From 4deb32bf1cfcbc7cc0f2ce383a32841c3a1d5219 Mon Sep 17 00:00:00 2001 From: Cyberes Date: Wed, 4 Oct 2023 10:32:11 -0600 Subject: [PATCH] test --- llm_server/llm/openai/moderation.py | 2 +- llm_server/routes/openai_request_handler.py | 1 - server.py | 4 ++++ 3 files changed, 5 insertions(+), 2 deletions(-) diff --git a/llm_server/llm/openai/moderation.py b/llm_server/llm/openai/moderation.py index 827d04b..f62241d 100644 --- a/llm_server/llm/openai/moderation.py +++ b/llm_server/llm/openai/moderation.py @@ -10,7 +10,7 @@ def check_moderation_endpoint(prompt: str): } response = requests.post('https://api.openai.com/v1/moderations', headers=headers, json={"input": prompt}, timeout=10) if response.status_code != 200: - print(response) + print('moderation failed:', response) response.raise_for_status() response = response.json() diff --git a/llm_server/routes/openai_request_handler.py b/llm_server/routes/openai_request_handler.py index 975bc59..0b768d1 100644 --- a/llm_server/routes/openai_request_handler.py +++ b/llm_server/routes/openai_request_handler.py @@ -73,7 +73,6 @@ class OpenAIRequestHandler(RequestHandler): print('sent success response') return self.build_openai_response(self.prompt, backend_response.json['results'][0]['text'], model=model), backend_response_status_code else: - print(backend_response_status_code, backend_response.data) return backend_response, backend_response_status_code def handle_ratelimited(self, do_log: bool = True): diff --git a/server.py b/server.py index 560f15d..a3074e6 100644 --- a/server.py +++ b/server.py @@ -1,3 +1,5 @@ +from llm_server.routes.queue import priority_queue + try: import gevent.monkey @@ -95,6 +97,8 @@ create_db() @app.route('/api/openai') @flask_cache.cached(timeout=10) def home(): + print(len(priority_queue)) + base_client_api = redis.get('base_client_api', dtype=str) stats = generate_stats() model_choices, default_model = get_model_choices()