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

# ---------- LLM and embeddings ----------
llm = ChatOllama(model="llama3", temperature=0.2)
embeddings = OllamaEmbeddings(model="nomic-embed-text")

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

# ---------- Text splitter ----------
from langchain_text_splitters import RecursiveCharacterTextSplitter
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 documents found."
    out_lines = []
    for doc, score in results:
        title = doc.metadata.get("title", "Untitled")
        content = doc.page_content[:200] + ("..." if len(doc.page_content) > 200 else "")
        out_lines.append(f"Title: {title}\nScore: {score:.4f}\nContent: {content}")
    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)
    docs = [Document(page_content=chunk, metadata={"title": title}) for chunk in chunks]
    vector_store.add_documents(docs)
    return f"Added {len(chunks)} chunks under title '{title}'."

# ---------- Agent ----------
system_prompt = """
You are an assistant that can search and add documents to a knowledge base.
Use the tools `search_knowledge_base` and `add_to_knowledge_base` as needed.
Respond with plain text. Do not mention tool usage explicitly unless required by the user.
"""
agent = create_agent(
    model=llm,
    tools=[search_knowledge_base, add_to_knowledge_base],
    system_prompt=system_prompt,
)

# ---------- CLI ----------
def main():
    print("RAG Agent CLI. Commands: /add <title> | <content>, /search <query>, /quit")
    while True:
        user_input = input("\nYou: ").strip()
        if not user_input:
            continue
        if user_input.lower() in ("exit", "quit", "/quit"):
            print("Goodbye!")
            break
        if user_input.startswith("/add "):
            try:
                _, rest = user_input.split(maxsplit=1)
                title, content = rest.split("|", 1)
                title = title.strip()
                content = content.strip()
                result_msg = add_to_knowledge_base(content=content, title=title)
                print(f"Bot: {result_msg}")
            except ValueError:
                print("Bot: Usage /add <title> | <content>")
        elif user_input.startswith("/search "):
            query = user_input[len("/search "):].strip()
            result_msg = search_knowledge_base(query=query, max_results=5)
            print(f"Bot:\n{result_msg}")
        else:
            # Regular chat
            response = agent.invoke({"messages": [{"role": "human", "content": user_input}]})
            ai_message = response["messages"][-1]
            print(f"Bot: {ai_message.content}")

if __name__ == "__main__":
    main()