Logging out... If you are not redirected, click here.
+
+
\ No newline at end of file
diff --git a/apps/ai_tutor/templates/unauthorized.html b/apps/ai_tutor/templates/unauthorized.html
new file mode 100644
index 0000000000000000000000000000000000000000..423cc12cd2195bc9b44e352ba365d28eee7a1858
--- /dev/null
+++ b/apps/ai_tutor/templates/unauthorized.html
@@ -0,0 +1,94 @@
+
+
+
+
+
+ Access Restricted
+
+
+
+
+
+
Access Restricted
+
+ We're currently testing things out for the DS598 course.
+ Access is restricted to students of the course. If you're enrolled in DS598 and seeing this message,
+ please reach out to us, and we'll help you get access.
+ P.S. Don't forget to use your BU email when logging in!
+
+
+
+
+
diff --git a/apps/chainlit_base/.chainlit/config.toml b/apps/chainlit_base/.chainlit/config.toml
new file mode 100644
index 0000000000000000000000000000000000000000..a91c4344a975334ac4a30c6f454ce17cdeb5fc09
--- /dev/null
+++ b/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"
diff --git a/apps/chainlit_base/chainlit.md b/apps/chainlit_base/chainlit.md
new file mode 100644
index 0000000000000000000000000000000000000000..4507ac4676a6387c4b52a0d1111e94753a102b32
--- /dev/null
+++ b/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.
diff --git a/apps/chainlit_base/chainlit_base.py b/apps/chainlit_base/chainlit_base.py
new file mode 100644
index 0000000000000000000000000000000000000000..740015fe0c5a2a75b6eff26de820b8f671513bc6
--- /dev/null
+++ b/apps/chainlit_base/chainlit_base.py
@@ -0,0 +1,381 @@
+import chainlit.data as cl_data
+import asyncio
+from typing import Any, Dict, no_type_check
+import chainlit as cl
+from edubotics_core.chat.llm_tutor import LLMTutor
+from edubotics_core.chat.helpers import (
+ get_sources,
+ get_history_setup_llm,
+)
+import copy
+from langchain_community.callbacks import get_openai_callback
+from config.config_manager import config_manager
+
+USER_TIMEOUT = 60_000
+SYSTEM = "System"
+LLM = "AI Tutor"
+AGENT = "Agent"
+YOU = "User"
+ERROR = "Error"
+
+config = config_manager.get_config().dict()
+
+
+class Chatbot:
+ def __init__(self, config):
+ """
+ Initialize the Chatbot class.
+ """
+ self.config = config
+
+ @no_type_check
+ async def setup_llm(self):
+ """
+ Set up the LLM with the provided settings. Update the configuration and initialize the LLM tutor.
+
+ #TODO: Clean this up.
+ """
+
+ llm_settings = cl.user_session.get("llm_settings", {})
+ (
+ chat_profile,
+ retriever_method,
+ memory_window,
+ llm_style,
+ generate_follow_up,
+ chunking_mode,
+ ) = (
+ llm_settings.get("chat_model"),
+ llm_settings.get("retriever_method"),
+ llm_settings.get("memory_window"),
+ llm_settings.get("llm_style"),
+ llm_settings.get("follow_up_questions"),
+ llm_settings.get("chunking_mode"),
+ )
+
+ chain = cl.user_session.get("chain")
+ memory_list = cl.user_session.get(
+ "memory",
+ (
+ list(chain.store.values())[0].messages
+ if len(chain.store.values()) > 0
+ else []
+ ),
+ )
+ conversation_list = get_history_setup_llm(memory_list)
+
+ old_config = copy.deepcopy(self.config)
+ self.config["vectorstore"]["db_option"] = retriever_method
+ self.config["llm_params"]["memory_window"] = memory_window
+ self.config["llm_params"]["llm_style"] = llm_style
+ self.config["llm_params"]["llm_loader"] = chat_profile
+ self.config["llm_params"]["generate_follow_up"] = generate_follow_up
+ self.config["splitter_options"]["chunking_mode"] = chunking_mode
+
+ self.llm_tutor.update_llm(
+ old_config, self.config
+ ) # update only llm attributes that are changed
+ self.chain = self.llm_tutor.qa_bot(
+ memory=conversation_list,
+ )
+
+ cl.user_session.set("chain", self.chain)
+ cl.user_session.set("llm_tutor", self.llm_tutor)
+
+ @no_type_check
+ async def update_llm(self, new_settings: Dict[str, Any]):
+ """
+ Update the LLM settings and reinitialize the LLM with the new settings.
