This is an automated email from the ASF dual-hosted git repository. Croway pushed a commit to branch main in repository https://gitbox.apache.org/repos/asf/camel.git
commit 3da8716e9adbd9ec533a3157d38bc724a2c87c53 Author: Karol <[email protected]> AuthorDate: Thu May 28 23:59:12 2026 +0200 CAMEL-23500: Document camel-openai usage with OpenAI-compatible providers Add an "OpenAI-Compatible Providers" section to the OpenAI component docs with baseUrl-based configuration examples for OpenRouter, Ollama, LM Studio, and vLLM, so users discover that no separate component is needed. For OpenRouter, document selecting models via cross-provider identifiers and controlling provider routing/fallbacks through additionalBodyProperty (a JSON body value). Note that OpenRouter's optional HTTP-Referer/X-Title attribution headers cannot be set today, since the component does not expose custom HTTP request headers. --- .../src/main/docs/openai-component.adoc | 107 +++++++++++++++++++++ 1 file changed, 107 insertions(+) diff --git a/components/camel-ai/camel-openai/src/main/docs/openai-component.adoc b/components/camel-ai/camel-openai/src/main/docs/openai-component.adoc index 61a90d3c1d9f..64c9bc046e93 100644 --- a/components/camel-ai/camel-openai/src/main/docs/openai-component.adoc +++ b/components/camel-ai/camel-openai/src/main/docs/openai-component.adoc @@ -492,6 +492,113 @@ String-valued fields are set directly. Non-string fields (numbers, booleans, obj NOTE: This maps fields from the response message's additional properties (fields not part of the standard schema). Standard response fields like `content`, `role`, and `tool_calls` are not accessible through this option. +== OpenAI-Compatible Providers + +Because the component speaks the OpenAI API, you do not need a separate component to use third-party +gateways or local model servers that expose an OpenAI-compatible API. Point `baseUrl` at the provider, +set `apiKey` if it requires one, and use the same operations and options as with OpenAI. + +[cols="1,2,2",options="header"] +|=== +| Provider | `baseUrl` | Notes + +| OpenAI | `https://api.openai.com/v1` | Default; `baseUrl` can be omitted +| OpenRouter | `https://openrouter.ai/api/v1` | Multi-model gateway with provider routing and fallbacks +| Ollama | `http://localhost:11434/v1` | Local LLM server +| LM Studio | `http://localhost:1234/v1` | Local model runner +| vLLM | `http://localhost:8000/v1` | High-throughput, self-hosted serving engine +|=== + +=== Ollama (local) + +Ollama runs models locally and does not require an API key. + +[tabs] +==== +Java:: ++ +[source,java] +---- +from("direct:chat") + .setBody(constant("What is Apache Camel?")) + .to("openai:chat-completion?baseUrl=http://localhost:11434/v1&model=llama3.2";); +---- + +YAML:: ++ +[source,yaml] +---- +- to: + uri: openai:chat-completion + parameters: + baseUrl: http://localhost:11434/v1 + model: llama3.2 + userMessage: What is Apache Camel? +---- +==== + +For local embeddings, use an embedding model such as `nomic-embed-text` (see the *Embedding Models by +Provider* table below). + +=== LM Studio (local) + +LM Studio serves the model currently loaded in the app. Set `model` to the identifier shown in its UI. + +[source,java] +---- +from("direct:chat") + .to("openai:chat-completion?baseUrl=http://localhost:1234/v1&model=local-model";); +---- + +=== vLLM (self-hosted) + +[source,java] +---- +from("direct:chat") + .to("openai:chat-completion?baseUrl=http://localhost:8000/v1"; + + "&model=meta-llama/Llama-3.1-8B-Instruct"); +---- + +If vLLM was started with `--api-key`, pass the same value via the `apiKey` option. + +=== OpenRouter + +https://openrouter.ai[OpenRouter] is an OpenAI-compatible gateway that routes requests across many +model providers. Set `baseUrl` to its endpoint and select a model with a cross-provider identifier: + +[source,java] +---- +from("direct:chat") + .to("openai:chat-completion?baseUrl=https://openrouter.ai/api/v1"; + + "&apiKey={{openrouter.api.key}}" + + "&model=anthropic/claude-sonnet-4-20250514"); +---- + +==== Provider Routing + +OpenRouter accepts a `provider` object in the request body to control routing order and fallbacks. +Pass it through the `additionalBodyProperty` option as a JSON value — the component parses JSON-valued +properties and adds them to the request body: + +[source,yaml] +---- +- to: + uri: openai:chat-completion + parameters: + baseUrl: https://openrouter.ai/api/v1 + apiKey: "{{openrouter.api.key}}" + model: anthropic/claude-sonnet-4-20250514 + additionalBodyProperty.provider: '{"order":["anthropic","google"],"allow_fallbacks":false}' +---- + +[NOTE] +==== +OpenRouter's optional attribution headers (`HTTP-Referer` and `X-Title`, which identify your app on +the OpenRouter rankings) are sent as HTTP request headers, not body properties. The component does not +currently expose a way to set custom HTTP request headers, so they cannot be configured today. They +are optional and do not affect chat completions. +==== + == Compatibility This component works with any OpenAI API-compatible endpoint by setting the `baseUrl` parameter. This includes:
