) -> Config:
+        with open(self.config_path, "r") as f:
+            config_data = yaml.safe_load(f)
+
+        with open(self.project_config_path, "r") as f:
+            project_config_data = yaml.safe_load(f)
+
+        # Merge the two configurations
+        merged_config = {**config_data, **project_config_data}
+
+        return Config(**merged_config)
+
+    def get_config(self) -> Config:
+        return ConfigWrapper(self.config)
+
+    def validate_config(self):
+        # If any required fields are missing, raise an error
+        # required_fields = [
+        #     "vectorstore", "llm_params", "chat_logging", "splitter_options",
+        #     "retriever", "metadata", "token_config", "misc", "api_config"
+        # ]
+        # for field in required_fields:
+        #     if not hasattr(self.config, field):
+        #         raise ValueError(f"Missing required configuration field: {field}")
+
+        # # Validate types of specific fields
+        # if not isinstance(self.config.vectorstore, VectorStoreConfig):
+        #     raise TypeError("vectorstore must be an instance of VectorStoreConfig")
+        # if not isinstance(self.config.llm_params, LLMParams):
+        #     raise TypeError("llm_params must be an instance of LLMParams")
+        pass
+
+
+class ConfigWrapper:
+    def __init__(self, config: Config):
+        self._config = config
+
+    def __getitem__(self, key):
+        return getattr(self._config, key)
+
+    def __getattr__(self, name):
+        return getattr(self._config, name)
+
+    def dict(self):
+        return self._config.dict()
+
+
+# Usage
+config_manager = ConfigManager(
+    config_path="config/config.yml", project_config_path="config/project_config.yml"
+)
+# config = config_manager.get_config().dict()

{code/modules → apps/ai_tutor}/config/constants.py

@@ -3,15 +3,6 @@ import os
 
 load_dotenv()
 
-TIMEOUT = 60
-COOLDOWN_TIME = 60
-REGEN_TIME = 180
-TOKENS_LEFT = 2000
-ALL_TIME_TOKENS_ALLOCATED = 1000000
-
-GITHUB_REPO = "https://github.com/DL4DS/dl4ds_tutor"
-DOCS_WEBSITE = "https://dl4ds.github.io/dl4ds_tutor/"
-
 # API Keys - Loaded from the .env file
 
 OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
@@ -20,6 +11,7 @@ HUGGINGFACE_TOKEN = os.getenv("HUGGINGFACE_TOKEN")
 LITERAL_API_KEY_LOGGING = os.getenv("LITERAL_API_KEY_LOGGING")
 LITERAL_API_URL = os.getenv("LITERAL_API_URL")
 CHAINLIT_URL = os.getenv("CHAINLIT_URL")
+EMAIL_ENCRYPTION_KEY = os.getenv("EMAIL_ENCRYPTION_KEY")
 
 OAUTH_GOOGLE_CLIENT_ID = os.getenv("OAUTH_GOOGLE_CLIENT_ID")
 OAUTH_GOOGLE_CLIENT_SECRET = os.getenv("OAUTH_GOOGLE_CLIENT_SECRET")

apps/ai_tutor/config/project_config.yml

@@ -0,0 +1,20 @@
+retriever:
+  retriever_hf_paths:
+    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"
+
+token_config:
+  cooldown_time: 60
+  regen_time: 180
+  tokens_left: 2000
+  all_time_tokens_allocated: 1000000
+
+misc:
+  github_repo: "https://github.com/DL4DS/dl4ds_tutor"
+  docs_website: "https://dl4ds.github.io/dl4ds_tutor/"
+
+api_config:
+  timeout: 60

apps/ai_tutor/encrypt_students.py

@@ -0,0 +1,53 @@
+import os
+import hashlib
+import json
+import argparse
+from dotenv import load_dotenv
+
+
+# Function to deterministically hash emails
+def deterministic_hash(email, salt):
+    return hashlib.pbkdf2_hmac("sha256", email.encode(), salt, 100000).hex()
+
+
+def main(args):
+    # Load the .env file
+    load_dotenv()
+
+    # Get the encryption key (salt)
+    encryption_salt = os.getenv("EMAIL_ENCRYPTION_KEY").encode()
+
+    # Load emails from the specified JSON file
+    with open(args.students_file, "r") as file:
+        emails = json.load(file)
+
+    # Replace emails with deterministic hashed emails, {hashed_email: [roles]}
+    hashed_emails = {
+        deterministic_hash(email, encryption_salt): roles
+        for email, roles in emails.items()
+    }
+
+    # Save hashed emails to the specified encrypted JSON file
+    with open(args.encrypted_students_file, "w") as file:
+        json.dump(hashed_emails, file)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="Encrypt student emails in a JSON file."
+    )
+    parser.add_argument(
+        "--students-file",
+        type=str,
+        default="private/students.json",
+        help="Path to the students JSON file",
+    )
+    parser.add_argument(
+        "--encrypted-students-file",
+        type=str,
+        default="public/files/students_encrypted.json",
+        help="Path to save the encrypted students JSON file",
+    )
+    args = parser.parse_args()
+
+    main(args)

