from pathlib import Path
import sys

from langchain_ollama import Ollama, OllamaEmbeddings
from langchain_qdrant import QdrantVectorStore
from qdrant_client import QdrantClient
from qdrant_client.http.models import Distance, VectorParams
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain.tools import tool
from langchain.agents import create_agent
from langchain_core.documents import Document

# ---------- LLM and embeddings ----------
llm = Ollama(
    model="llama3",          # local Ollama model
    temperature=0.7,
)

embeddings = OllamaEmbeddings(model="nomic-embed-text")

# ---------- Qdrant client ----------
client = QdrantClient(":memory:")
client.create_collection(
    collection_name="knowledge_base",
    vectors_config=VectorParams(size=embeddings.embedding_size, distance=Distance.COSINE),
)
vector_store = QdrantVectorStore(client=client, collection_name="knowledge_base", embedding=embeddings)

# ---------- Text splitter ----------
splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)

# ---------- 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 information found."
    out_lines = []
    for doc, score in results:
        title = doc.metadata.get("title", "Untitled")
        content_preview = doc.page_content[:200] + ("..." if len(doc.page_content) > 200 else "")
        out_lines.append(f"Score: {score:.3f}\nTitle: {title}\nContent: {content_preview}")
    return "\n\n".join(out_lines)

@tool
def add_to_knowledge_base(content: str, title: str = "Untitled") -> str:
    """Add a new document to the knowledge base."""
    chunks = splitter.split_text(content)
    documents = [
        Document(page_content=chunk, metadata={"title": f"{title} (part {i+1})"})
        for i, chunk in enumerate(chunks)
    ]
    vector_store.add_documents(documents)
    return f"Added {len(chunks)} chunks to the knowledge base under title '{title}'."

# ---------- Agent ----------
system_prompt = """
You are an assistant that can search and add information to a local knowledge base.
Use the tools `search_knowledge_base` and `add_to_knowledge_base` as needed.
"""

agent = create_agent(
    model=llm,
    tools=[search_knowledge_base, add_to_knowledge_base],
    system_prompt=system_prompt,
)

# ---------- CLI ----------
def load_documents_from_dir(directory: Path):
    for file_path in directory.rglob("*"):
        if file_path.is_file() and file_path.suffix.lower() in {".txt", ".md"}:
            content = file_path.read_text(encoding="utf-8")
            title = file_path.stem
            add_to_knowledge_base(content=content, title=title)

def main():
    # Load initial docs if provided as first arg
    if len(sys.argv) > 1:
        load_documents_from_dir(Path(sys.argv[1]))

    print("Agent ready. Commands: /add <title> <file>, /search <query>, /quit")
    while True:
        user_input = input("> ").strip()
        if not user_input:
            continue
        if user_input.lower() in {"quit", "exit"} or user_input == "/quit":
            print("Goodbye!")
            break

        if user_input.startswith("/add"):
            parts = user_input.split(maxsplit=2)
            if len(parts) < 3:
                print("Usage: /add <title> <file_path>")
                continue
            title, file_path = parts[1], Path(parts[2])
            if not file_path.is_file():
                print(f"File {file_path} does not exist.")
                continue
            content = file_path.read_text(encoding="utf-8")
            result = add_to_knowledge_base(content=content, title=title)
            print(result)

        elif user_input.startswith("/search"):
            query = user_input[len("/search"):].strip()
            if not query:
                print("Usage: /search <query>")
                continue
            response = agent.invoke({"messages": [{"role": "human", "content": query}]})
            for msg in response["messages"]:
                if hasattr(msg, "content"):
                    print(msg.content)

        else:
            # Regular chat with agent
            response = agent.invoke({"messages": [{"role": "human", "content": user_input}]})
            for msg in response["messages"]:
                if hasattr(msg, "content"):
                    print(msg.content)

if __name__ == "__main__":
    main()