search

crewAIInc / crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
https://crewai.com
MIT License
21.33k stars 2.96k forks source link

Problem using proxy openai #1456

Closed proto1994 closed 1 month ago

proto1994 commented 1 month ago

Description

Hi, I encountered some problems when I used the following openai way

Steps to Reproduce

Run the following code

Expected behavior

Correct output

Screenshots/Code snippets

llm = LLM( temperature=0.0, base_url=os.environ["OPENAI_API_BASE"], model="455-gpt-4o__2024-05-13", api_key=os.environ["OPENAI_API_KEY"], )

research_agent = Agent( role='Researcher', goal='Find and summarize the latest AI news', backstory="""You're a researcher at a large company. You're responsible for analyzing data and providing insights to the business.""", llm=llm, verbose=True )

to perform a semantic search for a specified query from a text's content across the internet

search_tool = SerperDevTool()

task = Task( description='Find and summarize the latest AI news', expected_output='A bullet list summary of the top 5 most important AI news', agent=research_agent, tools=[search_tool] )

crew = Crew( agents=[research_agent], tasks=[task], verbose=True )

result = crew.kickoff() print(result)

Operating System

Ubuntu 20.04

Python Version

3.12

crewAI Version

0.70.1

crewAI Tools Version

0.12.1

Virtual Environment

Venv

Evidence

Provider List: https://docs.litellm.ai/docs/providers

2024-10-16 21:40:27,109 - 8221871104 - llm.py-llm:178 - ERROR: Failed to get supported params: argument of type 'NoneType' is not iterable

Provider List: https://docs.litellm.ai/docs/providers

2024-10-16 21:40:27,121 - 8221871104 - llm.py-llm:178 - ERROR: Failed to get supported params: argument of type 'NoneType' is not iterable

Provider List: https://docs.litellm.ai/docs/providers

2024-10-16 21:40:27,123 - 8221871104 - llm.py-llm:178 - ERROR: Failed to get supported params: argument of type 'NoneType' is not iterable

Provider List: https://docs.litellm.ai/docs/providers

2024-10-16 21:40:27,125 - 8221871104 - llm.py-llm:178 - ERROR: Failed to get supported params: argument of type 'NoneType' is not iterable

Agent: Researcher

Task: Find and summarize the latest AI news

2024-10-16 21:40:27,139 - 8221871104 - llm.py-llm:161 - ERROR: LiteLLM call failed: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=455-gpt-4o__2024-05-13 Pass model as E.g. For 'Huggingface' inference endpoints pass in completion(model='huggingface/starcoder',..) Learn more: https://docs.litellm.ai/docs/providers

Provider List: https://docs.litellm.ai/docs/providers

2024-10-16 21:40:27,140 - 8221871104 - llm.py-llm:178 - ERROR: Failed to get supported params: argument of type 'NoneType' is not iterable

Agent: Researcher

Task: Find and summarize the latest AI news

2024-10-16 21:40:27,146 - 8221871104 - llm.py-llm:161 - ERROR: LiteLLM call failed: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=455-gpt-4o__2024-05-13 Pass model as E.g. For 'Huggingface' inference endpoints pass in completion(model='huggingface/starcoder',..) Learn more: https://docs.litellm.ai/docs/providers

Provider List: https://docs.litellm.ai/docs/providers

2024-10-16 21:40:27,147 - 8221871104 - llm.py-llm:178 - ERROR: Failed to get supported params: argument of type 'NoneType' is not iterable

Agent: Researcher

Task: Find and summarize the latest AI news

2024-10-16 21:40:27,154 - 8221871104 - llm.py-llm:161 - ERROR: LiteLLM call failed: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=455-gpt-4o2024-05-13 Pass model as E.g. For 'Huggingface' inference endpoints pass in completion(model='huggingface/starcoder',..) Learn more: https://docs.litellm.ai/docs/providers Traceback (most recent call last): File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/agent.py", line 228, in execute_task result = self.agent_executor.invoke( ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/agents/crew_agent_executor.py", line 92, in invoke formatted_answer = self._invoke_loop() ^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/agents/crew_agent_executor.py", line 173, in _invoke_loop raise e File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/agents/crew_agent_executor.py", line 113, in _invoke_loop answer = self.llm.call( ^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/llm.py", line 155, in call response = litellm.completion(*params) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/utils.py", line 1006, in wrapper raise e File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/utils.py", line 896, in wrapper result = original_function(args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/main.py", line 2959, in completion raise exception_type( File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/main.py", line 858, in completion model, custom_llm_provider, dynamic_api_key, api_base = get_llm_provider( ^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/litellm_core_utils/get_llm_provider_logic.py", line 520, in get_llm_provider raise e File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/litellm_core_utils/get_llm_provider_logic.py", line 497, in get_llm_provider raise litellm.exceptions.BadRequestError( # type: ignore litellm.exceptions.BadRequestError: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=455-gpt-4o2024-05-13 Pass model as E.g. For 'Huggingface' inference endpoints pass in completion(model='huggingface/starcoder',..) Learn more: https://docs.litellm.ai/docs/providers