apps/ai_tutor/helpers.py

@@ -0,0 +1,94 @@
+from datetime import datetime, timedelta, timezone
+import tiktoken
+from modules.chat_processor.helpers import update_user_info, convert_to_dict
+
+
+def get_time():
+    return datetime.now(timezone.utc).isoformat()
+
+
+async def check_user_cooldown(
+    user_info, current_time, COOLDOWN_TIME, TOKENS_LEFT, REGEN_TIME
+):
+    # # Check if no tokens left
+    tokens_left = user_info.metadata.get("tokens_left", 0)
+    if tokens_left > 0 and not user_info.metadata.get("in_cooldown", False):
+        return False, None
+
+    user_info = convert_to_dict(user_info)
+    last_message_time_str = user_info["metadata"].get("last_message_time")
+
+    # Convert from ISO format string to datetime object and ensure UTC timezone
+    last_message_time = datetime.fromisoformat(last_message_time_str).replace(
+        tzinfo=timezone.utc
+    )
+    current_time = datetime.fromisoformat(current_time).replace(tzinfo=timezone.utc)
+
+    # Calculate the elapsed time
+    elapsed_time = current_time - last_message_time
+    elapsed_time_in_seconds = elapsed_time.total_seconds()
+
+    # Calculate when the cooldown period ends
+    cooldown_end_time = last_message_time + timedelta(seconds=COOLDOWN_TIME)
+    cooldown_end_time_iso = cooldown_end_time.isoformat()
+
+    # Debug: Print the cooldown end time
+    print(f"Cooldown end time (ISO): {cooldown_end_time_iso}")
+
+    # Check if the user is still in cooldown
+    if elapsed_time_in_seconds < COOLDOWN_TIME:
+        return True, cooldown_end_time_iso  # Return in ISO 8601 format
+
+    user_info["metadata"]["in_cooldown"] = False
+    # If not in cooldown, regenerate tokens
+    await reset_tokens_for_user(user_info, TOKENS_LEFT, REGEN_TIME)
+
+    return False, None
+
+
+async def reset_tokens_for_user(user_info, TOKENS_LEFT, REGEN_TIME):
+    user_info = convert_to_dict(user_info)
+    last_message_time_str = user_info["metadata"].get("last_message_time")
+
+    last_message_time = datetime.fromisoformat(last_message_time_str).replace(
+        tzinfo=timezone.utc
+    )
+    current_time = datetime.fromisoformat(get_time()).replace(tzinfo=timezone.utc)
+
+    # Calculate the elapsed time since the last message
+    elapsed_time_in_seconds = (current_time - last_message_time).total_seconds()
+
+    # Current token count (can be negative)
+    current_tokens = user_info["metadata"].get("tokens_left_at_last_message", 0)
+    current_tokens = min(current_tokens, TOKENS_LEFT)
+
+    # Maximum tokens that can be regenerated
+    max_tokens = user_info["metadata"].get("max_tokens", TOKENS_LEFT)
+
+    # Calculate how many tokens should have been regenerated proportionally
+    if current_tokens < max_tokens:
+        # Calculate the regeneration rate per second based on REGEN_TIME for full regeneration
+        regeneration_rate_per_second = max_tokens / REGEN_TIME
+
+        # Calculate how many tokens should have been regenerated based on the elapsed time
+        tokens_to_regenerate = int(
+            elapsed_time_in_seconds * regeneration_rate_per_second
+        )
+
+        # Ensure the new token count does not exceed max_tokens
+        new_token_count = min(current_tokens + tokens_to_regenerate, max_tokens)
+
+        print(
+            f"\n\n Adding {tokens_to_regenerate} tokens to the user, Time elapsed: {elapsed_time_in_seconds} seconds, Tokens after regeneration: {new_token_count}, Tokens before: {current_tokens} \n\n"
+        )
+
+        # Update the user's token count
+        user_info["metadata"]["tokens_left"] = new_token_count
+
+        await update_user_info(user_info)
+
+
+def get_num_tokens(text, model):
+    encoding = tiktoken.encoding_for_model(model)
+    tokens = encoding.encode(text)
+    return len(tokens)

apps/ai_tutor/private/placeholder_students_file.json

@@ -0,0 +1,5 @@
+{
+    "[email protected]": ["student", "bu"],
+    "[email protected]": ["student", "bu"],
+    "[email protected]": ["admin", "instructor", "bu"]
+}

apps/ai_tutor/public/files/students_encrypted.json

@@ -0,0 +1 @@
+{"7f1cacca66ee914ddde2ee20e0f2c96651d60cd8aabd310ef25a9e6d88f42df0": ["instructor", "bu"], "f74d264b6b5b2b4c10ce69e4ec16e869e01cb5eb668ed846aa8f6dae5c96cda0": ["admin", "instructor", "bu"], "53401356a874b1539775c73a8564d5e5f4f840441630c9cf649e16d201454f20": ["instructor", "bu"]}

apps/ai_tutor/public/files/test.css

@@ -0,0 +1,32 @@
+a[href*='https://github.com/Chainlit/chainlit'] {
+    visibility: hidden;
+}
+
+/* Hide the default avatar image */ 
+.MuiAvatar-root img.MuiAvatar-img {
+    display: none;
+  }
+  
+/* Target the container of the image and set a custom background image */
+.MuiAvatar-root.MuiAvatar-circular.css-m2icte {
+    background-image: url('/public/assets/images/avatars/ai-tutor.png'); /* Replace with your custom image URL */
+    background-size: cover; /* Ensure the image covers the entire container */
+    background-position: center; /* Center the image */
+    width: 100px; /* Ensure the dimensions match the original */
+    height: 100px; /* Ensure the dimensions match the original */
+    border-radius: 50%; /* Maintain circular shape */
+}
+.MuiAvatar-root.MuiAvatar-circular.css-v72an7 {
+    background-image: url('/public/assets/images/avatars/ai-tutor.png'); /* Replace with your custom image URL */
+    background-size: cover; /* Ensure the image covers the entire container */
+    background-position: center; /* Center the image */
+    width: 40px; /* Ensure the dimensions match the original */
+    height: 40px; /* Ensure the dimensions match the original */
+    border-radius: 50%; /* Maintain circular shape */
+}
+
+.MuiStack-root.css-14k6mw7 img {
+    content: url('/public/assets/images/avatars/ai-tutor.png'); /* Replace with the path to your custom image */
+    max-height: 45px; /* Ensure the height remains consistent */
+    max-width: 45px; /* Ensure the width remains consistent */
+}

