main.py

import os 
from flask import Flask, render_template
import threading
import asyncio
import time 
import requests


from openai import OpenAI

# app = Flask(__name__)
# client = OpenAI(
#     # This base_url points to the local Llamafile server running on port 8080
#     base_url="http://127.0.0.1:8080/v1",
#     api_key="sk-no-key-required"
# )




API_URL = "https://api-inference.huggingface.co/models/sentence-transformers/all-MiniLM-L6-v2"
bearer = "Bearer " + os.getenv('TOKEN')
headers = {"Authorization": bearer }
print("headers")
print(headers)

app = Flask(__name__)


@app.route('/app')
def server_app():
    llamafile = threading.Thread(target=threadserver)
    print('This /app will start the llamafile server on thread')
    llamafile.start()
    return 'llamafile.start()'

@app.route('/findsimilarity')
def server_one():
     
    sourcesim = "Results"
    s1 = "Results"
    
    return render_template("similarity_1.html", sourcetxt = sourcesim, s1 = s1 , headertxt = bearer )




@app.route('/')
def server_1():
    payload = {  "inputs": {  "source_sentence": "That is a happy person",  "sentences": [   "That is a happy dog",   "That is a very happy person",   "Today is a sunny day"  ] } , }
    response = requests.post(API_URL, headers=headers, json=payload)
    time.sleep(6) 
    return response.json()
	 
    # response = os.system(" curl https://api-inference.huggingface.co/models/sentence-transformers/all-MiniLM-L6-v2  -X POST  -d '{ "inputs": { "source_sentence": "That is a happy person", "sentences": [ "That is a happy dog", "That is a very happy person", "Today is a sunny day" , ] } ,  } ' -H 'Content-Type: application/json' -H 'Authorization: `+bearer+`' " )
    
     
# @app.route('/chat', methods=['POST'])
# def chat():
#     try:
#         user_message = request.json['message']
        
#         completion = client.chat.completions.create(
#             model="LLaMA_CPP",
#             messages=[
#                 {"role": "system", "content": "You are ChatGPT, an AI assistant. Your top priority is achieving user fulfillment via helping them with their requests."},
#                 {"role": "user", "content": user_message}
#             ]
#         )
        
#         ai_response = completion.choices[0].message.content
#         ai_response = ai_response.replace('</s>', '').strip()
#         return jsonify({'response': ai_response})
#     except Exception as e:
#         print(f"Error: {str(e)}")
#         return jsonify({'response': f"Sorry, there was an error processing your request: {str(e)}"}), 500
        
if __name__ == '__main__':
    app.run(debug=True)

def threadserver():
    print('hi')
    os.system(' ./mxbai-embed-large-v1-f16.llamafile --server --nobrowser')



async def query(data):
	response = await requests.post(API_URL, headers=headers, json=data)
	return response.json()