+
+ Args:
+ new_settings (Dict[str, Any]): The new settings to update.
+ """
+ cl.user_session.set("llm_settings", new_settings)
+ await self.inform_llm_settings()
+ await self.setup_llm()
+
+ async def make_llm_settings_widgets(self, config=None):
+ """
+ Create and send the widgets for LLM settings configuration.
+
+ Args:
+ config: The configuration to use for setting up the widgets.
+ """
+ config = config or self.config
+ await cl.ChatSettings(
+ [
+ cl.input_widget.Select(
+ id="chat_model",
+ label="Model Name (Default GPT-3)",
+ values=["local_llm", "gpt-3.5-turbo-1106", "gpt-4", "gpt-4o-mini"],
+ initial_index=[
+ "local_llm",
+ "gpt-3.5-turbo-1106",
+ "gpt-4",
+ "gpt-4o-mini",
+ ].index(config["llm_params"]["llm_loader"]),
+ ),
+ cl.input_widget.Select(
+ id="retriever_method",
+ label="Retriever (Default FAISS)",
+ values=["FAISS", "Chroma", "RAGatouille", "RAPTOR"],
+ initial_index=["FAISS", "Chroma", "RAGatouille", "RAPTOR"].index(
+ config["vectorstore"]["db_option"]
+ ),
+ ),
+ cl.input_widget.Slider(
+ id="memory_window",
+ label="Memory Window (Default 3)",
+ initial=3,
+ min=0,
+ max=10,
+ step=1,
+ ),
+ cl.input_widget.Switch(
+ id="view_sources", label="View Sources", initial=False
+ ),
+ cl.input_widget.Switch(
+ id="stream_response",
+ label="Stream response",
+ initial=config["llm_params"]["stream"],
+ ),
+ cl.input_widget.Select(
+ id="chunking_mode",
+ label="Chunking mode",
+ values=["fixed", "semantic"],
+ initial_index=1,
+ ),
+ cl.input_widget.Switch(
+ id="follow_up_questions",
+ label="Generate follow up questions",
+ initial=False,
+ ),
+ cl.input_widget.Select(
+ id="llm_style",
+ label="Type of Conversation (Default Normal)",
+ values=["Normal", "ELI5"],
+ initial_index=0,
+ ),
+ ]
+ ).send()
+
+ @no_type_check
+ async def inform_llm_settings(self):
+ """
+ Inform the user about the updated LLM settings and display them as a message.
+ """
+ await cl.Message(
+ author=SYSTEM,
+ content="LLM settings have been updated. You can continue with your Query!",
+ ).send()
+
+ async def set_starters(self):
+ """
+ Set starter messages for the chatbot.
+ """
+
+ 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):
+ """
+ Rename the original author to a more user-friendly name.
+
+ Args:
+ orig_author (str): The original author's name.
+
+ Returns:
+ str: The renamed author.
+ """
+ rename_dict = {"Chatbot": LLM}
+ return rename_dict.get(orig_author, orig_author)
+
+ async def start(self):
+ """
+ Start the chatbot, initialize settings widgets,
+ and display and load previous conversation if chat logging is enabled.