{code → apps/ai_tutor}/templates/cooldown.html

@@ -121,7 +121,7 @@
 </head>
 <body>
     <div class="container">
-        <img src="/public/avatars/ai_tutor.png" alt="AI Tutor Avatar" class="avatar">
+        <img src="/public/assets/images/avatars/ai-tutor.png" alt="AI Tutor Avatar" class="avatar">
         <h1>Hello, {{ username }}</h1>
         <p>It seems like you need to wait a bit before starting a new session.</p>
         <p class="cooldown-message">Time remaining until the cooldown period ends:</p>

{code → apps/ai_tutor}/templates/dashboard.html

@@ -123,7 +123,7 @@
 </head>
 <body>
     <div class="container">
-        <img src="/public/avatars/ai_tutor.png" alt="AI Tutor Avatar" class="avatar">
+        <img src="/public/assets/images/avatars/ai-tutor.png" alt="AI Tutor Avatar" class="avatar">
         <h1>Welcome, {{ username }}</h1>
         <p>Ready to start your AI tutoring session?</p>
         <p class="tokens-left">Tokens Left: {{ tokens_left }}</p>

{code → apps/ai_tutor}/templates/login.html

@@ -107,7 +107,7 @@
 </head>
 <body>
     <div class="container">
-        <img src="/public/avatars/ai_tutor.png" alt="AI Tutor Avatar" class="avatar">
+        <img src="/public/assets/images/avatars/ai-tutor.png" alt="AI Tutor Avatar" class="avatar">
         <h1>Terrier Tutor</h1>
         <p>Welcome to the DS598 AI Tutor. Please sign in to continue.</p>
         <form action="/login/google" method="get">

apps/ai_tutor/templates/unauthorized.html

@@ -0,0 +1,94 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Access Restricted</title>
+    <style>
+        @import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;600&display=swap');
+
+        body, html {
+            margin: 0;
+            padding: 0;
+            font-family: 'Inter', sans-serif;
+            background-color: #f7f7f7; /* Light gray background */
+            background-image: url('https://www.transparenttextures.com/patterns/cubes.png'); /* Subtle geometric pattern */
+            background-repeat: repeat;
+            display: flex;
+            align-items: center;
+            justify-content: center;
+            height: 100vh;
+            color: #333;
+        }
+
+        .container {
+            background: rgba(255, 255, 255, 0.9);
+            border: 1px solid #ddd;
+            border-radius: 8px;
+            width: 100%;
+            max-width: 400px;
+            padding: 50px;
+            box-sizing: border-box;
+            text-align: center;
+            box-shadow: 0 4px 15px rgba(0, 0, 0, 0.1);
+            backdrop-filter: blur(10px);
+            -webkit-backdrop-filter: blur(10px);
+        }
+
+        .avatar {
+            width: 90px;
+            height: 90px;
+            border-radius: 50%;
+            margin-bottom: 25px;
+            border: 2px solid #ddd;
+        }
+
+        .container h1 {
+            margin-bottom: 20px;
+            font-size: 26px;
+            font-weight: 600;
+            color: #1a1a1a;
+        }
+
+        .container p {
+            font-size: 18px;
+            color: #4a4a4a;
+            margin-bottom: 35px;
+            line-height: 1.5;
+        }
+
+        .button {
+            padding: 14px 0;
+            margin: 12px 0;
+            font-size: 16px;
+            border-radius: 6px;
+            cursor: pointer;
+            width: 100%;
+            border: 1px solid #ccc;
+            background-color: #007BFF;
+            color: #fff;
+            transition: background-color 0.3s ease, border-color 0.3s ease;
+        }
+
+        .button:hover {
+            background-color: #0056b3;
+            border-color: #0056b3;
+        }
+    </style>
+</head>
+<body>
+    <div class="container">
+        <img src="/public/assets/images/avatars/ai-tutor.png" alt="AI Tutor Avatar" class="avatar">
+        <h1>Access Restricted</h1>
+        <p>
+            We're currently testing things out for the <strong>DS598</strong> course. 
+            Access is restricted to students of the course. If you're enrolled in <strong>DS598</strong> and seeing this message, 
+            please reach out to us, and we'll help you get access.<br><br>
+            <em>P.S. Don't forget to use your BU email when logging in!</em>
+        </p>
+        <form action="/" method="get">
+            <button type="submit" class="button">Return to Home</button>
+        </form>
+    </div>
+</body>
+</html>

