Added RAG application for Jupyter Notebook QA, integrated with Chainlit platform, and updated project configuration and dependencies.

.chainlit/config.toml

@@ -0,0 +1,109 @@
+[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]
+# Show the prompt playground
+prompt_playground = true
+
+# 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 upload files with messages
+[features.multi_modal]
+    enabled = true
+    accept = ["*/*"]
+    max_files = 20
+    max_size_mb = 500
+
+# Allows user to use speech to text
+[features.speech_to_text]
+    enabled = false
+    # See all languages here https://github.com/JamesBrill/react-speech-recognition/blob/HEAD/docs/API.md#language-string
+    # language = "en-US"
+
+[UI]
+# Name of the app and chatbot.
+name = "Chatbot"
+
+# Show the readme while the thread is empty.
+show_readme_as_default = true
+
+# Description of the app and chatbot. This is used for HTML tags.
+# description = ""
+
+# Large size content are by default collapsed for a cleaner ui
+default_collapse_content = true
+
+# The default value for the expand messages settings.
+default_expand_messages = false
+
+# Hide the chain of thought details from the user in the UI.
+hide_cot = false
+
+# 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/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 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"
+
+# Override default MUI light theme. (Check theme.ts)
+[UI.theme]
+    #font_family = "Inter, sans-serif"
+[UI.theme.light]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.light.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+
+# 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"
+
+
+[meta]
+generated_by = "1.0.506"

