github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3117] Api /tags should include type for embedding model or llm #27677

New Issue
Closed
opened 2026-04-22 05:12:43 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-22 05:12:43 -05:00
Owner
Copy Link

Originally created by @Hansson0728 on GitHub (Mar 13, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3117

As the title says, it would be nice to have that information so we can filter out embedd models if we want to allow for model switching on a frontend

Originally created by @Hansson0728 on GitHub (Mar 13, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3117 As the title says, it would be nice to have that information so we can filter out embedd models if we want to allow for model switching on a frontend
GiteaMirror added the feature requestapi labels 2026-04-22 05:12:44 -05:00
GiteaMirror commented 2026-04-22 05:12:46 -05:00
Author
Owner
Copy Link

@amila-ku commented on GitHub (Mar 15, 2024):

@Hansson0728 would you mind sharing an examples that show how you expect to see it in the response payload. Example response is here

<!-- gh-comment-id:1999650589 --> @amila-ku commented on GitHub (Mar 15, 2024): @Hansson0728 would you mind sharing an examples that show how you expect to see it in the response payload. Example response is [here](https://github.com/ollama/ollama/blob/main/docs/api.md#examples-5)
GiteaMirror commented 2026-04-22 05:12:47 -05:00
Author
Owner
Copy Link

@Hansson0728 commented on GitHub (Mar 18, 2024):

i would say somehing like:

`    {
      "name": "codellama:13b",
      "modified_at": "2023-11-04T14:56:49.277302595-07:00",
      "size": 7365960935,
      "digest": "9f438cb9cd581fc025612d27f7c1a6669ff83a8bb0ed86c94fcf4c5440555697",
      "details": {
        "format": "gguf",
        "family": "llama",
        "families": null,
        "Type": 'LLM' ('Embedding')
        "parameter_size": "13B",
        "quantization_level": "Q4_0"
      }
    },`
<!-- gh-comment-id:2003129704 --> @Hansson0728 commented on GitHub (Mar 18, 2024): i would say somehing like: ``` ` { "name": "codellama:13b", "modified_at": "2023-11-04T14:56:49.277302595-07:00", "size": 7365960935, "digest": "9f438cb9cd581fc025612d27f7c1a6669ff83a8bb0ed86c94fcf4c5440555697", "details": { "format": "gguf", "family": "llama", "families": null, "Type": 'LLM' ('Embedding') "parameter_size": "13B", "quantization_level": "Q4_0" } },` ```
GiteaMirror commented 2026-04-22 05:12:47 -05:00
Author
Owner
Copy Link

@it-s commented on GitHub (Jun 5, 2024):

i would say somehing like:

`    {
      "name": "codellama:13b",
      "modified_at": "2023-11-04T14:56:49.277302595-07:00",
      "size": 7365960935,
      "digest": "9f438cb9cd581fc025612d27f7c1a6669ff83a8bb0ed86c94fcf4c5440555697",
      "details": {
        "format": "gguf",
        "family": "llama",
        "families": null,
        "Type": 'LLM' ('Embedding')
        "parameter_size": "13B",
        "quantization_level": "Q4_0"
      }
    },`

I would suggest to also include a "capabilities" property as a list of tags that would describe what a model is capable of:

"capabilities": ["code-completion", "image-processing", "embedding", "story-telling", etc]

Since ollama now includes image-capable models such as llava UI should know if users are allowed to send images to a model, or not
https://github.com/ollama/ollama/issues/4835

<!-- gh-comment-id:2150152893 --> @it-s commented on GitHub (Jun 5, 2024): > i would say somehing like: > > ``` > ` { > "name": "codellama:13b", > "modified_at": "2023-11-04T14:56:49.277302595-07:00", > "size": 7365960935, > "digest": "9f438cb9cd581fc025612d27f7c1a6669ff83a8bb0ed86c94fcf4c5440555697", > "details": { > "format": "gguf", > "family": "llama", > "families": null, > "Type": 'LLM' ('Embedding') > "parameter_size": "13B", > "quantization_level": "Q4_0" > } > },` > ``` I would suggest to also include a "capabilities" property as a list of tags that would describe what a model is capable of: ``` "capabilities": ["code-completion", "image-processing", "embedding", "story-telling", etc] ``` Since ollama now includes image-capable models such as llava UI should know if users are allowed to send images to a model, or not https://github.com/ollama/ollama/issues/4835
GiteaMirror commented 2026-04-22 05:12:48 -05:00
Author
Owner
Copy Link

@it-s commented on GitHub (Jun 5, 2024):

Also I see that this is already done i the latest released version of ollama. So, this request can be closed :D

<!-- gh-comment-id:2150186823 --> @it-s commented on GitHub (Jun 5, 2024): Also I see that this is already done i the latest released version of ollama. So, this request can be closed :D
GiteaMirror commented 2026-04-22 05:12:48 -05:00
Author
Owner
Copy Link

@FreshLucas-git commented on GitHub (Jun 17, 2024):

Also I see that this is already done i the latest released version of ollama. So, this request can be closed :D

@it-s Hi. Could you tell me which version of Ollama has already implemented this feature? I didn't see this feature implemented in the latest version of Ollama.

<!-- gh-comment-id:2172115878 --> @FreshLucas-git commented on GitHub (Jun 17, 2024): > Also I see that this is already done i the latest released version of ollama. So, this request can be closed :D @it-s Hi. Could you tell me which version of Ollama has already implemented this feature? I didn't see this feature implemented in the latest version of Ollama.
GiteaMirror commented 2026-04-22 05:12:49 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 2, 2026):

$ curl -s localhost:11434/api/show -d '{"model":"codellama:13b"}' | jq .capabilities
[
  "completion"
]
$ curl -s localhost:11434/api/show -d '{"model":"nomic-embed-text"}' | jq .capabilities
[
  "embedding"
]
$ curl -s localhost:11434/api/show -d '{"model":"qwen3-vl"}' | jq .capabilities
[
  "completion",
  "vision",
  "tools",
  "thinking"
]
<!-- gh-comment-id:3837709004 --> @rick-github commented on GitHub (Feb 2, 2026): ```console $ curl -s localhost:11434/api/show -d '{"model":"codellama:13b"}' | jq .capabilities [ "completion" ] $ curl -s localhost:11434/api/show -d '{"model":"nomic-embed-text"}' | jq .capabilities [ "embedding" ] $ curl -s localhost:11434/api/show -d '{"model":"qwen3-vl"}' | jq .capabilities [ "completion", "vision", "tools", "thinking" ] ```
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label api feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#27677
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?