apps/chainlit_base/.chainlit/config.toml

@@ -0,0 +1,120 @@
+[project]
+# Whether to enable telemetry (default: true). No personal data is collected.
+enable_telemetry = true
+
+
+# List of environment variables to be provided by each user to use the app.
+user_env = []
+
+# Duration (in seconds) during which the session is saved when the connection is lost
+session_timeout = 3600
+
+# Enable third parties caching (e.g LangChain cache)
+cache = false
+
+# Authorized origins
+allow_origins = ["*"]
+
+# Follow symlink for asset mount (see https://github.com/Chainlit/chainlit/issues/317)
+# follow_symlink = false
+
+[features]
+# Process and display HTML in messages. This can be a security risk (see https://stackoverflow.com/questions/19603097/why-is-it-dangerous-to-render-user-generated-html-or-javascript)
+unsafe_allow_html = false
+
+# Process and display mathematical expressions. This can clash with "$" characters in messages.
+latex = false
+
+# Automatically tag threads with the current chat profile (if a chat profile is used)
+auto_tag_thread = true
+
+# Authorize users to spontaneously upload files with messages
+[features.spontaneous_file_upload]
+    enabled = true
+    accept = ["*/*"]
+    max_files = 20
+    max_size_mb = 500
+
+[features.audio]
+    # Threshold for audio recording
+    min_decibels = -45
+    # Delay for the user to start speaking in MS
+    initial_silence_timeout = 3000
+    # Delay for the user to continue speaking in MS. If the user stops speaking for this duration, the recording will stop.
+    silence_timeout = 1500
+    # Above this duration (MS), the recording will forcefully stop.
+    max_duration = 15000
+    # Duration of the audio chunks in MS
+    chunk_duration = 1000
+    # Sample rate of the audio
+    sample_rate = 44100
+
+edit_message = true
+
+[UI]
+# Name of the assistant.
+name = "Assistant"
+
+# Description of the assistant. This is used for HTML tags.
+# description = ""
+
+# Large size content are by default collapsed for a cleaner ui
+default_collapse_content = true
+
+# Chain of Thought (CoT) display mode. Can be "hidden", "tool_call" or "full".
+cot = "full"
+
+# Link to your github repo. This will add a github button in the UI's header.
+# github = ""
+
+# Specify a CSS file that can be used to customize the user interface.
+# The CSS file can be served from the public directory or via an external link.
+custom_css = "/public/files/test.css"
+
+# Specify a Javascript file that can be used to customize the user interface.
+# The Javascript file can be served from the public directory.
+# custom_js = "/public/test.js"
+
+# Specify a custom font url.
+# custom_font = "https://fonts.googleapis.com/css2?family=Inter:wght@400;500;700&display=swap"
+
+# Specify a custom meta image url.
+# custom_meta_image_url = "https://chainlit-cloud.s3.eu-west-3.amazonaws.com/logo/chainlit_banner.png"
+
+# Specify a custom build directory for the frontend.
+# This can be used to customize the frontend code.
+# Be careful: If this is a relative path, it should not start with a slash.
+# custom_build = "./public/build"
+
+[UI.theme]
+    default = "dark"
+    #layout = "wide"
+    #font_family = "Inter, sans-serif"
+# Override default MUI light theme. (Check theme.ts)
+[UI.theme.light]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.light.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+    [UI.theme.light.text]
+        #primary = "#212121"
+        #secondary = "#616161"
+
+# Override default MUI dark theme. (Check theme.ts)
+[UI.theme.dark]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.dark.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+    [UI.theme.dark.text]
+        #primary = "#EEEEEE"
+        #secondary = "#BDBDBD"
+
+[meta]
+generated_by = "1.1.402"

apps/chainlit_base/chainlit.md

@@ -0,0 +1,14 @@
+# Welcome to Chainlit! 🚀🤖
+
+Hi there, Developer! 👋 We're excited to have you on board. Chainlit is a powerful tool designed to help you prototype, debug and share applications built on top of LLMs.
+
+## Useful Links 🔗
+
+- **Documentation:** Get started with our comprehensive [Chainlit Documentation](https://docs.chainlit.io) 📚
+- **Discord Community:** Join our friendly [Chainlit Discord](https://discord.gg/k73SQ3FyUh) to ask questions, share your projects, and connect with other developers! 💬
+
+We can't wait to see what you create with Chainlit! Happy coding! 💻😊
+
+## Welcome screen
+
+To modify the welcome screen, edit the `chainlit.md` file at the root of your project. If you do not want a welcome screen, just leave this file empty.

{code → apps/chainlit_base}/chainlit_base.py

@@ -1,19 +1,16 @@
 import chainlit.data as cl_data
 import asyncio
-import yaml
 from typing import Any, Dict, no_type_check
 import chainlit as cl
 from modules.chat.llm_tutor import LLMTutor
 from modules.chat.helpers import (
     get_sources,
-    get_history_chat_resume,
     get_history_setup_llm,
-    get_last_config,
 )
 import copy
-from chainlit.types import ThreadDict
 import time
 from langchain_community.callbacks import get_openai_callback
+from config.config_manager import config_manager
 
 USER_TIMEOUT = 60_000
 SYSTEM = "System"
@@ -22,22 +19,7 @@ AGENT = "Agent"
 YOU = "User"
 ERROR = "Error"
 
-with open("modules/config/config.yml", "r") as f:
-    config = yaml.safe_load(f)
-
-
-# async def setup_data_layer():
-#     """
-#     Set up the data layer for chat logging.
-#     """
-#     if config["chat_logging"]["log_chat"]:
-#         data_layer = CustomLiteralDataLayer(
-#             api_key=LITERAL_API_KEY_LOGGING, server=LITERAL_API_URL
-#         )
-#     else:
-#         data_layer = None
-
-#     return data_layer
+config = config_manager.get_config().dict()
 
 
 class Chatbot:
@@ -47,13 +29,6 @@ class Chatbot:
         """
         self.config = config
 
-    async def _load_config(self):
-        """
-        Load the configuration from a YAML file.
-        """
-        with open("modules/config/config.yml", "r") as f:
-            return yaml.safe_load(f)
-
     @no_type_check
     async def setup_llm(self):
         """
@@ -225,38 +200,29 @@ class Chatbot:
         """
         Set starter messages for the chatbot.
         """
-        # Return Starters only if the chat is new
-
-        try:
-            thread = cl_data._data_layer.get_thread(
-                cl.context.session.thread_id
-            )  # see if the thread has any steps
-            if thread.steps or len(thread.steps) > 0:
-                return None
-        except Exception as e:
-            print(e)
-            return [
-                cl.Starter(
-                    label="recording on CNNs?",
-                    message="Where can I find the recording for the lecture on Transformers?",
-                    icon="/public/adv-screen-recorder-svgrepo-com.svg",
-                ),
-                cl.Starter(
-                    label="where's the slides?",
-                    message="When are the lectures? I can't find the schedule.",
-                    icon="/public/alarmy-svgrepo-com.svg",
-                ),
-                cl.Starter(
-                    label="Due Date?",
-                    message="When is the final project due?",
-                    icon="/public/calendar-samsung-17-svgrepo-com.svg",
-                ),
-                cl.Starter(
-                    label="Explain backprop.",
-                    message="I didn't understand the math behind backprop, could you explain it?",
-                    icon="/public/acastusphoton-svgrepo-com.svg",
-                ),
-            ]
+
+        return [
+            cl.Starter(
+                label="recording on Transformers?",
+                message="Where can I find the recording for the lecture on Transformers?",
+                icon="/public/assets/images/starter_icons/adv-screen-recorder-svgrepo-com.svg",
+            ),
+            cl.Starter(
+                label="where's the slides?",
+                message="When are the lectures? I can't find the schedule.",
+                icon="/public/assets/images/starter_icons/alarmy-svgrepo-com.svg",
+            ),
+            cl.Starter(
+                label="Due Date?",
+                message="When is the final project due?",
+                icon="/public/assets/images/starter_icons/calendar-samsung-17-svgrepo-com.svg",
+            ),
+            cl.Starter(
+                label="Explain backprop.",
+                message="I didn't understand the math behind backprop, could you explain it?",
+                icon="/public/assets/images/starter_icons/acastusphoton-svgrepo-com.svg",
+            ),
+        ]
 
     def rename(self, orig_author: str):
         """
@@ -271,7 +237,7 @@ class Chatbot:
         rename_dict = {"Chatbot": LLM}
         return rename_dict.get(orig_author, orig_author)
 
-    async def start(self, config=None):
+    async def start(self):
         """
         Start the chatbot, initialize settings widgets,
         and display and load previous conversation if chat logging is enabled.
@@ -279,26 +245,13 @@ class Chatbot:
 
         start_time = time.time()
 
-        self.config = (
-            await self._load_config() if config is None else config
-        )  # Reload the configuration on chat resume
-
         await self.make_llm_settings_widgets(self.config)  # Reload the settings widgets
 
-        user = cl.user_session.get("user")
-
         # TODO: remove self.user with cl.user_session.get("user")
-        try:
-            self.user = {
-                "user_id": user.identifier,
-                "session_id": cl.context.session.thread_id,
-            }
-        except Exception as e:
-            print(e)
-            self.user = {
-                "user_id": "guest",
-                "session_id": cl.context.session.thread_id,
-            }
+        self.user = {
+            "user_id": "guest",
+            "session_id": cl.context.session.thread_id,
+        }
 
         memory = cl.user_session.get("memory", [])
         self.llm_tutor = LLMTutor(self.config, user=self.user)
@@ -432,22 +385,8 @@ class Chatbot:
             elements=source_elements,
             author=LLM,
             actions=actions,
-            metadata=self.config,
         ).send()
 
-    async def on_chat_resume(self, thread: ThreadDict):
-        thread_config = None
-        steps = thread["steps"]
-        k = self.config["llm_params"][
-            "memory_window"
-        ]  # on resume, alwyas use the default memory window
-        conversation_list = get_history_chat_resume(steps, k, SYSTEM, LLM)
-        thread_config = get_last_config(
-            steps
-        )  # TODO: Returns None for now - which causes config to be reloaded with default values
-        cl.user_session.set("memory", conversation_list)
-        await self.start(config=thread_config)
-
     async def on_follow_up(self, action: cl.Action):
         user = cl.user_session.get("user")
         message = await cl.Message(
@@ -466,12 +405,9 @@ chatbot = Chatbot(config=config)
 
 
 async def start_app():
-    # cl_data._data_layer = await setup_data_layer()
-    # chatbot.literal_client = cl_data._data_layer.client if cl_data._data_layer else None
     cl.set_starters(chatbot.set_starters)
     cl.author_rename(chatbot.rename)
     cl.on_chat_start(chatbot.start)
-    cl.on_chat_resume(chatbot.on_chat_resume)
     cl.on_message(chatbot.main)
     cl.on_settings_update(chatbot.update_llm)
     cl.action_callback("follow up question")(chatbot.on_follow_up)

apps/chainlit_base/config/config.yml

@@ -0,0 +1,60 @@
+log_dir: 'storage/logs' # str
+log_chunk_dir: 'storage/logs/chunks' # str
+device: 'cpu' # str [cuda, cpu]
+
+vectorstore:
+  load_from_HF: True # bool
+  reparse_files: True # bool
+  data_path: 'storage/data' # str
+  url_file_path: 'storage/data/urls.txt' # str
+  expand_urls: True # bool
+  db_option : 'RAGatouille' # str [FAISS, Chroma, RAGatouille, RAPTOR]
+  db_path : 'vectorstores' # str
+  model : 'sentence-transformers/all-MiniLM-L6-v2' # str [sentence-transformers/all-MiniLM-L6-v2, text-embedding-ada-002']
+  search_top_k : 3 # int
+  score_threshold : 0.2 # float
+
+  faiss_params: # Not used as of now
+    index_path: 'vectorstores/faiss.index' # str
+    index_type: 'Flat' # str [Flat, HNSW, IVF]
+    index_dimension: 384 # int
+    index_nlist: 100 # int
+    index_nprobe: 10 # int
+
+  colbert_params:
+    index_name: "new_idx" # str
+
+llm_params: 
+  llm_arch: 'langchain' # [langchain]
+  use_history: True # bool
+  generate_follow_up: False # bool
+  memory_window: 3 # int
+  llm_style: 'Normal' # str [Normal, ELI5]
+  llm_loader: 'gpt-4o-mini' # str [local_llm, gpt-3.5-turbo-1106, gpt-4, gpt-4o-mini]
+  openai_params:
+    temperature: 0.7 # float
+  local_llm_params:
+    temperature: 0.7 # float
+    repo_id: 'TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF' # HuggingFace repo id
+    filename: 'tinyllama-1.1b-chat-v1.0.Q5_0.gguf' # Specific name of gguf file in the repo
+    model_path: 'storage/models/tinyllama-1.1b-chat-v1.0.Q5_0.gguf' # Path to the model file
+  stream: False # bool
+  pdf_reader: 'gpt' # str [llama, pymupdf, gpt]
+
+chat_logging:
+  log_chat: True # bool
+  platform: 'literalai'
+  callbacks: True # bool
+
+splitter_options:
+  use_splitter: True # bool
+  split_by_token : True # bool
+  remove_leftover_delimiters: True # bool
+  remove_chunks: False # bool
+  chunking_mode: 'semantic' # str [fixed, semantic]
+  chunk_size : 300 # int
+  chunk_overlap : 30 # int
+  chunk_separators : ["\n\n", "\n", " ", ""] # list of strings
+  front_chunks_to_remove : null # int or None
+  last_chunks_to_remove : null # int or None
+  delimiters_to_remove : ['\t', '\n', '   ', '  '] # list of strings

