8,786 questions
0
votes
0
answers
23
views
Plivo AI Agent not calling human agent after transferCall redirect
I have an inbound call flow where:
Incoming call β handled by /incoming, which connects the call to Ultravox AI through a .
AI Agent conversation β if the caller asks for a human, the AI triggers /...
-2
votes
0
answers
15
views
Sending same image in parallel to Meta-Llama-3.2-90B-Vision-Instruct yields different results [closed]
We have a use case of a PDF file with 5 pages.
Each page has the SAME image.
We crop the image from each page and perform in parallel 5 requests with same prompt for that image.
We ensured that the ...
- 27
-1
votes
0
answers
40
views
Why accuracy stagnates or moves extremely slow after a certain number of epochs? [closed]
I managed to train a VIT model from scratch on CIFAR-10 achieving a maximum accuracy of 92% which is an all-time highest using a light VIT. (will share experiment findings in a later post).
One trend ...
-2
votes
0
answers
22
views
AWS Classifying Document Types [closed]
I need to classify what type of documents based on the documents characteristics like forms, tables, texts and fields once I get the document in AWS S3.
Can I use and train AI for this? If so, can you ...
-2
votes
0
answers
29
views
How to increase quota and limit for my personal account for multimodalembedding in google vertex ai [closed]
Iβm new here.
Iβm using multimodalembedding in google vertex ai for my image vector search to generate vector for my images but it get error quota limit exceeded despite that I just put only image to ...
0
votes
0
answers
25
views
How to Fix the Speech to text Package issue in Flutter?
I am trying to use the speech_to_text package in my Flutter project to convert voice input into text. However, I am facing issues when initializing or starting the speech recognition. The app either ...
-3
votes
0
answers
58
views
LLM, AI integration [closed]
When calling openai.ChatCompletion.create with more than ~4000 tokens, I get InvalidRequestError: This model's maximum context length is 4096 tokens. What is the recommended way in Python to trim or ...
-4
votes
0
answers
46
views
How to implement a segmentation model for medical project? [closed]
A CSE UG here, doing polyp-detection using colonoscopy videos as a project. We have successfully implemented detection using YOLO model by using kvasir-SEG dataset. Now, we are facing difficulties on ...
0
votes
1
answer
120
views
LangGraph: The parallel mapReduce task implemented by langGraph has an incorrect execution order
Background
The node relationships in the graph are as follows:
enter image description here
Parallel operation of nodes b and c
No blocking in nodes b and b2
Node C has sleep
Question:
Why should ...
0
votes
0
answers
31
views
Cursor AI Agent terminal never stops (spinner keeps running) after dotnet build finishes
Iβm running a .NET project from the Cursor AI Agent terminal. The build finishes (I see the final summary line), but the Agentβs terminal keeps βrunningβ forever (spinner never stops). I have to press ...
- 697
1
vote
1
answer
38
views
How to upsert documents to Flowise document store using API Loader instead of file upload?
βm currently working with Flowise and trying to update my document store via API requests.
I followed the documentation here.
Specifically, I want to try Scenario 2: In the same document store, ...
- 41
-2
votes
0
answers
47
views
MobileNetV3Large with (224,224,1) input works, but channel mismatch error on testing β why? [closed]
I created a Keras MobileNetV3Large model with ImageNet weights and explicitly defined the input layer as having shape (224,224,1) to accept grayscale images. When creating the model, no errors were ...
- 1
0
votes
0
answers
45
views
Configuring MCP with Microsoft.Extensions.AI
Using the following Microsoft template as my base:
https://devblogs.microsoft.com/dotnet/announcing-dotnet-ai-template-preview1/
I want to be able to add my local stdio MCP server as a tool but can't ...
- 746
0
votes
0
answers
39
views
How to accelerate my corpus embedding to the chromadb
I have the corpus.jsonl which has 6.5gb storage.And i use the one h100 gpu to embedding the corpus to the chromadb,but it seems very slowly.I want to find how can i accelerate the progress(gpu,cpu,io)....
- 23
0
votes
2
answers
106
views
How to use DI with Semantic Kernel plugins?
I'm trying out Microsoft's Semantic Kernel for chat completion in a Blazor app. I added a service that uses EF Core:
public interface ISearchService
{
Task<string?> GetCustomerAsync(string ...
- 1,016