Unable to pip install llama-index-embeddings-ollama leading to pipeline problems #104

New Issue

2026-02-15T19:15:55-05:00

yindo commented

2026-02-15 19:15:55 -05:00

Originally created by @UmiVilbig on GitHub (Aug 23, 2024).

I used /examples/pipelines/rag/llamaindex_ollama_github_pipeline.py and uploaded the file through the main UI. I then get a status 500 but upon refreshing the page the pipeline exists in the page.

After the pipeline has been uploaded, if you restart the container you are now in a perpetual container restart loop. The error installing package causes the container to crash, it restarts, and hits the same blocker.

Looking through the logs on docker, it looks like the problem stems from the package llama-index-embeddings-ollama. I tried pip installing it inside the container and I get the error could not find a version that satisfies the requirement llama-index-embeddings-ollama (from versions: none)

This could just be a python version problem

Originally created by @UmiVilbig on GitHub (Aug 23, 2024). I used `/examples/pipelines/rag/llamaindex_ollama_github_pipeline.py` and uploaded the file through the main UI. I then get a status 500 but upon refreshing the page the pipeline exists in the page. After the pipeline has been uploaded, if you restart the container you are now in a perpetual container restart loop. The error installing package causes the container to crash, it restarts, and hits the same blocker. Looking through the logs on docker, it looks like the problem stems from the package `llama-index-embeddings-ollama`. I tried pip installing it inside the container and I get the error `could not find a version that satisfies the requirement llama-index-embeddings-ollama (from versions: none)` This could just be a python version problem

yindo commented

2026-02-15 19:15:55 -05:00

@nickibarlowSDI commented on GitHub (Sep 6, 2024):

An infinite "updating but incompatible" loop happens to me when I run: docker run -d -p 9099:9099 --add-host=host.docker.internal:host-gateway -v pipelines:/app/pipelines --name pipelines-official --restart always ghcr.io/open-webui/pipelines:main

ex: llama-index-cli 0.1.13 requires llama-index-core<0.11.0,>=0.10.11.post1, but you have llama-index-core 0.11.6 which is incompatible.

I believe this is caused by the

branch_data: GitBranchResponseModel = self._loop.run_until_complete(

and/or the lack of a GITHUB_TOKEN for one of the default pipelines.

@nickibarlowSDI commented on GitHub (Sep 6, 2024): An infinite "updating but incompatible" loop happens to me when I run: docker run -d -p 9099:9099 --add-host=host.docker.internal:host-gateway -v pipelines:/app/pipelines --name pipelines-official --restart always ghcr.io/open-webui/pipelines:main ex: llama-index-cli 0.1.13 requires llama-index-core<0.11.0,>=0.10.11.post1, but you have llama-index-core 0.11.6 which is incompatible. I believe this is caused by the ``` branch_data: GitBranchResponseModel = self._loop.run_until_complete( ``` and/or the lack of a GITHUB_TOKEN for one of the default pipelines.

yindo referenced this issue

2026-02-15 20:15:02 -05:00

[PR #104] [MERGED] Refactor message content handling in schemas.py to add capability for images #305

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: open-webui/pipelines#104