updates

.gitignore

@@ -178,4 +178,6 @@ code/storage/models/
 
 **/vectorstores/*
 
-**/private/students.json
+**/private/students.json
+
+**/apps/*/storage/logs/*

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

@@ -30,26 +30,31 @@ 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 +69,7 @@ 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

apps/ai_tutor/app.py

@@ -8,27 +8,32 @@ 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
 GOOGLE_REDIRECT_URI = f"{CHAINLIT_URL}/auth/oauth/google/callback"
@@ -246,7 +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")
 
 
@@ -280,7 +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"]
@@ -353,7 +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:

apps/ai_tutor/config/config_manager.py

@@ -0,0 +1,188 @@
+from pydantic import BaseModel, Field, conint, confloat, conlist, 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()

apps/ai_tutor/config/constants.py

@@ -0,0 +1,26 @@
+from dotenv import load_dotenv
+import os
+
+load_dotenv()
+
+# API Keys - Loaded from the .env file
+
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+LLAMA_CLOUD_API_KEY = os.getenv("LLAMA_CLOUD_API_KEY")
+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")
+
+opening_message = "Hey, What Can I Help You With?\n\nYou can me ask me questions about the course logistics, course content, about the final project, or anything else!"
+chat_end_message = (
+    "I hope I was able to help you. If you have any more questions, feel free to ask!"
+)
+
+# Model Paths
+
+LLAMA_PATH = "../storage/models/tinyllama"

apps/ai_tutor/config/project_config.yml

@@ -4,4 +4,17 @@ 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"
+
+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/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/main.py

@@ -1,6 +1,6 @@
 import chainlit.data as cl_data
 import asyncio
-from modules.config.constants import (
+from config.constants import (
     LITERAL_API_KEY_LOGGING,
     LITERAL_API_URL,
 )
@@ -18,11 +18,13 @@ 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 +32,7 @@ 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 +41,8 @@ AGENT = "Agent"
 YOU = "User"
 ERROR = "Error"
 
-with open("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 +84,6 @@ class Chatbot:
         """
         self.config = config
 
-    async def _load_config(self):
-        """
-        Load the configuration from a YAML file.
-        """
-        with open("config/config.yml", "r") as f:
-            return yaml.safe_load(f)
-
     @no_type_check
     async def setup_llm(self):
         """
@@ -305,7 +301,7 @@ 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 +309,6 @@ 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 +378,11 @@ 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)
@@ -524,13 +520,12 @@ class Chatbot:
             + str(tokens_left)
             + "</span></footer>\n"
         )
-
+        
         await cl.Message(
             content=answer_with_sources,
             elements=source_elements,
             author=LLM,
             actions=actions,
-            metadata=self.config,
         ).send()
 
     async def on_chat_resume(self, thread: ThreadDict):

apps/chainlit_base/chainlit_base.py

@@ -11,9 +11,9 @@ from modules.chat.helpers import (
     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"
@@ -22,23 +22,7 @@ AGENT = "Agent"
 YOU = "User"
 ERROR = "Error"
 
-with open("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:
     def __init__(self, config):
@@ -47,13 +31,6 @@ class Chatbot:
         """
         self.config = config
 
-    async def _load_config(self):
-        """
-        Load the configuration from a YAML file.
-        """
-        with open("config/config.yml", "r") as f:
-            return yaml.safe_load(f)
-
     @no_type_check
     async def setup_llm(self):
         """
@@ -225,38 +202,29 @@ 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 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",
+            ),
+        ]
 
     def rename(self, orig_author: str):
         """
@@ -271,7 +239,7 @@ 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 +247,15 @@ 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 +389,8 @@ 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 +409,9 @@ 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_manager.py

@@ -0,0 +1,174 @@
+from pydantic import BaseModel, Field, conint, confloat, conlist, 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()

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"
+        ),
+    },
+}

modules/chat/helpers.py

@@ -1,4 +1,4 @@
-from modules.config.prompts import prompts  # TODO: MOVE THIS TO APP SPECIFIC DIRECTORY
+from config.prompts import prompts
 import chainlit as cl
 
 

modules/chat_processor/helpers.py

@@ -1,9 +1,6 @@
 import os
 from literalai import AsyncLiteralClient
-from datetime import datetime, timedelta, timezone
-from modules.config.constants import COOLDOWN_TIME, TOKENS_LEFT, REGEN_TIME
 from typing_extensions import TypedDict
-import tiktoken
 from typing import Any, Generic, List, Literal, Optional, TypeVar, Union
 
 Field = TypeVar("Field")
@@ -136,10 +133,6 @@ def convert_to_dict(user_info):
     return user_info
 
 
-def get_time():
-    return datetime.now(timezone.utc).isoformat()
-
-
 async def get_user_details(user_email_id):
     user_info = await literal_client.api.get_or_create_user(identifier=user_email_id)
     return user_info
@@ -155,91 +148,6 @@ async def update_user_info(user_info):
     )
 
 
-async def check_user_cooldown(user_info, current_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)
-
-    return False, None
-
-
-async def reset_tokens_for_user(user_info):
-    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)
-
-
 async def get_thread_step_info(thread_id):
     step = await literal_client.api.get_step(thread_id)
     return step
-
-
-def get_num_tokens(text, model):
-    encoding = tiktoken.encoding_for_model(model)
-    tokens = encoding.encode(text)
-    return len(tokens)

modules/config/constants.py

@@ -1,35 +1,12 @@
-from dotenv import load_dotenv
+# from .env setup all constants here
+
 import os
+from dotenv import load_dotenv
 
 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
-
+# Required Constants # TODO: MOVE THIS TO APP SPECIFIC DIRECTORY
+TIMEOUT = os.getenv("TIMEOUT", 60)
 OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
 LLAMA_CLOUD_API_KEY = os.getenv("LLAMA_CLOUD_API_KEY")
 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")
-
-opening_message = "Hey, What Can I Help You With?\n\nYou can me ask me questions about the course logistics, course content, about the final project, or anything else!"
-chat_end_message = (
-    "I hope I was able to help you. If you have any more questions, feel free to ask!"
-)
-
-# Model Paths
-
-LLAMA_PATH = "../storage/models/tinyllama"

modules/dataloader/data_loader.py

@@ -423,6 +423,15 @@ if __name__ == "__main__":
     parser.add_argument(
         "--links", nargs="+", required=True, help="List of links to process."
     )
+    parser.add_argument(
+        "--config_file", type=str, help="Path to the main config file", required=True
+    )
+    parser.add_argument(
+        "--project_config_file",
+        type=str,
+        help="Path to the project config file",
+        required=True,
+    )
 
     args = parser.parse_args()
     links_to_process = args.links
@@ -430,10 +439,10 @@ if __name__ == "__main__":
     logger = logging.getLogger(__name__)
     logger.setLevel(logging.INFO)
 
-    with open("../code/modules/config/config.yml", "r") as f:
+    with open(args.config_file, "r") as f:
         config = yaml.safe_load(f)
 
-    with open("../code/modules/config/project_config.yml", "r") as f:
+    with open(args.project_config_file, "r") as f:
         project_config = yaml.safe_load(f)
 
     # Combine project config with the main config