update: update Koog and MCP descriptions #5177
Conversation
koshachy
force-pushed
the
update-ai-development-overview
branch
from
3e47f14 to
2d3a65e
Compare
devcrocod
left a comment
devcrocod
left a comment
There was a problem hiding this comment.
lgtm 👍
left a couple of comments
| } | ||
| ``` | ||
|
|
||
| <a href="https://www.google.com/url?q=https://docs.koog.ai/getting-started/"><img src="get-started-with-koog.svg" width="700" alt="Get started with Koog" style="block"/></a> |
There was a problem hiding this comment.
Why is this link being used?
When I followed it, I got a "Redirect Notice", was that intentional?
| } | ||
| ``` | ||
|
|
||
| <a href="https://www.google.com/url?q=https://docs.koog.ai/getting-started/"><img src="get-started-with-koog.svg" width="700" alt="Get started with Koog" style="block"/></a> |
There was a problem hiding this comment.
width="700"
Wouldn’t using a fixed width break the layout on mobile devices?
| such as W&B Weave and Langfuse for monitoring and debugging AI applications. | ||
| * **LLM switching and seamless history adaptation**. Koog allows switching to a different LLM with a new set of tools | ||
| at any point without losing the existing conversation history. | ||
| It also enables rerouting between multiple LLM providers, including OpenAI, Anthropic, Google, and others. |
There was a problem hiding this comment.
I think it would be worth mentioning the ability to run agents locally. I couldn’t find "local" or "ollama" mentioned
| @@ -1,4 +1,4 @@ | |||
| [//]: # (title: Build a Kotlin app that uses Spring AI to answer questions based on documents stored in Qdrant — tutorial) | |||
| [//]: # (title: Create a Kotlin app that answers questions with Spring AI — tutorial) | |||
There was a problem hiding this comment.
Should keep qdrant in the title?
| * [OpenAI](https://github.com/openai/openai-java) — official Java SDK for the OpenAI API. It covers responses and chat, images, and audio. | ||
| * [Anthropic (Claude)](https://github.com/anthropics/anthropic-sdk-java) — official Java SDK for the Claude Messages API. It includes modules for Vertex AI and Bedrock integrations. |
There was a problem hiding this comment.
Do you think it’s worth mentioning that these sdk (openai and anthropic) are written entirely in kotlin?
| * Provide context for LLMs in a structured and standardized way, separating context handling from the interaction with LLMs. | ||
| * Build MCP clients that consume resources from the existing servers. | ||
| * Create MCP servers that expose prompts, tools, and resources for LLMs. | ||
| * Use standard communication transports such as stdio, SSE, and WebSocket. |
There was a problem hiding this comment.
FYI
the mcp specification currently defines two transports: stdio and streamable. sse has been deprecated.
In our mcp kotlin sdk, streamable support is only partially implemented right now, but it will be fully completed within the next month. So the statement is technically correct at the moment, but it will need to be updated soon
No description provided.