docs: add Symfony AI integration guide

[MVS-source]

What

Symfony AI shipped an official Eden AI bridge in v0.14.0, released 25 September 2026. This adds the guide, under AI Frameworks.

Guide	Nav group	Upstream	Package
symfony.mdx	AI Frameworks	symfony/ai#2417, merged, in v0.14.0	symfony/ai-eden-ai-platform

Same format as the last integration PRs: frontmatter plus <TechArticleSchema>, docs.json nav registration, and a currentColor line icon in the style of the existing small ones. The page lands last in its group, matching the add-order that group already uses.

Why this one is worth more than a chat wrapper

The bridge covers both halves of the V3 API, which is unusual for a framework integration:

• The OpenAI-compatible endpoints, /v3/chat/completions and /v3/embeddings, with streaming and tool calling.
• The expert models on /v3/universal-ai: OCR, document parsing, text to speech, speech to text, image analysis and image generation.

Two behaviours that are worth having written down: binary content is uploaded through /v3/upload transparently before the request, and async transcription returns a job handle instead of blocking inside invoke(), so it can be stored and resumed by a worker, or resolved from a webhook.

Where the configuration comes from

Lifted from the merged upstream code, not reconstructed from memory.

The code samples come from the runnable scripts in examples/edenai/ in symfony/ai, from docs/components/platform/edenai.rst, and from the bridge source under src/platform/src/Bridge/EdenAi/. Namespaces, factory methods and result classes match the released package.

The streaming, tool calling, resume parsing and job timeout sections are built on stream.php, toolcall.php, resume-parser.php and speech-to-text-upload.php rather than on the shorter snippets in the reference page, so the guide shows what the bridge actually does in an application: an Agent with a toolbox, a local PDF uploaded transparently, and a job handle stored for a worker when the wait times out.

The YAML block was checked against src/ai-bundle/config/platform/edenai.php, which declares api_key as required and an optional http_client service id, and against the platform example in docs/bundles/ai-bundle.rst for the nesting.

Verification

• Every model id cited was checked against the live catalogue. Eight chat and embedding ids, all active. Twelve expert feature/subfeature/provider combinations, all present with is_working true.
• The expert identifiers are the bridge's own strings, taken from the Symfony documentation. For example the bridge writes audio/tts/... where our catalogue names the subfeature text_to_speech.
• All internal links resolve to existing pages.
• The SVG parses as XML and follows the existing 24x24 currentColor format.
• docs.json parses.
• No exhaustive model list, consistent with the other gateway pages. The guide points to the catalog and to the listing endpoint.
• No Python snippets, so the snippet test workflow has nothing new to execute.

References

• Symfony docs page: https://symfony.com/doc/current/ai/components/platform/edenai.html
• Release: https://github.com/symfony/ai/releases/tag/v0.14.0
• Package: https://packagist.org/packages/symfony/ai-eden-ai-platform

[mintlify]

Preview deployment for your docs. Learn more about Mintlify Previews.

Project	Status	Preview	Updated
edenai	🟢 Ready	View Preview	Sep 25, 2026, 12:50 PM

💡 Tip: Enable Automations to automatically generate PRs for you.

[coderabbitai]

Important

• 🔍 Trigger review

This repository does not receive automatic reviews because it has fewer than 10 stars.

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Advanced

Run ID: 737ec53e-5a8b-4f72-b369-39cbd6f256fb

---

_{Comment @coderabbitai help to get the list of available commands.}