+ """
+
+ await self.make_llm_settings_widgets(self.config) # Reload the settings widgets
+
+ # TODO: remove self.user with cl.user_session.get("user")
+ 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)
+
+ self.chain = self.llm_tutor.qa_bot(
+ memory=memory,
+ )
+ self.question_generator = self.llm_tutor.question_generator
+ cl.user_session.set("llm_tutor", self.llm_tutor)
+ cl.user_session.set("chain", self.chain)
+
+ async def stream_response(self, response):
+ """
+ Stream the response from the LLM.
+
+ Args:
+ response: The response from the LLM.
+ """
+ msg = cl.Message(content="")
+ await msg.send()
+
+ output = {}
+ for chunk in response:
+ if "answer" in chunk:
+ await msg.stream_token(chunk["answer"])
+
+ for key in chunk:
+ if key not in output:
+ output[key] = chunk[key]
+ else:
+ output[key] += chunk[key]
+ return output
+
+ async def main(self, message):
+ """
+ Process and Display the Conversation.
+
+ Args:
+ message: The incoming chat message.
+ """
+
+ chain = cl.user_session.get("chain")
+ token_count = 0 # initialize token count
+ if not chain:
+ await self.start() # start the chatbot if the chain is not present
+ chain = cl.user_session.get("chain")
+
+ # update user info with last message time
+ llm_settings = cl.user_session.get("llm_settings", {})
+ view_sources = llm_settings.get("view_sources", False)
+ stream = llm_settings.get("stream_response", False)
+ stream = False # Fix streaming
+ user_query_dict = {"input": message.content}
+ # Define the base configuration
+ cb = cl.AsyncLangchainCallbackHandler()
+ chain_config = {
+ "configurable": {
+ "user_id": self.user["user_id"],
+ "conversation_id": self.user["session_id"],
+ "memory_window": self.config["llm_params"]["memory_window"],
+ },
+ "callbacks": (
+ [cb]
+ if cl_data._data_layer and self.config["chat_logging"]["callbacks"]
+ else None
+ ),
+ }
+
+ with get_openai_callback() as token_count_cb:
+ if stream:
+ res = chain.stream(user_query=user_query_dict, config=chain_config)
+ res = await self.stream_response(res)
+ else:
+ res = await chain.invoke(
+ user_query=user_query_dict,
+ config=chain_config,
+ )
+ token_count += token_count_cb.total_tokens
+
+ answer = res.get("answer", res.get("result"))
+
+ answer_with_sources, source_elements, sources_dict = get_sources(
+ res, answer, stream=stream, view_sources=view_sources
+ )
+ answer_with_sources = answer_with_sources.replace("$$", "$")
+
+ actions = []
+
+ if self.config["llm_params"]["generate_follow_up"]:
+ cb_follow_up = cl.AsyncLangchainCallbackHandler()
+ config = {
+ "callbacks": (
+ [cb_follow_up]
+ if cl_data._data_layer and self.config["chat_logging"]["callbacks"]
+ else None
+ )
+ }
+ with get_openai_callback() as token_count_cb:
+ list_of_questions = await self.question_generator.generate_questions(
+ query=user_query_dict["input"],
+ response=answer,
+ chat_history=res.get("chat_history"),
+ context=res.get("context"),
+ config=config,
+ )
+
+ token_count += token_count_cb.total_tokens
+
+ for question in list_of_questions:
+ actions.append(
+ cl.Action(
+ name="follow up question",
+ value="example_value",
+ description=question,
+ label=question,
+ )
+ )
+
+ await cl.Message(
+ content=answer_with_sources,
+ elements=source_elements,
+ author=LLM,
+ actions=actions,
+ ).send()
+
+ async def on_follow_up(self, action: cl.Action):
+ user = cl.user_session.get("user")
+ message = await cl.Message(
+ content=action.description,
+ type="user_message",
+ author=user.identifier,
+ ).send()
+ async with cl.Step(
+ name="on_follow_up", type="run", parent_id=message.id
+ ) as step:
+ await self.main(message)
+ step.output = message.content
+
+
+chatbot = Chatbot(config=config)
+
+
+async def start_app():
+ cl.set_starters(chatbot.set_starters)
+ cl.author_rename(chatbot.rename)
+ cl.on_chat_start(chatbot.start)
+ cl.on_message(chatbot.main)
+ cl.on_settings_update(chatbot.update_llm)
+ cl.action_callback("follow up question")(chatbot.on_follow_up)
+
+
+loop = asyncio.get_event_loop()
+if loop.is_running():
+ asyncio.ensure_future(start_app())
+else:
+ asyncio.run(start_app())
diff --git a/apps/chainlit_base/config/config.yml b/apps/chainlit_base/config/config.yml
new file mode 100644
index 0000000000000000000000000000000000000000..eed8ee7b9bf5e63c79f94af8116656ba48843325
--- /dev/null
+++ b/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
diff --git a/apps/chainlit_base/config/config_manager.py b/apps/chainlit_base/config/config_manager.py
new file mode 100644
index 0000000000000000000000000000000000000000..da88660ed14b5b4f9834e19dabae6c687c6c1fcf
--- /dev/null
+++ b/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()
diff --git a/apps/chainlit_base/config/project_config.yml b/apps/chainlit_base/config/project_config.yml
new file mode 100644
index 0000000000000000000000000000000000000000..2ffa4671c0221496668d45e311784ae35e9c9083
--- /dev/null
+++ b/apps/chainlit_base/config/project_config.yml
@@ -0,0 +1,10 @@
+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"
+
+api_config:
+ timeout: 60
\ No newline at end of file
diff --git a/apps/chainlit_base/config/prompts.py b/apps/chainlit_base/config/prompts.py
new file mode 100644
index 0000000000000000000000000000000000000000..bdd6611f333a94637f55e4a604748acec462a8fc
--- /dev/null
+++ b/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"
+ ),
+ },
+}
diff --git a/apps/chainlit_base/public/assets/images/avatars/ai-tutor.png b/apps/chainlit_base/public/assets/images/avatars/ai-tutor.png
new file mode 100644
index 0000000000000000000000000000000000000000..ca144c996c7ed7baef6c2d1addc6912131e0d9cd
--- /dev/null
+++ b/apps/chainlit_base/public/assets/images/avatars/ai-tutor.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a899bc45dc6d84ef265aecdc21fbfb085c2fc0c16760107c5e782811b19ddfb7
+size 168742
diff --git a/apps/chainlit_base/public/assets/images/avatars/ai_tutor.png b/apps/chainlit_base/public/assets/images/avatars/ai_tutor.png
new file mode 100644
index 0000000000000000000000000000000000000000..ca144c996c7ed7baef6c2d1addc6912131e0d9cd
--- /dev/null
+++ b/apps/chainlit_base/public/assets/images/avatars/ai_tutor.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a899bc45dc6d84ef265aecdc21fbfb085c2fc0c16760107c5e782811b19ddfb7
+size 168742
diff --git a/apps/chainlit_base/public/assets/images/starter_icons/acastusphoton-svgrepo-com.svg b/apps/chainlit_base/public/assets/images/starter_icons/acastusphoton-svgrepo-com.svg
new file mode 100644
index 0000000000000000000000000000000000000000..e8edaf55d695486fbf134388dbfb84f7dbb7ca8c
--- /dev/null
+++ b/apps/chainlit_base/public/assets/images/starter_icons/acastusphoton-svgrepo-com.svg
@@ -0,0 +1,2 @@
+
+
\ No newline at end of file
