From 8c0d2a61fc785bdb7357596dcbd276614f4421c4 Mon Sep 17 00:00:00 2001 From: MVS-source Date: Thu, 16 Jul 2026 15:53:38 +0200 Subject: [PATCH 1/2] docs: add Eden AI integration guides for Pi and Open Code Review Add two new integration guides under the existing "Coding Agents" nav group: - Pi: MIT-licensed coding agent (registers Eden AI as a custom provider from an extension); the same catalog powers Flue - Open Code Review: AI code-review CLI with Eden AI as a built-in preset Both use the docs house-style env var EDEN_AI_API_KEY and point at https://api.edenai.run/v3. Includes square icon SVGs (currentColor) and docs.json nav entries. --- docs.json | 4 +- integration-logo/open-code-review-icondoc.svg | 1 + integration-logo/pi-icondoc.svg | 4 + v3/integrations/open-code-review.mdx | 94 ++++++++++++++++++ v3/integrations/pi.mdx | 96 +++++++++++++++++++ 5 files changed, 198 insertions(+), 1 deletion(-) create mode 100644 integration-logo/open-code-review-icondoc.svg create mode 100644 integration-logo/pi-icondoc.svg create mode 100644 v3/integrations/open-code-review.mdx create mode 100644 v3/integrations/pi.mdx diff --git a/docs.json b/docs.json index c24f4a7..2a3adeb 100644 --- a/docs.json +++ b/docs.json @@ -235,7 +235,9 @@ "v3/integrations/cline", "v3/integrations/codex-cli", "v3/integrations/continue-dev", - "v3/integrations/opencode" + "v3/integrations/opencode", + "v3/integrations/open-code-review", + "v3/integrations/pi" ] }, { diff --git a/integration-logo/open-code-review-icondoc.svg b/integration-logo/open-code-review-icondoc.svg new file mode 100644 index 0000000..ff16180 --- /dev/null +++ b/integration-logo/open-code-review-icondoc.svg @@ -0,0 +1 @@ + diff --git a/integration-logo/pi-icondoc.svg b/integration-logo/pi-icondoc.svg new file mode 100644 index 0000000..6d95214 --- /dev/null +++ b/integration-logo/pi-icondoc.svg @@ -0,0 +1,4 @@ + + + + diff --git a/v3/integrations/open-code-review.mdx b/v3/integrations/open-code-review.mdx new file mode 100644 index 0000000..9060e6d --- /dev/null +++ b/v3/integrations/open-code-review.mdx @@ -0,0 +1,94 @@ +--- +title: "Open Code Review" +icon: "/integration-logo/open-code-review-icondoc.svg" +description: "Use Open Code Review with Eden AI to review your code with 500+ AI models through one API." +--- + +import { TechArticleSchema } from "/snippets/TechArticleSchema.mdx"; + + + +Use Open Code Review with Eden AI to review your code with 500+ AI models through one API. + +## Overview + +Open Code Review (`ocr`) is Alibaba's open-source AI code-review tool. It reviews commits and pull requests through a unified provider system, and **Eden AI ships as a built-in provider preset** — supply a key and review your code with OpenAI, Anthropic, Google, Mistral and 500+ models, behind one key, with EU-based, GDPR-aligned inference and unified billing. + +## Installation + + +```bash npm +npm install -g @alibaba-group/open-code-review +``` + +```bash Install script +curl -fsSL https://raw.githubusercontent.com/alibaba/open-code-review/main/install.sh | sh +``` + + +## Configuration + +Eden AI is a built-in preset, so you only need a key. Configure it interactively: + + +```bash Interactive +ocr config provider # select "edenai" +ocr config model # pick an Eden AI model, e.g. anthropic/claude-sonnet-4-5 +``` + + +Or write the config directly (scripts / CI): + + +```bash CLI +ocr config set provider edenai +ocr config set providers.edenai.api_key YOUR_EDEN_AI_API_KEY +ocr config set providers.edenai.model anthropic/claude-sonnet-4-5 +``` + + +The `edenai` preset supplies the base URL (`https://api.edenai.run/v3`) and the OpenAI-compatible protocol automatically. Run `ocr llm providers` to list all built-in providers. If `EDEN_AI_API_KEY` is set in your environment, `ocr` picks it up automatically. + +## Available Models + +Pick any Eden AI model using the `provider/model` format: + +**OpenAI** +- `openai/gpt-4o` +- `openai/gpt-4o-mini` + +**Anthropic** +- `anthropic/claude-sonnet-4-5` +- `anthropic/claude-opus-4-5` + +**Google** +- `google/gemini-2.5-pro` +- `google/gemini-2.5-flash` + +**Mistral** +- `mistral/mistral-large-latest` +- `mistral/mistral-small-latest` + +## Environment Variables + + +```bash .env +EDEN_AI_API_KEY=your_api_key_here +``` + + +## Next Steps + +- [Chat Completions](/v3/llms/chat-completions) - Core LLM endpoint +- [List LLM Models](/v3/llms/listing-models) - Browse available providers and models +- [OpenAI SDK (Python)](/v3/integrations/openai-sdk-python) - Direct SDK usage diff --git a/v3/integrations/pi.mdx b/v3/integrations/pi.mdx new file mode 100644 index 0000000..3eb0b51 --- /dev/null +++ b/v3/integrations/pi.mdx @@ -0,0 +1,96 @@ +--- +title: "Pi" +icon: "/integration-logo/pi-icondoc.svg" +description: "Use Pi with Eden AI to power your coding agent (and Flue) with 500+ AI models through one API." +--- + +import { TechArticleSchema } from "/snippets/TechArticleSchema.mdx"; + + + +Use Pi with Eden AI to power your coding agent (and Flue) with 500+ AI models through one API. + +## Overview + +Pi is an MIT-licensed coding agent whose model catalog also powers Flue. Pi lets extensions register custom model providers, so you can add Eden AI with a small extension — no fork, no core change — and reach models from OpenAI, Anthropic, Google, Cohere, Meta and more behind one key, with EU-based, GDPR-aligned inference. The same provider flows through to Flue. + +## Installation + + +```bash Install script +curl -fsSL https://pi.dev/install.sh | sh +``` + +```bash npm +npm install -g --ignore-scripts @earendil-works/pi-coding-agent +``` + + +## Quick Start + +Register Eden AI as a custom provider from a Pi extension: + + +```typescript extension.ts +import { pi } from "@earendil-works/pi-coding-agent"; + +pi.registerProvider("edenai", { + name: "Eden AI", + api: "openai-completions", + baseUrl: "https://api.edenai.run/v3", + apiKey: process.env.EDEN_AI_API_KEY, + models: [ + "openai/gpt-4o", + "openai/gpt-4o-mini", + "anthropic/claude-sonnet-4-5", + "mistral/mistral-small-latest", + ], +}); +``` + + +Then select any `edenai/` in Pi. The same catalog is available in Flue. + +## Available Models + +Access models from multiple providers using the `provider/model` format: + +**OpenAI** +- `openai/gpt-4o` +- `openai/gpt-4o-mini` + +**Anthropic** +- `anthropic/claude-sonnet-4-5` +- `anthropic/claude-haiku-4-5` + +**Google** +- `google/gemini-2.5-pro` +- `google/gemini-2.5-flash` + +**Mistral** +- `mistral/mistral-large-latest` +- `mistral/mistral-small-latest` + +## Environment Variables + + +```bash .env +EDEN_AI_API_KEY=your_api_key_here +``` + + +## Next Steps + +- [Chat Completions](/v3/llms/chat-completions) - Core LLM endpoint +- [List LLM Models](/v3/llms/listing-models) - Browse available providers and models +- [OpenAI SDK (Python)](/v3/integrations/openai-sdk-python) - Direct SDK usage From f882970934c41d63ed754926ac362858a2f9b64a Mon Sep 17 00:00:00 2001 From: MVS-source Date: Thu, 16 Jul 2026 18:04:58 +0200 Subject: [PATCH 2/2] docs: use current model IDs (gpt-5.5, gpt-5-mini, claude-sonnet-5, gemini-3.5-flash, mistral-*) --- v3/integrations/open-code-review.mdx | 18 +++++++++--------- v3/integrations/pi.mdx | 20 ++++++++++---------- 2 files changed, 19 insertions(+), 19 deletions(-) diff --git a/v3/integrations/open-code-review.mdx b/v3/integrations/open-code-review.mdx index 9060e6d..a23147d 100644 --- a/v3/integrations/open-code-review.mdx +++ b/v3/integrations/open-code-review.mdx @@ -43,7 +43,7 @@ Eden AI is a built-in preset, so you only need a key. Configure it interactively ```bash Interactive ocr config provider # select "edenai" -ocr config model # pick an Eden AI model, e.g. anthropic/claude-sonnet-4-5 +ocr config model # pick an Eden AI model, e.g. anthropic/claude-sonnet-5 ``` @@ -53,7 +53,7 @@ Or write the config directly (scripts / CI): ```bash CLI ocr config set provider edenai ocr config set providers.edenai.api_key YOUR_EDEN_AI_API_KEY -ocr config set providers.edenai.model anthropic/claude-sonnet-4-5 +ocr config set providers.edenai.model anthropic/claude-sonnet-5 ``` @@ -64,20 +64,20 @@ The `edenai` preset supplies the base URL (`https://api.edenai.run/v3`) and the Pick any Eden AI model using the `provider/model` format: **OpenAI** -- `openai/gpt-4o` -- `openai/gpt-4o-mini` +- `openai/gpt-5.5` +- `openai/gpt-5-mini` **Anthropic** -- `anthropic/claude-sonnet-4-5` -- `anthropic/claude-opus-4-5` +- `anthropic/claude-sonnet-5` +- `anthropic/claude-opus-4-8` **Google** - `google/gemini-2.5-pro` -- `google/gemini-2.5-flash` +- `google/gemini-3.5-flash` **Mistral** -- `mistral/mistral-large-latest` -- `mistral/mistral-small-latest` +- `mistral/mistral-large-2512` +- `mistral/mistral-small-2603` ## Environment Variables diff --git a/v3/integrations/pi.mdx b/v3/integrations/pi.mdx index 3eb0b51..2d092d8 100644 --- a/v3/integrations/pi.mdx +++ b/v3/integrations/pi.mdx @@ -50,10 +50,10 @@ pi.registerProvider("edenai", { baseUrl: "https://api.edenai.run/v3", apiKey: process.env.EDEN_AI_API_KEY, models: [ - "openai/gpt-4o", - "openai/gpt-4o-mini", - "anthropic/claude-sonnet-4-5", - "mistral/mistral-small-latest", + "openai/gpt-5.5", + "openai/gpt-5-mini", + "anthropic/claude-sonnet-5", + "mistral/mistral-small-2603", ], }); ``` @@ -66,20 +66,20 @@ Then select any `edenai/` in Pi. The same catalog is available in Flue. Access models from multiple providers using the `provider/model` format: **OpenAI** -- `openai/gpt-4o` -- `openai/gpt-4o-mini` +- `openai/gpt-5.5` +- `openai/gpt-5-mini` **Anthropic** -- `anthropic/claude-sonnet-4-5` +- `anthropic/claude-sonnet-5` - `anthropic/claude-haiku-4-5` **Google** - `google/gemini-2.5-pro` -- `google/gemini-2.5-flash` +- `google/gemini-3.5-flash` **Mistral** -- `mistral/mistral-large-latest` -- `mistral/mistral-small-latest` +- `mistral/mistral-large-2512` +- `mistral/mistral-small-2603` ## Environment Variables