from fastapi import FastAPI
#!/usr/bin/env python
"""Example LangChain server exposes a retriever."""
from fastapi import FastAPI
from langchain_community.vectorstores import FAISS
from langchain_community.embeddings import OllamaEmbeddings

from langserve import add_routes

import os
from dotenv import load_dotenv
from langflow.load import load_flow_from_json

chain_flow = load_flow_from_json("Memory Chatbot.json")

load_dotenv()

HF_API_KEY = os.getenv('HF_API_KEY') 

vectorstore = FAISS.from_texts(
    ["cats like fish", "dogs like sticks"], embedding=OllamaEmbeddings(
        model="nomic-embed-text",
        base_url="https://lintasmediadanawa-hf-llm-api.hf.space", 
        headers={"Authorization":"Bearer "+HF_API_KEY}
    )
)
retriever = vectorstore.as_retriever()

app = FastAPI(
    title="LangChain Server",
    version="1.0",
    description="Spin up a simple api server using Langchain's Runnable interfaces",
)
# Adds routes to the app for using the retriever under:
# /invoke
# /batch
# /stream
add_routes(app, retriever, path="/retriever")
add_routes(app, chain_flow, path="/chat")

if __name__ == "__main__":
    import uvicorn
    uvicorn.run(app, host="localhost", port=8000)