Issue Station
Sign In
Tools hereToolbox

llamaIndex - ✅(Solved) Fix [Feature Request]: Add dated snapshot model for GPT-5.4 [1 pull requests, 1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
run-llama/llama_index#21127•Fetched 2026-04-08 01:21:42
View on GitHub
Comments
0
Participants
1
Timeline
4
Reactions
0
Author
laslil7437laslil7437
Participants
laslil7437laslil7437
Timeline (top)
labeled ×2closed ×1cross-referenced ×1

PR fix notes

PR #21191: feat(llama-index-integrations): add gpt-5.4-2026-03-05 dated snapshot model to openai model registry

Description (problem / solution / changelog)

New Feature

Problem

The issue requests adding support for the dated snapshot model gpt-5.4-2026-03-05 to the OpenAI LLM package model registry. This model is a pinned version of GPT-5.4 that allows users to ensure reproducibility and avoid unexpected changes when the gpt-5.4 alias is updated in the future. Based on the issue references (#21065 and #20976), the base gpt-5.4 model was already added, but the dated snapshot was not included.

Severity: low File: llama-index-integrations/llms/llama-index-llms-openai/llama_index/llms/openai/utils.py

Solution

The issue requests adding support for the dated snapshot model gpt-5.4-2026-03-05 to the OpenAI LLM package model registry. This model is a pinned version of GPT-5.4 that allows users to ensure reproducibility and avoid unexpected changes when the gpt-5.4 alias is updated in the future. Based on the issue references (#21065 and #20976), the base gpt-5.4 model was already added, but the dated snapshot was not included.

Changes

  • llama-index-integrations/llms/llama-index-llms-openai/llama_index/llms/openai/utils.py (modified)

Description

Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.

Fixes # (issue)

New Package?

Did I fill in the tool.llamahub section in the pyproject.toml and provide a detailed README.md for my new integration or package?

  • Yes
  • No

Version Bump?

Did I bump the version in the pyproject.toml file of the package I am updating? (Except for the llama-index-core package)

  • Yes
  • No

Type of Change

Please delete options that are not relevant.

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

How Has This Been Tested?

Your pull-request will likely not be merged unless it is covered by some form of impactful unit testing.

  • I added new unit tests to cover this change
  • I believe this change is already covered by existing unit tests

Suggested Checklist:

  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas
  • I have made corresponding changes to the documentation
  • I have added Google Colab support for the newly added notebooks.
  • My changes generate no new warnings
  • I have added tests that prove my fix is effective or that my feature works
  • New and existing unit tests pass locally with my changes
  • I ran uv run make format; uv run make lint to appease the lint gods Contributed by Lê Thành Chỉnh Code is a tool. Mindset is the real value.

Closes #21127

Changed files

  • llama-index-integrations/llms/llama-index-llms-openai/llama_index/llms/openai/utils.py (modified, +1/-0)
  • llama-index-integrations/llms/llama-index-llms-openai/pyproject.toml (modified, +1/-1)
RAW_BUFFERClick to expand / collapse

Feature Description

Currently, llms/openai/utils.py supports gpt-5.4 and related 5.4 models (#21065 and #20976). However, OpenAI has a dated gpt-5.4-2026-03-05 snapshot that is not currently supported by LlamaIndex's supported model list.

Could gpt-5.4-2026-03-05 please be added to the OpenAI LLM package model registry so that users do not have to rely on the alias gpt-5.4?

Reason

Using the alias gpt-5.4 as a substitute does work functionally for now, but does not allow pinning to the dated snapshot that OpenAI has made available to users already (gpt-5.4-2026-03-05)

Value of Feature

Reproducibility, pinning behavior to the dated snapshot, and avoiding unexpected changes when GPT-5.4 undergoes future updates

extent analysis

Fix Plan

To add support for the gpt-5.4-2026-03-05 model, we need to update the model registry in llms/openai/utils.py.

  • Add the gpt-5.4-2026-03-05 model to the SUPPORTED_MODELS list:
SUPPORTED_MODELS = [
    # ... existing models ...
    "gpt-5.4-2026-03-05",
]
  • Update the model alias mapping to include the dated snapshot:
MODEL_ALIASES = {
    # ... existing aliases ...
    "gpt-5.4": "gpt-5.4-2026-03-05",
}
  • Verify that the model is correctly registered by checking the SUPPORTED_MODELS list and the MODEL_ALIASES dictionary.

Verification

To verify that the fix worked, check that the gpt-5.4-2026-03-05 model is recognized by the LlamaIndex and that users can pin to this specific model version.

Extra Tips

  • Make sure to update the documentation to reflect the addition of the new model.
  • Consider adding a test case to ensure that the model is correctly registered and functional.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#device allocation#model download#tokenizer error#prompt formatting#chain error

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING