Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-18 19:34:33 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #633] Ollama setup Not working #361

New Issue
Closed
opened 2026-02-22 18:19:07 -05:00 by yindo · 4 comments
yindo commented 2026-02-22 18:19:07 -05:00
Owner
Copy Link
Copy Source

Originally created by @rdhillbb on GitHub (Jan 21, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/633

I am unable to get ollama to work. I have included in this submission the following
System Configuration
AnythingLLM Olama Entry
Docker File Change for local host.
End User Error Message
Internal Error Message
If you can provide some guidance on document I need to look at or configuration setting. Much appreciated.

Thank You

System Configuration:
Macbook Pro running Sonoma
I9 Intel Processor
32 G memory

Configuration anythingLLM Olama LLM Selection
Ollama Base URL
http://127.0.0.1:11434
Chat Model Selection
-- loading available models --

Token context window
4096

Container Setup Docker Yamal File
extra_hosts:
- "host.docker.internal:127.0.0.1"

Displayed Error Message
Failed to save LLM settings:

localhost, 127.0.0.1, or 0.0.0.0 origins cannot be reached from inside the Anything LLM container. Please use host.docker.internal, a real machine IP, or domain to connect to your service.

Internal Error Message
nything-llm | TypeError: fetch failed
anything-llm | at Object.fetch (node:internal/deps/undici/undici:11730:11)
anything-llm | at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
anything-llm | at async ollamaAIModels (/app/server/utils/helpers/customModels.js:88:18)
anything-llm | at async getCustomModels (/app/server/utils/helpers/customModels.js:21:14)
anything-llm | at async /app/server/endpoints/system.js:718:35 {
anything-llm | cause: Error: connect ECONNREFUSED 127.0.0.1:11434
anything-llm | at TCPConnectWrap.afterConnect [as oncomplete] (node:net:1555:16) {
anything-llm | errno: -111,
anything-llm | code: 'ECONNREFUSED',
anything-llm | syscall: 'connect',
anything-llm | address: '127.0.0.1',
anything-llm | port: 11434
anything-llm | }
anything-llm | }

Originally created by @rdhillbb on GitHub (Jan 21, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/633 I am unable to get ollama to work. I have included in this submission the following System Configuration AnythingLLM Olama Entry Docker File Change for local host. End User Error Message Internal Error Message If you can provide some guidance on document I need to look at or configuration setting. Much appreciated. **_Thank You_** **System Configuration:** Macbook Pro running Sonoma I9 Intel Processor 32 G memory **Configuration anythingLLM Olama LLM Selection** Ollama Base URL http://127.0.0.1:11434 Chat Model Selection -- loading available models -- **<NOTHING LOADADS>** Token context window 4096 **Container Setup Docker Yamal File** extra_hosts: - "host.docker.internal:127.0.0.1" **Displayed Error Message** Failed to save LLM settings: localhost, 127.0.0.1, or 0.0.0.0 origins cannot be reached from inside the Anything LLM container. Please use host.docker.internal, a real machine IP, or domain to connect to your service. **Internal Error Message** nything-llm | TypeError: fetch failed anything-llm | at Object.fetch (node:internal/deps/undici/undici:11730:11) anything-llm | at process.processTicksAndRejections (node:internal/process/task_queues:95:5) anything-llm | at async ollamaAIModels (/app/server/utils/helpers/customModels.js:88:18) anything-llm | at async getCustomModels (/app/server/utils/helpers/customModels.js:21:14) anything-llm | at async /app/server/endpoints/system.js:718:35 { anything-llm | cause: Error: connect ECONNREFUSED 127.0.0.1:11434 anything-llm | at TCPConnectWrap.afterConnect [as oncomplete] (node:net:1555:16) { anything-llm | errno: -111, anything-llm | code: 'ECONNREFUSED', anything-llm | syscall: 'connect', anything-llm | address: '127.0.0.1', anything-llm | port: 11434 anything-llm | } anything-llm | }
yindo closed this issue 2026-02-22 18:19:07 -05:00
yindo commented 2026-02-22 18:19:07 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jan 21, 2024):

Yes, because in docker 127.0.0.1 resolves internally in the container, not on the host.

"host.docker.internal:127.0.0.1"

is probably not required.

In AnythingLLM, just use http://host.docker.internal:11434 instead of 127.0.0.1. That is what that error message is trying to tell you. Localhost doesn't work in docker because it resolves inside the container.

@timothycarambat commented on GitHub (Jan 21, 2024): Yes, because in docker `127.0.0.1` resolves internally in the container, not on the host. ``` "host.docker.internal:127.0.0.1" ``` is probably not required. In AnythingLLM, just use `http://host.docker.internal:11434` instead of `127.0.0.1`. That is what that error message is trying to tell you. Localhost doesn't work in docker because it resolves inside the container.
yindo commented 2026-02-22 18:19:07 -05:00
Author
Owner
Copy Link
Copy Source

@rdhillbb commented on GitHub (Jan 22, 2024):

Thank you.
I will test it out.

@rdhillbb commented on GitHub (Jan 22, 2024): Thank you. I will test it out.
yindo commented 2026-02-22 18:19:08 -05:00
Author
Owner
Copy Link
Copy Source

@rdhillbb commented on GitHub (Jan 22, 2024):

All good. Oly issue is Ollam is very slow.

@rdhillbb commented on GitHub (Jan 22, 2024): All good. Oly issue is Ollam is very slow.
yindo commented 2026-02-22 18:19:08 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jan 22, 2024):

@rdhillbb The issue mainly here is the Ollama is using you're running on an Intel CPU. It's slow on my computer as well, but on an M-series chip it's lightning fast. That's just how it works for the amd86-based arch and no GPU support :/

@timothycarambat commented on GitHub (Jan 22, 2024): @rdhillbb The issue mainly here is the Ollama is using you're running on an Intel CPU. It's slow on my computer as well, but on an M-series chip it's lightning fast. That's just how it works for the amd86-based arch and no GPU support :/
yindo changed title from Ollama setup Not working to [GH-ISSUE #633] Ollama setup Not working 2026-06-05 14:34:54 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#361
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?