apps/chainlit_base/config/config_manager.py

@@ -0,0 +1,174 @@
+from pydantic import BaseModel, conint, confloat, HttpUrl
+from typing import Optional, List
+import yaml
+
+
+class FaissParams(BaseModel):
+    index_path: str = "vectorstores/faiss.index"
+    index_type: str = "Flat"  # Options: [Flat, HNSW, IVF]
+    index_dimension: conint(gt=0) = 384
+    index_nlist: conint(gt=0) = 100
+    index_nprobe: conint(gt=0) = 10
+
+
+class ColbertParams(BaseModel):
+    index_name: str = "new_idx"
+
+
+class VectorStoreConfig(BaseModel):
+    load_from_HF: bool = True
+    reparse_files: bool = True
+    data_path: str = "storage/data"
+    url_file_path: str = "storage/data/urls.txt"
+    expand_urls: bool = True
+    db_option: str = "RAGatouille"  # Options: [FAISS, Chroma, RAGatouille, RAPTOR]
+    db_path: str = "vectorstores"
+    model: str = (
+        "sentence-transformers/all-MiniLM-L6-v2"  # Options: [sentence-transformers/all-MiniLM-L6-v2, text-embedding-ada-002]
+    )
+    search_top_k: conint(gt=0) = 3
+    score_threshold: confloat(ge=0.0, le=1.0) = 0.2
+
+    faiss_params: Optional[FaissParams] = None
+    colbert_params: Optional[ColbertParams] = None
+
+
+class OpenAIParams(BaseModel):
+    temperature: confloat(ge=0.0, le=1.0) = 0.7
+
+
+class LocalLLMParams(BaseModel):
+    temperature: confloat(ge=0.0, le=1.0) = 0.7
+    repo_id: str = "TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF"  # HuggingFace repo id
+    filename: str = (
+        "tinyllama-1.1b-chat-v1.0.Q5_0.gguf"  # Specific name of gguf file in the repo
+    )
+    model_path: str = (
+        "storage/models/tinyllama-1.1b-chat-v1.0.Q5_0.gguf"  # Path to the model file
+    )
+
+
+class LLMParams(BaseModel):
+    llm_arch: str = "langchain"  # Options: [langchain]
+    use_history: bool = True
+    generate_follow_up: bool = False
+    memory_window: conint(ge=1) = 3
+    llm_style: str = "Normal"  # Options: [Normal, ELI5]
+    llm_loader: str = (
+        "gpt-4o-mini"  # Options: [local_llm, gpt-3.5-turbo-1106, gpt-4, gpt-4o-mini]
+    )
+    openai_params: Optional[OpenAIParams] = None
+    local_llm_params: Optional[LocalLLMParams] = None
+    stream: bool = False
+    pdf_reader: str = "gpt"  # Options: [llama, pymupdf, gpt]
+
+
+class ChatLoggingConfig(BaseModel):
+    log_chat: bool = True
+    platform: str = "literalai"
+    callbacks: bool = True
+
+
+class SplitterOptions(BaseModel):
+    use_splitter: bool = True
+    split_by_token: bool = True
+    remove_leftover_delimiters: bool = True
+    remove_chunks: bool = False
+    chunking_mode: str = "semantic"  # Options: [fixed, semantic]
+    chunk_size: conint(gt=0) = 300
+    chunk_overlap: conint(ge=0) = 30
+    chunk_separators: List[str] = ["\n\n", "\n", " ", ""]
+    front_chunks_to_remove: Optional[conint(ge=0)] = None
+    last_chunks_to_remove: Optional[conint(ge=0)] = None
+    delimiters_to_remove: List[str] = ["\t", "\n", "   ", "  "]
+
+
+class RetrieverConfig(BaseModel):
+    retriever_hf_paths: dict[str, str] = {"RAGatouille": "XThomasBU/Colbert_Index"}
+
+
+class MetadataConfig(BaseModel):
+    metadata_links: List[HttpUrl] = [
+        "https://dl4ds.github.io/sp2024/lectures/",
+        "https://dl4ds.github.io/sp2024/schedule/",
+    ]
+    slide_base_link: HttpUrl = "https://dl4ds.github.io"
+
+
+class APIConfig(BaseModel):
+    timeout: conint(gt=0) = 60
+
+
+class Config(BaseModel):
+    log_dir: str = "storage/logs"
+    log_chunk_dir: str = "storage/logs/chunks"
+    device: str = "cpu"  # Options: ['cuda', 'cpu']
+
+    vectorstore: VectorStoreConfig
+    llm_params: LLMParams
+    chat_logging: ChatLoggingConfig
+    splitter_options: SplitterOptions
+    retriever: RetrieverConfig
+    metadata: MetadataConfig
+    api_config: APIConfig
+
+
+class ConfigManager:
+    def __init__(self, config_path: str, project_config_path: str):
+        self.config_path = config_path
+        self.project_config_path = project_config_path
+        self.config = self.load_config()
+        self.validate_config()
+
+    def load_config(self) -> Config:
+        with open(self.config_path, "r") as f:
+            config_data = yaml.safe_load(f)
+
+        with open(self.project_config_path, "r") as f:
+            project_config_data = yaml.safe_load(f)
+
+        # Merge the two configurations
+        merged_config = {**config_data, **project_config_data}
+
+        return Config(**merged_config)
+
+    def get_config(self) -> Config:
+        return ConfigWrapper(self.config)
+
+    def validate_config(self):
+        # If any required fields are missing, raise an error
+        # required_fields = [
+        #     "vectorstore", "llm_params", "chat_logging", "splitter_options",
+        #     "retriever", "metadata", "token_config", "misc", "api_config"
+        # ]
+        # for field in required_fields:
+        #     if not hasattr(self.config, field):
+        #         raise ValueError(f"Missing required configuration field: {field}")
+
+        # # Validate types of specific fields
+        # if not isinstance(self.config.vectorstore, VectorStoreConfig):
+        #     raise TypeError("vectorstore must be an instance of VectorStoreConfig")
+        # if not isinstance(self.config.llm_params, LLMParams):
+        #     raise TypeError("llm_params must be an instance of LLMParams")
+        pass
+
+
+class ConfigWrapper:
+    def __init__(self, config: Config):
+        self._config = config
+
+    def __getitem__(self, key):
+        return getattr(self._config, key)
+
+    def __getattr__(self, name):
+        return getattr(self._config, name)
+
+    def dict(self):
+        return self._config.dict()
+
+
+# Usage
+config_manager = ConfigManager(
+    config_path="config/config.yml", project_config_path="config/project_config.yml"
+)
+# config = config_manager.get_config().dict()

