docs: add Eden AI integration guide for any-llm (Mozilla AI)

[MVS-source]

What

New integration guide for any-llm (Mozilla AI's unified LLM interface), under AI Frameworks.

Eden AI is a built-in any-llm provider (src/any_llm/providers/edenai/), so this doc shows how to use it.

How it works

• Model selection: completion(model="edenai:<provider>/<model>", ...) — the edenai: prefix + Eden AI's provider/model id.
• The provider auto-uses https://api.edenai.run/v3 and reads the key from EDENAI_API_KEY (ENV_API_KEY_NAME = "EDENAI_API_KEY"). Optional EDENAI_API_BASE override.
• Install: pip install 'any-llm-sdk[edenai]'.
• Supports completion, streaming, embeddings and moderation.

Files

• v3/integrations/any-llm.mdx (new)
• integration-logo/any-llm-icondoc.svg (new, square, currentColor — placeholder mark, swap for an official logo if available)
• docs.json — any-llm added to AI Frameworks

Conventions

• Format matches existing integration docs (<TechArticleSchema> + <CodeGroup>).
• Env var EDENAI_API_KEY (tool-mandated by the provider).
• Current model IDs (gpt-5.5, claude-sonnet-5, mistral-large-2512, gemini-3.5-flash).
• Python snippets marked {/* skip-test */} (any-llm-sdk isn't in tests/requirements-lock.txt).

Summary by CodeRabbit

• New Features
  • Added documentation for integrating any-llm (Mozilla AI) with Eden AI.
  • Included setup instructions, quick-start examples, model switching, streaming, embeddings, and configuration guidance.
  • Added the integration to the V3 documentation navigation under AI Frameworks.

[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: Pro Plus

Run ID: 4c5957d3-1d65-4150-af32-b72eb71081ba

Walkthrough

Added documentation for using any-llm with Eden AI, including setup, model usage, streaming, embeddings, environment variables, and related links. Registered the new page in the V3 AI Frameworks navigation.

Changes

any-llm integration documentation

Layer / File(s)	Summary
any-llm integration page v3/integrations/any-llm.mdx	Adds page metadata, structured article schema, installation and usage examples, model switching, streaming, supported model IDs, embeddings, environment variables, and next-step links.
AI Frameworks navigation registration docs.json	Adds v3/integrations/any-llm to the V3 AI Frameworks navigation list.

Estimated code review effort: 1 (Trivial) | ~5 minutes

Possibly related PRs

• edenai/docs#70: Adds another Eden AI integration page and updates V3 integrations navigation.
• edenai/docs#75: Adds a new V3 AI Frameworks integration and updates the same navigation list.
• edenai/docs#76: Registers another Eden AI integration under V3 AI Frameworks.

Suggested reviewers: tristantelleb

Poem

I’m a rabbit with docs in my den,
Now any-llm hops into Eden.
Models stream bright, embeddings take flight,
Navigation points readers right.
Sniff, click, and code with delight!

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly matches the main change: adding an Eden AI integration guide for any-llm.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch integrations/any-llm

---

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

[mintlify]

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

Project	Status	Preview	Updated (UTC)
edenai	🟢 Ready	View Preview	Jul 20, 2026, 7:59 AM

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

[coderabbitai]

Actionable comments posted: 1

🧹 Nitpick comments (1)

v3/integrations/any-llm.mdx (1)

71-86: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low value

Remove redundant <CodeGroup> wrappers for single snippets.

As per coding guidelines, the <CodeGroup> component is intended for multi-language code snippet tabs. Wrapping a single code block in a <CodeGroup> creates a redundant single-tab UI. Consider removing the <CodeGroup> wrapper for standalone snippets.

• v3/integrations/any-llm.mdx#L71-L86: Remove the <CodeGroup> tags surrounding this single Python snippet.
• v3/integrations/any-llm.mdx#L92-L108: Remove the <CodeGroup> tags surrounding this single Python snippet.
• v3/integrations/any-llm.mdx#L135-L147: Remove the <CodeGroup> tags surrounding this single Python snippet.
• v3/integrations/any-llm.mdx#L151-L157: Remove the <CodeGroup> tags surrounding this single .env snippet.

