Hi, I am trying to run solution locally on laptop and using ollama. Its failing to init knowledge as its looking of OPENAI Key even though I have tried to configure embedding to ollama. Appreciate your help. [2025-02-02 20:47:39][WARNING]: Failed to init knowledge: Please provide an OpenAI API key…

Missed while copying the code. I did specify the base_url and ollama is running. llm = LLM( model="ollama/llama3.2-vision:11b", base_url="http://localhost:11434", temperature=0 ) [image]

I have the same problem from crewai import Agent, Crew, Process, Task from crewai.project import CrewBase, agent, crew, task from crewai.knowledge.source.pdf_knowledge_source import PDFKnowledgeSource from crewai import LLM from dotenv import load_dotenv import os #from langchain_ollama impor…

hello, i am having the same problem, did you manage to solve it?

Failing to embed knowledge source using ollama

CrewAI Community Support

Guigui_DuSud February 6, 2025, 9:02am 4

see String Knowledge sources not working with Gemini

Topic		Replies	Views
Problem with Ollama and knowledge usage Crews memory	2	228	August 11, 2025
How to embed knowledge source with ollama2 CrewAI Community Support	10	2278	May 31, 2025
CrewAI is not allowing the use of a knowledge source when using an Ollama-based LLM. It defaults to requiring an OpenAI API key, even though Ollama is correctly configure General openai , agent , crewai	6	1070	February 6, 2025
Custom knowledge source embedding failing for local Ollama model General	3	743	January 8, 2025
String Knowledge sources not working with Gemini CrewAI Community Support tools_issues	61	2394	April 19, 2025

Failing to embed knowledge source using ollama

Related topics