NineteenAI gives free access to Lllama 70B which is what im trying to use. The api and stuff can be found here:
NineteenAI | Decentralised Inference.
(I have given the specific error below, but its basically that i cannot set up the llm)
This is what i was trying to do:
@CrewBase
class AiNews():
"""AiNews crew"""
agents_config = 'config/agents.yaml'
tasks_config = 'config/tasks.yaml'
llm = LLM(
api_key="rayon_******643iy5YauprMqfjJM9tbV",
base_url="https://api.nineteen.ai/v1",
model = "hugging-quants/Meta-Llama-3.1-70B-Instruct-AWQ-INT4",
)
@agent
def retrieve_news(self) -> Agent:
return Agent(
config=self.agents_config['retrieve_news'],
tools = [SerperDevTool()],
verbose=True,
llm = self.llm
)
@agent
def website_scraper(self) -> Agent:
return Agent(
config=self.agents_config['website_scraper'],
tools=[ScrapeWebsiteTool()],
verbose=True,
llm= self.llm
)
The rest of the code is like the usual default poem crew from crewai.
The error being recieved is basically this:
litellm.exceptions.BadRequestError: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=hugging-quants/Meta-Llama-3.1-70B-Instruct-AWQ-INT4