Project RAG app for nvidia file

.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 = "1.0.301"

.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"
+            }
+        }
+    }
+}

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.9
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+WORKDIR $HOME/Mid-term_copy
+COPY --chown=user . $HOME/Mid-term_copy
+COPY ./requirements.txt ~/Mid_term_copy/requirements.txt
+RUN pip install -r requirements.txt
+COPY . .
+CMD ["chainlit", "run", "app.py", "--port", "7860"]

README.md

@@ -0,0 +1,13 @@
+---
+title: RAG NVIDIA Report
+emoji: 🐨
+colorFrom: pink
+colorTo: indigo
+sdk: streamlit
+sdk_version: 1.32.2
+app_file: app.py
+pinned: false
+license: openrail
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,185 @@
+#NVIDIA_report_app
+
+#In the following notebook we'll build RAG pipelines that will allow us to interactively retrieve information from the report "NVIDIA 10-k Filings". 
+#We will further use Ragas to evaluate component-wise metrics, as well as end-to-end metrics about the performance of our RAG pipelines.
+
+import os
+import openai
+from openai import AsyncOpenAI  # importing openai for API usage
+import chainlit as cl  # importing chainlit for our app
+#from chainlit.prompt import Prompt, PromptMessage  # importing prompt tools
+from chainlit.prompt import Prompt, PromptMessage 
+from chainlit.playground.providers import ChatOpenAI  # importing ChatOpenAI tools
+
+
+
+from getpass import getpass
+
+openai.api_key = getpass("Please provide your OpenAI Key: ")
+os.environ["OPENAI_API_KEY"] = openai.api_key
+
+
+
+#Loading data
+from langchain_community.document_loaders import PyMuPDFLoader
+
+loader = PyMuPDFLoader(
+    "NVIDIA_report.pdf",
+)
+
+documents = loader.load()
+
+#Splitting data
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+text_splitter = RecursiveCharacterTextSplitter(
+    chunk_size = 1000,
+    chunk_overlap = 100
+)
+
+documents = text_splitter.split_documents(documents)
+
+#Loading OpenAI embeddings model:
+from langchain_openai import OpenAIEmbeddings
+
+embeddings = OpenAIEmbeddings(
+    model="text-embedding-3-small"
+)
+
+#Creating a FAISS VectorStore:
+from langchain_community.vectorstores import FAISS
+
+vector_store = FAISS.from_documents(documents, embeddings)
+
+#Creating a retriever:
+retriever = vector_store.as_retriever()
+
+#Creating a prompt template:
+from langchain.prompts import ChatPromptTemplate
+
+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}
+"""
+
+prompt = ChatPromptTemplate.from_template(template)
+
+#Creating a RAG chain:
+from operator import itemgetter
+
+from langchain_openai import ChatOpenAI
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables import RunnablePassthrough
+
+primary_qa_llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)
+
+retrieval_augmented_qa_chain = (
+    # INVOKE CHAIN WITH: {"question" : "<<SOME USER QUESTION>>"}
+    # "question" : populated by getting the value of the "question" key
+    # "context"  : populated by getting the value of the "question" key and chaining it into the base_retriever
+    {"context": itemgetter("question") | retriever, "question": itemgetter("question")}
+    # "context"  : is assigned to a RunnablePassthrough object (will not be called or considered in the next step)
+    #              by getting the value of the "context" key from the previous step
+    | RunnablePassthrough.assign(context=itemgetter("context"))
+    # "response" : the "context" and "question" values are used to format our prompt object and then piped
+    #              into the LLM and stored in a key called "response"
+    # "context"  : populated by getting the value of the "context" key from the previous step
+    | {"response": prompt | primary_qa_llm, "context": itemgetter("context")}
+)
+
+#We will be using the advanced Multiquery retriever provided by Langchain:
+from langchain.retrievers import MultiQueryRetriever
+advanced_retriever = MultiQueryRetriever.from_llm(retriever=retriever, llm=primary_qa_llm)
+
+#We create a chain to stuff our documents into our prompt:
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain import hub
+
+retrieval_qa_prompt = hub.pull("langchain-ai/retrieval-qa-chat")
+document_chain = create_stuff_documents_chain(primary_qa_llm, retrieval_qa_prompt)
+
+#Create the new retrieval chain with advanced retriever:
+from langchain.chains import create_retrieval_chain
+retrieval_chain = create_retrieval_chain(advanced_retriever, document_chain)
+
+#And we create our chatbot functions:
+user_template = """{input}
+Think through your response step by step.
+"""
+@cl.on_chat_start  # marks a function that will be executed at the start of a user session
+async def start_chat():
+    settings = {
+        "model": "gpt-3.5-turbo",
+        "temperature": 1.0,
+        "max_tokens": 500,
+        "top_p": 1,
+        "frequency_penalty": 0,
+        "presence_penalty": 0,
+    }
+
+    cl.user_session.set("settings", settings)
+
+
+@cl.on_message  # marks a function that should be run each time the chatbot receives a message from a user
+async def main(message: cl.Message):
+    settings = cl.user_session.get("settings")
+
+    client = AsyncOpenAI(
+    api_key=os.environ.get("OPENAI_API_KEY"),
+)
+    print(message.content)
+
+    prompt = Prompt(
+        #provider=ChatOpenAI.id,
+        provider="ChatOpenAI",
+        messages=[
+            PromptMessage(
+                role="system",
+                template=template,
+                formatted=template,
+            ),
+            PromptMessage(
+                role="user",
+                template=user_template,
+                formatted=user_template.format(input=message.content),
+            ),
+        ],
+        inputs={"input": message.content},
+        settings=settings,
+    )
+
+    print([m.to_openai() for m in prompt.messages])
+
+    msg = cl.Message(content="")
+
+    # Call OpenAI
+    #async for stream_resp in await client.chat.completions.create(
+    #    messages=[m.to_openai() for m in prompt.messages], stream=True, **settings
+    #):
+        
+    #    token = stream_resp.choices[0].delta.content
+    #    if not token:
+    #        token = ""
+    #    await msg.stream_token(token)
+
+    # Update the prompt object with the completion
+    result = retrieval_chain.invoke({"input":message.content})
+    msg.content = result["answer"]
+    #print(temp)
+    #prompt.completion = msg.content
+    #prompt.completion = temp
+    #msg.content = temp
+    
+
+    #prompt.completion = completion
+    msg.prompt = prompt
+
+    # Send and close the message stream
+    await msg.send()
+    
+     
+

chainlit.md

@@ -0,0 +1,2 @@
+# Talk to NVIDIA 10-k Filings report
+

requirements.txt

@@ -0,0 +1,14 @@
+chainlit
+cohere==4.37
+openai
+tiktoken
+python-dotenv==1.0.0
+langchain 
+langchain-openai 
+langchain_core 
+langchain-community 
+langchainhub 
+ragas
+faiss_cpu
+pymupdf 
+pandas