curl -fsSL https://ollama.com/install.sh | sh

ollama -v
# Kết quả ví dụ: ollama version 0.6.5

ollama run mistral

>>> tell me about ollama run mistral

langchain
chromadb
sentence-transformers
ollama
langchain-community
langchain-ollama
langchain-huggingface

sudo dnf install gcc-c++ python3-devel  # Nếu dùng Fedora/CentOS
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

from langchain_community.document_loaders import DirectoryLoader, TextLoader
import os

def load_sop_files(directory: str):
    allowed_exts = ('.md', '.asciidoc', '.txt')
    docs = []
    for root, _, files in os.walk(directory):
        for file in files:
            if file.lower().endswith(allowed_exts):
                path = os.path.join(root, file)
                try:
                    loader = TextLoader(path, encoding='utf-8')
                    docs.extend(loader.load())
                except Exception as e:
                    print(f"❌ Error loading {path}: {e}")
    return docs

from utils.loaders import load_sop_files
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import Chroma
from langchain.chains import RetrievalQA
from langchain_ollama import OllamaLLM

print("📂 Loading SOP documents...")
docs = load_sop_files("../help/sops/")

print("🧩 Splitting documents into chunks...")
splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
chunks = splitter.split_documents(docs)

print("🧠 Creating vector database...")
embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
db = Chroma.from_documents(chunks, embeddings)

print("🤖 Setting up AI assistant...")
retriever = db.as_retriever()
llm = OllamaLLM(model="mistral")
qa = RetrievalQA.from_chain_type(llm=llm, retriever=retriever, return_source_documents=True)

print("🤖 SOP Assistant ready. Type your question below. Type 'exit' to quit.")

while True:
    query = input("\n📝 You: ")
    if query.lower() in ("exit", "quit"):
        print("👋 Bye! Take care.")
        break
    result = qa.invoke({"query": query})
    print("\n🤖 Assistant:\n", result["result"])
    print("\n📎 Sources:")
    for doc in result["source_documents"]:
        print(f" - {doc.metadata.get('source')}")