forked from phoenix/litellm-mirror
14165d3648
* feat(together_ai/completion): handle together ai completion calls * fix: handle list of int / list of list of int for text completion calls * fix(utils.py): check if base model in bedrock converse model list Fixes https://github.com/BerriAI/litellm/issues/6003 * test(test_optional_params.py): add unit tests for bedrock optional param mapping Fixes https://github.com/BerriAI/litellm/issues/6003 * feat(utils.py): enable passing dummy tool call for anthropic/bedrock calls if tool_use blocks exist Fixes https://github.com/BerriAI/litellm/issues/5388 * fixed an issue with tool use of claude models with anthropic and bedrock (#6013) * fix(utils.py): handle empty schema for anthropic/bedrock Fixes https://github.com/BerriAI/litellm/issues/6012 * fix: fix linting errors * fix: fix linting errors * fix: fix linting errors * fix(proxy_cli.py): fix import route for app + health checks path (#6026) * (testing): Enable testing us.anthropic.claude-3-haiku-20240307-v1:0. (#6018) * fix(proxy_cli.py): fix import route for app + health checks gettsburg.wav Fixes https://github.com/BerriAI/litellm/issues/5999 --------- Co-authored-by: David Manouchehri <david.manouchehri@ai.moda> --------- Co-authored-by: Ved Patwardhan <54766411+vedpatwardhan@users.noreply.github.com> Co-authored-by: David Manouchehri <david.manouchehri@ai.moda>
104 lines
13 KiB
Text
104 lines
13 KiB
Text
============================= test session starts ==============================
|
||
platform darwin -- Python 3.11.4, pytest-8.3.2, pluggy-1.5.0 -- /Users/krrishdholakia/Documents/litellm/myenv/bin/python3.11
|
||
cachedir: .pytest_cache
|
||
rootdir: /Users/krrishdholakia/Documents/litellm
|
||
configfile: pyproject.toml
|
||
plugins: asyncio-0.23.8, respx-0.21.1, anyio-4.6.0
|
||
asyncio: mode=Mode.STRICT
|
||
collecting ... collected 1 item
|
||
|
||
test_function_calling.py::test_aaparallel_function_call[claude-3-haiku-20240307] <module 'litellm' from '/Users/krrishdholakia/Documents/litellm/litellm/__init__.py'>
|
||
|
||
|
||
[92mRequest to litellm:[0m
|
||
[92mlitellm.completion(model='claude-3-haiku-20240307', messages=[{'role': 'user', 'content': "What's the weather like in San Francisco, Tokyo, and Paris? - give me 3 responses"}], tools=[{'type': 'function', 'function': {'name': 'get_current_weather', 'description': 'Get the current weather in a given location', 'parameters': {'type': 'object', 'properties': {'location': {'type': 'string', 'description': 'The city and state'}, 'unit': {'type': 'string', 'enum': ['celsius', 'fahrenheit']}}, 'required': ['location']}}}], tool_choice='auto')[0m
|
||
|
||
|
||
SYNC kwargs[caching]: False; litellm.cache: None; kwargs.get('cache')['no-cache']: False
|
||
Final returned optional params: {'tools': [{'type': 'function', 'function': {'name': 'get_current_weather', 'description': 'Get the current weather in a given location', 'parameters': {'type': 'object', 'properties': {'location': {'type': 'string', 'description': 'The city and state'}, 'unit': {'type': 'string', 'enum': ['celsius', 'fahrenheit']}}, 'required': ['location']}}}], 'tool_choice': {'type': 'auto'}}
|
||
optional_params: {'tools': [{'type': 'function', 'function': {'name': 'get_current_weather', 'description': 'Get the current weather in a given location', 'parameters': {'type': 'object', 'properties': {'location': {'type': 'string', 'description': 'The city and state'}, 'unit': {'type': 'string', 'enum': ['celsius', 'fahrenheit']}}, 'required': ['location']}}}], 'tool_choice': {'type': 'auto'}}
|
||
