Anush Hey @yusuf-eren. I’m from the Qdrant team (anush.shetty@qdrant.com). We’d be happy to help build/maintain this integration for the community. Looking forward to hearing from the Vercel AI SDK team.
Gregor @anush a community plugin would be great, we will be happy to add it to the list of AI SDK community providers: ai-sdk.dev/providers/community-providers. The AI SDK does support reranking and embedding, but we do not have a store abstraction built into the AI SDK, that’s currently out of scope. Maybe you can add a guide on how to use Qdrant with AI SDK using your community provider and vector store?
Anush Hey @gr2m I’m a fan of your work on Octokit.js and Semantic Release. Thank you. but we do not have a store abstraction built into the AI SDK, that’s currently out of scope. I see. Building a plugin without a common abstraction means users won’t have the ability to swap the vector store providers. Like with other components. How about we have examples/guides on how to use the AI SDK with the Qdrant client instead? UPDATE: npmjs.com/package/qdrant-ai-sdk github.com/vercel/ai/pull/25237
Pauline P. Narvas The NS_BASE_STREAM_CLOSED error typically occurs when the MCP client connection is closed prematurely. When you're using MCP tools with streaming, the client needs to stay open until the entire response completes, if it closes early, you'll hit this error. Here's what I'd recommend checking: Make sure your MCP client isn't timing out or disconnecting before the stream finishes Verify that your connection handling code keeps the client alive throughout the entire streaming response Check if there are any timeout settings that might be causing the connection to close early Let me know if you hav
phanithlim Thanks Pauline P. Narvas for the response! I’ve been stuck on this for about 3 days now and still can't resolve it. I was previously using experimental_createMCPClient, and it worked perfectly. However, since I updated my code to use the standard createMCPClient, I began facing the NS_BASE_STREAM_CLOSED issue mentioned above. The connection seems to drop the moment the LLM starts streaming the tool output back to the UI. Since I am using streamText with toUIMessageStreamResponse(), I suspect the new createMCPClient handles transport lifecycles differently, causing it to be garbage collected or
Pauline P. Narvas Thanks for sharing, Steve! This is super useful for everyone building with the AI SDK. Oh, and welcome to the Vercel Community 👋
Stevef24 Thanks Pauline, really appreciate it 😀 I have been a member for quite a while now and posted a few times last year, but I had to take a few months off due to health, but I’m back now and excited to start posting more and being more involved in the community!
Anshuman Bhardwaj Hi @drewradcliff, welcome to the Vercel Community! Thanks for taking the initiative and sharing it with the community! I'll also share this with our AI SDK team.
Pauline P. Narvas @drewradcliff Could you give a summary of what the use case could be here for the community? It would be helpful as people go through the community / search on Google :D
Pauline P. Narvas Hey @drewradcliff! Just wanted to check in on your AI SDK model router. Have you had a chance to get any feedback, or do you still need help? Excited to see how it's coming along and what use cases you're thinking about! Thanks for being part of the community!
Anshuman Bhardwaj Hi @tal32123, I'm not sure if I understand your concern correctly. There's not enough info here for us to see what's causing the error. We have another post with suggested details to include. community.vercel.com/t/how-to-get-good-answers/158 Please take a look and then add whatever you can here to help the rest of us see what's going wrong
Anshuman Bhardwaj Hi @tal32123, I wanted to check in regarding your question about frontend tools and stop reasons. Have you found a solution, or do you still need assistance? Let me know if you need more details.
Pauline P. Narvas For the “stop reason length”, this means your response hit the token limit before completing. Try increasing maxTokens significantly (like 4000+ depending on your model) or switch to a model with a larger context window.
Pauline P. Narvas Hey @tal32123! Just checking in to see if you still need help with your workflow and prompts. Have you found a solution, or is there anything specific you’d like to dive deeper into? Excited to help!