Skip to content

local AI and chrome issues #164

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
RepairYourTech opened this issue Jan 26, 2025 · 4 comments
Open

local AI and chrome issues #164

RepairYourTech opened this issue Jan 26, 2025 · 4 comments

Comments

@RepairYourTech
Copy link

RepairYourTech commented Jan 26, 2025

first of all it refuses to use my ollama i get connection errors no matter what i try
secondly it never uses my browser and always makes me use vnc to see it use its own

@iammrbt
Copy link

iammrbt commented Jan 29, 2025

How are you running ollama? If the answer is docker you'll need to use your local IP rather than localhost. for instance, http://192.168.1.3:11434 . Also the model names require the tag after the colon (:) as well. So llama3.1:latest, rather than llama3.1

Did you define the chrome dir correctly in the .env file?
For example:

Chrome settings

CHROME_PATH="C:\Program Files\Google\Chrome\Application\chrome.exe"
CHROME_USER_DATA=""
CHROME_DEBUGGING_PORT=9222
CHROME_DEBUGGING_HOST=localhost

Set to true to keep browser open between AI tasks

CHROME_PERSISTENT_SESSION=true

@1achy
Copy link

1achy commented Feb 7, 2025

I HAVE same issue ['[Errno 111] Connection refused', '[Errno 111] Connection refused', '[Errno 111] Connection refused', '[Errno 111] Connection refused', '[Errno 111] Connection refused']

Image

@Bacca1997
Copy link

Bacca1997 commented Feb 26, 2025

EDIT: resolved running ollama as a docker container #146 (comment)

I have the same issue. I use Ollama on a Docker container and have it configured with local IP.

Image

Image

Image

@AliYmn
Copy link
Contributor

AliYmn commented Mar 14, 2025

If you're working with Ollama, you should update the OLLAMA_ENDPOINT to "http://host.docker.internal:11434" in your .env file. This allows the Docker container to communicate with the Ollama application running on your host machine, as "localhost" inside a container refers to the container itself, not your computer.

also I made pr about this issue : #399

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants