import os
import asyncio
from langchain_ollama import Ollama, OllamaEmbeddings
from langchain.tools import tool
from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
from langchain_qdrant import QdrantVectorStore
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_core.documents import Document
from langchain_core.messages import HumanMessage

# Инициализация эмбеддинговой модели Ollama
embeddings = OllamaEmbeddings(model="nomic-embed-text")

# Инициализация векторного хранилища Qdrant
vector_store = QdrantVectorStore(
    url="http://localhost:6333",
    collection_name="knowledge",
    embedding_function=embeddings
)

# Инструмент: поиск в базе знаний
@tool
def search_knowledge_base(query: str, max_results: int = 3) -> str:
    """Search the knowledge base for relevant information."""
    docs = vector_store.similarity_search(query, k=max_results)
    return "\n".join(d.page_content for d in docs) if docs else "No results."

# Инструмент: добавление документа в базу знаний
@tool
def add_to_knowledge_base(content: str, title: str = "doc") -> str:
    """Add content to the knowledge base."""
    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
    chunks = splitter.split_text(content)
    docs = [Document(page_content=chunk, metadata={"title": title}) for chunk in chunks]
    vector_store.add_documents(docs)
    return f"Added: {title} ({len(chunks)} chunks)"

# Инициализация LLM Ollama
llm = Ollama(model="llama3")

# Backend для deepagents
backend = CompositeBackend([
    LocalShellBackend(workspace_dir="./workspace"),
    FilesystemBackend(),
])

# Системный промпт агента
system_prompt = (
    "You are a helpful agent with access to a knowledge base. "
    "Use the provided tools to search and add information. "
    "When answering user queries, first search the knowledge base and then provide a concise response."
)

# Создание агента
agent = create_deep_agent(
    model=llm,
    tools=[search_knowledge_base, add_to_knowledge_base],
    backend=backend,
    system_prompt=system_prompt,
)

# Загрузка документов из директории в векторное хранилище
def load_documents_from_dir(dir_path: str):
    for root, dirs, files in os.walk(dir_path):
        for file in files:
            if file.lower().endswith(".txt"):
                path = os.path.join(root, file)
                with open(path, "r", encoding="utf-8") as f:
                    content = f.read()
                title = os.path.splitext(file)[0]
                result = add_to_knowledge_base(content, title)
                print(result)

# Интерактивный клиент
async def interactive_cli():
    print("Welcome to the RAG agent. Commands: /add <file_path>, /search <query>, /quit")
    while True:
        user_input = input(">> ")
        if not user_input.strip():
            continue
        if user_input.startswith("/add"):
            parts = user_input.split(maxsplit=1)
            if len(parts) < 2:
                print("Usage: /add <file_path>")
                continue
            file_path = parts[1]
            if not os.path.isfile(file_path):
                print(f"File not found: {file_path}")
                continue
            with open(file_path, "r", encoding="utf-8") as f:
                content = f.read()
            title = os.path.splitext(os.path.basename(file_path))[0]
            result = add_to_knowledge_base(content, title)
            print(result)
        elif user_input.startswith("/search"):
            parts = user_input.split(maxsplit=1)
            if len(parts) < 2:
                print("Usage: /search <query>")
                continue
            query = parts[1]
            response = await agent.ainvoke(
                {"messages": [HumanMessage(content=query)]},
                {"configurable": {"thread_id": "session-1"}},
            )
            print(response["messages"][-1].content)
        elif user_input.startswith("/quit"):
            print("Goodbye!")
            break
        else:
            print("Unknown command. Use /add, /search, /quit")

async def main():
    # При необходимости загрузить начальные документы
    # load_documents_from_dir("./docs")
    await interactive_cli()

if __name__ == "__main__":
    asyncio.run(main())