{code/modules → apps/chainlit_base}/config/project_config.yml

@@ -4,4 +4,7 @@ retriever:
 
 metadata:
   metadata_links: ["https://dl4ds.github.io/sp2024/lectures/", "https://dl4ds.github.io/sp2024/schedule/"]
-  slide_base_link: "https://dl4ds.github.io"
+  slide_base_link: "https://dl4ds.github.io"
+
+api_config:
+  timeout: 60

apps/chainlit_base/config/prompts.py

@@ -0,0 +1,97 @@
+prompts = {
+    "openai": {
+        "rephrase_prompt": (
+            "You are someone that rephrases statements. Rephrase the student's question to add context from their chat history if relevant, ensuring it remains from the student's point of view. "
+            "Incorporate relevant details from the chat history to make the question clearer and more specific. "
+            "Do not change the meaning of the original statement, and maintain the student's tone and perspective. "
+            "If the question is conversational and doesn't require context, do not rephrase it. "
+            "Example: If the student previously asked about backpropagation in the context of deep learning and now asks 'what is it', rephrase to 'What is backpropagation.'. "
+            "Example: Do not rephrase if the user is asking something specific like 'cool, suggest a project with transformers to use as my final project' "
+            "Chat history: \n{chat_history}\n"
+            "Rephrase the following question only if necessary: '{input}'"
+            "Rephrased Question:'"
+        ),
+        "prompt_with_history": {
+            "normal": (
+                "You are an AI Tutor for the course DS598, taught by Prof. Thomas Gardos. Answer the user's question using the provided context. Only use the context if it is relevant. The context is ordered by relevance. "
+                "If you don't know the answer, do your best without making things up. Keep the conversation flowing naturally. "
+                "Use chat history and context as guides but avoid repeating past responses. Provide links from the source_file metadata. Use the source context that is most relevant. "
+                "Render math equations in LaTeX format between $ or $$ signs, stick to the parameter and variable icons found in your context. Be sure to explain the parameters and variables in the equations."
+                "Speak in a friendly and engaging manner, like talking to a friend. Avoid sounding repetitive or robotic.\n\n"
+                "Do not get influenced by the style of conversation in the chat history. Follow the instructions given here."
+                "Chat History:\n{chat_history}\n\n"
+                "Context:\n{context}\n\n"
+                "Answer the student's question below in a friendly, concise, and engaging manner. Use the context and history only if relevant, otherwise, engage in a free-flowing conversation.\n"
+                "Student: {input}\n"
+                "AI Tutor:"
+            ),
+            "eli5": (
+                "You are an AI Tutor for the course DS598, taught by Prof. Thomas Gardos. Your job is to explain things in the simplest and most engaging way possible, just like the 'Explain Like I'm 5' (ELI5) concept."
+                "If you don't know the answer, do your best without making things up. Keep your explanations straightforward and very easy to understand."
+                "Use the chat history and context to help you, but avoid repeating past responses. Provide links from the source_file metadata when they're helpful."
+                "Use very simple language and examples to explain any math equations, and put the equations in LaTeX format between $ or $$ signs."
+                "Be friendly and engaging, like you're chatting with a young child who's curious and eager to learn. Avoid complex terms and jargon."
+                "Include simple and clear examples wherever you can to make things easier to understand."
+                "Do not get influenced by the style of conversation in the chat history. Follow the instructions given here."
+                "Chat History:\n{chat_history}\n\n"
+                "Context:\n{context}\n\n"
+                "Answer the student's question below in a friendly, simple, and engaging way, just like the ELI5 concept. Use the context and history only if they're relevant, otherwise, just have a natural conversation."
+                "Give a clear and detailed explanation with simple examples to make it easier to understand. Remember, your goal is to break down complex topics into very simple terms, just like ELI5."
+                "Student: {input}\n"
+                "AI Tutor:"
+            ),
+            "socratic": (
+                "You are an AI Tutor for the course DS598, taught by Prof. Thomas Gardos. Engage the student in a Socratic dialogue to help them discover answers on their own. Use the provided context to guide your questioning."
+                "If you don't know the answer, do your best without making things up. Keep the conversation engaging and inquisitive."
+                "Use chat history and context as guides but avoid repeating past responses. Provide links from the source_file metadata when relevant. Use the source context that is most relevant."
