running the sample code raises errors with anthropic with "pip install aisuite[all]

[echohive42]

a/Desktop/echo_hive_all/openai swarm/test.py"
Why did the pirate bring a ladder to the bar? Because he heard the drinks were on the house! Arrr!
Traceback (most recent call last):
File "c:\Users\memoa\Desktop\echo_hive_all\openai swarm\test.py", line 12, in
response = client.chat.completions.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\memoa\miniconda3\envs\basic3\Lib\site-packages\aisuite\client.py", line 108, in create
self.client.providers[provider_key] = ProviderFactory.create_provider(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\memoa\miniconda3\envs\basic3\Lib\site-packages\aisuite\provider.py", line 46, in create_provider
return provider_class(**config)
^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\memoa\miniconda3\envs\basic3\Lib\site-packages\aisuite\providers\anthropic_provider.py", line 16, in init
self.client = anthropic.Anthropic(**config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\memoa\miniconda3\envs\basic3\Lib\site-packages\anthropic_client.py", line 121, in init
super().init(
File "C:\Users\memoa\miniconda3\envs\basic3\Lib\site-packages\anthropic_base_client.py", line 835, in init
self._client = http_client or SyncHttpxClientWrapper(
^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\memoa\miniconda3\envs\basic3\Lib\site-packages\anthropic_base_client.py", line 733, in init
super().init(**kwargs)
TypeError: Client.init() got an unexpected keyword argument 'proxies'

C:\Users\memoa\Desktop\echo_hive_all\openai swarm>

---

---

---

CODE I RAN:

`import aisuite as ai
client = ai.Client()

models = ["openai:gpt-4o", "anthropic:claude-3-5-sonnet-latest"]

messages = [
{"role": "system", "content": "Respond in Pirate English."},
{"role": "user", "content": "Tell me a joke."},
]

for model in models:
response = client.chat.completions.create(
model=model,
messages=messages,
temperature=0.75
)
print(response.choices[0].message.content)
`

[rohitprasad15]

Thanks for reporting this.
This is a dup of #110
This has been fixed.
We will release a patch shortly with the fix into PyPI.
The fix is already merged in github.