Chat Your Doc is an experimental project aimed at exploring various applications based on LLM. Although it is nominally a chatbot project, its purpose is broader. The project explores various applications using tools such as LangChain or scikit-learn LLM. In the "Lab Apps" section, you can find many examples, including simple and complex ones. The project focuses on researching and exploring various LLM applications, while also incorporating other fields such as UX and computer vision. The "Lab App" section includes a table with links to various apps, descriptions, launch commands, and demos.

• Setup
  • Some keys
  • Conda
  • Pip
• Storage
• Lab Apps
  • Simple
  • Intermediate
  • Advanced
• Notes

For OpenAI, set API-KEY to your environment variables.

Get OpenAI API-KEY

export OPENAI_API_KEY="sk-$TJHGFHJDSFDGAFDFRTHT§$%$%&§%&"

conda env create -n chat-ur-doc -f environment.yml
conda activate chat-ur-doc

pip install -r requirements.txt

ref: https://python.langchain.com/docs/modules/data_connection/vectorstores/

Chroma, FAISS

pip install chromadb

pip install faiss-cpu

App	Models & Components	Description	Launch	Demo
chat_ur_docs.py	ConversationalRetrievalChain, ConversationBufferMemory, ChatOpenAI, LangChain	Chat with documents freely	streamlit run advanced/chat_ur_docs.py --server.port 8004 --server.enableCORS false
chatbot.py	ConversationChain, ConversationBufferMemory, ChatOpenAI, LangChain	Basic chatbot	streamlit run simple/chatbot.py --server.port 8003 --server.enableCORS false
faiss_app.py	OpenAI, FAISS, OpenAIEmbeddings, RecursiveCharacterTextSplitter, VectorDBQAWithSourcesChain LangChain	Ask info from a internet file, find similar docs and answer with VectorDBQAWithSourcesChain	streamlit run advanced/faiss_app.py --server.port 8005 --server.enableCORS false

App	Models & Components	Description	Launch	Demo
i-ask.sh	OpenAI http-request	Simply ask & answer via OpenAI API	i-ask.sh "Who is Joe Biden?"
chat_openai.py	ChatOpenAI, LangChain	Just one chat session	streamlit run simple/chat_openai.py --server.port 8000 --server.enableCORS false
open_api_llm_app.py	OpenAI, LLMChain, LangChain	Use OpenAI LLM to answer simple question	streamlit run simple/open_api_llm_app.py --server.port 8001 --server.enableCORS false
read_html_app.py	CharacterTextSplitter, LangChain	Get html content and chunk	streamlit run simple/read_html_app.py --server.port 8002 --server.enableCORS false
💥 chatbot.py	ConversationChain, ConversationBufferMemory, ChatOpenAI, LangChain	Basic chatbot	streamlit run simple/chatbot.py --server.port 8003 --server.enableCORS false

App	Models & Components	Description	Launch	Demo
💥 sim_app.py	Chroma, RecursiveCharacterTextSplitter, OpenAIEmbeddings, LangChain	Use the vector database to save file in chunks and retrieve similar content from the database	streamlit run intermediate/sim_app.py --server.port 8002 --server.enableCORS false
llm_chain_translator_app.py	ChatOpenAI, LLMChain, LangChain	Use LLMChain to do language translation	streamlit run intermediate/llm_chain_translator_app.py --server.port 8003 --server.enableCORS false
html_summary_chat_app.py	ChatOpenAI, LangChain	Summary html content	streamlit run intermediate/html_summary_chat_app.py --server.port 8004 --server.enableCORS false
💥 html_2_json_app.py	ChatOpenAI, LangChain	Summary html keypoints into keypoint json	streamlit run intermediate/html_2_json_app.py --server.port 8005 --server.enableCORS false

App	Models & Components	Description	Launch	Demo
qa_chain_pdf_app.py	OpenAI, Chroma, RecursiveCharacterTextSplitter, load_qa_chain->BaseCombineDocumentsChain, LangChain	Ask info from PDF file, chat with it	streamlit run advanced/qa_chain_pdf_app.py --server.port 8004 --server.enableCORS false
faiss_app.py	OpenAI, FAISS, OpenAIEmbeddings, RecursiveCharacterTextSplitter, VectorDBQAWithSourcesChain LangChain	Ask info from a internet file, find similar docs and answer with VectorDBQAWithSourcesChain	streamlit run advanced/faiss_app.py --server.port 8005 --server.enableCORS false
html_2_json_output_app.py	ResponseSchema, StructuredOutputParser, LangChain	Load html content and summary into json objects	streamlit run advanced/html_2_json_output_app.py --server.port 8006 --server.enableCORS false
joke_bot.py	ChatPromptTemplate, HumanMessagePromptTemplate, SystemMessagePromptTemplate ResponseSchema, StructuredOutputParser, ChatOpenAI, LangChain	Prompt engineering to get one random joke or rate one joke	python advanced/joke_bot.py --rate "Why couldn't the bicycle stand up by itself? It was two tired." or python advanced/joke_bot.py --tell --num 4
chat_ur_docs.py	ConversationalRetrievalChain, ConversationBufferMemory, ChatOpenAI, LangChain	Chat with documents freely	streamlit run advanced/chat_ur_docs.py --server.port 8004 --server.enableCORS false

These key notes can be very helpful in getting up to speed quickly. Look for them while you're learning and share them with others. These notes are especially useful when you're asking yourself questions like why, what, and how.

<style> table { width: 100%; border-collapse: collapse; } td { padding: 8px; text-align: center; } img { width: 100%; height: auto; } @media screen and (max-width: 600px) { table, td, tr { display: block; } td { text-align: center; border-bottom: none; } } </style>