github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-09 01:59:50 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #15416] gemma4:e4b thinking failing with structured output #9856

New Issue
Closed
opened 2026-04-12 22:43:03 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 22:43:03 -05:00
Owner
Copy Link

Originally created by @Raa23 on GitHub (Apr 8, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15416

What is the issue?

llm client calls produce output with json fences when thinking is not set to False.
using package ollama 0.6.1

Reproducible code:

import ollama
from pydantic import BaseModel, ValidationError

class TestModel(BaseModel):
    name: str
    age: int

def test_llm_client():
    client = ollama.Client()
    system = "You are a helpful assistant that generates JSON objects with name and age."
    prompt = "Generate a JSON object with name and age."
    try:
        response = client.chat(
            model="gemma4:e4b",
            messages=[
                    {"role": "system", "content": system},
                    {"role": "user",   "content": prompt},
                ],
                format=TestModel.model_json_schema(),
                think="low",
                options={
                    "temperature": 1.0,
                    "top_p": 0.95,
                    "top_k": 64,
                },
            )
        content = response.message.content or ""
        print("LLM Response:", content)
        result = TestModel.model_validate_json(content)
        print("Parsed Result:", result)
    except ValidationError as ve:
        print("Validation Error:", ve)
    except Exception as e:
        print("Error:", e)

if __name__ == "__main__":
    test_llm_client()

Relevant log output

LLM Response: 
{
  "name": "Alice",
  "age": 30
}

Validation Error: 1 validation error for TestModel
  Invalid JSON: expected value at line 1 column 1 [type=json_invalid, input_value='\n{\n  "name": "A...",\n  "age": 30\n}\n', input_type=str]
    For further information visit https://errors.pydantic.dev/2.12/v/json_invalid

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.20.3

Originally created by @Raa23 on GitHub (Apr 8, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15416 ### What is the issue? llm client calls produce output with json fences when thinking is not set to False. using package ollama 0.6.1 Reproducible code: ```python import ollama from pydantic import BaseModel, ValidationError class TestModel(BaseModel): name: str age: int def test_llm_client(): client = ollama.Client() system = "You are a helpful assistant that generates JSON objects with name and age." prompt = "Generate a JSON object with name and age." try: response = client.chat( model="gemma4:e4b", messages=[ {"role": "system", "content": system}, {"role": "user", "content": prompt}, ], format=TestModel.model_json_schema(), think="low", options={ "temperature": 1.0, "top_p": 0.95, "top_k": 64, }, ) content = response.message.content or "" print("LLM Response:", content) result = TestModel.model_validate_json(content) print("Parsed Result:", result) except ValidationError as ve: print("Validation Error:", ve) except Exception as e: print("Error:", e) if __name__ == "__main__": test_llm_client() ``` ### Relevant log output ```shell LLM Response: { "name": "Alice", "age": 30 } Validation Error: 1 validation error for TestModel Invalid JSON: expected value at line 1 column 1 [type=json_invalid, input_value='\n{\n "name": "A...",\n "age": 30\n}\n', input_type=str] For further information visit https://errors.pydantic.dev/2.12/v/json_invalid ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.20.3
GiteaMirror added the bug label 2026-04-12 22:43:03 -05:00
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#9856
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?