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 c3a9b61112cdb4e612e814aed31247864eaac322 Author: Karol <[email protected]> AuthorDate: Sat May 30 20:08:33 2026 +0200 CAMEL-23500: Add install commands and provider links per review feedback Per review on PR #23614: - Ollama: link to ollama.com and the "ollama run llama3.2" command - LM Studio: link to lmstudio.ai - vLLM: link to docs.vllm.ai, "pip install vllm" + "vllm serve" command, plus a note on the vllm-mlx variant for Apple Silicon with an example command --- .../src/main/docs/openai-component.adoc | 26 ++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) 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 64c9bc046e93..c5b2e8509375 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 @@ -511,7 +511,13 @@ set `apiKey` if it requires one, and use the same operations and options as with === Ollama (local) -Ollama runs models locally and does not require an API key. +https://ollama.com[Ollama] runs models locally and does not require an API key. Install Ollama and +pull the model used in the example below: + +[source,bash] +---- +ollama run llama3.2 +---- [tabs] ==== @@ -542,7 +548,8 @@ 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. +https://lmstudio.ai[LM Studio] serves the model currently loaded in the app. Set `model` to the +identifier shown in its UI. [source,java] ---- @@ -552,6 +559,14 @@ from("direct:chat") === vLLM (self-hosted) +https://docs.vllm.ai[vLLM] is a high-throughput LLM serving engine. Install it with `pip install vllm` +and start the model used in the example below: + +[source,bash] +---- +vllm serve meta-llama/Llama-3.1-8B-Instruct --port 8000 +---- + [source,java] ---- from("direct:chat") @@ -561,6 +576,13 @@ from("direct:chat") If vLLM was started with `--api-key`, pass the same value via the `apiKey` option. +On Apple Silicon, the `vllm-mlx` variant uses Apple's MLX framework and runs the same way: + +[source,bash] +---- +vllm-mlx serve mlx-community/Qwen2.5-7B-Instruct-4bit --port 8000 +---- + === OpenRouter https://openrouter.ai[OpenRouter] is an OpenAI-compatible gateway that routes requests across many
