Extraherar tillgängliga LLM:er för varje endpoint i yaml-filen. Rensat ut kommentarer och oanvänd kod.
This commit is contained in:
@@ -69,41 +69,31 @@ def configure():
|
|||||||
|
|
||||||
if isinstance(updated_config.get('endpoints'), list): # Extract info on endpoint, model, url, provider et cetera from list
|
if isinstance(updated_config.get('endpoints'), list): # Extract info on endpoint, model, url, provider et cetera from list
|
||||||
global_state.set_endpoints(endpoints=updated_config.get('endpoints')) # Extract and set list of endpoints
|
global_state.set_endpoints(endpoints=updated_config.get('endpoints')) # Extract and set list of endpoints
|
||||||
logger.debug("endpoints = \n{}".format(json.dumps(global_state.get_endpoints(), indent=4)))
|
# logger.debug("endpoints = \n{}".format(json.dumps(global_state.get_endpoints(), indent=4)))
|
||||||
fetch_models_from_endpoints(global_state.get_endpoints(), global_state) # Call the new function
|
fetch_models_from_endpoints(global_state.get_endpoints(), global_state) # Call the new function
|
||||||
|
endpoints = global_state.get_endpoints()
|
||||||
|
for endpoint in endpoints: # Set default LLM for each endpoint
|
||||||
# TODO: Remove this section when not needed anymore
|
available_llms = global_state.get_list_of_available_llms(endpoint=endpoint)
|
||||||
if isinstance(updated_config.get('ollama'), dict): # Look for 'ollama' key
|
llm = next(iter(available_llms),None) # First available LLM or None. Default for AUTODETECT and requests for non-existing LLMs
|
||||||
if isinstance(updated_config['ollama'].get('model'), str): # Look for 'model' key
|
logger.debug(f"url {endpoint['url']} = {available_llms}")
|
||||||
model_to_use = updated_config['ollama'].get('model')
|
if endpoint["model"] in available_llms: # Check if specific LLM requested
|
||||||
global_state.set_llm(model_to_use)
|
llm = endpoint["model"]
|
||||||
logger.debug("configure(): LLM is set to: %s",global_state.get_llm())
|
endpoint["default_llm"] = llm
|
||||||
|
|
||||||
return updated_config
|
|
||||||
|
|
||||||
|
|
||||||
# def start_frontend(config):
|
|
||||||
# parsed_url = urllib.parse.urlparse(config['frontend']['url'])
|
|
||||||
# hostname = parsed_url.netloc.split(':')[0] # Split by ':' and take the first part, i.e., 'localhost', IP, or domain name
|
|
||||||
# port = parsed_url.port # This is the server port
|
|
||||||
|
|
||||||
# # Use the socket module in Python to check whether a port is in use,
|
|
||||||
# # which would indicate that a server is already running on that port.
|
|
||||||
# with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
|
|
||||||
# try:
|
|
||||||
# s.bind((hostname, port))
|
|
||||||
# logger.debug("No server is running on %s -— starting one.", parsed_url.netloc)
|
|
||||||
# # Start frontend (web server) as a separate process
|
|
||||||
# subprocess.Popen(["python", "-m", "http.server", str(port)])
|
|
||||||
# except socket.error as e:
|
|
||||||
# if e.errno == 48:
|
|
||||||
# logger.debug("A server is already running on %s -— will use this.", parsed_url.netloc)
|
|
||||||
# else:
|
|
||||||
# raise # Unexpected error, re-raise it so we can see the traceback
|
|
||||||
# except Exception as e:
|
|
||||||
# logger.error("Failed to start frontend: %s", str(e)) # Corresponds to print(f"Failed to start frontend: {e}")
|
|
||||||
|
|
||||||
|
|
||||||
|
global_state.set_host_url(next(iter(endpoints),None)) # Set initial host to the first item in endpoints (or None)
|
||||||
|
global_state.set_llm(llm) # Set which server and llm to use
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
# # TODO: Remove this section when not needed anymore
|
||||||
|
# if isinstance(updated_config.get('ollama'), dict): # Look for 'ollama' key
|
||||||
|
# if isinstance(updated_config['ollama'].get('model'), str): # Look for 'model' key
|
||||||
|
# model_to_use = updated_config['ollama'].get('model')
|
||||||
|
# global_state.set_llm(model_to_use)
|
||||||
|
# logger.debug("configure(): LLM is set to: %s",global_state.get_llm())
|
||||||
|
|
||||||
|
return updated_config
|
||||||
|
|
||||||
|
|
||||||
def start_backend(config):
|
def start_backend(config):
|
||||||
@@ -120,6 +110,6 @@ def start_backend(config):
|
|||||||
|
|
||||||
if __name__ == '__main__':
|
if __name__ == '__main__':
|
||||||
conf = configure() # Read config from file and set up config dict
|
conf = configure() # Read config from file and set up config dict
|
||||||
logger.debug('conf dictionary set to \n{}'.format(json.dumps(conf, indent=4)))
|
# logger.debug('conf dictionary set to \n{}'.format(json.dumps(conf, indent=4)))
|
||||||
# start_frontend(config=conf) # Not needed as we are using Flask for backend now
|
# start_frontend(config=conf) # Not needed as we are using Flask for backend now
|
||||||
start_backend(config=conf)
|
start_backend(config=conf)
|
||||||
|
|||||||
Reference in New Issue
Block a user