github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9739] gemma3 embeddings support #6366

New Issue
Closed
opened 2026-04-12 17:52:51 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 17:52:51 -05:00
Owner
Copy Link

Originally created by @rectalogic on GitHub (Mar 13, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9739

What is the issue?

gemma3:1b fails to generate embeddings, other models work.

$ curl http://localhost:11434/api/embed -d '{
                                    "model": "gemma3:1b",
                                    "input": "Llamas are members of the camelid family"
                                  }'
{"model":"gemma3:1b","embeddings":[null],"total_duration":795587042,"load_duration":644392083,"prompt_eval_count":10}⏎

Relevant log output

time=2025-03-13T13:49:34.664-04:00 level=INFO source=server.go:624 msg="llama runner started in 0.50 seconds"
time=2025-03-13T13:49:34.846-04:00 level=WARN source=runner.go:429 msg="generation of embedding outputs not yet supported"
[GIN] 2025/03/13 - 13:49:34 | 200 |  818.674917ms |       127.0.0.1 | POST     "/api/embed"

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.6.0

Originally created by @rectalogic on GitHub (Mar 13, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9739 ### What is the issue? gemma3:1b fails to generate embeddings, other models work. ```sh-session $ curl http://localhost:11434/api/embed -d '{ "model": "gemma3:1b", "input": "Llamas are members of the camelid family" }' {"model":"gemma3:1b","embeddings":[null],"total_duration":795587042,"load_duration":644392083,"prompt_eval_count":10}⏎ ``` ### Relevant log output ```shell time=2025-03-13T13:49:34.664-04:00 level=INFO source=server.go:624 msg="llama runner started in 0.50 seconds" time=2025-03-13T13:49:34.846-04:00 level=WARN source=runner.go:429 msg="generation of embedding outputs not yet supported" [GIN] 2025/03/13 - 13:49:34 | 200 | 818.674917ms | 127.0.0.1 | POST "/api/embed" ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.6.0
GiteaMirror added the bug label 2026-04-12 17:52:51 -05:00
GiteaMirror commented 2026-04-12 17:52:51 -05:00
Author
Owner
Copy Link

@dhirajpatra commented on GitHub (Apr 26, 2025):

Yes same here with Docker, MAC i7

private_ai_rag_graph-rag_service-1 | INFO:httpx:HTTP Request: POST http://ollama_server_lite:11434/api/embed "HTTP/1.1 500 Internal Server Error"
private_ai_rag_graph-rag_service-1 | ERROR:root:[blog_retriever] Error: this model does not support embeddings (status code: 500)
private_ai_rag_graph-rag_service-1 | ERROR:root:Chat processing failed.
private_ai_rag_graph-rag_service-1 | Traceback (most recent call last):
private_ai_rag_graph-rag_service-1 | File "/app/app.py", line 40, in chat
private_ai_rag_graph-rag_service-1 | reply = run_rag_chain(query=input_msg.text) # Ensure this is a valid string or dict
private_ai_rag_graph-rag_service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
private_ai_rag_graph-rag_service-1 | File "/app/graph/rag_graph.py", line 73, in run_rag_chain
private_ai_rag_graph-rag_service-1 | result = rag_graph.invoke(initial_state)
private_ai_rag_graph-rag_service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
private_ai_rag_graph-rag_service-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/init.py", line 2795, in invoke
private_ai_rag_graph-rag_service-1 | for chunk in self.stream(
private_ai_rag_graph-rag_service-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/init.py", line 2433, in stream
private_ai_rag_graph-rag_service-1 | for _ in runner.tick(
private_ai_rag_graph-rag_service-1 | File "/app/graph/rag_graph.py", line 36, in retrieve
private_ai_rag_graph-rag_service-1 | raise ValueError("Retriever tool failed")
private_ai_rag_graph-rag_service-1 | ValueError: Retriever tool failed
private_ai_rag_graph-rag_service-1 | During task with name 'retrieve' and id '4b23d69e-2279-89b9-910c-1bb115861060'
private_ai_rag_graph-rag_service-1 | INFO: 172.19.0.4:42642 - "POST /chat HTTP/1.1" 500 Internal Server Error
private_ai_rag_graph-rag_service-1 | INFO: 127.0.0.1:41316 - "POST /runs/batch HTTP/1.1" 200 OK

