From 298448b54936f62dcf636d390d74ea34c29c4c15 Mon Sep 17 00:00:00 2001 From: Elias TOURNEUX Date: Mon, 17 Nov 2025 18:02:34 -0500 Subject: [PATCH] Create OVHcloud AI Endpoints community documentation --- .../model-providers/ovhcloud-ai-endpoints.md | 118 ++++++++++++++++++ .../model-providers/ovhcloud-ai-endpoints.md | 5 + docs/user-guide/quickstart.md | 1 + mkdocs.yml | 2 + 4 files changed, 126 insertions(+) create mode 100644 docs/community/model-providers/ovhcloud-ai-endpoints.md create mode 100644 docs/user-guide/concepts/model-providers/ovhcloud-ai-endpoints.md diff --git a/docs/community/model-providers/ovhcloud-ai-endpoints.md b/docs/community/model-providers/ovhcloud-ai-endpoints.md new file mode 100644 index 00000000..79b5e89d --- /dev/null +++ b/docs/community/model-providers/ovhcloud-ai-endpoints.md @@ -0,0 +1,118 @@ +# OVHcloud AI Endpoints + +{{ community_contribution_banner }} + +[OVHcloud](https://www.ovhcloud.com) is a global player and the leading European cloud provider operating over 450,000 servers within 40 data centers across 4 continents to reach 1.6 million customers in over 140 countries. [OVHcloud AI Endpoints](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/) offers access to various models with sovereignty, data privacy and GDPR compliance. + +OVHcloud AI Endpoints provides OpenAI-compatible API access to a wide range of language models. This allows easy and portable integration with the Strands Agents SDK using the familiar OpenAI interface. + +## Installation + +The Strands Agents SDK provides access to OVHcloud AI Endpoints models through the OpenAI compatibility layer, configured as an optional dependency. To install, run: + +```bash +pip install 'strands-agents[openai]' strands-agents-tools +``` + +## Usage + +After installing the `openai` package, you can import and initialize the Strands Agents' OpenAI-compatible provider for OVHcloud AI Endpoints models as follows: + +```python +from strands import Agent +from strands.models.openai import OpenAIModel +from strands_tools import calculator + +model = OpenAIModel( + client_args={ + "api_key": "", # Optional: empty string or omit for free tier with rate limit + "base_url": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", + }, + model_id="Meta-Llama-3_3-70B-Instruct", # See catalog for available models + params={ + "max_tokens": 5000, + "temperature": 0.1 + } +) + +agent = Agent(model=model, tools=[calculator]) +agent("What is 2+2?") +``` + +### Using with an API Key + +If you have an API key, you can use it to access higher rate limits and additional features: + +```python +model = OpenAIModel( + client_args={ + "api_key": "", # Your OVHcloud AI Endpoints API key + "base_url": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1", + }, + model_id="Meta-Llama-3_3-70B-Instruct", + params={ + "max_tokens": 5000, + "temperature": 0.1 + } +) +``` + +## Configuration + +### Client Configuration + +The `client_args` configure the underlying OpenAI-compatible client. When using OVHcloud AI Endpoints, you must set: + +* `api_key`: Your OVHcloud AI Endpoints API key (optional). + * **Free tier**: You can use an empty string `""` or omit the `api_key` parameter entirely to access the API with rate limits. + * **With API key**: To generate an API key, go to the [OVHcloud Manager](https://ovh.com/manager), then navigate to **Public Cloud** → **AI & Machine Learning** → **AI Endpoints** → **API keys**. +* `base_url`: `https://oai.endpoints.kepler.ai.cloud.ovh.net/v1` + +### Model Configuration + +The `model_config` specifies which OVHcloud AI Endpoints model to use and any additional parameters. + +| Parameter | Description | Example | Options | +| ---------- | ------------------------- | ------------------------------------------ | ------------------------------------------------------------------ | +| `model_id` | Model name | `Meta-Llama-3_3-70B-Instruct` | See [OVHcloud AI Endpoints Catalog](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/) | +| `params` | Model-specific