SENT optional_params: {'tools': [{'type': 'function', 'function': {'name': 'get_current_weather', 'description': 'Get the current weather in a given location', 'parameters': {'type': 'object', 'properties': {'location': {'type': 'string', 'description': 'The city and state'}, 'unit': {'type': 'string', 'enum': ['celsius', 'fahrenheit']}}, 'required': ['location']}}}], 'tool_choice': {'type': 'auto'}, 'max_tokens': 4096}
|
||
tool: {'type': 'function', 'function': {'name': 'get_current_weather', 'description': 'Get the current weather in a given location', 'parameters': {'type': 'object', 'properties': {'location': {'type': 'string', 'description': 'The city and state'}, 'unit': {'type': 'string', 'enum': ['celsius', 'fahrenheit']}}, 'required': ['location']}}}
|
||
[92m
|
||
|
||
POST Request Sent from LiteLLM:
|
||
curl -X POST \
|
||
https://api.anthropic.com/v1/messages \
|
||
-H 'accept: *****' -H 'anthropic-version: *****' -H 'content-type: *****' -H 'x-api-key: sk-ant-api03-bJf1M8qp-JDptRcZRE5ve5efAfSIaL5u-SZ9vItIkvuFcV5cUsd********************************************' -H 'anthropic-beta: *****' \
|
||
-d '{'messages': [{'role': 'user', 'content': [{'type': 'text', 'text': "What's the weather like in San Francisco, Tokyo, and Paris? - give me 3 responses"}]}], 'tools': [{'name': 'get_current_weather', 'description': 'Get the current weather in a given location', 'input_schema': {'type': 'object', 'properties': {'location': {'type': 'string', 'description': 'The city and state'}, 'unit': {'type': 'string', 'enum': ['celsius', 'fahrenheit']}}, 'required': ['location']}}], 'tool_choice': {'type': 'auto'}, 'max_tokens': 4096, 'model': 'claude-3-haiku-20240307'}'
|
||
[0m
|
||
|
||
_is_function_call: False
|
||
RAW RESPONSE:
|
||
{"id":"msg_01HRugqzL4WmcxMmbvDheTph","type":"message","role":"assistant","model":"claude-3-haiku-20240307","content":[{"type":"text","text":"Okay, let's check the current weather in those three cities:"},{"type":"tool_use","id":"toolu_016U6G3kpxjHSiJLwVCrrScz","name":"get_current_weather","input":{"location":"San Francisco","unit":"celsius"}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":379,"output_tokens":87}}
|
||
|
||
|
||
raw model_response: {"id":"msg_01HRugqzL4WmcxMmbvDheTph","type":"message","role":"assistant","model":"claude-3-haiku-20240307","content":[{"type":"text","text":"Okay, let's check the current weather in those three cities:"},{"type":"tool_use","id":"toolu_016U6G3kpxjHSiJLwVCrrScz","name":"get_current_weather","input":{"location":"San Francisco","unit":"celsius"}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":379,"output_tokens":87}}
|
||
Logging Details LiteLLM-Success Call: Cache_hit=None
|
||
Looking up model=claude-3-haiku-20240307 in model_cost_map
|
||
Looking up model=claude-3-haiku-20240307 in model_cost_map
|
||
Response
|
||
ModelResponse(id='chatcmpl-7222f6c2-962a-4776-8639-576723466cb7', choices=[Choices(finish_reason='tool_calls', index=0, message=Message(content="Okay, let's check the current weather in those three cities:", role='assistant', tool_calls=[ChatCompletionMessageToolCall(index=1, function=Function(arguments='{"location": "San Francisco", "unit": "celsius"}', name='get_current_weather'), id='toolu_016U6G3kpxjHSiJLwVCrrScz', type='function')], function_call=None))], created=1727897483, model='claude-3-haiku-20240307', object='chat.completion', system_fingerprint=None, usage=Usage(completion_tokens=87, prompt_tokens=379, total_tokens=466, completion_tokens_details=None))
|
||
length of tool calls 1
|
||
Expecting there to be 3 tool calls
|
||
tool_calls: [ChatCompletionMessageToolCall(index=1, function=Function(arguments='{"location": "San Francisco", "unit": "celsius"}', name='get_current_weather'), id='toolu_016U6G3kpxjHSiJLwVCrrScz', type='function')]
|
||
Response message
|
||
