"Medical Document Assistant APP with LLM RAG framework --YY

.dockerignore

@@ -0,0 +1,8 @@
+.venv
+__pycache__
+.idea
+.gitignore
+.git
+README.md
+Dockerfile*
+docker-compose*

.gitattributes

@@ -1,35 +1,37 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+data/The_GALE_ENCYCLOPEDIA_of_MEDICINE_SECOND.pdf filter=lfs diff=lfs merge=lfs -text
+vectorstore/db_faiss/index.faiss filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,8 @@
+.chainlit
+.files
+langchain
+vectorstore
+*.bin
+logs.txt
+.idea
+__pycache__

Dockerfile

@@ -0,0 +1,23 @@
+# Use the official python 3.9 image
+FROM python:3.10-slim-bullseye
+
+# Set the working directory to corrent folder
+WORKDIR .
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+# Copy the requirements to working directory
+COPY --chown=user ./requirements.txt requirements.txt
+
+# Install all packages in requirements.txt
+RUN pip install --no-cache-dir --upgrade -r ./requirements.txt
+
+WORKDIR app/
+COPY --chown=user . /app
+
+EXPOSE 7860
+
+CMD ["python", "-m", "chainlit", "run", "model.py", "-h", "--port", "7860", "--host", "0.0.0.0"]
+

README.md

@@ -1,12 +1,39 @@
----
-title: Chainlit Doc
-emoji: 🔥
-colorFrom: yellow
-colorTo: green
-sdk: docker
-pinned: false
-license: mit
-short_description: Document assistant with LLM RAG framework
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## Necessary resources
+
+### Model must be downloaded to local ai_workshop folder:
+Llama 2 Model (Quantized one by the Bloke): https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/blob/main/llama-2-7b-chat.ggmlv3.q8_0.bin
+
+### License and other reference
+The code in all scripts subjects to a licence of 96harsh52/LLaMa_2_chatbot (https://github.com/96harsh52/LLaMa_2_chatbot)
+Youtube instruction (https://www.youtube.com/watch?v=kXuHxI5ZcG0&list=PLrLEqwuz-mRIdQrfeCjeCyFZ-Pl6ffPIN&index=18)
+
+Llama 2 HF Model (Original One): https://huggingface.co/meta-llama
+Chainlit docs: https://github.com/Chainlit/chainlit
+
+## Create virtual Environment
+
+1. Create Virtual env:
+	>`cd ai_workshop`
+	>`python -m venv langchain`
+
+2. Activate virtual evn:
+	>`langchain\Scripts\activate`
+
+*NOTE: if you see the read warning in cmd terminal said "running scripts is disabled on this system" , use Powershell to setup API server:
+	1. open Powershell
+	   > `Set-ExecutionPolicy Unrestricted -Scope Process`
+	2. activate virtual env as previous steps
+
+3. install requirements.txt
+    > `python -m ensurepip --upgrade`
+    > `python -m pip install --upgrade setuptools`
+	> `python -m pip install -r requirements.txt`
+   
+
+## Create local vectors storage database
+
+After activate virtual environment, run `python .\ingest.py`
+
+## Setup Medical chatbot server with chainlit
+
+After set up the database folder of "vectorstore/db_faiss", run `chainlit run .\model.py > logs.txt`

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.

data/The_GALE_ENCYCLOPEDIA_of_MEDICINE_SECOND.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b2e1ac7a12e3f9a97bbd997972f27cb13786de256de83627a51e69d09208973
+size 12226938

docker-compose.yml

@@ -0,0 +1,8 @@
+services:
+  aiworkshop:
+    image: aiworkshop:latest
+    build: .
+    ports:
+      - "7860:7860"
+#    command:
+#      - chainlit run /app/model.py --server.port 8080

ingest.py

@@ -0,0 +1,28 @@
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain_community.vectorstores import FAISS
+from langchain_community.llms import HuggingFaceHub
+
+DATA_PATH = 'data/'
+DB_FAISS_PATH = 'vectorstore/db_faiss'
+
+# ingest model and create vector database
+def create_vector_db():
+    loader = DirectoryLoader(DATA_PATH,
+                             glob='*.pdf',
+                             loader_cls=PyPDFLoader)
+    documents = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500,
+                                                   chunk_overlap=50)
+    texts = text_splitter.split_documents(documents)
+
+    embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2',
+                                       model_kwargs={'device': 'cpu'})
+    db = FAISS.from_documents(texts, embeddings)
+    db.save_local(DB_FAISS_PATH)
+    return db
+
+
+if __name__ == "__main__":
+    create_vector_db()

llama-2-7b-chat.ggmlv3.q8_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bfdde943555c78294626a6ccd40184162d066d39774bd2c98dae24943d32cc3
+size 7160799872

model.py

@@ -0,0 +1,110 @@
+"""
+The code in this script subjects to a licence of 96harsh52/LLaMa_2_chatbot (https://github.com/96harsh52/LLaMa_2_chatbot)
+Youtube instruction (https://www.youtube.com/watch?v=kXuHxI5ZcG0&list=PLrLEqwuz-mRIdQrfeCjeCyFZ-Pl6ffPIN&index=18)
+Llama 2 Model (Quantized one by the Bloke): https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/blob/main/llama-2-7b-chat.ggmlv3.q8_0.bin
+Llama 2 HF Model (Original One): https://huggingface.co/meta-llama
+Chainlit docs: https://github.com/Chainlit/chainlit
+"""
+
+from langchain import PromptTemplate
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain.chains import RetrievalQA
+from langchain_community.llms import CTransformers
+import chainlit as cl
+
+DB_FAISS_PATH = 'vectorstore/db_faiss'
+
+custom_prompt_template = """Use the following pieces of information to answer the user's question.
+If you don't know the answer, just say that you don't know, don't try to make up an answer.
+
+Context: {context}
+Question: {question}
+
+Only return the helpful answer below and nothing else.
+Helpful answer:
+"""
+
+
+def set_custom_prompt():
+    """
+    Prompt template for QA retrieval for each vectorstore
+    """
+    prompt = PromptTemplate(template=custom_prompt_template,
+                            input_variables=['context', 'question'])
+    return prompt
+
+
+def load_llm():
+    """
+    Load the language model
+    """
+    llm = CTransformers(model='llama-2-7b-chat.ggmlv3.q8_0.bin',
+                        model_type='llama',
+                        max_new_tokens=512,
+                        temperature=0.5)
+    return llm
+
+
+def retrieval_qa_chain(llm, prompt, db):
+    """
+    Create a retrieval QA chain
+    """
+    qa_chain = RetrievalQA.from_chain_type(
+        llm=llm,
+        chain_type='stuff',
+        retriever=db.as_retriever(search_kwargs={'k': 2}),
+        return_source_documents=True,
+        chain_type_kwargs={'prompt': prompt}
+    )
+    return qa_chain
+
+
+def qa_bot():
+    """
+    Create a QA bot
+    """
+    embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2',
+                                       model_kwargs={'device': 'cpu'})
+    db = FAISS.load_local(DB_FAISS_PATH, embeddings, allow_dangerous_deserialization=True)
+    llm = load_llm()
+    qa_prompt = set_custom_prompt()
+    qa = retrieval_qa_chain(llm, qa_prompt, db)
+    return qa
+
+
+def final_result(query):
+    qa_result = qa_bot()
+    response = qa_result({'query': query})
+    return response
+
+
+@cl.on_chat_start
+async def start():
+    chain = qa_bot()
+    msg = cl.Message(content="Starting the bot...")
+    await msg.send()
+    msg.content = "Hi, Welcome to Medical Chatbot. What is your query?"
+    await msg.update()
+    cl.user_session.set("chain", chain)
+
+
+@cl.on_message
+async def main(message: cl.Message):
+    chain = cl.user_session.get("chain")
+    cb = cl.AsyncLangchainCallbackHandler(
+        stream_final_answer=True, answer_prefix_tokens=["FINAL", "ANSWER"]
+    )
+    cb.answer_reached = True
+    res = await chain.acall(message.content, callbacks=[cb])
+    answer = res["result"]
+    sources = res["source_documents"]
+
+    if sources:
+        answer += f"\nSources:" + str(sources)
+    else:
+        answer += "\nNo sources found"
+
+    await cl.Message(content=answer).send()
+
+

requirements.txt

@@ -0,0 +1,25 @@
+matplotlib
+plotly
+scikit-learn
+azure-ai-formrecognizer
+azure-cognitiveservices-speech
+azure-ai-textanalytics
+python-dotenv
+huggingface_hub
+accelerate>=0.16.0,<1
+transformers[torch]
+safetensors
+tensorflow
+datasets
+evaluate
+langchain==0.3.3
+langchain-community==0.3.2
+streamlit
+pypdf
+tiktoken
+faiss-cpu
+google-search-results
+sentence-transformers
+chainlit
+tf-keras
+ctransformers

vectorstore/db_faiss/index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dddac424aced14116b13523b7a1ba6dc67e52ebcbff17fd280457955b735356b
+size 10873389

vectorstore/db_faiss/index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca969d9d3c1ded0b845754f3a22f1cf9f68174d93d8e50731f9474b4b4d386ab
+size 3984324