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/agent.py", line 228, in execute_task result = self.agent_executor.invoke( ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/agents/crew_agent_executor.py", line 92, in invoke formatted_answer = self._invoke_loop() ^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/agents/crew_agent_executor.py", line 173, in _invoke_loop raise e File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/agents/crew_agent_executor.py", line 113, in _invoke_loop answer = self.llm.call( ^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/llm.py", line 155, in call response = litellm.completion(*params) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/utils.py", line 1006, in wrapper raise e File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/utils.py", line 896, in wrapper result = original_function(args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/main.py", line 2959, in completion raise exception_type( File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/main.py", line 858, in completion model, custom_llm_provider, dynamic_api_key, api_base = get_llm_provider( ^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/litellm_core_utils/get_llm_provider_logic.py", line 520, in get_llm_provider raise e File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/litellm_core_utils/get_llm_provider_logic.py", line 497, in get_llm_provider raise litellm.exceptions.BadRequestError( # type: ignore litellm.exceptions.BadRequestError: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=455-gpt-4o__2024-05-13 Pass model as E.g. For 'Huggingface' inference endpoints pass in completion(model='huggingface/starcoder',..) Learn more: https://docs.litellm.ai/docs/providers

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/Users/proto/flight/roamrank/search-hot-agent/app.py", line 56, in result = crew.kickoff() ^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/crew.py", line 490, in kickoff result = self._run_sequential_process() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/crew.py", line 594, in _run_sequential_process return self._execute_tasks(self.tasks) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/crew.py", line 692, in _execute_tasks task_output = task.execute_sync( ^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/task.py", line 191, in execute_sync return self._execute_core(agent, context, tools) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/task.py", line 247, in _execute_core result = agent.execute_task( ^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/agent.py", line 240, in execute_task result = self.execute_task(task, context, tools) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/agent.py", line 240, in execute_task result = self.execute_task(task, context, tools) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/agent.py", line 239, in execute_task raise e File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/agent.py", line 228, in execute_task result = self.agent_executor.invoke( ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/agents/crew_agent_executor.py", line 92, in invoke formatted_answer = self._invoke_loop() ^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/agents/crew_agent_executor.py", line 173, in _invoke_loop raise e File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/agents/crew_agent_executor.py", line 113, in _invoke_loop answer = self.llm.call( ^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/crewai/llm.py", line 155, in call response = litellm.completion(*params) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/utils.py", line 1006, in wrapper raise e File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/utils.py", line 896, in wrapper result = original_function(args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/main.py", line 2959, in completion raise exception_type( File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/main.py", line 858, in completion model, custom_llm_provider, dynamic_api_key, api_base = get_llm_provider( ^^^^^^^^^^^^^^^^^ File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/litellm_core_utils/get_llm_provider_logic.py", line 520, in get_llm_provider raise e File "/Users/proto/flight/roamrank/search-hot-agent/venv/lib/python3.12/site-packages/litellm/litellm_core_utils/get_llm_provider_logic.py", line 497, in get_llm_provider raise litellm.exceptions.BadRequestError( # type: ignore litellm.exceptions.BadRequestError: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=455-gpt-4o__2024-05-13 Pass model as E.g. For 'Huggingface' inference endpoints pass in completion(model='huggingface/starcoder',..) Learn more: https://docs.litellm.ai/docs/providers

Possible Solution

None

Additional context

None

punitchauhan771 commented 1 month ago

Hi @proto1994

Can you try this ?

llm = LLM(
temperature=0.0,
base_url=os.environ["OPENAI_API_BASE"],
model="openai/455-gpt-4o__2024-05-13",
api_key=os.environ["OPENAI_API_KEY"],
)

I am using this as a reference.

proto1994 commented 1 month ago

@punitchauhan771 It works!!! Thank you very much