119 lines
3.9 KiB
Python
119 lines
3.9 KiB
Python
|
|
# Import the necessary functions from ollama, Flask, requests, threading
|
|
from ollama import Client
|
|
from flask import Flask, request, jsonify, send_from_directory
|
|
from flask_cors import CORS, cross_origin # CORS stands for Cross-Origin Resource Sharing. This is necessary to allow the frontend to make requests to our backend.
|
|
import requests
|
|
import json
|
|
import logging
|
|
from utils import set_local_logger
|
|
|
|
logger = logging.getLogger(__name__) # Separate logger for this module
|
|
set_local_logger(logger) # Set log level for logger
|
|
logger.debug("Logging level of backend logger has been configured")
|
|
|
|
# Initialize a Flask application
|
|
app = Flask(__name__)
|
|
app.config['STATIC_FOLDER'] = 'static' # Adjust if needed
|
|
|
|
|
|
@app.route('/<path:filename>')
|
|
def serve_static(filename):
|
|
return send_from_directory(app.config['STATIC_FOLDER'], filename)
|
|
|
|
|
|
# CORS(app, resources={
|
|
# r"/api/chat": {
|
|
# "origins": "*",
|
|
# "headers": ["Origin", "Content-Type", "Authorization"],
|
|
# }
|
|
# })
|
|
|
|
CORS(app, resources={
|
|
r"/api/chat": {
|
|
"origins": "*"
|
|
}
|
|
})
|
|
|
|
@app.route('/api/chat', methods=['POST'])
|
|
def chat(url_server = "http://localhost:11434/api/generate", model = "phi3:mini"):
|
|
"""
|
|
This function handles the chat. The frontend client (web browser) calls the
|
|
backend server through this endpoint (/api/chat) that manage queries
|
|
to the LLM (Large Language Model) server and it also manages the response
|
|
from the LLM server.
|
|
"""
|
|
# Get the message from the JSON in the request body
|
|
data = request.get_json()
|
|
message = data.get('query')
|
|
|
|
logger.debug("data = %s\nmessage = %s", str(data), str(message))
|
|
try:
|
|
url = url_server
|
|
model_to_use = model
|
|
data = {
|
|
"model": model_to_use,
|
|
'prompt': message,
|
|
"stream": False
|
|
}
|
|
headers = {
|
|
"Content-Type": "application/json",
|
|
}
|
|
# With API key
|
|
# headers = {
|
|
# "Content-Type": "application/json",
|
|
# "Authorization": "Bearer YOUR_API_KEY" # Replace with your API key
|
|
# }
|
|
|
|
response = requests.post(url,
|
|
headers=headers,
|
|
data=json.dumps(data))
|
|
response.raise_for_status() # Raise an exception for bad status codes
|
|
return response.json()
|
|
except requests.exceptions.RequestException as e:
|
|
logger.error("Request Exception: %s", str(e))
|
|
return jsonify({'error': 'Failed to process request'}), 500
|
|
except json.JSONDecodeError as e:
|
|
logger.error("JSON Decode Error: %s", str(e)) # Corresponds to print(f"JSON Decode Error: {e}")
|
|
return jsonify({'error': 'Invalid JSON response from server'}), 500
|
|
|
|
|
|
@app.route('/smartassist', methods=["POST"])
|
|
def smartassist():
|
|
# Extract the query from the incoming JSON data
|
|
data = request.json
|
|
user_query = data['query']
|
|
|
|
# Get the response from the OLLAMA API based on the user's query
|
|
# NOTE: Should we append message history here? Maybe interact with SQLlite?
|
|
response = get_response(user_query)
|
|
|
|
# Return the response as a JSON object in the HTTP response
|
|
return jsonify({"response": response})
|
|
|
|
def get_response(user_query):
|
|
# Create a client object for interacting with OLLAMA API
|
|
client = Client()
|
|
# Generate and retrieve the response based on user's query
|
|
response = client.generate_response(user_query)
|
|
# Return the generated response
|
|
return response
|
|
|
|
def run_flask(fport=5005):
|
|
"""
|
|
Starts the Flask server
|
|
"""
|
|
# Flask endpoint for user interaction
|
|
logger.debug("Entering run_flask()")
|
|
# app.run(port = str(str(fport)), debug=False)
|
|
app.run(port = str(str(fport)), debug=True)
|
|
# app.run(port=5000, debug=True, use_reloader=False)
|
|
logger.debug("Exiting run_flask()")
|
|
|
|
|
|
if __name__ == '__main__':
|
|
# Run the Flask application
|
|
run_flask()
|
|
|
|
|