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@v3/integrations/any-llm.mdx` around lines 71 - 86, Remove the redundant
CodeGroup wrappers around each standalone snippet: v3/integrations/any-llm.mdx
lines 71-86, 92-108, 135-147, and 151-157. Leave each Python or .env fenced code
block intact while deleting only its surrounding CodeGroup tags.

Source: Coding guidelines

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@v3/integrations/any-llm.mdx`:
- Line 49: Replace the generic your_api_key_here placeholder with api_token or
sandbox_api_token at v3/integrations/any-llm.mdx lines 49-49 and 153-153, using
api_token for production examples and sandbox_api_token for testing examples.

---

Nitpick comments:
In `@v3/integrations/any-llm.mdx`:
- Around line 71-86: Remove the redundant CodeGroup wrappers around each
standalone snippet: v3/integrations/any-llm.mdx lines 71-86, 92-108, 135-147,
and 151-157. Leave each Python or .env fenced code block intact while deleting
only its surrounding CodeGroup tags.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: 44f64792-6e91-4be9-9af0-406e5f42de6e

📥 Commits

Reviewing files that changed from the base of the PR and between aaf25fe and bd6eb82.

⛔ Files ignored due to path filters (1)

• integration-logo/any-llm-icondoc.svg is excluded by !**/*.svg

📒 Files selected for processing (2)

• docs.json
• v3/integrations/any-llm.mdx

[coderabbitai]

📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win

Use standardized token placeholders.

As per coding guidelines, token types in code examples should be distinguished using api_token for production and sandbox_api_token for testing (no real provider calls), rather than generic placeholders like your_api_key_here.

• v3/integrations/any-llm.mdx#L49-L49: Replace your_api_key_here with api_token (or sandbox_api_token).
• v3/integrations/any-llm.mdx#L153-L153: Replace your_api_key_here with api_token (or sandbox_api_token).

📍 Affects 1 file

• v3/integrations/any-llm.mdx#L49-L49 (this comment)
• v3/integrations/any-llm.mdx#L153-L153

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@v3/integrations/any-llm.mdx` at line 49, Replace the generic
your_api_key_here placeholder with api_token or sandbox_api_token at
v3/integrations/any-llm.mdx lines 49-49 and 153-153, using api_token for
production examples and sandbox_api_token for testing examples.

Source: Coding guidelines

[mintlify]

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

Project	Status	Preview	Updated (UTC)
edenai	🟡 Building	–	Jul 20, 2026, 7:58 AM

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

[MVS-source]

Rebased onto current main and pushed as eaeef11. This was CONFLICTING and is now MERGEABLE, so it is reviewable again.

The conflict was one hunk in docs.json: the AI Frameworks group had gained haystack and atomic-agents since this branch was cut. Resolved by keeping both and appending any-llm last, which matches the add-order the group already uses. The JSON parses and the rendered nav now lists 24 integration pages including this one.

I re-verified the content rather than just resolving the conflict, since the guide was five weeks old:

• All ten model ids in the page are still served. The nine chat ids were checked against the live /v3/models and openai/text-embedding-3-small against /v3/embeddings/models, which is a separate catalogue.
• pip install 'any-llm-sdk[edenai]' is valid. The extra is declared in the published wheel for 1.26.0. Note for anyone checking this the way I first did: the extra is empty, so it does not appear in requires_dist on the PyPI JSON API and looks missing. It is in Provides-Extra in the wheel metadata.
• The provider in any-llm main still confirms every claim on the page: base URL https://api.edenai.run/v3, EDENAI_API_KEY, the optional EDENAI_API_BASE override, provider key edenai, and streaming plus embeddings both supported.
• The four internal links resolve to real pages, and the Mintlify preview renders the page correctly.

I also set datePublished and dateModified to today, matching what the neighbouring pages do (they carry the date the page landed in the repo, not the date it was drafted).

One thing that is not mine: Execution Tests is red, and it is red on every PR in this repo since around 11 August. It fails in pytest_sessionstart, before any test runs, on tests/helpers/api.py getting 401 Unauthorized from https://staging-api.edenai.run/v2/user/custom_token/. Same error on #96, #95, #94, #93, #92, #91, #90 and #98. The last green run was #88 on 4 August. Looks like the staging credential in the CI secrets expired or was rotated, and it is blocking the whole docs pipeline, not just this PR. Worth fixing separately.

The provider itself has been merged upstream since 17 July, so this page is the only thing still missing.