+                "Speak in a friendly and engaging manner, encouraging critical thinking and self-discovery."
+                "Use questions to lead the student to explore the topic and uncover answers."
+                "Chat History:\n{chat_history}\n\n"
+                "Context:\n{context}\n\n"
+                "Answer the student's question below by guiding them through a series of questions and insights that lead to deeper understanding. Use the context and history only if relevant, otherwise, engage in a free-flowing conversation."
+                "Foster an inquisitive mindset and help the student discover answers through dialogue."
+                "Student: {input}\n"
+                "AI Tutor:"
+            ),
+        },
+        "prompt_no_history": (
+            "You are an AI Tutor for the course DS598, taught by Prof. Thomas Gardos. Answer the user's question using the provided context. Only use the context if it is relevant. The context is ordered by relevance. "
+            "If you don't know the answer, do your best without making things up. Keep the conversation flowing naturally. "
+            "Provide links from the source_file metadata. Use the source context that is most relevant. "
+            "Speak in a friendly and engaging manner, like talking to a friend. Avoid sounding repetitive or robotic.\n\n"
+            "Context:\n{context}\n\n"
+            "Answer the student's question below in a friendly, concise, and engaging manner. Use the context and history only if relevant, otherwise, engage in a free-flowing conversation.\n"
+            "Student: {input}\n"
+            "AI Tutor:"
+        ),
+    },
+    "tiny_llama": {
+        "prompt_no_history": (
+            "system\n"
+            "Assistant is an intelligent chatbot designed to help students with questions regarding the course DS598, taught by Prof. Thomas Gardos. Answer the user's question using the provided context. Only use the context if it is relevant. The context is ordered by relevance.\n"
+            "If you don't know the answer, do your best without making things up. Keep the conversation flowing naturally.\n"
+            "Provide links from the source_file metadata. Use the source context that is most relevant.\n"
+            "Speak in a friendly and engaging manner, like talking to a friend. Avoid sounding repetitive or robotic.\n"
+            "\n\n"
+            "user\n"
+            "Context:\n{context}\n\n"
+            "Question: {input}\n"
+            "\n\n"
+            "assistant"
+        ),
+        "prompt_with_history": (
+            "system\n"
+            "You are an AI Tutor for the course DS598, taught by Prof. Thomas Gardos. Answer the user's question using the provided context. Only use the context if it is relevant. The context is ordered by relevance. "
+            "If you don't know the answer, do your best without making things up. Keep the conversation flowing naturally. "
+            "Use chat history and context as guides but avoid repeating past responses. Provide links from the source_file metadata. Use the source context that is most relevant. "
+            "Speak in a friendly and engaging manner, like talking to a friend. Avoid sounding repetitive or robotic.\n"
+            "\n\n"
+            "user\n"
+            "Chat History:\n{chat_history}\n\n"
+            "Context:\n{context}\n\n"
+            "Question: {input}\n"
+            "\n\n"
+            "assistant"
+        ),
+    },
+}

apps/chainlit_base/public/files/students_encrypted.json

@@ -0,0 +1 @@
+{"7f1cacca66ee914ddde2ee20e0f2c96651d60cd8aabd310ef25a9e6d88f42df0": ["instructor", "bu"], "f74d264b6b5b2b4c10ce69e4ec16e869e01cb5eb668ed846aa8f6dae5c96cda0": ["admin", "instructor", "bu"], "53401356a874b1539775c73a8564d5e5f4f840441630c9cf649e16d201454f20": ["instructor", "bu"]}

{code/public → apps/chainlit_base/public/files}/test.css

@@ -2,20 +2,23 @@ a[href*='https://github.com/Chainlit/chainlit'] {
     visibility: hidden;
 }
 
-
+/* TODO: Default image is still shown in the starter questions */
+/* Hide the default avatar image */ 
+.MuiAvatar-root img.MuiAvatar-img {
+    display: none;
+  }
+  
 /* Target the container of the image and set a custom background image */
 .MuiAvatar-root.MuiAvatar-circular.css-m2icte {
-    background-image: url('/public/avatars/ai-tutor.png'); /* Replace with your custom image URL */
+    background-image: url('/public/assets/images/avatars/ai-tutor.png'); /* Replace with your custom image URL */
     background-size: cover; /* Ensure the image covers the entire container */
     background-position: center; /* Center the image */
     width: 100px; /* Ensure the dimensions match the original */
     height: 100px; /* Ensure the dimensions match the original */
     border-radius: 50%; /* Maintain circular shape */
 }
-
-
 .MuiAvatar-root.MuiAvatar-circular.css-v72an7 {
-    background-image: url('/public/avatars/ai-tutor.png'); /* Replace with your custom image URL */
+    background-image: url('/public/assets/images/avatars/ai-tutor.png'); /* Replace with your custom image URL */
     background-size: cover; /* Ensure the image covers the entire container */
     background-position: center; /* Center the image */
     width: 40px; /* Ensure the dimensions match the original */