Merge pull request #43 from dohuyduc2002/develop for adding Module 1 …

…projects

Add all module 1 projects

.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

Module_1/RAG_project/README.md

@@ -0,0 +1,47 @@
+# RAG Project Overview
+
+This project, located in the `RAG_project` folder, leverages the vicuna-7b language model (LLM) for a question-answering system specifically designed to work with PDF files. Utilizing the Retrieval-Augmented Generation (RAG) approach, the system aims to provide accurate answers by retrieving relevant information from the provided PDF documents.
+
+## Key Features
+
+- **Language Model**: Utilizes `vicuna-7b-v1.5`, a powerful language model, for generating answers.
+- **File Processing**: Supports PDF file uploads for question-answering tasks.
+- **RAG Approach**: Employs Retrieval-Augmented Generation to enhance answer accuracy by retrieving relevant information from the uploaded documents.
+
+## Getting Started
+
+To get started with this project, follow the steps below:
+
+1. **Clone the Repository**: Ensure you have the project cloned to your local machine.
+2. **Install Dependencies**: A `requirements.txt` file will be provided. Install the necessary dependencies by running `pip install -r requirements.txt` in your terminal.
+3. **Run the Application**: Navigate to the `RAG_project` directory and run `app.py` to start the application.
+
+## Usage
+
+1. **Upload a PDF**: Upon starting the application, you will be prompted to upload a PDF file.
+2. **Ask Questions**: After uploading, you can start asking questions related to the content of the PDF file.
+3. **Receive Answers**: The system will process your questions and provide answers based on the content of the uploaded PDF.
+
+## Requirements
+
+The project requires the following main dependencies:
+
+- `torch`
+- `transformers`
+- `chainlit`
+- `langchain`
+
+A detailed list of all dependencies will be provided in the `requirements.txt` file.
+
+To develop a demon using ngrok, install localtunnel using npm in `localtunnel.txt` file
+
+## To host a local run using ngrok, follow this instructions
+1. Create an account on ngrok
+2. Get personal secret authentication key
+3. Running all code block **Do not cancel notebook run during this process**
+4. Click on `Your app is available at http://localhost:8000` to accessing your demo
+
+This magic method will create an UI file using chainlit
+```python
+%%writefile app.py
+```

Module_1/RAG_project/app.py

@@ -0,0 +1,132 @@
+import chainlit as cl
+import torch
+
+from chainlit.types import AskFileResponse
+
+from transformers import BitsAndBytesConfig
+from transformers import AutoTokenizer , AutoModelForCausalLM , pipeline
+from langchain_huggingface.llms import HuggingFacePipeline
+
+from langchain.memory import ConversationBufferMemory
+from langchain_community.chat_message_histories import ChatMessageHistory
+from langchain.chains import ConversationalRetrievalChain
+
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_chroma import Chroma
+from langchain_community.document_loaders import PyPDFLoader, TextLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_core.runnables import RunnablePassthrough
+from langchain_core.output_parsers import StrOutputParser
+from langchain import hub
+
+text_splitter = RecursiveCharacterTextSplitter (chunk_size =1000 ,chunk_overlap =100)
+embedding = HuggingFaceEmbeddings ()
+
+def process_file(file: AskFileResponse):
+    if file.type == 'text/plain':
+        loader = TextLoader
+    elif file.type == 'application/pdf':
+        loader = PyPDFLoader
+
+    loader = loader(file.path)
+    documents = loader.load()
+    docs = text_splitter.split_documents(documents)
+    for i,doc in enumerate(docs):
+        doc.metadata['source'] = f'source_{i}'
+    return docs
+
+def get_vector_db(file: AskFileResponse):
+    docs = process_file(file)
+    cl.user_session.set('docs',docs)
+    vector_db = Chroma.from_documents(
+        documents = docs,
+        embedding = embedding
+    )
+    return vector_db
+
+def get_huggingface_llm(model_name: str = 'lmsys/vicuna-7b-v1.5',
+                        max_new_token: int = 512):
+    nf4_config = BitsAndBytesConfig(
+        load_in_4bit=True,
+        bnb_4bit_quant_type='nf4',
+        bnb4bit_use_double_quant=True,
+        bnb_4bit_compute_dtype=torch.bfloat16
+    )
+    model = AutoModelForCausalLM.from_pretrained(
+        model_name,
+        quantization_config=nf4_config,
+        low_cpu_mem_usage=True
+    )
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+    model_pipeline = pipeline(
+        'text-generation',
+        model=model,
+        tokenizer=tokenizer,
+        max_new_tokens=max_new_token,
+        pad_token_id=tokenizer.eos_token_id,
+        device_map='auto'
+    )
+    llm = HuggingFacePipeline(pipeline=model_pipeline)
+    return llm
+
+LLM = get_huggingface_llm()
+
+welcome_message = """ Welcome to the PDF QA! To get started :
+1.Upload a PDF or text file
+2.Ask a question about the file
+"""
+
+@cl.on_chat_start
+async def on_chat_start():
+    files = None
+    while files is None:
+        files = await cl.AskFileMessage(
+            content = welcome_message,
+            accept=['text/plain','application/pdf'],
+            max_size_mb = 20,
+            timeout=180
+        ).send()
+        file = files[0]
+
+        msg = cl.Message(content = f'Processing file {file.name}...',
+                         disable_feedback=True)
+        await msg.send()
+
+        vector_db = await cl.make_async(get_vector_db)(file)
+
+        message_history = ChatMessageHistory()
+        memory = ConversationBufferMemory(memory_key='chat_history',
+                                          output_key = 'answer',
+                                          chat_memory = message_history,
+                                          return_messages = True)
+        retriever = vector_db.as_retriever(search_type = 'mmr',search_kwargs = {'k':3})
+        chain = ConversationalRetrievalChain.from_llm(llm = LLM,
+                                                      chain_type = 'stuff',
+                                                      retriever = retriever,
+                                                      memory = memory,return_source_documents = True)
+        msg.content = f"'{file.name} processed. You can now ask question!"
+        await msg.update()
+
+        cl.user_session.set('chain',chain)
+
+@cl.on_message
+async def on_message(message:cl.Message):
+    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"]
+    text_elements = []
+
+    if source_documents :
+        for source_idx , source_doc in enumerate(source_documents) :
+            source_name = f"source_{source_idx}"
+            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()

Module_1/RAG_project/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.

Module_1/RAG_project/localtunnel.txt

@@ -0,0 +1 @@
+localtunnel

Module_1/RAG_project/requirements.txt

@@ -0,0 +1,26 @@
+transformers==4.41.2
+bitsandbytes==0.43.1
+accelerate==0.31.0
+langchain==0.2.5
+langchainhub==0.1.20
+langchain-chroma==0.1.1
+langchain-community==0.2.5
+langchain_huggingface==0.0.3
+python-dotenv==1.0.1
+pypdf==4.2.0
+
+transformers==4.41.2
+bitsandbytes==0.43.1
+accelerate==0.31.0
+langchain==0.2.5
+langchainhub==0.1.20
+langchain-chroma==0.1.1
+langchain-community==0.2.5
+langchain-openai==0.1.9
+langchain_huggingface==0.0.3
+chainlit==1.1.304
+python-dotenv==1.0.1
+pypdf==4.2.0
+
+
+pyngrok