Message(content="Okay, let's check the current weather in those three cities:", role='assistant', tool_calls=[ChatCompletionMessageToolCall(index=1, function=Function(arguments='{"location": "San Francisco", "unit": "celsius"}', name='get_current_weather'), id='toolu_016U6G3kpxjHSiJLwVCrrScz', type='function')], function_call=None)
|
||
messages: [{'role': 'user', 'content': "What's the weather like in San Francisco, Tokyo, and Paris? - give me 3 responses"}, Message(content="Okay, let's check the current weather in those three cities:", role='assistant', tool_calls=[ChatCompletionMessageToolCall(index=1, function=Function(arguments='{"location": "San Francisco", "unit": "celsius"}', name='get_current_weather'), id='toolu_016U6G3kpxjHSiJLwVCrrScz', type='function')], function_call=None), {'tool_call_id': 'toolu_016U6G3kpxjHSiJLwVCrrScz', 'role': 'tool', 'name': 'get_current_weather', 'content': '{"location": "San Francisco", "temperature": "72", "unit": "fahrenheit"}'}]
|
||
|
||
|
||
[92mRequest to litellm:[0m
|
||
[92mlitellm.completion(model='claude-3-haiku-20240307', messages=[{'role': 'user', 'content': "What's the weather like in San Francisco, Tokyo, and Paris? - give me 3 responses"}, Message(content="Okay, let's check the current weather in those three cities:", role='assistant', tool_calls=[ChatCompletionMessageToolCall(index=1, function=Function(arguments='{"location": "San Francisco", "unit": "celsius"}', name='get_current_weather'), id='toolu_016U6G3kpxjHSiJLwVCrrScz', type='function')], function_call=None), {'tool_call_id': 'toolu_016U6G3kpxjHSiJLwVCrrScz', 'role': 'tool', 'name': 'get_current_weather', 'content': '{"location": "San Francisco", "temperature": "72", "unit": "fahrenheit"}'}], temperature=0.2, seed=22, drop_params=True)[0m
|
||
|
||
|
||
SYNC kwargs[caching]: False; litellm.cache: None; kwargs.get('cache')['no-cache']: False
|
||
Final returned optional params: {'temperature': 0.2, 'tools': [{'type': 'function', 'function': {'name': 'dummy-tool', 'description': '', 'parameters': {'type': 'object', 'properties': {}}}}]}
|
||
optional_params: {'temperature': 0.2, 'tools': [{'type': 'function', 'function': {'name': 'dummy-tool', 'description': '', 'parameters': {'type': 'object', 'properties': {}}}}]}
|
||
SENT optional_params: {'temperature': 0.2, 'tools': [{'type': 'function', 'function': {'name': 'dummy-tool', 'description': '', 'parameters': {'type': 'object', 'properties': {}}}}], 'max_tokens': 4096}
|
||
tool: {'type': 'function', 'function': {'name': 'dummy-tool', 'description': '', 'parameters': {'type': 'object', 'properties': {}}}}
|
||
[92m
|
||
|
||
POST Request Sent from LiteLLM:
|
||
curl -X POST \
|
||
https://api.anthropic.com/v1/messages \
|
||
-H 'accept: *****' -H 'anthropic-version: *****' -H 'content-type: *****' -H 'x-api-key: sk-ant-api03-bJf1M8qp-JDptRcZRE5ve5efAfSIaL5u-SZ9vItIkvuFcV5cUsd********************************************' -H 'anthropic-beta: *****' \
|
||
-d '{'messages': [{'role': 'user', 'content': [{'type': 'text', 'text': "What's the weather like in San Francisco, Tokyo, and Paris? - give me 3 responses"}]}, {'role': 'assistant', 'content': [{'type': 'tool_use', 'id': 'toolu_016U6G3kpxjHSiJLwVCrrScz', 'name': 'get_current_weather', 'input': {'location': 'San Francisco', 'unit': 'celsius'}}]}, {'role': 'user', 'content': [{'type': 'tool_result', 'tool_use_id': 'toolu_016U6G3kpxjHSiJLwVCrrScz', 'content': '{"location": "San Francisco", "temperature": "72", "unit": "fahrenheit"}'}]}], 'temperature': 0.2, 'tools': [{'name': 'dummy-tool', 'description': '', 'input_schema': {'type': 'object', 'properties': {}}}], 'max_tokens': 4096, 'model': 'claude-3-haiku-20240307'}'
|
||
[0m
|
||
|
||
_is_function_call: False
|
||
RAW RESPONSE:
|
||
