Implement mcp-sse-client-server locally with ollama and mistral #1606
+11
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
Author
|
First error: |
diegolovison
changed the title
Collaborator
|
Thanks! @jmartisk do you want to take a look at the bug that this PR surfaces? |
Collaborator
|
I pushed an update to the PR, but it seems that the model you have chosen does not support tools: |
Contributor
Author
My example started from https://github.com/eugenp/tutorials/blob/master/quarkus-modules/quarkus-mcp-langchain/quarkus-mcp-client/src/main/resources/application.properties I see: |
Collaborator
|
Right, I changed it because those values are wrong |
Contributor
Author
|
Updated the configuration It is slow on my machine, but I have also |
Contributor
Author
|
Can |
Collaborator
|
I was able to get your sample to work and now I'm looking into the warning you are seeing.
No, they are totally different things |
Collaborator
|
@diegolovison What you can do is the following: quarkus.langchain4j.timeout=1000s
quarkus.vertx.max-worker-execute-time=${quarkus.langchain4j.timeout} |
Contributor
Author
|
Ready for review |
geoand
reviewed
Jul 11, 2025
samples/mcp-sse-client-server/mcp-client/src/main/resources/application.properties
Outdated
Show resolved
Hide resolved
geoand
approved these changes
Jul 11, 2025
cescoffier
requested changes
Jul 11, 2025
Collaborator
cescoffier
left a comment
cescoffier
left a comment
There was a problem hiding this comment.
Could you use a profile to avoid overriding the default implementation, like %ollama.
This comment has been minimized.
This comment has been minimized.
Contributor
Author
Do you mean something like ( First time contributing to quarkus / I read https://quarkus.io/guides/config-reference ): But how about <dependency>
<groupId>io.quarkiverse.langchain4j</groupId>
<artifactId>quarkus-langchain4j-openai</artifactId>
</dependency>
<dependency>
<groupId>io.quarkiverse.langchain4j</groupId>
<artifactId>quarkus-langchain4j-ollama</artifactId>
</dependency> |
Collaborator
|
Yes, you will need both extensions. We would need to see if each profile needs to be extended a bit to ensure it works in both cases. We do something similar in https://github.com/cescoffier/langchain4j-deep-dive/blob/main/2-ai-services/5-langchain4j-ai-service-chat-memory/src/main/resources/application.properties |
Contributor
Author
|
On Maven, it must be a different dependency. The default should be |
Collaborator
They can if you set |
Contributor
Author
|
Done |
cescoffier
approved these changes
Jul 14, 2025
cescoffier
approved these changes
Jul 14, 2025
Status for workflow
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Implement mcp-sse-client-server locally with ollama and mistral
See the discussion on #1605