diff --git a/apps/chainlit_base/public/assets/images/starter_icons/adv-screen-recorder-svgrepo-com.svg b/apps/chainlit_base/public/assets/images/starter_icons/adv-screen-recorder-svgrepo-com.svg
new file mode 100644
index 0000000000000000000000000000000000000000..439e638eaf976a2278a2aa043de2feb2d65c3862
--- /dev/null
+++ b/apps/chainlit_base/public/assets/images/starter_icons/adv-screen-recorder-svgrepo-com.svg
@@ -0,0 +1,2 @@
+
+
\ No newline at end of file
diff --git a/apps/chainlit_base/public/assets/images/starter_icons/alarmy-svgrepo-com.svg b/apps/chainlit_base/public/assets/images/starter_icons/alarmy-svgrepo-com.svg
new file mode 100644
index 0000000000000000000000000000000000000000..d2dee1b557beab61067452d4700fa1d62ba0b0e8
--- /dev/null
+++ b/apps/chainlit_base/public/assets/images/starter_icons/alarmy-svgrepo-com.svg
@@ -0,0 +1,2 @@
+
+
\ No newline at end of file
diff --git a/apps/chainlit_base/public/assets/images/starter_icons/calendar-samsung-17-svgrepo-com.svg b/apps/chainlit_base/public/assets/images/starter_icons/calendar-samsung-17-svgrepo-com.svg
new file mode 100644
index 0000000000000000000000000000000000000000..8f9caa7ac74d4ea04369169e830e4042b267de89
--- /dev/null
+++ b/apps/chainlit_base/public/assets/images/starter_icons/calendar-samsung-17-svgrepo-com.svg
@@ -0,0 +1,36 @@
+
+
+
+
\ No newline at end of file
diff --git a/apps/chainlit_base/public/files/students_encrypted.json b/apps/chainlit_base/public/files/students_encrypted.json
new file mode 100644
index 0000000000000000000000000000000000000000..826570552b1dcbfdf9cc1472a7bb5a3c68d9c2e5
--- /dev/null
+++ b/apps/chainlit_base/public/files/students_encrypted.json
@@ -0,0 +1 @@
+{"7f1cacca66ee914ddde2ee20e0f2c96651d60cd8aabd310ef25a9e6d88f42df0": ["instructor", "bu"], "f74d264b6b5b2b4c10ce69e4ec16e869e01cb5eb668ed846aa8f6dae5c96cda0": ["admin", "instructor", "bu"], "53401356a874b1539775c73a8564d5e5f4f840441630c9cf649e16d201454f20": ["instructor", "bu"]}
\ No newline at end of file
diff --git a/apps/chainlit_base/public/files/test.css b/apps/chainlit_base/public/files/test.css
new file mode 100644
index 0000000000000000000000000000000000000000..b82b60b6ebd358fef85b73389e1d5b1e4d8856b9
--- /dev/null
+++ b/apps/chainlit_base/public/files/test.css
@@ -0,0 +1,27 @@
+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/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 */
+}
diff --git a/apps/chainlit_base/public/logo_dark.png b/apps/chainlit_base/public/logo_dark.png
new file mode 100644
index 0000000000000000000000000000000000000000..ca144c996c7ed7baef6c2d1addc6912131e0d9cd
--- /dev/null
+++ b/apps/chainlit_base/public/logo_dark.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a899bc45dc6d84ef265aecdc21fbfb085c2fc0c16760107c5e782811b19ddfb7
+size 168742
diff --git a/apps/chainlit_base/public/logo_light.png b/apps/chainlit_base/public/logo_light.png
new file mode 100644
index 0000000000000000000000000000000000000000..ca144c996c7ed7baef6c2d1addc6912131e0d9cd
--- /dev/null
+++ b/apps/chainlit_base/public/logo_light.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a899bc45dc6d84ef265aecdc21fbfb085c2fc0c16760107c5e782811b19ddfb7
+size 168742
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000000000000000000000000000000000000..8bb6ee5f516fa6b137341c9dc98b6f9eacf8b9f9
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,2 @@
+[tool.black]
+line-length = 88
+