import requests
from openai import OpenAI

# Base URL for API
BASE_URL = "https://vedaya-kge.fly.dev"

# Authentication - API works without it
headers = {"Content-Type": "application/json"}
# If you have an API key (optional):
# headers["Authorization"] = f"Bearer {API_KEY}"

# For OpenAI-compatible queries
client = OpenAI(
    api_key="sk-dummy",  # Works with any dummy key
    base_url=f"{BASE_URL}/v1"
)

import requests
import time
from openai import OpenAI

# 1. Upload text documents (recommended method)
documents = [
    "Your first document content here...",
    "Your second document content here..."
]

response = requests.post(
    f"{BASE_URL}/documents/texts",
    headers={"Content-Type": "application/json"},
    json={
        "texts": documents,
        "file_sources": [f"doc_{i}.txt" for i in range(len(documents))]
    }
)

# 2. Wait for processing (usually seconds, not minutes)
for i in range(30):
    status = requests.get(f"{BASE_URL}/documents/pipeline_status").json()
    if not status.get('busy', False):
        print("✅ Processing complete!")
        break
    time.sleep(2)

# 3. Query using OpenAI-compatible interface (primary method)
client = OpenAI(api_key="sk-dummy", base_url=f"{BASE_URL}/v1")

response = client.chat.completions.create(
    model="vedaya-hybrid",  # Special RAG model
    messages=[{"role": "user", "content": "Your question here"}],
    temperature=0.7,
    max_tokens=500
)

print(response.choices[0].message.content)

def query_vedaya(question, mode="vedaya-hybrid"):
    """Query with automatic HTTP fallback"""
    try:
        from openai import OpenAI
        client = OpenAI(api_key="sk-dummy", base_url=f"{BASE_URL}/v1")
        response = client.chat.completions.create(
            model=mode,
            messages=[{"role": "user", "content": question}],
            temperature=0.7,
            max_tokens=500
        )
        return response.choices[0].message.content
    except:
        # Fallback to HTTP
        response = requests.post(
            f"{BASE_URL}/v1/chat/completions",
            json={
                "model": mode,
                "messages": [{"role": "user", "content": question}],
                "temperature": 0.7,
                "max_tokens": 500
            }
        )
        if response.status_code == 200:
            return response.json()['choices'][0]['message']['content']
        return f"Error: {response.status_code}"