<!-- gh-comment-id:2832230138 --> @dhirajpatra commented on GitHub (Apr 26, 2025): Yes same here with Docker, MAC i7 private_ai_rag_graph-rag_service-1 | INFO:httpx:HTTP Request: POST http://ollama_server_lite:11434/api/embed "HTTP/1.1 500 Internal Server Error" private_ai_rag_graph-rag_service-1 | ERROR:root:[blog_retriever] Error: this model does not support embeddings (status code: 500) private_ai_rag_graph-rag_service-1 | ERROR:root:Chat processing failed. private_ai_rag_graph-rag_service-1 | Traceback (most recent call last): private_ai_rag_graph-rag_service-1 | File "/app/app.py", line 40, in chat private_ai_rag_graph-rag_service-1 | reply = run_rag_chain(query=input_msg.text) # Ensure this is a valid string or dict private_ai_rag_graph-rag_service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ private_ai_rag_graph-rag_service-1 | File "/app/graph/rag_graph.py", line 73, in run_rag_chain private_ai_rag_graph-rag_service-1 | result = rag_graph.invoke(initial_state) private_ai_rag_graph-rag_service-1 | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ private_ai_rag_graph-rag_service-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 2795, in invoke private_ai_rag_graph-rag_service-1 | for chunk in self.stream( private_ai_rag_graph-rag_service-1 | File "/usr/local/lib/python3.11/site-packages/langgraph/pregel/__init__.py", line 2433, in stream private_ai_rag_graph-rag_service-1 | for _ in runner.tick( private_ai_rag_graph-rag_service-1 | File "/app/graph/rag_graph.py", line 36, in retrieve private_ai_rag_graph-rag_service-1 | raise ValueError("Retriever tool failed") private_ai_rag_graph-rag_service-1 | ValueError: Retriever tool failed private_ai_rag_graph-rag_service-1 | During task with name 'retrieve' and id '4b23d69e-2279-89b9-910c-1bb115861060' private_ai_rag_graph-rag_service-1 | INFO: 172.19.0.4:42642 - "POST /chat HTTP/1.1" 500 Internal Server Error private_ai_rag_graph-rag_service-1 | INFO: 127.0.0.1:41316 - "POST /runs/batch HTTP/1.1" 200 OK
GiteaMirror commented 2026-04-12 17:52:51 -05:00
Author
Owner
Copy Link

@pepitoenpeligro commented on GitHub (May 11, 2025):

It's not problem from Ollama, it's Gemma3

curl http://localhost:11434/api/embed -d '{
  "model": "gemma3:latest",
  "input": "Who is the winner of Eurovision Song Contest 2022?"
}'
{"error":"this model does not support embeddings"}
<!-- gh-comment-id:2870024689 --> @pepitoenpeligro commented on GitHub (May 11, 2025): It's not problem from Ollama, it's Gemma3 ```bash curl http://localhost:11434/api/embed -d '{ "model": "gemma3:latest", "input": "Who is the winner of Eurovision Song Contest 2022?" }' {"error":"this model does not support embeddings"} ```
GiteaMirror commented 2026-04-12 17:52:52 -05:00
Author
Owner
Copy Link

@dhirajpatra commented on GitHub (May 12, 2025):

Yes, I have changed the embedding model for ollama. Thanks

<!-- gh-comment-id:2870438225 --> @dhirajpatra commented on GitHub (May 12, 2025): Yes, I have changed the embedding model for ollama. Thanks
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 bug
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#6366
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?