Using Anthropic - Max retries exceeded
QuentinSc opened this issue · 3 comments
QuentinSc commented
Hello,
Thank you for this awesome app.
I have an Anthropic API key with credits.
I set up the docker-compose.yml with
- ENABLE_OPENAI=false
- ENABLE_ANTHROPIC=true
- ANTHROPIC_API_KEY=sk-ant-api03XXXXXXXXXX....
I rundocker compose up
On the UI I've got
ConnectionError: HTTPConnectionPool(host='skyvern', port=8000): Max retries exceeded with url: /api/v1/internal/tasks?page=1&page_size=15 (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7fa29bd9a910>: Failed to establish a new connection: [Errno 111] Connection refused'))
File "/usr/local/lib/python3.11/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 584, in _run_script
exec(code, module.__dict__)
File "/app/streamlit_app/visualizer/streamlit.py", line 258, in <module>
tasks_response = repository.get_tasks(task_page_number)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/streamlit_app/visualizer/repository.py", line 15, in get_tasks
return self.client.get_agent_tasks(page=page, page_size=page_size)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/app/streamlit_app/visualizer/api.py", line 59, in get_agent_tasks
response = requests.get(url, params=params, headers=headers)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/requests/api.py", line 73, in get
return request("get", url, params=params, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/requests/api.py", line 59, in request
return session.request(method=method, url=url, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/requests/sessions.py", line 589, in request
resp = self.send(prep, **send_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/requests/sessions.py", line 703, in send
r = adapter.send(request, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/requests/adapters.py", line 519, in send
raise ConnectionError(e, request=request)
LOGS When booting the skyvern container :
host=0.0.0.0 port=8000
2024-05-08 10:23:39 [INFO] Will watch for changes in these directories: ['/app']
2024-05-08 10:23:39 [INFO] Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
2024-05-08 10:23:39 [INFO] Started reloader process [21] using WatchFiles
2024-05-08 10:23:43 [INFO] Registering LLM config
llm_key=ANTHROPIC_CLAUDE3
2024-05-08 10:23:43 Process SpawnProcess-1:
2024-05-08 10:23:43 Traceback (most recent call last):
2024-05-08 10:23:43 File "/usr/local/lib/python3.11/multiprocessing/process.py", line 314, in _bootstrap
2024-05-08 10:23:43 self.run()
2024-05-08 10:23:43 File "/usr/local/lib/python3.11/multiprocessing/process.py", line 108, in run
2024-05-08 10:23:43 self._target(*self._args, **self._kwargs)
2024-05-08 10:23:43 File "/usr/local/lib/python3.11/site-packages/uvicorn/_subprocess.py", line 76, in subprocess_started
2024-05-08 10:23:43 target(sockets=sockets)
2024-05-08 10:23:43 File "/usr/local/lib/python3.11/site-packages/uvicorn/server.py", line 61, in run
2024-05-08 10:23:43 return asyncio.run(self.serve(sockets=sockets))
2024-05-08 10:23:43 File "/usr/local/lib/python3.11/asyncio/runners.py", line 190, in run
2024-05-08 10:23:43 return runner.run(main)
2024-05-08 10:23:43 File "/usr/local/lib/python3.11/asyncio/runners.py", line 118, in run
2024-05-08 10:23:43 return self._loop.run_until_complete(task)
2024-05-08 10:23:43 File "uvloop/loop.pyx", line 1517, in uvloop.loop.Loop.run_until_complete
2024-05-08 10:23:43 File "/usr/local/lib/python3.11/site-packages/uvicorn/server.py", line 68, in serve
2024-05-08 10:23:43 config.load()
2024-05-08 10:23:43 File "/usr/local/lib/python3.11/site-packages/uvicorn/config.py", line 467, in load
2024-05-08 10:23:43 self.loaded_app = import_from_string(self.app)
2024-05-08 10:23:43 File "/usr/local/lib/python3.11/site-packages/uvicorn/importer.py", line 21, in import_from_string
2024-05-08 10:23:43 module = importlib.import_module(module_str)
2024-05-08 10:23:43 File "/usr/local/lib/python3.11/importlib/__init__.py", line 126, in import_module
2024-05-08 10:23:43 return _bootstrap._gcd_import(name[level:], package, level)
2024-05-08 10:23:43 File "<frozen importlib._bootstrap>", line 1204, in _gcd_import
2024-05-08 10:23:43 File "<frozen importlib._bootstrap>", line 1176, in _find_and_load
2024-05-08 10:23:43 File "<frozen importlib._bootstrap>", line 1147, in _find_and_load_unlocked
2024-05-08 10:23:43 File "<frozen importlib._bootstrap>", line 690, in _load_unlocked
2024-05-08 10:23:43 File "<frozen importlib._bootstrap_external>", line 940, in exec_module
2024-05-08 10:23:43 File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
2024-05-08 10:23:43 File "/app/skyvern/forge/app.py", line 37, in <module>
2024-05-08 10:23:43 LLM_API_HANDLER = LLMAPIHandlerFactory.get_llm_api_handler(SettingsManager.get_settings().LLM_KEY)
2024-05-08 10:23:43 File "/app/skyvern/forge/sdk/api/llm/api_handler_factory.py", line 130, in get_llm_api_handler
2024-05-08 10:23:43 llm_config = LLMConfigRegistry.get_config(llm_key)
2024-05-08 10:23:43 File "/app/skyvern/forge/sdk/api/llm/config_registry.py", line 41, in get_config
2024-05-08 10:23:43 raise InvalidLLMConfigError(llm_key)
2024-05-08 10:23:43 skyvern.forge.sdk.api.llm.exceptions.InvalidLLMConfigError: LLM config with key OPENAI_GPT4V is not a valid LLMConfig
suchintan commented
I think you need to update your .env file. It's currently set to ENABLE_ANTHROPIC=true, but LLM_KEY still points to OpenAI
Update LLM_KEY=ANTHROPIC_CLAUDE3_SONNET
QuentinSc commented
Thank you, didn't see this conf.
Need to udpate to LLM_KEY=ANTHROPIC_CLAUDE3 (sonnet is not recognized)
suchintan commented
Perfect. The latest version of Skyvern requires the SONNET piece (although your current config is backwards compatible)