8,789 questions
- Bountied 0
- Unanswered
- Frequent
- Score
- Trending
- Week
- Month
- Unanswered (my tags)
-1
votes
1
answer
93
views
Why does PyTorch-based LLM inference remain non-deterministic during inference even with fixed seeds and greedy decoding? [closed]
I am running inference on a locally hosted large language model using PyTorch. The same prompt is passed repeatedly with identical generation parameters, yet the generated output differs slightly ...
4
votes
1
answer
81
views
Symfony AI: How to add additional models for the LM Studio bridge?
I’m working with Symfony AI and the LM Studio bridge to manage my language models locally.
My goal is to add custom models that are not included in Symfony’s default ModelCatalog.
My YAML ...
Advice
1
vote
4
replies
79
views
Looking for ideas for a Master’s thesis topic in Data Science & AI (Banking – Fraud Detection – PDF Analysis)
I’m a final-year Data Science & AI Master’s student, currently defining my thesis topic. I’ll be doing my research in a bank, working on fraud detection, with a focus on PDF document analysis.
I’m ...
Tooling
0
votes
4
replies
64
views
I am confused, when to use tensorflow and pytorch
I am always confused between tensorflow and pytorch when to use which, because both are used for same task but when to use tensorflow and pytorch, like situation oriented. Some people's said suggested ...
-2
votes
0
answers
68
views
Integration of ml model to flutter application that works totally offline [closed]
this application is totally offline and i tried to add ml model to the application but it did not support the file type and only support(tflite_flutter).
local_notification (it is also not working)
...
1
vote
1
answer
74
views
How can i correctly change the LLAMA3 default maxtoken=256 in Blazor app on .NET 10.0?
Description
I am creating a local LLM app, which works OK, but on response it stops at 170 words which are = 256 tokens.
The models I have tried are so far: Meta-Llama-3.1-8B-Instruct-Q8_0.gguf and ...
Advice
1
vote
2
replies
93
views
General Curiosity about ai
Currently i am exploring about agentic ai and found some cool use-cases of it in real world and amazed to see how it's been continously growing over the market and automating simple process together ...
Tooling
0
votes
2
replies
54
views
ASP.NET With AI
I’m working with ASP.NET and I would like to integrate an AI model into my backend API.
Could you please explain the available approaches, the required tools or services, and the best practices for ...
0
votes
0
answers
37
views
Autogen- Unable to create the single conversational chat agent application
I am trying to create a simple conversational AI using autogen.
where user should able to continuesly interact with the agent
Below is the code
~~~
def get_location_suggestion() -> str:
...
3
votes
1
answer
52
views
How to reorder Corpus+LLM chat bubbles in the correct order?
I'm writing a generative AI Corpus and AI Vocal Analysis tool that is for training peoples voice and giving feedback. I'm using qwen4b-instruct as an LLM and have prompted it really good however my ...
2
votes
2
answers
40
views
How to use types correctly and avoid errors in PDDL
In my PDDL domain, as soon as I add "type" to each of variables, there is an error as follows, but it has no error if I remove these elements. Anyone knows the reason? Thanks!
......
->...
2
votes
1
answer
196
views
Update ChatMessageContent value in Semantic Kernel response
I have a simple chat bot built with Semantic Kernel:
var response = _chatCompletionService.GetChatMessageContentAsync(
chatHistory,
executionSettings: execSettings,
kernel: kernel);
...
2
votes
0
answers
32
views
Architectural considerations for safely integrating LLM-based responses into web automation
I am experimenting with Python-based web automation (e.g. Selenium) and would like to understand the architectural and security considerations when integrating an LLM to generate natural language ...
Best practices
0
votes
2
replies
58
views
Is it possible to create a custom GPT and connect it to external services like Notion?
Is it possible to create a custom GPT and connect it with available connectors?
I want to create a GPT that can create and read documents in Notion, basically acting like a second memory/brain. The ...
2
votes
0
answers
84
views
Why isn't Windsurf's autocomplete working in my IntelliJ IDEA 2024?
Just installed Windsurf in IDEA 2024 and enabled autocomplete. The Chat agent works fine (I'm in China, so probably not a full network block).
But inline suggestions aren't appearing at all. Example: ...