midterm

.chainlit/config.toml

@@ -0,0 +1,97 @@
+[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
+
+# Authorize users to upload files with messages
+multi_modal = true
+
+# 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"
+
+# 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 = "1.0.401"

.chainlit/translations/en-US.json

@@ -0,0 +1,155 @@
+{
+    "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": {
+                "expandMessages": "Expand Messages",
+                "hideChainOfThought": "Hide Chain of Thought",
+                "darkMode": "Dark Mode"
+            }
+        },
+        "organisms": {
+            "chat": {
+                "history": {
+                    "index": {
+                        "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..."
+                    },
+                    "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"
+        }
+    }
+}

.chainlit/translations/pt-BR.json

@@ -0,0 +1,155 @@
+{
+    "components": {
+        "atoms": {
+            "buttons": {
+                "userButton": {
+                    "menu": {
+                        "settings": "Configura\u00e7\u00f5es",
+                        "settingsKey": "S",
+                        "APIKeys": "Chaves de API",
+                        "logout": "Sair"
+                    }
+                }
+            }
+        },
+        "molecules": {
+            "newChatButton": {
+                "newChat": "Nova Conversa"
+            },
+            "tasklist": {
+                "TaskList": {
+                    "title": "\ud83d\uddd2\ufe0f Lista de Tarefas",
+                    "loading": "Carregando...",
+                    "error": "Ocorreu um erro"
+                }
+            },
+            "attachments": {
+                "cancelUpload": "Cancelar envio",
+                "removeAttachment": "Remover anexo"
+            },
+            "newChatDialog": {
+                "createNewChat": "Criar novo chat?",
+                "clearChat": "Isso limpar\u00e1 as mensagens atuais e iniciar\u00e1 uma nova conversa.",
+                "cancel": "Cancelar",
+                "confirm": "Confirmar"
+            },
+            "settingsModal": {
+                "expandMessages": "Expandir Mensagens",
+                "hideChainOfThought": "Esconder Sequ\u00eancia de Pensamento",
+                "darkMode": "Modo Escuro"
+            }
+        },
+        "organisms": {
+            "chat": {
+                "history": {
+                    "index": {
+                        "lastInputs": "\u00daltimas Entradas",
+                        "noInputs": "Vazio...",
+                        "loading": "Carregando..."
+                    }
+                },
+                "inputBox": {
+                    "input": {
+                        "placeholder": "Digite sua mensagem aqui..."
+                    },
+                    "speechButton": {
+                        "start": "Iniciar grava\u00e7\u00e3o",
+                        "stop": "Parar grava\u00e7\u00e3o"
+                    },
+                    "SubmitButton": {
+                        "sendMessage": "Enviar mensagem",
+                        "stopTask": "Parar Tarefa"
+                    },
+                    "UploadButton": {
+                        "attachFiles": "Anexar arquivos"
+                    },
+                    "waterMark": {
+                        "text": "Constru\u00eddo com"
+                    }
+                },
+                "Messages": {
+                    "index": {
+                        "running": "Executando",
+                        "executedSuccessfully": "executado com sucesso",
+                        "failed": "falhou",
+                        "feedbackUpdated": "Feedback atualizado",
+                        "updating": "Atualizando"
+                    }
+                },
+                "dropScreen": {
+                    "dropYourFilesHere": "Solte seus arquivos aqui"
+                },
+                "index": {
+                    "failedToUpload": "Falha ao enviar",
+                    "cancelledUploadOf": "Envio cancelado de",
+                    "couldNotReachServer": "N\u00e3o foi poss\u00edvel conectar ao servidor",
+                    "continuingChat": "Continuando o chat anterior"
+                },
+                "settings": {
+                    "settingsPanel": "Painel de Configura\u00e7\u00f5es",
+                    "reset": "Redefinir",
+                    "cancel": "Cancelar",
+                    "confirm": "Confirmar"
+                }
+            },
+            "threadHistory": {
+                "sidebar": {
+                    "filters": {
+                        "FeedbackSelect": {
+                            "feedbackAll": "Feedback: Todos",
+                            "feedbackPositive": "Feedback: Positivo",
+                            "feedbackNegative": "Feedback: Negativo"
+                        },
+                        "SearchBar": {
+                            "search": "Buscar"
+                        }
+                    },
+                    "DeleteThreadButton": {
+                        "confirmMessage": "Isso deletar\u00e1 a conversa, assim como suas mensagens e elementos.",
+                        "cancel": "Cancelar",
+                        "confirm": "Confirmar",
+                        "deletingChat": "Deletando conversa",
+                        "chatDeleted": "Conversa deletada"
+                    },
+                    "index": {
+                        "pastChats": "Conversas Anteriores"
+                    },
+                    "ThreadList": {
+                        "empty": "Vazio..."
+                    },
+                    "TriggerButton": {
+                        "closeSidebar": "Fechar barra lateral",
+                        "openSidebar": "Abrir barra lateral"
+                    }
+                },
+                "Thread": {
+                    "backToChat": "Voltar para a conversa",
+                    "chatCreatedOn": "Esta conversa foi criada em"
+                }
+            },
+            "header": {
+                "chat": "Conversa",
+                "readme": "Leia-me"
+            }
+        },
+        "hooks": {
+            "useLLMProviders": {
+                "failedToFetchProviders": "Falha ao buscar provedores:"
+            }
+        },
+        "pages": {
+            "Design": {},
+            "Env": {
+                "savedSuccessfully": "Salvo com sucesso",
+                "requiredApiKeys": "Chaves de API necess\u00e1rias",
+                "requiredApiKeysInfo": "Para usar este aplicativo, as seguintes chaves de API s\u00e3o necess\u00e1rias. As chaves s\u00e3o armazenadas localmente em seu dispositivo."
+            },
+            "Page": {
+                "notPartOfProject": "Voc\u00ea n\u00e3o faz parte deste projeto."
+            },
+            "ResumeButton": {
+                "resumeChat": "Continuar Conversa"
+            }
+        }
+    }
+}

