cyberes
/
local-llm-server
Archived
1
1
Fork 0
Code Issues Pull Requests Packages Projects Releases 1 Wiki Activity

allow disabling ssl verification

This commit is contained in:
Cyberes 2023-08-23 16:11:32 -06:00
parent a6b0bb0183
commit 9fc674878d
6 changed files with 8 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
config/config.yml
View File

@ -1,6 +1,7 @@
# TODO: add this file to gitignore and add a .sample.yml # TODO: add this file to gitignore and add a .sample.yml
log_prompts: true log_prompts: true
verify_ssl: false # Python request has issues with self-signed certs
mode: oobabooga mode: oobabooga
auth_required: false auth_required: false

2
llm_server/llm/hf_textgen/generate.py
View File

@ -35,7 +35,7 @@ def prepare_json(json_data: dict):
def generate(json_data: dict): def generate(json_data: dict):
print(json.dumps(prepare_json(json_data))) print(json.dumps(prepare_json(json_data)))
# try: # try:
r = requests.post(f'{opts.backend_url}/generate', json=prepare_json(json_data)) r = requests.post(f'{opts.backend_url}/generate', json=prepare_json(json_data), verify=opts.verify_ssl)
print(r.text) print(r.text)
# except Exception as e: # except Exception as e:
# return False, None, f'{e.__class__.__name__}: {e}' # return False, None, f'{e.__class__.__name__}: {e}'

4
llm_server/llm/info.py
View File

@ -6,7 +6,7 @@ from llm_server import opts
def get_running_model(): def get_running_model():
if opts.mode == 'oobabooga': if opts.mode == 'oobabooga':
try: try:
backend_response = requests.get(f'{opts.backend_url}/api/v1/model', timeout=3) backend_response = requests.get(f'{opts.backend_url}/api/v1/model', timeout=3, verify=opts.verify_ssl)
except Exception as e: except Exception as e:
return False, e return False, e
try: try:
@ -16,7 +16,7 @@ def get_running_model():
return False, e return False, e
elif opts.mode == 'hf-textgen': elif opts.mode == 'hf-textgen':
try: try:
backend_response = requests.get(f'{opts.backend_url}/info') backend_response = requests.get(f'{opts.backend_url}/info', verify=opts.verify_ssl)
except Exception as e: except Exception as e:
return False, e return False, e
try: try:

2
llm_server/llm/oobabooga/generate.py
View File

@ -5,7 +5,7 @@ from llm_server import opts
def generate(json_data: dict): def generate(json_data: dict):
try: try:
r = requests.post(f'{opts.backend_url}/api/v1/generate', json=json_data) r = requests.post(f'{opts.backend_url}/api/v1/generate', json=json_data, verify=opts.verify_ssl)
except Exception as e: except Exception as e:
return False, None, f'{e.__class__.__name__}: {e}' return False, None, f'{e.__class__.__name__}: {e}'
if r.status_code != 200: if r.status_code != 200:

1
llm_server/opts.py
View File

@ -10,3 +10,4 @@ auth_required = False
log_prompts = False log_prompts = False
frontend_api_client = '' frontend_api_client = ''
http_host = None http_host = None
verify_ssl = True

3
server.py
View File

@ -21,7 +21,7 @@ if config_path_environ:
else: else:
config_path = Path(script_path, 'config', 'config.yml') config_path = Path(script_path, 'config', 'config.yml')
default_vars = {'mode': 'oobabooga', 'log_prompts': False, 'database_path': './proxy-server.db', 'auth_required': False, 'concurrent_gens': 3, 'frontend_api_client': ''} default_vars = {'mode': 'oobabooga', 'log_prompts': False, 'database_path': './proxy-server.db', 'auth_required': False, 'concurrent_gens': 3, 'frontend_api_client': '', 'verify_ssl': True}
required_vars = ['token_limit'] required_vars = ['token_limit']
config_loader = ConfigLoader(config_path, default_vars, required_vars) config_loader = ConfigLoader(config_path, default_vars, required_vars)
success, config, msg = config_loader.load_config() success, config, msg = config_loader.load_config()
@ -46,6 +46,7 @@ opts.log_prompts = config['log_prompts']
opts.concurrent_gens = config['concurrent_gens'] opts.concurrent_gens = config['concurrent_gens']
opts.frontend_api_client = config['frontend_api_client'] opts.frontend_api_client = config['frontend_api_client']
opts.context_size = config['token_limit'] opts.context_size = config['token_limit']
opts.verify_ssl = config['verify_ssl']
SemaphoreCheckerThread(concurrent_semaphore).start() SemaphoreCheckerThread(concurrent_semaphore).start()