Implement mcp-sse-client-server locally with ollama and mistral

[diegolovison]

As a developer, I wish to have an example working locally with ollama, and the model can be Mistral.

Example of mcp-client configuration:

quarkus.langchain4j.timeout=60s
quarkus.langchain4j.chat-model.provider=ollama
quarkus.langchain4j.ollama.chat-model.model-id=mistral
quarkus.langchain4j.ollama.base-url=http://localhost:11434
quarkus.langchain4j.mcp.default.transport-type=http
quarkus.langchain4j.mcp.default.url=http://localhost:9000/mcp/sse

All examples are using quarkus.langchain4j.openai.api-key and having one that is running locally is a super good fit for our samples.

[geoand]

We'd be more than happy to include such an example in our samples

[diegolovison]

Can it be on top of https://github.com/quarkiverse/quarkus-langchain4j/tree/main/samples/mcp-sse-client-server ?

[geoand]

I would prefer we don't have the exact same sample that simply uses a different model, but instead have something a little different

[diegolovison]

Nice. In this case, Can I keep https://github.com/quarkiverse/quarkus-langchain4j/tree/main/samples/mcp-sse-client-server as is and only remove the openai-api-key and use ollama with Mistral ?

[geoand]

Sure yeah

[diegolovison]

#1606