parameters | `{"max_tokens": 5000, "temperature": 0.7}` | Standard OpenAI-compatible parameters | + +## Getting an API Key + +To generate an API key for OVHcloud AI Endpoints: + +1. Go to the [OVHcloud Manager](https://ovh.com/manager) +2. Navigate to **Public Cloud** section +3. Select **AI & Machine Learning** → **AI Endpoints** +4. Go to **API keys** section +5. Create a new API key + +You can use the API for free with rate limits if you don't provide an API key or use an empty string. + +## Troubleshooting + +### `ModuleNotFoundError: No module named 'openai'` + +You must install the `openai` dependency to use this provider: + +```bash +pip install 'strands-agents[openai]' +``` + +### Unexpected model behavior? + +Ensure you're using a model ID from the [OVHcloud AI Endpoints Catalog](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/), and your `base_url` is set to `https://oai.endpoints.kepler.ai.cloud.ovh.net/v1`. + +### Rate limit errors + +If you encounter rate limit errors, consider: +- Using an API key for higher rate limits +- Reviewing the [OVHcloud AI Endpoints documentation](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/) for rate limit details + +## References + +* [OVHcloud AI Endpoints](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/) +* [OVHcloud AI Endpoints Catalog](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/) +* [OVHcloud Manager](https://ovh.com/manager) +* [Strands Agents API](../../api-reference/models.md) + diff --git a/docs/user-guide/concepts/model-providers/ovhcloud-ai-endpoints.md b/docs/user-guide/concepts/model-providers/ovhcloud-ai-endpoints.md new file mode 100644 index 00000000..e4e25944 --- /dev/null +++ b/docs/user-guide/concepts/model-providers/ovhcloud-ai-endpoints.md @@ -0,0 +1,5 @@ + + + +This guide has moved to [community/model-providers/ovhcloud-ai-endpoints](../../../community/model-providers/ovhcloud-ai-endpoints.md). + diff --git a/docs/user-guide/quickstart.md b/docs/user-guide/quickstart.md index 43caa9b9..fd89c25e 100644 --- a/docs/user-guide/quickstart.md +++ b/docs/user-guide/quickstart.md @@ -445,6 +445,7 @@ Strands Agents supports several other model providers beyond Amazon Bedrock: - **[Cohere community](../community/model-providers/cohere.md)** - Use Cohere models through an OpenAI compatible interface - **[CLOVA Studio community](../community/model-providers/clova-studio.md)** - Korean-optimized AI models from Naver Cloud Platform - **[FireworksAI community](../community/model-providers/fireworksai.md)** - Use FireworksAI models through an OpenAI compatible interface +- **[OVHcloud AI Endpoints community](../community/model-providers/ovhcloud-ai-endpoints.md)** - Use OVHcloud AI Endpoints models with sovereignty, data privacy and GDPR compliance. - **[Custom Providers](concepts/model-providers/custom_model_provider.md)** - Build your own provider for specialized needs ## Capturing Streamed Data & Events diff --git a/mkdocs.yml b/mkdocs.yml index bdc84fd2..7aa6ceb9 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -104,6 +104,7 @@ nav: - Cohere community: user-guide/concepts/model-providers/cohere.md # ALWAYS ADD A SPACE BEFORE COMMUNITY - CLOVA Studio community: user-guide/concepts/model-providers/clova-studio.md - FireworksAI community: user-guide/concepts/model-providers/fireworksai.md + - OVHcloud AI Endpoints community: user-guide/concepts/model-providers/ovhcloud-ai-endpoints.md - Streaming: - Overview: user-guide/concepts/streaming/overview.md - Async Iterators: user-guide/concepts/streaming/async-iterators.md @@ -161,6 +162,7 @@ nav: - Cohere: community/model-providers/cohere.md - CLOVA Studio: community/model-providers/clova-studio.md - Fireworks AI: community/model-providers/fireworksai.md + - OVHcloud AI Endpoints: community/model-providers/ovhcloud-ai-endpoints.md - Session Managers: - Amazon AgentCore Memory: community/session-managers/agentcore-memory.md - Valkey/Redis: community/session-managers/strands-valkey-session-manager.md