.gitignore

@@ -0,0 +1 @@
+.env

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.11.7
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+WORKDIR $HOME/app
+COPY --chown=user . $HOME/app
+COPY ./requirements.txt ~/app/requirements.txt
+RUN pip install -r requirements.txt
+COPY . .
+CMD ["chainlit", "run", "app.py", "--port", "7860"]

app.py

@@ -0,0 +1,117 @@
+from dotenv import load_dotenv
+from langchain_community.document_loaders import PyMuPDFLoader
+import chainlit as cl
+from langchain_community.vectorstores import FAISS
+from langchain_openai import OpenAIEmbeddings
+from langchain.memory import ChatMessageHistory, ConversationBufferMemory
+from langchain.chains import (
+    ConversationalRetrievalChain,
+)
+from langchain_openai import ChatOpenAI
+from langchain.docstore.document import Document
+from langchain.prompts import ChatPromptTemplate
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+import tiktoken
+from typing import List
+#from langchain_community.callbacks import wandb_tracing_enabled
+import os
+
+def tiktoken_len(text):
+    tokens = tiktoken.encoding_for_model("gpt-3.5-turbo").encode(
+        text,
+    )
+    return len(tokens)
+
+text_splitter = RecursiveCharacterTextSplitter(
+    chunk_size = 800,
+    chunk_overlap = 50,
+    length_function = tiktoken_len,
+)
+
+template = """Answer the question based only on the following context. If you cannot answer the question with the context, please respond with 'I don't know':
+
+Context:
+{context}
+
+Question:
+{question}
+"""
+
+
+load_dotenv()
+
+@cl.on_chat_start
+async def on_chat_start():
+    msg = cl.Message(content="Processing Nvidia filing...", disable_feedback=True)
+    await msg.send()
+
+    docs = PyMuPDFLoader("https://d18rn0p25nwr6d.cloudfront.net/CIK-0001045810/1cbe8fe7-e08a-46e3-8dcc-b429fc06c1a4.pdf").load()
+
+    # split the documents into chunks
+    split_chunks = text_splitter.split_documents(docs)
+
+    # Create a FAISS vector store
+    embeddings = OpenAIEmbeddings(
+        model="text-embedding-3-small"
+    )
+
+    vector_store = FAISS.from_documents(split_chunks, embeddings)
+
+    message_history = ChatMessageHistory()
+
+    memory = ConversationBufferMemory(
+        memory_key="chat_history",
+        output_key="answer",
+        chat_memory=message_history,
+        return_messages=True,
+    )
+
+    retriever = vector_store.as_retriever()
+
+    prompt = ChatPromptTemplate.from_template(template)
+
+     # Create a chain that uses the Chroma vector store
+    chain = ConversationalRetrievalChain.from_llm(
+        ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0, streaming=True),
+        chain_type="stuff",
+        retriever=retriever,
+        memory=memory,
+        return_source_documents=True,
+        combine_docs_chain_kwargs={"prompt": prompt}
+    )
+    
+    # Let the user know that the system is ready
+    msg.content = "Nvidia filing processed. You can now ask questions against this document https://d18rn0p25nwr6d.cloudfront.net/CIK-0001045810/1cbe8fe7-e08a-46e3-8dcc-b429fc06c1a4.pdf!"
+    await msg.update()
+
+    cl.user_session.set("chain", chain)
+
+@cl.on_message
+async def on_message(message: cl.Message):
+    # unset the environment variable and use a context manager instead
+    #if "LANGCHAIN_WANDB_TRACING" in os.environ:
+    #    del os.environ["LANGCHAIN_WANDB_TRACING"]
+
+    #with wandb_tracing_enabled():
+    chain = cl.user_session.get("chain")
+    cb = cl.AsyncLangchainCallbackHandler()
+    res = await chain.ainvoke(message.content, callbacks=[cb])
+    answer = res["answer"]
+    source_documents = res["source_documents"]  # type: List[Document]
+    text_elements = []  # type: List[cl.Text]
+
+    if source_documents:
+        for source_idx, source_doc in enumerate(source_documents):
+            source_name = f"source_{source_idx}"
+            # Create the text element referenced in the message
+            text_elements.append(
+                cl.Text(content=source_doc.page_content, name=source_name)
+            )
+            source_names = [text_el.name for text_el in text_elements]
+
+        if source_names:
+            answer += f"\nSources: {', '.join(source_names)}"
+        else:
+            answer += "\nNo sources found"
+
+    await cl.Message(content=answer, elements=text_elements).send()

requirements.txt

@@ -0,0 +1,7 @@
+chainlit==1.0.401
+langchain==0.1.12
+langchain_community==0.0.28
+langchain_openai==0.0.8
+python-dotenv==1.0.1
+tiktoken==0.6.0
+faiss-cpu