from pathlib import Path
import os
from typing import List

# LLM and embeddings via Ollama
from langchain_ollama import ChatOllama, OllamaEmbeddings
# Tools
from langchain.tools import tool
# Vector store
from langchain_qdrant import QdrantVectorStore
from qdrant_client import QdrantClient
from qdrant_client.http.models import Distance, VectorParams
# Text splitter
from langchain_text_splitters import RecursiveCharacterTextSplitter
# Agent
from langchain.agents import create_agent
# Document type
from langchain_core.documents import Document

# -------------------- 1. RAG tools --------------------
@tool
def search_knowledge_base(query: str, max_results: int = 5) -> str:
    """Search the knowledge base for relevant documents."""
    results = vector_store.similarity_search_with_score(query, k=max_results)
    if not results:
        return "No relevant documents found."
    response_lines = []
    for doc, score in results:
        title = doc.metadata.get("title", "Untitled")
        snippet = doc.page_content[:200] + ("..." if len(doc.page_content) > 200 else "")
        response_lines.append(f"Score: {score:.4f}\nTitle: {title}\nContent: {snippet}")
    return "\n\n".join(response_lines)

@tool
def add_to_knowledge_base(content: str, title: str) -> str:
    """Add a new document to the knowledge base."""
    doc = Document(page_content=content, metadata={"title": title})
    vector_store.add_documents([doc])
    return f"Document '{title}' added successfully."

# -------------------- 2. Vector store setup --------------------
client = QdrantClient(":memory:")
client.create_collection(
    collection_name="knowledge",
    vectors_config=VectorParams(size=384, distance=Distance.COSINE),
)

embeddings = OllamaEmbeddings(model="nomic-embed-text")
vector_store = QdrantVectorStore(
    client=client,
    collection_name="knowledge",
    embedding=embeddings,
)

# -------------------- 3. Text splitter --------------------
splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)

# -------------------- 4. Agent --------------------
agent = create_agent(
    model=ChatOllama(model="llama3", temperature=0.2),
    tools=[search_knowledge_base, add_to_knowledge_base],
    system_prompt="You are a helpful assistant that can search and add documents to the knowledge base.",
)

# -------------------- 5. Load docs from directory --------------------
def load_docs_from_dir(directory: str) -> List[Document]:
    docs = []
    for file_path in Path(directory).rglob("*.txt"):
        text = file_path.read_text(encoding="utf-8")
        chunks = splitter.split_text(text)
        for i, chunk in enumerate(chunks):
            docs.append(
                Document(page_content=chunk, metadata={"title": f"{file_path.name} #{i+1}"})
            )
    return docs

def init_knowledge_base(directory: str):
    docs = load_docs_from_dir(directory)
    vector_store.add_documents(docs)

# -------------------- 6. Interactive CLI --------------------
def main():
    print("Initializing knowledge base...")
    init_knowledge_base("./docs")  # replace with your docs folder
    print("Ready! Use /add, /search, or /quit.")
    while True:
        user_input = input("> ").strip()
        if not user_input:
            continue
        if user_input.lower() == "/quit":
            break
        if user_input.startswith("/add"):
            try:
                _, title, content = user_input.split(" ", 2)
                result = add_to_knowledge_base(content=content, title=title)
                print(result)
            except ValueError:
                print("Usage: /add <title> <content>")
        elif user_input.startswith("/search"):
            query = user_input[len("/search"):].strip()
            if not query:
                print("Provide a search query.")
                continue
            result = search_knowledge_base(query=query, max_results=3)
            print(result)
        else:
            # Regular chat with agent
            response = agent.invoke({"messages": [{"role": "human", "content": user_input}]})
            ai_msg = response["messages"][-1]
            print(ai_msg.content)

if __name__ == "__main__":
    main()