1,668 questions
0
votes
0
answers
21
views
Firebase Genkit using prompt in chat
I am using chat with genKit library like below:
const session = agenticAi.createSession<any>({
initialState: {
uid: uid,
},
});
const chat = session.chat({
model: googleAI.model('...
- 1,342
-4
votes
0
answers
33
views
Which open-source language model can be run locally with minimal output restrictions for research chatbot development? [closed]
I’m developing a local AI chatbot as part of a research project. The system will run entirely offline, so there are no end-user safety concerns — I just need to evaluate model behavior and reasoning ...
- 1
0
votes
0
answers
15
views
How can I make an MCP tool ask the LLM to request missing parameters instead of sending empty strings?
I'm building an MCP server (with spring ai 1.1.0-M3) that exposes a tool for searching contacts in my internal system.
Here’s a simplified version of the tool method:
public class myTool {
@...
- 35
-2
votes
0
answers
17
views
i am seeing this error as im sending my tool output to LLM , invalid character '\u0026' in string escape code , what might be reason [closed]
my python function is fetching some documents from elastic search and sendning these documents to LLM (mistral small) , and while llm is processing im getting this error
Status code: 500, body:
{&...
0
votes
0
answers
19
views
AgentDojo repo on Github: I can't reproduce the table results, because the Security results are always 0.00%
I tried running this command with GPT_4O_MINI_2024_07_18, so that the rate limits wouldn't block the execution before the results are printed
python -m agentdojo.scripts.benchmark -s workspace -ut ...
-2
votes
0
answers
23
views
How much time it takes to index text data QDrant using Open WebUI? [closed]
I use a non-default Vector database for indexing knowledge bases in Open Web UI, but for a text file of size 0.2GB, it is now been running for 5 hours: is that normal?
I run the application on my I9, ...
- 1
0
votes
0
answers
37
views
How to implement on device llm using flutter_gemma or any other package from assets? [closed]
How to implement on device llm using flutter_gemma or any other package model from assets?
- 91
-2
votes
0
answers
36
views
Anaconda: PackagesNotFoundError: "-package name" missing [closed]
I am following a LLM tutorial and encountered this issue with anaconda where I encountered a message displaying a very vague missing component, "package_name", when I issued "conda env ...
0
votes
1
answer
25
views
Getting "FATAL FIPS SELFTEST FAILURE" when importing qwen-vl-utils
When I run
from qwen_vl_utils import process_vision_info
in my Python environment, I get
crypto/fips/fips.c:154: OpenSSL internal error: FATAL FIPS SELFTEST FAILURE
Aborted
I'm using
OpenSSL 3.3.2
...
- 351
0
votes
0
answers
57
views
Installation error while installing GroundingDino
I am trying to install the GroundingDino as instructed in the README file of their official GitHub repo, but I am facing the error below:
Obtaining file:///home/kgupta/workspace/Synthetic_Data_gen/...
0
votes
0
answers
46
views
Langgraph node state update is not updating messages [closed]
I'm making a simple agent with simple tools to test out the new AG-UI protocol. My agent's state is a TypeDict that contains messages. My first node will make the decision to call tools or not and ...
- 1,602
0
votes
0
answers
26
views
How to reduce latency in a context-aware chatbot with chart + dataset inputs
I’m building a chatbot for my research project that helps participants understand a chart. The chatbot runs on a website built with React.
My goal is to make it feel just like using ChatGPT in the ...
- 161
0
votes
1
answer
84
views
Error while deploying, but not in local: "crewai Failed to upsert documents: "Expected IDs to be unique, found 28 Duplicate IDs"
When I initialize a Crew in Azure, I get an error:
crewai Failed to upsert documents: "Expected IDs to be unique, found 28 Duplicate IDs"
followed by lots of uuids.
from crewai import ...
- 3,994
0
votes
1
answer
42
views
What does total_token_count means from gemini response?
I'm trying to understand how total_token_count is calculated for the gemini-2.5-flash model.
The official documentation suggests total_token_count = prompt_token_count + candidates_token_count, but my ...
- 31
-1
votes
1
answer
53
views
How to reconstruct sentences from mean-pooled embeddings (embedding inversion) [closed]
I’m working on a research problem where I want to reconstruct or paraphrase sentences starting from synthetic embeddings.
The embeddings are global (mean-pooled), not token-level, so they lose ...
