AgentOps-AI / agentops

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks like CrewAI, Langchain, and Autogen
https://agentops.ai
MIT License
2.07k stars 202 forks source link

ModuleNotFoundError: No module named 'ollama' #277

Closed AIAnytime closed 4 months ago

AIAnytime commented 4 months ago

Here is my code: `from crewai import Agent, Task, Crew, Process import os from dotenv import load_dotenv

load_dotenv()

os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")

import agentops

agentops.init("", tags=["crewai-agent"])

researcher = Agent( role="Researcher", goal="Discover new insights", verbose=True, backstory=( "You are a world class researcher working on a major data science company" ), allow_delegation=False, )

writer = Agent( role="Writer", goal="Create Engaging content", verbose=True, backstory=( "You are a famous technical writer, specialized on writing data related content" ), allow_delegation=False, )

task1 = Task( description=("Investigate the latest AI trends"), expected_output="Investigate the latest AI trends", agent=researcher, ) tast2 = Task( description=("Write a blog post on AI advancements"), expected_output="Write a detailed blog post", agent=writer, )

crew = Crew( agents=[researcher, writer], tasks=[task1, tast2], verbose=True, )

result = crew.kickoff()

print("The outputs have been compiled") print("Result=> ", result)

agentops.end_session("Success")`

It gives me import ollama ModuleNotFoundError: No module named 'ollama'

I am not even using ollama.

albertkimjunior commented 4 months ago

@areibman hm

AIAnytime commented 4 months ago

any update? Poor docs, no solution.

areibman commented 4 months ago

any update? Poor docs, no solution.

Hey @AIAnytime -- thought we replied. We're taking a look to see what's going on. Can you verify which version of AgentOps you're on?

siyangqiu commented 4 months ago

Please update to agentops v0.2.6 which contains the patch for this issue