{"id":"msg_01Wp8NVScugz6yAGsmB5trpZ","type":"message","role":"assistant","model":"claude-3-haiku-20240307","content":[{"type":"text","text":"The current weather in San Francisco is 72°F (22°C)."},{"type":"tool_use","id":"toolu_01HTXEYDX4MspM76STtJqs1n","name":"get_current_weather","input":{"location":"Tokyo","unit":"celsius"}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":426,"output_tokens":90}}
|
||
|
||
|
||
raw model_response: {"id":"msg_01Wp8NVScugz6yAGsmB5trpZ","type":"message","role":"assistant","model":"claude-3-haiku-20240307","content":[{"type":"text","text":"The current weather in San Francisco is 72°F (22°C)."},{"type":"tool_use","id":"toolu_01HTXEYDX4MspM76STtJqs1n","name":"get_current_weather","input":{"location":"Tokyo","unit":"celsius"}}],"stop_reason":"tool_use","stop_sequence":null,"usage":{"input_tokens":426,"output_tokens":90}}
|
||
Logging Details LiteLLM-Success Call: Cache_hit=None
|
||
Looking up model=claude-3-haiku-20240307 in model_cost_map
|
||
Looking up model=claude-3-haiku-20240307 in model_cost_map
|
||
second response
|
||
ModelResponse(id='chatcmpl-c4ed5c25-ba7c-49e5-a6be-5720ab25fff0', choices=[Choices(finish_reason='tool_calls', index=0, message=Message(content='The current weather in San Francisco is 72°F (22°C).', role='assistant', tool_calls=[ChatCompletionMessageToolCall(index=1, function=Function(arguments='{"location": "Tokyo", "unit": "celsius"}', name='get_current_weather'), id='toolu_01HTXEYDX4MspM76STtJqs1n', type='function')], function_call=None))], created=1727897484, model='claude-3-haiku-20240307', object='chat.completion', system_fingerprint=None, usage=Usage(completion_tokens=90, prompt_tokens=426, total_tokens=516, completion_tokens_details=None))
|
||
PASSED
|
||
|
||
=============================== warnings summary ===============================
|
||
../../myenv/lib/python3.11/site-packages/pydantic/_internal/_config.py:284
|
||
/Users/krrishdholakia/Documents/litellm/myenv/lib/python3.11/site-packages/pydantic/_internal/_config.py:284: PydanticDeprecatedSince20: Support for class-based `config` is deprecated, use ConfigDict instead. Deprecated in Pydantic V2.0 to be removed in V3.0. See Pydantic V2 Migration Guide at https://errors.pydantic.dev/2.7/migration/
|
||
warnings.warn(DEPRECATION_MESSAGE, DeprecationWarning)
|
||
|
||
../../litellm/utils.py:17
|
||
/Users/krrishdholakia/Documents/litellm/litellm/utils.py:17: DeprecationWarning: 'imghdr' is deprecated and slated for removal in Python 3.13
|
||
import imghdr
|
||
|
||
../../litellm/utils.py:124
|
||
/Users/krrishdholakia/Documents/litellm/litellm/utils.py:124: DeprecationWarning: open_text is deprecated. Use files() instead. Refer to https://importlib-resources.readthedocs.io/en/latest/using.html#migrating-from-legacy for migration advice.
|
||
with resources.open_text("litellm.llms.tokenizers", "anthropic_tokenizer.json") as f:
|
||
|
||
test_function_calling.py:56
|
||
/Users/krrishdholakia/Documents/litellm/tests/local_testing/test_function_calling.py:56: PytestUnknownMarkWarning: Unknown pytest.mark.flaky - is this a typo? You can register custom marks to avoid this warning - for details, see https://docs.pytest.org/en/stable/how-to/mark.html
|
||
@pytest.mark.flaky(retries=3, delay=1)
|
||
|
||
tests/local_testing/test_function_calling.py::test_aaparallel_function_call[claude-3-haiku-20240307]
|
||
tests/local_testing/test_function_calling.py::test_aaparallel_function_call[claude-3-haiku-20240307]
|
||
/Users/krrishdholakia/Documents/litellm/myenv/lib/python3.11/site-packages/httpx/_content.py:202: DeprecationWarning: Use 'content=<...>' to upload raw bytes/text content.
|
||
warnings.warn(message, DeprecationWarning)
|
||
|
||
-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
|
||
======================== 1 passed, 6 warnings in 1.89s =========================
|