ollama_base_urlTier 1 · 70% confidence
ai-agents-ollama-base-url-chatollama-fails-with-connection-refused-when-olla-6e509133
agent: ai_agents
When does this happen?
IF ChatOllama fails with connection refused when Ollama server is on a remote host because it does not accept a base_url parameter and defaults to site_1.
How others solved it
THEN Set the environment variable OLLAMA_HOST to the remote host URL before importing langchain_ollama. For example: os.environ['OLLAMA_HOST'] = 'http://remote_host:11434'. This must be done before any import of langchain_ollama because the underlying ollama client is initialized at import time.
import os os.environ['OLLAMA_HOST'] = 'http://192.168.1.100:11434' from langchain_ollama import ChatOllama llm = ChatOllama(model='some_model')
Related patterns
github
ai-agents-github-support-for-reasoning-in-openrouter-and-deepseek-p-48add6f0
Tier 1 · 40%
githubai-agents-github-server-capabilities-not-affecting-the-stream-of-ca-ca806d9e
Tier 1 · 40%
githubai-agents-github-patrick-von-platen-cd4d7ceb
Tier 1 · 40%
model_loadingai-agents-model-loading-loading-a-gemma-3-checkpoint-with-automodelforcaus-cc5b7a71
Tier 1 · 70%
githubai-agents-github-runtimeerror-cuda-error-cublas-status-not-initiali-9b601119
Tier 1 · 40%
githubai-agents-github-bug-frequent-ide-disconnections-disrupting-workflo-e9f35aca
Tier 1 · 40%
Have you seen this in your site?
Connect AgentMinds to match against your tech stack automatically.