Add initial application

.chainlit/config.toml

@@ -0,0 +1,118 @@
+[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 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
+
+[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"
+
+[UI.theme]
+    #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"
+
+# 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 = "1.1.101"

.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"
+        }
+    }
+}

app.py

@@ -0,0 +1,107 @@
+import json
+from langchain_openai import ChatOpenAI
+from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain.schema.runnable import Runnable
+from langchain.schema.runnable.config import RunnableConfig
+
+from langchain.memory import ChatMessageHistory
+from langchain_core.chat_history import BaseChatMessageHistory
+from langchain_core.runnables.history import RunnableWithMessageHistory
+
+from langchain.chains import create_history_aware_retriever, create_retrieval_chain
+from langchain.chains.combine_documents import create_stuff_documents_chain
+
+import chainlit as cl
+from retriever import fetch_retriever_or_load_local_retriever
+
+# to run locally use: chainlit run app.py -w
+# see https://python.langchain.com/v0.1/assets/images/conversational_retrieval_chain-5c7a96abe29e582bc575a0a0d63f86b0.png for architecture diagram
+
+llm = ChatOpenAI(model="gpt-4o", temperature=0, streaming=True)
+
+# load local FAISS retriever with preloaded embeddings
+retriever = fetch_retriever_or_load_local_retriever()
+
+### Contextualize question ###
+contextualize_q_system_prompt = """Given a chat history and the latest user question \
+which might reference context in the chat history, formulate a standalone question \
+which can be understood without the chat history. Do NOT answer the question, \
+just reformulate it if needed and otherwise return it as is."""
+contextualize_q_prompt = ChatPromptTemplate.from_messages(
+    [
+        ("system", contextualize_q_system_prompt),
+        MessagesPlaceholder("chat_history"),
+        ("human", "{input}"),
+    ]
+)
+
+# also manages the case where chat_history is empty, and otherwise applies prompt | llm | StrOutputParser() | retriever in sequence.
+history_aware_retriever = create_history_aware_retriever(
+    llm, retriever, contextualize_q_prompt
+)
+### Answer question
+qa_system_prompt = """You're an assistant that answers questions about movies and films. \
+and eloquent answers to questions about movies. Use the following pieces of \
+retrieved context to answer the question. Use three sentences maximum and \
+keep the answer concise.
+
+{context}"""
+qa_prompt = ChatPromptTemplate.from_messages(
+    [
+        ("system", qa_system_prompt),
+        MessagesPlaceholder("chat_history"),
+        ("human", "{input}"),
+    ]
+)
+
+# chain to accept the retrieved context alongside the conversation history and query to generate an answer
+question_answer_chain = create_stuff_documents_chain(llm, qa_prompt)
+
+#  This chain applies the history_aware_retriever and question_answer_chain in sequence, retaining intermediate outputs such as the retrieved context for convenience
+rag_chain = create_retrieval_chain(history_aware_retriever, question_answer_chain)
+
+### Statefully manage chat history
+store = {}
+
+
+def get_session_history(session_id: str) -> BaseChatMessageHistory:
+    if session_id not in store:
+        store[session_id] = ChatMessageHistory()
+    return store[session_id]
+
+
+@cl.on_chat_start
+async def on_chat_start():
+    conversational_rag_chain = RunnableWithMessageHistory(
+        rag_chain,
+        get_session_history,
+        input_messages_key="input",
+        history_messages_key="chat_history",
+        output_messages_key="answer",
+    )
+    cl.user_session.set("runnable", conversational_rag_chain)
+
+
+@cl.on_message
+async def on_message(message: cl.Message):
+    runnable = cl.user_session.get("runnable")  # type: Runnable
+    msg = cl.Message(content="")
+
+    async for chunk in runnable.astream(
+        {"input": message.content},
+        config=RunnableConfig(
+            callbacks=[cl.LangchainCallbackHandler()],
+            configurable={"session_id": cl.user_session.get("id")},
+        ),
+    ):
+        # process Documents to be JSON serializable and passed into the context window but not served up as part of the tokened response
+        if "context" in chunk:
+            docs = chunk["context"]
+            docs_dict = [
+                {"page_content": doc.page_content, "metadata": doc.metadata}
+                for doc in docs
+            ]
+            chunk["context"] = json.dumps(docs_dict)
+        if "answer" in chunk:
+            await msg.stream_token(chunk["answer"])
+            await msg.send()

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 +1,7 @@
+datasets
+tiktoken
+pandas
+chainlit
+langchain-community
+langchain==0.2.0
+langchain-openai==0.1.7

retriever.py

@@ -0,0 +1,38 @@
+import os
+from datasets import load_dataset
+from langchain_community.document_loaders.csv_loader import CSVLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_openai import OpenAIEmbeddings
+from langchain.embeddings import CacheBackedEmbeddings
+from langchain.storage import LocalFileStore
+from langchain_community.vectorstores import FAISS
+
+
+def fetch_retriever_or_load_local_retriever():
+    csv_path = "./imdb.csv"
+    if not os.path.exists(csv_path):
+        dataset = load_dataset("ShubhamChoksi/IMDB_Movies")
+        dataset["train"].to_csv("imdb.csv")
+
+    loader = CSVLoader(file_path=csv_path)
+    data = loader.load()
+
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+    chunked_documents = text_splitter.split_documents(data)
+
+    embedding_model = OpenAIEmbeddings()
+    store = LocalFileStore("./cache/")
+    cached_embedder = CacheBackedEmbeddings.from_bytes_store(
+        embedding_model, store, namespace=embedding_model.model
+    )
+
+    index_path = "local_index"
+    if os.path.exists(index_path):
+        vector_store = FAISS.load_local(
+            index_path, cached_embedder, allow_dangerous_deserialization=True
+        )
+    else:
+        vector_store = FAISS.from_documents(chunked_documents, cached_embedder)
+        vector_store.save_local(index_path)
+
+    return vector_store.as_retriever()