8,771 questions
Advice
0
votes
0
replies
34
views
Speech to AI generated image
i have a project for a museum where i need to develop a generative AI program to interpret visitors' words and transform their stories into stylized digital drawings.
The visitor push on a buton then ...
- 1
Advice
1
vote
0
replies
21
views
How can I design “story-driven NPCs” in a reinforcement-learned environment? Looking for development directions and architectural advice
I’m working on a thesis about "story-driven NPCs in a reinforcement-learning world", and I’m building a small multi-agent RL environment as a prototype. However, I’m unsure how to push the ...
Best practices
0
votes
1
replies
36
views
Best method to manage metrics of prompts that are stored in a git repository
We are building an LLM-based application which takes a lot of user data from various internal sources.
It then sends the data to various prompts which provide the answers needed to fill out forms ...
- 3
0
votes
0
answers
23
views
Qwen-vLLM metadata extraction works prompts where the language is the same, but fails when document language differs from prompt [closed]
I’m using Qwen + vLLM to extract metadata (title, author, date, etc.) from documents.
When the prompt and the document are in the same language, everything works perfectly.
But when I keep my prompt ...
- 7
-2
votes
0
answers
14
views
AI effect on StackOverflow [migrated]
I would like to know how much the advent of AI tools like chatGpt and many other affected the usage of stackoverflow!
Before it was a holy place for developers right. How much did AI effect the ...
- 5
-3
votes
0
answers
31
views
Inaccurate Embedding Scores for Word Similarity Comparisons [closed]
I'm trying to find models that perform well at modelling word similarities. Naturally, I navigated to embedding models.
With gemini-embedding-001, I'm seeing wildly inaccurate scores. I'd like to know ...
- 10.3k
0
votes
0
answers
63
views
What output format should I use for SQL query results in a Postgres Model Context Protocol (MCP) server? [closed]
I’m building a Postgres Model Context Protocol (MCP) server and For the executeQuery MCP tool, which output format should I use for SQL query results?
What’s the best format to return SQL query ...
Advice
0
votes
0
replies
52
views
AI/IDE Integration: Claude Code for VS Code vs. Cursor Models
I seem to be missing the subtleties in the IDE integration between these two options:
Claude Code for VS Code
Cursor Models
I've been been using Cursor for the Models; I've toggled a few, seems to ...
- 1,086
1
vote
1
answer
201
views
ModuleNotFoundError when importing ConversationBufferMemory and ConversationalRetrievalChain from LangChain
I'm trying to import ConversationBufferMemory and ConversationalRetrievalChain in my Python notebook as follows:
from langchain.memory import ConversationBufferMemory
from langchain.chains import ...
- 23
Advice
1
vote
4
replies
127
views
How to retain CrewAI Short-Term Memory with Azure OpenAI Embeddings?
I'm working on implementing CrewAI's short-term memory feature, but it's not behaving as expected.
embedder_config = {
"provider": "openai",
"config": {
&...
- 399
0
votes
0
answers
55
views
Chat model returns empty content when I inject a delayed ToolMessage from a scheduled callback
I have a scheduler that triggers a tool function later (outside the original user–model exchange).
When the scheduled time comes, it sends a ToolMessage back into the chat model — but the model ...
- 9
-4
votes
1
answer
77
views
Troubles with the creation of tools and agents in langchain [closed]
I’m trying to create an agent in LangChain using Google Gemini, but I’m running into some issues because of the latest LangChain updates. As a result, I haven’t been able to create a chain with the ...
0
votes
0
answers
81
views
How can I run the inference on the HunyuanImage-3.0 model?
I follow the instructions on https://github.com/Tencent-Hunyuan/HunyuanImage-3.0:
conda create -y -n hunyuan312 python=3.12
conda activate hunyuan312
# 1. First install PyTorch (CUDA 12.8 Version)
...
- 84.7k
1
vote
0
answers
52
views
Transformer model outputs degrade after ONNX export — what could be causing this?
I’ve exported a fine-tuned BERT-based QA model to ONNX for faster inference, but I’m noticing that the predictions from the ONNX model are consistently less accurate than those from the original ...
- 41
0
votes
1
answer
342
views
Getting “Sizes of tensors must match” error when using ComfyUI WanVideoWrapper (wan2.2) to generate video
I am trying to generate a video using Wan 2.2. My goal is to take a motion sequence from an input video and a single reference image, and then generate a new video where the character in the reference ...
- 11
2
votes
1
answer
128
views
Langchain-based model memory
I am referring to the official documentation of langchain to learn how to build a simple agent. But the model don't have memory even though I have used MemeorySaver
the link of official document is ...
- 23
0
votes
0
answers
47
views
Flet python dialog close and Save is not working
im using flet to make a UI for an API app and i get a gray box when i try to click a button to open a pop up but when i close or save the pop up it dose not close but add a new pop up that can not go ...
-1
votes
1
answer
121
views
How to download Open Images V7, images on device? [closed]
I wanted a perticular class Images ('Turban') from the Open Images, However these images are not in the Boxable Category. Due to which my follow OIDv6 code is Failing
oidv6 downloader en --dataset ./...
0
votes
0
answers
135
views
Zep Graphiti - core - Adding Episode fails the LLM structured output
On the ingestion part to the graph db, I pass a json file, as an episode, custom entities (and edges), using gemini api, but I get some discrepancy on the structured output, like so:
LLM generation ...
0
votes
0
answers
54
views
How to send extra headers from RAGFlow Agent to a Spring Boot MCP server tool call?
I am using RAGFlow
connected to a Spring Boot MCP server.
My agent flow is simple:
Begin node → collects inputs (auth_token, tenant_id, x_request_status)
Agent (gpt-4o) → connected to
MCP Tool (server)...
- 729
0
votes
0
answers
72
views
Plivo AI Agent not calling human agent after transferCall redirect
I have an inbound call flow where:
Incoming call → handled by /incoming, which connects the call to Ultravox AI through a .
AI Agent conversation → if the caller asks for a human, the AI triggers /...
0
votes
1
answer
145
views
Cursor AI Agent terminal never stops (spinner keeps running) after dotnet build finishes
I’m running a .NET project from the Cursor AI Agent terminal. The build finishes (I see the final summary line), but the Agent’s terminal keeps “running” forever (spinner never stops). I have to press ...
- 697
0
votes
0
answers
138
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 ...
- 756
0
votes
2
answers
319
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
1
vote
1
answer
248
views
Firecrawl self-hosted crawler throws Connection violated security rules error
I set up a self-hosted Firecrawl instance and I want to crawl my internal intranet site (e.g. https://intranet.xxx.gov.tr/).
I can access the site directly both from the host machine and from inside ...
- 307