Skip to content

docs: blog post on Open Responses compliance and OpenAI compatibility#5232

Merged
franciscojavierarceo merged 21 commits intollamastack:mainfrom
franciscojavierarceo:blog/open-responses-openai-compatibility
Mar 26, 2026
Merged

docs: blog post on Open Responses compliance and OpenAI compatibility#5232
franciscojavierarceo merged 21 commits intollamastack:mainfrom
franciscojavierarceo:blog/open-responses-openai-compatibility

Conversation

@franciscojavierarceo
Copy link
Collaborator

@franciscojavierarceo franciscojavierarceo commented Mar 20, 2026

Summary

  • Adds a blog post covering Llama Stack's 100% Open Responses compliance and recognition by the Open Responses community
  • Highlights comprehensive OpenAI API feature support: Files, Vector Stores, Conversations, Prompts, Chat Completions, Responses, MCP, and Connectors
  • Covers the value proposition for end users: data sovereignty, cost control, model freedom, and drop-in framework compatibility

Context

Test plan

  • Review blog post content for accuracy
  • Verify code examples match current API signatures
  • Confirm Docusaurus renders the post correctly
  • Review with co-author @cdoern

🤖 Generated with Claude Code

…lity

Adds a blog post covering Llama Stack's 100% Open Responses compliance,
comprehensive OpenAI API feature support (Files, Vector Stores, Conversations,
Prompts, Chat Completions, Responses, MCP, Connectors), and the value
proposition for running AI infrastructure on your own terms.

Co-Authored-By: Charlie Doern <cdoern@redhat.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
@meta-cla meta-cla bot added the CLA Signed This label is managed by the Meta Open Source bot. label Mar 20, 2026
Copy link
Collaborator

@cdoern cdoern left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

just some initial comments!


# Advanced responses with tool orchestration (e.g., with Fireworks)
response = client.responses.create(
model="meta-llama/Llama-3.2-3B-Instruct",
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit, but should we use a more modern model here like ollama/gpt-oss:20b?

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

oh also I think either way the provider id is wrong here and should be ollama/

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yeah we can use ollama/gpts-oss:20b

```python
# Standard chat completions (e.g., with Ollama)
completion = client.chat.completions.create(
model="ollama/llama3.2:3b", messages=[{"role": "user", "content": "Explain RAG"}]
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

same here, maybe a different model?

franciscojavierarceo and others added 6 commits March 20, 2026 21:07
Co-authored-by: Charlie Doern <charlie@doern.me>
Co-authored-by: Charlie Doern <charlie@doern.me>
Co-authored-by: Charlie Doern <charlie@doern.me>
Co-authored-by: Charlie Doern <charlie@doern.me>
Co-authored-by: Charlie Doern <charlie@doern.me>
Co-authored-by: Charlie Doern <charlie@doern.me>
Combines feedback from cdoern (Ollama setup flow) and gyliu513 (uv-based
install) into a single getting started section.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
franciscojavierarceo and others added 4 commits March 23, 2026 14:53
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
@franciscojavierarceo franciscojavierarceo marked this pull request as ready for review March 25, 2026 15:33
franciscojavierarceo and others added 2 commits March 25, 2026 12:14
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
Copy link
Collaborator

@cdoern cdoern left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

one nit, but LGTM

@franciscojavierarceo franciscojavierarceo merged commit c238fb5 into llamastack:main Mar 26, 2026
14 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

CLA Signed This label is managed by the Meta Open Source bot.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants