posit-dev / posit-dev/chatlas

Can't list ollama models without providing a `model`

Open
#166 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
176
Forks
28
Avg merge
18h 42m
Merged PRs (30d)
16

Description

One of the awkward bits of having to create a Chat instance to access .list_models() is that in ChatOllama() you have to provide a model name... to be able to list the models.

import chatlas
chatlas.ChatOllama().list_models()
#> Traceback (most recent call last):
#>   File "<string>", line 1, in <module>
#>   File "/Users/garrick/Library/Caches/uv/archive-v0/gi-SY39HQeSIVUWk13RdX/lib/python3.12/site-packages/chatlas/_provider_ollama.py", line 95, in ChatOllama
#>     raise ValueError(
#> ValueError: Must specify model. Locally installed models: qwen3:14b, phi4-mini, granite3.3:8b, gemma3:4b, qwen3:4b, qwen2.5-coder:14b-instruct-q2_K, deepseek-r1:14b, nomic-embed-text, llama3.1:8b, llama3.2

It's helpful that the error message gives you a list of installed models! But a little awkward.

And note that you don't need to provide an installed model to access the model list.

chatlas.ChatOllama("not-a-model").list_models()
#> [ { 'created_at': '2025-07-05T08:52:32.279311903-04:00',
#>     'id': 'qwen3:14b',
#>     'size': 9276198565},
#>   { 'created_at': '2025-07-05T08:49:29.346200434-04:00',
#>     'id': 'phi4-mini',
#>     'size': 2491876774},
#>   { 'created_at': '2025-07-03T16:01:14.509286837-04:00',
#>     'id': 'granite3.3:8b',
#>     'size': 4942891653},
#>   { 'created_at': '2025-07-03T16:00:39.590685087-04:00',
#>     'id': 'gemma3:4b',
#>     'size': 3338801804},
#>   { 'created_at': '2025-05-12T23:12:53.22791702-04:00',
#>     'id': 'qwen3:4b',
#>     'size': 2620788019},
#>   { 'created_at': '2025-03-02T09:54:13.568493478-05:00',
#>     'id': 'qwen2.5-coder:14b-instruct-q2_K',
#>     'size': 5770511454},
#>   { 'created_at': '2025-01-30T20:31:16.927061496-05:00',
#>     'id': 'deepseek-r1:14b',
#>     'size': 8988112040},
#>   { 'created_at': '2024-10-14T17:01:39.820091269-04:00',
#>     'id': 'nomic-embed-text',
#>     'size': 274302450},
#>   { 'created_at': '2024-10-08T09:03:40.302847808-04:00',
#>     'id': 'llama3.1:8b',
#>     'size': 4661230766},
#>   { 'created_at': '2024-10-01T09:04:15.313810108-04:00',
#>     'id': 'llama3.2',
#>     'size': 2019393189}]

Created at 2025-08-31 08:54 EDT by reprexlite v1.0.0

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start in _provider_ollama.py at ChatOllama and the model validation that raises the error when no model is supplied. Check the list_models() entry point, then verify that ChatOllama().list_models() returns the installed model list without requiring a model name.

Written by the indexing model from the issue text.

Assessment

Tech stack
ollama, python
Domain
ai
Issue type
Bug
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Clearly specified
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.