.chainlit/translations/en-US.json

@@ -0,0 +1,231 @@
+{
+    "components": {
+        "atoms": {
+            "buttons": {
+                "userButton": {
+                    "menu": {
+                        "settings": "Settings",
+                        "settingsKey": "S",
+                        "APIKeys": "API Keys",
+                        "logout": "Logout"
+                    }
+                }
+            }
+        },
+        "molecules": {
+            "newChatButton": {
+                "newChat": "New Chat"
+            },
+            "tasklist": {
+                "TaskList": {
+                    "title": "\ud83d\uddd2\ufe0f Task List",
+                    "loading": "Loading...",
+                    "error": "An error occured"
+                }
+            },
+            "attachments": {
+                "cancelUpload": "Cancel upload",
+                "removeAttachment": "Remove attachment"
+            },
+            "newChatDialog": {
+                "createNewChat": "Create new chat?",
+                "clearChat": "This will clear the current messages and start a new chat.",
+                "cancel": "Cancel",
+                "confirm": "Confirm"
+            },
+            "settingsModal": {
+                "settings": "Settings",
+                "expandMessages": "Expand Messages",
+                "hideChainOfThought": "Hide Chain of Thought",
+                "darkMode": "Dark Mode"
+            },
+            "detailsButton": {
+                "using": "Using",
+                "running": "Running",
+                "took_one": "Took {{count}} step",
+                "took_other": "Took {{count}} steps"
+            },
+            "auth": {
+                "authLogin": {
+                    "title": "Login to access the app.",
+                    "form": {
+                        "email": "Email address",
+                        "password": "Password",
+                        "noAccount": "Don't have an account?",
+                        "alreadyHaveAccount": "Already have an account?",
+                        "signup": "Sign Up",
+                        "signin": "Sign In",
+                        "or": "OR",
+                        "continue": "Continue",
+                        "forgotPassword": "Forgot password?",
+                        "passwordMustContain": "Your password must contain:",
+                        "emailRequired": "email is a required field",
+                        "passwordRequired": "password is a required field"
+                    },
+                    "error": {
+                        "default": "Unable to sign in.",
+                        "signin": "Try signing in with a different account.",
+                        "oauthsignin": "Try signing in with a different account.",
+                        "redirect_uri_mismatch": "The redirect URI is not matching the oauth app configuration.",
+                        "oauthcallbackerror": "Try signing in with a different account.",
+                        "oauthcreateaccount": "Try signing in with a different account.",
+                        "emailcreateaccount": "Try signing in with a different account.",
+                        "callback": "Try signing in with a different account.",
+                        "oauthaccountnotlinked": "To confirm your identity, sign in with the same account you used originally.",
+                        "emailsignin": "The e-mail could not be sent.",
+                        "emailverify": "Please verify your email, a new email has been sent.",
+                        "credentialssignin": "Sign in failed. Check the details you provided are correct.",
+                        "sessionrequired": "Please sign in to access this page."
+                    }
+                },
+                "authVerifyEmail": {
+                    "almostThere": "You're almost there! We've sent an email to ",
+                    "verifyEmailLink": "Please click on the link in that email to complete your signup.",
+                    "didNotReceive": "Can't find the email?",
+                    "resendEmail": "Resend email",
+                    "goBack": "Go Back",
+                    "emailSent": "Email sent successfully.",
+                    "verifyEmail": "Verify your email address"
+                },
+                "providerButton": {
+                    "continue": "Continue with {{provider}}",
+                    "signup": "Sign up with {{provider}}"
+                },
+                "authResetPassword": {
+                    "newPasswordRequired": "New password is a required field",
+                    "passwordsMustMatch": "Passwords must match",
+                    "confirmPasswordRequired": "Confirm password is a required field",
+                    "newPassword": "New password",
+                    "confirmPassword": "Confirm password",
+                    "resetPassword": "Reset Password"
+                },
+                "authForgotPassword": {
+                    "email": "Email address",
+                    "emailRequired": "email is a required field",
+                    "emailSent": "Please check the email address {{email}} for instructions to reset your password.",
+                    "enterEmail": "Enter your email address and we will send you instructions to reset your password.",
+                    "resendEmail": "Resend email",
+                    "continue": "Continue",
+                    "goBack": "Go Back"
+                }
+            }
+        },
+        "organisms": {
+            "chat": {
+                "history": {
+                    "index": {
+                        "showHistory": "Show history",
+                        "lastInputs": "Last Inputs",
+                        "noInputs": "Such empty...",
+                        "loading": "Loading..."
+                    }
+                },
+                "inputBox": {
+                    "input": {
+                        "placeholder": "Type your message here..."
+                    },
+                    "speechButton": {
+                        "start": "Start recording",
+                        "stop": "Stop recording"
+                    },
+                    "SubmitButton": {
+                        "sendMessage": "Send message",
+                        "stopTask": "Stop Task"
+                    },
+                    "UploadButton": {
+                        "attachFiles": "Attach files"
+                    },
+                    "waterMark": {
+                        "text": "Built with"
+                    }
+                },
+                "Messages": {
+                    "index": {
+                        "running": "Running",
+                        "executedSuccessfully": "executed successfully",
+                        "failed": "failed",
+                        "feedbackUpdated": "Feedback updated",
+                        "updating": "Updating"
+                    }
+                },
+                "dropScreen": {
+                    "dropYourFilesHere": "Drop your files here"
+                },
+                "index": {
+                    "failedToUpload": "Failed to upload",
+                    "cancelledUploadOf": "Cancelled upload of",
+                    "couldNotReachServer": "Could not reach the server",
+                    "continuingChat": "Continuing previous chat"
+                },
+                "settings": {
+                    "settingsPanel": "Settings panel",
+                    "reset": "Reset",
+                    "cancel": "Cancel",
+                    "confirm": "Confirm"
+                }
+            },
+            "threadHistory": {
+                "sidebar": {
+                    "filters": {
+                        "FeedbackSelect": {
+                            "feedbackAll": "Feedback: All",
+                            "feedbackPositive": "Feedback: Positive",
+                            "feedbackNegative": "Feedback: Negative"
+                        },
+                        "SearchBar": {
+                            "search": "Search"
+                        }
+                    },
+                    "DeleteThreadButton": {
+                        "confirmMessage": "This will delete the thread as well as it's messages and elements.",
+                        "cancel": "Cancel",
+                        "confirm": "Confirm",
+                        "deletingChat": "Deleting chat",
+                        "chatDeleted": "Chat deleted"
+                    },
+                    "index": {
+                        "pastChats": "Past Chats"
+                    },
+                    "ThreadList": {
+                        "empty": "Empty...",
+                        "today": "Today",
+                        "yesterday": "Yesterday",
+                        "previous7days": "Previous 7 days",
+                        "previous30days": "Previous 30 days"
+                    },
+                    "TriggerButton": {
+                        "closeSidebar": "Close sidebar",
+                        "openSidebar": "Open sidebar"
+                    }
+                },
+                "Thread": {
+                    "backToChat": "Go back to chat",
+                    "chatCreatedOn": "This chat was created on"
+                }
+            },
+            "header": {
+                "chat": "Chat",
+                "readme": "Readme"
+            }
+        }
+    },
+    "hooks": {
+        "useLLMProviders": {
+            "failedToFetchProviders": "Failed to fetch providers:"
+        }
+    },
+    "pages": {
+        "Design": {},
+        "Env": {
+            "savedSuccessfully": "Saved successfully",
+            "requiredApiKeys": "Required API Keys",
+            "requiredApiKeysInfo": "To use this app, the following API keys are required. The keys are stored on your device's local storage."
+        },
+        "Page": {
+            "notPartOfProject": "You are not part of this project."
+        },
+        "ResumeButton": {
+            "resumeChat": "Resume Chat"
+        }
+    }
+}

CHANGELOG.md

@@ -0,0 +1,8 @@
+version 0.1.0 [2024-05-13]
+
+## Added
+
+- Introduced a RAG application for QA in a Jupyter Notebook, enhancing the project's capabilities for document processing and query answering.
+- Implemented Chainlit's `chainlit` Python package to support the RAG application's integration with the Chainlit platform.
+- Added a new `app.py` script, establishing the core functionality for the RAG application, including document loading, retrieval QA chain, query processing, and user interaction.
+- Updated project configuration and dependencies to support the new RAG application features.

app.py

@@ -0,0 +1,133 @@
+import os
+from operator import itemgetter
+
+import chainlit as cl
+import tiktoken
+from dotenv import load_dotenv
+
+
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.retrievers import MultiQueryRetriever
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.runnables import RunnablePassthrough
+from langchain_community.document_loaders import PyMuPDFLoader, PythonLoader, NotebookLoader
+from langchain_community.vectorstores import Qdrant
+from langchain_openai import ChatOpenAI
+from langchain_openai.embeddings import OpenAIEmbeddings
+
+# Load environment variables
+load_dotenv()
+
+# Configuration for OpenAI
+OPENAI_API_KEY = os.environ["OPENAI_API_KEY"]
+openai_chat_model = ChatOpenAI(model="gpt-4-turbo", temperature=0)
+
+# Define the RAG prompt
+RAG_PROMPT = """
+CONTEXT:
+{context}
+
+QUERY:
+{question}
+
+Answer the query in a pretty format if the context is related to it; otherwise, answer: 'Sorry, I can't answer.'
+"""
+rag_prompt = ChatPromptTemplate.from_template(RAG_PROMPT)
+
+
+# ChainLit setup for chat interaction
+@cl.on_chat_start
+async def start_chat():
+    settings = {
+        "model": "gpt-3.5-turbo",
+        "temperature": 0,
+        "top_p": 1,
+        "frequency_penalty": 0,
+        "presence_penalty": 0,
+    }
+    cl.user_session.set("settings", settings)
+
+    # Display a welcoming message with instructions
+    welcome_message = "Welcome to the AIMS-Tutor! Please upload a Jupyter notebook (.ipynb and max. 5mb) to start."
+    await cl.Message(content=welcome_message).send()
+
+    # Wait for the user to upload a file
+    files = None
+    while files is None:
+        files = await cl.AskFileMessage(
+            content="Please upload a Jupyter notebook (.ipynb, max. 5mb):",
+            accept={"application/x-ipynb+json": [".ipynb"]},
+            max_size_mb=5
+        ).send()
+
+    file = files[0] # Get the first file
+
+    if file:
+        # Load the Jupyter notebook
+        notebook_path = file.path # Extract the path from the AskFileResponse object
+
+        loader = NotebookLoader(
+            notebook_path,
+            include_outputs=True,
+            max_output_length=20,
+            remove_newline=True,
+            traceback=False
+        )
+        docs = loader.load()
+        cl.user_session.set("docs", docs) # Store the docs in the user session
+
+        # Initialize the retriever components after loading document
+        text_splitter = RecursiveCharacterTextSplitter(chunk_size=200, chunk_overlap=50, length_function=tiktoken_len) # Initialize the text splitter
+        split_chunks = text_splitter.split_documents(docs) # Split the documents into chunks
+        embedding_model = OpenAIEmbeddings(model="text-embedding-3-small") # Initialize the embedding model
+        qdrant_vectorstore = Qdrant.from_documents(split_chunks, embedding_model, location=":memory:", collection_name="Notebook") # Create a Qdrant vector store
+        qdrant_retriever = qdrant_vectorstore.as_retriever() # Set the Qdrant vector store as a retriever
+        multiquery_retriever = MultiQueryRetriever.from_llm(retriever=qdrant_retriever, llm=openai_chat_model) # Create a multi-query retriever on top of the Qdrant retriever
+
+        # Store the multiquery_retriever in the user session
+        cl.user_session.set("multiquery_retriever", multiquery_retriever)
+
+@cl.on_message
+async def main(message: cl.Message):
+    # Retrieve the multi-query retriever from session
+    multiquery_retriever = cl.user_session.get("multiquery_retriever")
+
+    if not multiquery_retriever:
+        await message.reply("No document processing chain found. Please upload a Jupyter notebook first.")
+        return
+
+    question = message.content
+    response = handle_query(question, multiquery_retriever)  # Process the question
+
+    msg = cl.Message(content=response)
+    await msg.send()
+
+
+@cl.on_message
+async def main(message: cl.Message):
+    # Retrieve the multi-query retriever from session
+    multiquery_retriever = cl.user_session.get("multiquery_retriever")
+    if not multiquery_retriever:
+        await message.reply("No document processing setup found. Please upload a Jupyter notebook first.")
+        return
+
+    question = message.content
+    response = handle_query(question, multiquery_retriever)  # Process the question
+
+    msg = cl.Message(content=response)
+    await msg.send()
+
+def handle_query(question, retriever):
+    # Define the retrieval augmented query-answering chain
+    retrieval_augmented_qa_chain = (
+        {"context": itemgetter("question") | retriever, "question": itemgetter("question")}
+        | RunnablePassthrough.assign(context=itemgetter("context"))
+        | {"response": rag_prompt | openai_chat_model, "context": itemgetter("context")}
+    )
+    response = retrieval_augmented_qa_chain.invoke({"question": question})
+    return response["response"].content
+
+# Tokenization function
+def tiktoken_len(text):
+    tokens = tiktoken.encoding_for_model("gpt-3.5-turbo").encode(text)
+    return len(tokens)

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.

requirements.txt

@@ -0,0 +1,5 @@
+langchain==0.1.20
+crewai==0.30.0
+qdrant-client==1.9.1
+python-dotenv==1.0.1
+chainlit==1.0.506